Anomaly detection has been extensively investigated in numerous application areas. Hand-crafted rules have gradually given way to supervised classification techniques, which frequently rely on a small number of anomaly labels and related architectures. When it comes to human motion, abnormalities emerge at a fine-grained temporal or joint level rather than over a whole video sequence. This study introduces NFlowAD, a self-supervised system that analyzes body joints to detect irregularities in human motion. It blends normalizing flows with masked motion modeling to describe normal motion data without the need for anomaly labels. Inference uses both reconstruction mistakes and flow-based likelihoods to detect anomalies. The validation pipeline on various state-of-the-art datasets demonstrates NFlowAD’s efficiency in recognizing, locating, and analyzing anomalous motion sequences, while maintaining robust detection and interpretability.

Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available generative techniques, as well as the scarcity of high-quality open source datasets of diverse nature for this task, make training and benchmarking synthetic image source attribution models very challenging. WILD1is a new in-the-Wild Image Linkage Dataset designed to provide a powerful training and benchmarking tool for synthetic image attribution models. The dataset is built out of a closed set of 10 popular commercial generators, which constitutes the training base of attribution models, and an open set of 10 additional generators, simulating a real-world in-the-wild scenario. Each generator is represented by 1,000 images, for a total of 10,000 images in the closed set and 10,000 images in the open set. Half of the images are post-processed with a wide range of operators. WILD allows benchmarking attribution models in a wide range of tasks, including closed and open set identification and verification, and robust attribution with respect to post-processing and adversarial attacks. Models trained on WILD are expected to benefit from the challenging scenario represented by the dataset itself. Moreover, an assessment of seven baseline methodologies on closed and open set attribution is presented, including robustness tests with respect to post-processing.

Haptic feedback has been integrated into Virtual and Augmented Reality, complementing acoustic and visual information and contributing to an all-round immersive experience in multiple fields, spanning from the medical domain to entertainment and gaming. Haptic technologies involve complex cross-disciplinary research that encompasses sensing, data representation, interactive rendering, perception, and quality of experience. The standard processing pipeline, consists of (I) sensing physical features in the real world using a transducer, (II) modeling and storing the collected information in some digital format, (III) communicating the information, and finally, (IV) rendering the haptic information through appropriate devices, thus producing a user experience (V) perceptually close to the original physical world. Among these areas, sensing, rendering and perception have been deeply investigated and are the subject of different comprehensive surveys available in the literature. Differently, research dealing with haptic surface modeling and data representation still lacks a comprehensive dissection. In this work, we aim at providing an overview on modeling and representation of haptic surfaces from a signal processing perspective, covering the aspects that lie in between haptic information acquisition on one side and rendering and perception on the other side. We analyze, categorize, and compare research papers that address the haptic surface modeling and data representation, pointing out existing gaps and possible research directions.

We introduce UniCrowd1, a human crowd simulator for the modeling of human-related dynamics. The simulator is accompanied by a meticulously collected dataset within its synthetic environment, along with a comprehensive validation pipeline. Leveraging simulation as a powerful tool for generating annotated data, UniCrowd addresses the increasing demand for large training datasets, mimicking both the behavioral and visual aspect of crowds. Recent advancements in rendering and virtualization engines have enhanced the simulators capabilities to represent complex scenes, encompassing environmental factors such as weather conditions, surface reflectance, and human-related events like actions and behaviors. The adaptability and the non-deterministic nature of the human behavioral module of UniCrowd, coupled with its 3D rendering represents an improvement over available crowd simulators. We demonstrate the suitability of our simulator and its associated dataset for various computer vision tasks. We highlight applications such as detection and segmentation, as well as specialized tasks including crowd counting, human pose estimation, trajectory analysis and prediction.1The simulator and the dataset can be accessed at github.com/mmlabcvUniCrowd

The term “mimicry attack” has been coined in computer security and used in adversarial machine learning: an attacker observes what a machine-learning system has learned and adjusts the malicious input so that it mimics a benign input. In this paper we extend this concept to image forensics, to allow an attacker modifying a manipulated image so that it appears pristine when analyzed by a target forensic detector. Recent work has shown that such attacks can be executed against detectors based on deep networks for hiding image tampering. We do more than that: our mimicry attack can force the target detector to identify arbitrary fictitious manipulations, while hiding the true ones. Accordingly, the user of the forensic detector is completely misled. From a methodological viewpoint, the proposed attack artificially alters the detector-specific intermediate representations according to the pixel distribution in the manipulated image, by applying a gradient-based optimization process. Experimental tests on different data sets and detectors demonstrate that our approach succeeds in jointly hiding manipulated areas and arbitrarily adding new ones, favorably comparing with the state-of-the-art in the first task.

The amount of multimedia content shared everyday, combined with the level of realism reached by recent fake-generating technologies, threatens to impair the trustworthiness of online information sources. The process of uploading and sharing data tends to hinder standard media forensic analyses, since multiple re-sharing steps progressively hide the traces of past manipulations. At the same time though, new traces are introduced by the platforms themselves, enabling the reconstruction of the sharing history of digital objects, with possible applications in information flow monitoring and source identification. In this work, we propose a supervised framework for the reconstruction of image sharing chains on social media platforms. The system is structured as a cascade of backtracking blocks, each of them tracing back one step of the sharing chain at a time. Blocks are designed as ensembles of classifiers trained to analyse the input image independently from one another by leveraging different feature representations that describe both content and container of the media object. Individual decisions are then properly combined by a late fusion strategy. Results highlight the advantages of employing multiple clues, which allow accurately tracing back up to three steps along the sharing chain.

In this article, we propose a framework for crowd behavior prediction in complicated scenarios. The fundamental framework is designed using the standard encoder-decoder scheme, which is built upon the long short-term memory module to capture the temporal evolution of crowd behaviors. To model interactions among humans and environments, we embed both the social and the physical attention mechanisms into the long short-term memory. The social attention component can model the interactions among different pedestrians, whereas the physical attention component helps to understand the spatial configurations of the scene. Since pedestrians’ behaviors demonstrate multi-modal properties, we use the generative model to produce multiple acceptable future paths. The proposed framework not only predicts an individual’s trajectory accurately but also forecasts the ongoing group behaviors by leveraging on the coherent filtering approach. Experiments are carried out on the standard crowd benchmarks (namely, the ETH, the UCY, the CUHK crowd, and the CrowdFlow datasets), which demonstrate that the proposed framework is effective in forecasting crowd behaviors in complex scenarios.

Positive unlabeled (PU) learning is useful in various practical situations, where there is a need to learn a classifier for a class of interest from an unlabeled data set, which may contain anomalies as well as samples from unknown classes. The learning task can be formulated as an optimization problem under the framework of statistical learning theory. Recent studies have theoretically analyzed its properties and generalization performance, nevertheless, little effort has been made to consider the problem of scalability, especially when large sets of unlabeled data are available. In this work we propose a novel scalable PU learning algorithm that is theoretically proven to provide the optimal solution, while showing superior computational and memory performance. Experimental evaluation confirms the theoretical evidence and shows that the proposed method can be successfully applied to a large variety of real-world problems involving PU learning.

Clustering images according to their acquisition devices is a well-known problem in multimedia forensics, which is typically faced by means of camera sensor pattern noise (SPN). Such an issue is challenging since SPN is a noise-like signal, hard to be estimated, and easy to be attenuated or destroyed by many factors. Moreover, the high dimensionality of SPN hinders large-scale applications. Existing approaches are typically based on the correlation among SPNs in the pixel domain, which might not be able to capture intrinsic data structure in the union of vector subspaces. In this paper, we propose an accurate clustering framework, which exploits linear dependences among SPNs in their intrinsic vector subspaces. Such dependences are encoded under sparse representations, which are obtained by solving an LASSO problem with non-negativity constraint. The proposed framework is highly accurate in a number of clusters' estimation and image association. Moreover, our framework is scalable to the number of images and robust against double JPEG compression as well as the presence of outliers, owning big potential for real-world applications. Experimental results on Dresden and Vision database show that our proposed framework can adapt well to both medium-scale and large-scale contexts and outperforms the state-of-the-art methods.

Finegrained recognition focuses on the challenging task of automatically identifying the subtle differences between similar categories. Current state-of-the-art approaches require elaborated feature learning procedures, involving tuning several hyper-parameters, or rely on expensive human annotations such as objects or parts location. In this paper we propose a simple method for fine-grained recognition that exploits a nearly cost-free attention-based focus operation to construct an ensemble of increasingly specialized Convolutional Neural Networks. Our method achieves state-of-the-art results on three of the most popular datasets used for fine-grained classification namely CUB Birds 200-2011, FGVC-Aircraft and Stanford Cars requiring minimal hyperparameter tuning and no annotations.

Studying the impact of sharing platforms like social networks and messaging services on multimedia content nowadays represents a due step in multimedia forensics research. In this framework, we study the characteristics of images that are uploaded and shared through three popular mobile messaging apps combined with two different sending mobile operating systems (OS). In our analysis, we consider information contained both in the image signal and in the metadata of the image file. We show that it is generally possible to identify a posteriori the last app and the OS that have been used for uploading. This is done by considering different scenarios involving images shared both once and twice. Moreover, we show that, by leveraging the knowledge of the last sharing app and system, it is possible to retrieve information on the previous sharing step for double shared images. In relation to prior works, a discussion on the influence of the rescaling and recompression mechanism - usually performed differently through apps and OSs - is also proposed, and the feasibility of retrieving the compression parameters of the image before being shared is assessed.

In this article, we address the problem of recognizing an event from a single related picture. Given the large number of event classes and the limited information contained in a single shot, the problem is known to be particularly hard. To achieve a reliable detection, we propose a combination of multiple classifiers, and we compare three alternative strategies to fuse the results of each classifier, namely: (i) induced order weighted averaging operators, (ii) genetic algorithms, and (iii) particle swarm optimization. Each method is aimed at determining the optimal weights to be assigned to the decision scores yielded by different deep models, according to the relevant optimization strategy. Experimental tests have been performed on three event recognition datasets, evaluating the performance of various deep models, both alone and selectively combined. Experimental results demonstrate that the proposed approach outperforms traditional multiple classifier solutions based on uniform weighting, and outperforms recent state-of-the-art approaches.

This paper proposes a novel two-stage framework for event recognition in still images. First, for a generic event image, deep features, obtained via different pre-trained models, are fed into an ensemble of classifiers, whose posterior classification probabilities are thereafter fused by means of an order-induced scheme, which penalizes the yielded scores according to their confidence in classifying the image at hand, and then averages them. Second, we combine the fusion results with a reverse matching paradigm in order to draw the final output of our proposed pipeline. We evaluate our approach on three challenging datasets and we show that better results can be attained, advancing recent leading works.

Morphological operators are widely used in binary image processing for several purposes, such as removing noise, detecting contours or particular structures, and regularizing shapes. In particular, morphological filters are largely adopted in scanned documents to correct the artifacts caused by acquisition and binarization, as well as other processing. In this paper, we propose a novel approach for forensics detection of morphological filtering on binary images. The proposed technique exploits some mathematical properties of the two basic morphologic operators, erosion and dilation, to define an algorithm able not only to detect the application of the filter, but also to estimate the shape of the relevant structuring element. Experimental tests demonstrate that the technique is effective and robust to the most common operations performed on binary image documents.

In this paper we address the issue of photo galleries synchronization, where pictures related to the same event are collected by different users. Existing solutions to address the problem are usually based on unrealistic assumptions, like time consistency across photo galleries, and often heavily rely on heuristics, therefore limiting the applicability to real-world scenarios. We propose a solution that achieves better generalization performance for the synchronization task compared to the available literature. The method is characterized by three stages: at first, deep convolutional neural network features are used to assess the visual similarity among the photos; then, pairs of similar photos are detected across different galleries and used to construct a graph; eventually, a probabilistic graphical model is used to estimate the temporal offset of each pair of galleries, by traversing the minimum spanning tree extracted from this graph. The experimental evaluation is conducted on four publicly available datasets covering different types of events, demonstrating the strength of our proposed method. A thorough discussion of the obtained results is provided for a critical assessment of the quality in synchronization.

In this article, we present a novel framework that can produce a visual description of a tourist attraction by choosing the most diverse pictures from community-contributed datasets, which describe different details of the queried location. The main strength of the proposed approach is its flexibility that permits us to filter out non-relevant images and to obtain a reliable set of diverse and relevant images by first clustering similar images according to their textual descriptions and their visual content and then extracting images from different clusters according to a measure of the user’s credibility. Clustering is based on a two-step process, where textual descriptions are used first and the clusters are then refined according to the visual features. The degree of diversification can be further increased by exploiting users’ judgments on the results produced by the proposed algorithm through a novel approach, where users not only provide a relevance feedback but also a diversity feedback. Experimental results performed on the MediaEval 2015 “Retrieving Diverse Social Images” dataset show that the proposed framework can achieve very good performance both in the case of automatic retrieval of diverse images and in the case of the exploitation of the users’ feedback. The effectiveness of the proposed approach has been also confirmed by a small case study involving a number of real users.

No abstract available.

Deep Learning (DL) has become a crucial technology for multimedia computing. It offers a powerful instrument to automatically produce high-level abstractions of complex multimedia data, which can be exploited in a number of applications, including object detection and recognition, speech-to- text, media retrieval, multimodal data analysis, and so on. The availability of affordable large-scale parallel processing architectures, and the sharing of effective open-source codes implementing the basic learning algorithms, caused a rapid diffusion of DL methodologies, bringing a number of new technologies and applications that outperform, in most cases, traditional machine learning technologies. In recent years, the possibility of implementing DL technologies on mobile devices has attracted significant attention. Thanks to this technology, portable devices may become smart objects capable of learning and acting. The path toward these exciting future scenarios, however, entangles a number of important research challenges. DL architectures and algorithms are hardly adapted to the storage and computation resources of a mobile device. Therefore, there is a need for new generations of mobile processors and chipsets, small footprint learning and inference algorithms, new models of collaborative and distributed processing, and a number of other fundamental building blocks. This survey reports the state of the art in this exciting research area, looking back to the evolution of neural networks, and arriving to the most recent results in terms of methodologies, technologies, and applications for mobile environments.

In this work we propose a novel parametric Bayesian model for the problem of semi-supervised classification and clustering. Standard approaches of semi-supervised classification can recognize classes but cannot find groups of data. On the other hand, semi-supervised clustering techniques are able to discover groups of data but cannot find the associations between clusters and classes. The proposed model can classify and cluster samples simultaneously, allowing the analysis of data in the presence of an unknown number of classes and/or an arbitrary number of clusters per class. Experiments on synthetic and real world data show that the proposed model compares favourably to state-of-the-art approaches for semi-supervised clustering and that the discovered clusters can help to enhance classification performance, even in cases where the cluster and the low density separation assumptions do not hold. We finally show that when applied to a challenging real-world problem of subgroup discovery in breast cancer, the method is capable of maximally exploiting the limited information available and identifying highly promising subgroups.

In this paper, we propose a novel approach for face spoofing detection using the high-order Local Derivative Pattern from Three Orthogonal Planes (LDP-TOP). The proposed method is not only simple to derive and implement, but also highly efficient, since it takes into account both spatial and temporal information in different directions of subtle face movements. According to experimental results, the proposed approach outperforms state-of-the-art methods on three reference datasets, namely Idiap REPLAY-ATTACK, CASIA-FASD, and MSU MFSD. Moreover, it requires only 25 video frames from each video, i.e., only one second, and thus potentially can be performed in real time even on low-cost devices.

In this paper we present a novel method for crowd behavior identification. In our method, the motion flow field is obtained from the video by computing the dense optical flow. Then, a thermal diffusion process (TDP) is exploited to increase the coherence of the motion flow. Approximating the moving particles to individuals, their interaction forces are computed using a modified variant of the social force model (M-SFM) to highlight potential particles of interest. Besides capturing the effect of neighboring individuals on each other, the M-SFM also takes into account the crowd disorder, usually triggered by regions of high interactions. The experimental evaluation is conducted on a set of benchmark video sequences, commonly used for crowd motion analysis, and the obtained results are compared against a state of the art technique.

Event discovery from single pictures is a challenging problem that has raised significant interest in the last decade. During this time, a number of interesting solutions have been proposed to tackle event discovery in still images. However, a large scale benchmarking image dataset for the evaluation and comparison of event discovery algorithms from single images is still lagging behind. To this aim, in this paper we provide a large-scale properly annotated and balanced dataset of 490,000 images, covering every aspect of 14 different types of social events, selected among the most shared ones in the social network. Such a large scale collection of event-related images is intended to become a powerful support tool for the research community in multimedia analysis by providing a common benchmark for training, testing, validation and comparison of existing and novel algorithms. In this paper, we provide a detailed description of how the dataset is collected, organized and how it can be beneficial for the researchers in the multimedia analysis domain. Moreover, a deep learning based approach is introduced into event discovery from single images as one of the possible applications of this dataset with a belief that deep learning can prove to be a breakthrough also in this research area. By providing this dataset, we hope to gather research community in the multimedia and signal processing domains to advance this application.

In this paper, we propose a forensic technique that is able to detect the application of a median filter to 1D data. The method relies on deterministic mathematical properties of the median filter, which lead to the identification of specific relationships among the sample values that cannot be found in the filtered sequences. Hence, their presence in the analyzed 1D sequence allows excluding the application of the median filter. Owing to its deterministic nature, the method ensures 0% false negatives, and although false positives (sequences not filtered classified as filtered) are theoretically possible, experimental results show that the false alarm rate is null for sufficiently long sequences. Furthermore, the proposed technique has the capability to locate with good precision a median filtered part of 1-D data and provides a good estimate of the window size used.

In this paper we present a novel method for automatic traffic accident detection, based on Smoothed Particles Hydrodynamics (SPH). In our method, a motion flow field is obtained from the video through dense optical flow extraction. Then a thermal diffusion process (TDP) is exploited to turn the motion flow field into a coherent motion field. Approximating the moving particles to individuals, their interaction forces, represented as endothermic reactions, are computed using the enthalpy measure, thus obtaining the potential particles of interest. Furthermore, we exploit SPH that accumulates the contribution of each particle in a weighted form, based on a kernel function. The experimental evaluation is conducted on a set of video sequences collected from Youtube, and the obtained results are compared against a state of the art technique.

In this paper, we present a novel method that can produce a visual description of a landmark by choosing the most diverse pictures that best describe all the details of the queried location from community-contributed datasets. The main idea of this method is to filter out non-relevant images at a first stage and then cluster the images according to textual descriptors first, and then to visual descriptors. The extraction of images from different clusters according to a measure of user's credibility, allows obtaining a reliable set of diverse and relevant images. Experimental results performed on the MediaEval 2014 “Retrieving Diverse Social Images” dataset show that the proposed approach can achieve very good performance outperforming state-of-art techniques.

In this paper, we propose a framework to recognize complex human interactions. First, we adopt trajectories to represent human motion in a video. Then, the extracted trajectories are clustered into different groups (named as local motion patterns) using the coherent filtering algorithm. As trajectories within the same group exhibit similar motion properties (i.e., velocity, direction), we adopt the histogram of large-displacement optical flow (denoted as HO-LDOF) as the group motion feature vector. Thus, each video can be briefly represented by a collection of local motion patterns that are described by the HO-LDOF. Finally, classification is achieved using the citation-KNN, which is a typical multiple-instance-learning algorithm. Experimental results on the TV human interaction dataset and the UT human interaction dataset demonstrate the applicability of our method.

HuEvent'15 is a continuation of previous year's successful workshop on events in multimedia. It focuses on the human-centered aspects of understanding events from multimedia content. This includes the notion of objects and their relation to events. The workshop brings together researchers from the different areas in multimedia and beyond that are interested in understanding the concept of events.

Modern computer graphics technologies brought realism in computer-generated characters, making them achieve truly natural appearance. Besides traditional virtual reality applications such as avatars, games, or cinema, these synthetic characters may be used to generate realistic fakes, which may lead to improper use of the technology. This fact raises the demand for advanced tools able to discriminate real and artificial human faces in digital media. In this paper, we propose a method to distinguish between computer generated and natural faces by modeling and evaluating their dynamic behavior. Because of a 3D-model-based video analysis, the proposed technique allows identifying synthetic characters by detecting their more limited variability over time. Experimental results demonstrate the effectiveness of the proposed approach also on very challenging and realistic video sequences.

The concept of “event” emerged in recent years as a key feature to efficiently index and retrieve media. Several approaches have been proposed to analyze the relationship between events and media, enable event discovery, and perform event-based media tagging, indexing, and retrieval. Despite the outstanding work done in this area, a major problem that remains open is how to infer the link between visual concepts and events. In particular, the possibility of understanding which perceptual elements allow a human recognizing the event depicted by an image would open new directions in event media discovery. In this paper we introduce the concept of event saliency to define the above event-revealing perceptual elements, and we propose an original method to detect it by exploiting crowd knowledge through gamification. We propose an adversarial game with a hidden purpose, where users are engaged in competitive roles: masking photos to prevent competitors recognizing the related event, and discovering events in photos masked by other players. Rules and incentives are defined to minimize cheating and force players to focus on details that really matter. A suitable algorithm composes the masks created by different players on the same media, thus producing a saliency map that, different from the traditional concept of saliency, does not focus on perceptual prominence but rather on event-related semantics of media. A thorough validation on public datasets is presented, and initial experiments to apply event saliency in detection tasks are proposed . Furthermore, an event-saliency dataset is disclosed to allow further research.

In this article, we present a novel approach to segment discriminative patches in human activity videos. First, we adopt the spatio-temporal interest points (STIPs) to represent significant motion patterns in the video sequence. Then, nonnegative sparse coding is exploited to generate a sparse representation of each STIP descriptor. We construct the feature vector for each video by applying a two-stage sum-pooling and l 2 -normalization operation. After training a multi-class classifier through the error-correcting code SVM, the discriminative portion of each video is determined as the patch that has the highest confidence while also being correctly classified according to the video category. Experimental results show that the video patches extracted by our method are more separable, while preserving the perceptually relevant portion of each activity.

Social Networks have been developed dramatically just in decades. People now have a convenient way to interact with both social media and other people by making the most of using these social networks. Nevertheless, there is still lack of useful tools that can help users (both consumers and providers) managing such social media under events perspective. In order to meet one of these emerging requirements, a user-centric parallel split-n-merge framework applied for un-supervised clustering social media events is introduced. The purpose of this framework is to cluster social media to events they depict by exploiting and exploring the role of users (who) and the way users interact with data (where, what, when) and others (what, who). The output of the proposed framework can be used for event organization/summarization, and as pre-processing stage for event detection and tracking. Major advantages of the proposed framework are (1) low computational solution w.r.t large-scale data, (2) parallel running, and (3) unsupervised clustering with no training data and third-party information requirements. The comparison between the proposed framework and up-to-date methods with MediaEval20131test-bed and evaluation tools shows a very competitive result.

Given the recent development of advanced multimedia techniques able to support the creation of realistic computer generated characters, there is the parallel need of automatic tools allowing users to verify the source of the multimedia data they are observing, thus discriminating between artificial and natural information. In this paper, we focus on video representing human beings and we propose a novel method to identify computer generated characters by analysing the evolution of the face model in chronological order. Experimental results show that photorealistic facial animations, which are usually performed following fixed patterns, can be distinguished from natural ones, which follow much more complicated and various geometric distortions.

In this paper, we propose a novel approach to detect abrupt camera viewpoint changes in edited video materials (movies, TV shows), to improve human activity recognition. The motivation for this work lies in the difficulty of correctly identifying actions in case of camera motion and viewpoint changes, because of the abrupt variations in the appearance model of the scene, which significantly deteriorate the continuity of the spatio-temporal features under investigation. To this aim, we compute the motion interchange pattern (MIP) for each pixel in a video, from which a feature descriptor is constructed for the entire frame. The change in camera viewpoint is achieved through the one-class SVM. We apply our detector on the TV human interaction dataset (TVHI). The experimental results show that our approach can distinguish the abrupt changes with a high accuracy, allowing for an improvement also in the activity recognition performance.

This workshop focuses on the human-centered aspects of understanding events from multimedia content. This includes the notion of objects and their relation to events. The workshop brings together researchers from the different areas in multimedia and beyond that are interested in understanding the concept of events.

In this paper we propose a novel method to recognize different types of two-person interactions in video sequences. After extracting the spatio-temporal interest points (STIPs) from the visual scene through the 3D Harris detector, K-means clustering is applied to construct the visual codebook. We adopt a new feature selection procedure, called knowledge gain, based on the rough set theory to identify the most meaningful visual words in the codebook. For each video sequence, the histogram of selected visual words is used to train a multi-class SVM classifier. The algorithm is tested on two different datasets in order to demonstrate the applicability of the technique in different environmental configurations. Experimental results show that knowledge gain can improve the classification performance.

In this contribution, we propose a watershed-based method with support from external data sources and visual information to detect social events in web multimedia. The idea is based on two main observations: (1) people cannot be involved in more than one event at the same time, and (2) people tend to introduce similar annotations for all images associated to the same event. Based on these observations, the metadata is turned to an image so that each row contains all records belonging to one user; and these records are sorted by time. Thus, the social event detection is turned to watershed-based image segmentation, where Markers are generated by using (keyword, location, visual) features with support of external data sources, and the Flood progress is carried on by taking into account (tags set, time, visual) features. We test our algorithm on the MediaEval 2012 dataset both using only external data but also introducing visual information.

Median filtering is a well-known non linear denoising filter often used as an harmless post-processing, sometimes also employed to affect the reliability of some forensic techniques. In this work, we present a novel counter-forensic method able to conceal the characteristic traces left by median filtering. By exploiting the knowledge of features used in existing median filtering detectors, we are able to remove the characteristic footprints via suitable random pixel modification, while keeping the quality of the counter-attacked image high. Experimental results show that the proposed method is very effective, computationally efficient and competitive with other state-of-the-art techniques.

In this paper we present a method of visual salient region detection based on depth maps estimated from 2D images. Depth estimation aims at better understanding spatial scene layout and relationship between objects. From depth maps we extract geometry related features that are further fused with color contrast. We solve saliency detection problem in segment-wise domain that allows prediction of objects rather than separate pixels. Modelling of saliency is done using conditional random field that allows for pairwise dependencies of segments. Parameters tuning is done by learning from ground-truth data. The evaluation has shown feasibility and good performance of the proposed method.

In this paper, a new framework of hybrid mobile-fixed video surveillance system (HMFVSS) is introduced. The purpose of this framework is to overcome common problems of existing mobile or fixed video surveillance systems: (1) moral harassment: due to unfriendly or unnaturally installed mobile sensors, and (2) blind areas: due to narrow-scope moving of fixed cameras. A case study of abandoned object's owner alert system (AOOAS) is also presented to emphasize the framework's advantages. IP cameras and "Spyglass" (i.e. a mobile camera embedded on glasses) are used as fixed and mobile sensors, respectively. There are three main tasks are inherited, developed, and integrated: (1) image registration for automatically locating abandoned object, (2) common histogram based abandoned object's owner detection, and (3) faces recognition. The experimental results with careful evaluation and comparison with others shows that the proposed framework moves a step ahead in video surveillance system.

The large diffusion of photo cameras makes quite common that an event is acquired from different devices, conveying different subjects and perspectives of the same happening. Often, these photo collections are shared among different users through social networks and networked communities. Automatic tools are more and more used to support the users in organizing such archives, and it is largely accepted that time/space information is fundamental to this purpose. Unfortunately, both data are often unreliable, and in particular, timestamps may be affected by erroneous or imprecise setting of the camera clock, thus making the retrieval based on temporal tagging unreliable. In this paper, we propose to solve this well-known problem by introducing a synchronization algorithm that exploit the content of pictures to estimate the mutual delays among different cameras, thus achieving an a-posteriori synchronization of various photo collections referring to the same event. Experimental results show that, for sufficiently large archives, a notable accuracy can be achieved in the estimation of the synchronization information.

Events are becoming very popular as a tool to organize and access large media collections. An unsolved problem however, is how to define event models. Most part of the approaches so far proposed in the literature are based on a-priori knowledge, and translate into hierarchical data structures or taxonomies a more or less intuitive definition of what a given type of event is. The association of media and event models is then a consequent process, in which one tries to learn the distinctive characteristics of media associated to a certain event or sub-event. In this paper, we attempt to reverse this paradigm, inferring from a set of media collections belonging to the same event class the underlying taxonomy in an unconstrained way. As a result we obtain a hierarchy of natural clusters, largely shared by the different collections, which capture the essence of the event itself. Although it is not possible to compare the proposed approach with state-of-the-art method based on a-priori event structures, experimental results demonstrate that this approach may become an effective support for discovering and defining event models and managing event-related data collections.

This demo showcases our system which classifies a collection of pictures into events and its individual images into subevents. We reach this goal by analysizing visual features with an efficient implementation of a Bag-of-Words method and by leveraging time information both for events and sub-events. The system allows the user to analyze a collection of images - named as event-album - from disk or from internet sharing services such as Picasa and Flickr. The results are displayed in a web-browser window allowing the user to view the pictures of the entire recognized event, as well as their recognised sub-events.

This paper presents a novel method of visual saliency detection. The use of saliency promises benefits to multimedia applications. However, up to now just few reasonable applications of saliency exist. It is clear that limited accuracy is one of the possible reasons for this. Another reason could be that in general saliency allows us to detect salient regions of the image rather than objects. To fill this gap we study to what extend the integration of segmentation into saliency detection allows the estimation of saliency of objects. In this paper we propose a method that operates with segments rather than with separate pixels. The comparison with state-of-the-art methods shows that our method is successful in highlighting the mass of the object of interest. Finally, we discuss possible directions for the further work.

Quick reorganizing and draft annotating personal photo albums under event scheme is an emerging trend. In this research, a method has been developed to meet such requirements using the idea of gist and mosaic art so that viewers could understand the meaning of a whole scene without paying much attention in individual details. First, given a photo album, all chronologically ordered images are normalized to a smaller size, and then mosaicked side-by-side to create a signature image representing for that album. Next, by integrating the optimized linear programming with the color descriptor of the signature image, not only the event-type of the album but also all sub-event-types of the sub-sequence photos are decided. More than 19,000 images of five varied event-types have been used to evaluate the proposed method. Experimental results show that the proposed method could detect events towards annotation and re-organization of personal photo albums with high accuracy at a rapid speed.

In this paper we propose a novel method to analyze trajectories in surveillance scenarios relying on automatically learned Context-Free Grammars. Given a training corpus of trajectories associated to a set of actions, an initial processing is carried out to extract the syntactical structure of the activities; then, the rules characterizing different behaviors are retrieved and coded as CFG models. The classification of the new trajectories vs the learned templates is performed through a parsing engine allowing the online recognition as well as the detection of nested activities. The proposed system has been validated in the framework of assisted living applications. The obtained results demonstrate the capability of the system in recognizing activity patterns in different configurations, also in presence of noise.

Images are powerful means of communication. Adding images to documents, websites, magazines, helps attracting the attention and providing an immediate feeling about the content of the document itself. At the same time, images can be used to influence the attitude of the reader. In the digital era it is easier than ever to create and share multimedia documents making extensive use of visual data. Furthermore, it is extremely easy to modify and adapt the images in order to make them more suitable to convey a concept. These modifications may simply consist in focusing the attention on a specific part of the image, to heavier manipulations such as changing the visual appearance or the contents to bias the opinion of the observer. This creates a rising interest for the availability of automatic blind tools able to detect possible modifications of images, and to correlate these modifications with the relevant impact on the viewer. This paper proposes an example of application of these concepts that exploits a tool for automatic detection of contrast modifications and analyzes their impact on human feeling. The results of instrumental and subjective studies are presented and discussed.

Understanding the subjective meaning of a visual query, by converting it into numerical parameters that can be extracted and compared by a computer, is the paramount challenge in the field of intelligent image retrieval, also referred to as the ¿semantic gap¿ problem. In this paper, an innovative approach is proposed that combines a relevance feedback (RF) approach with an evolutionary stochastic algorithm, called particle swarm optimizer (PSO), as a way to grasp user's semantics through optimized iterative learning. The retrieval uses human interaction to achieve a twofold goal: 1) to guide the swarm particles in the exploration of the solution space towards the cluster of relevant images; 2) to dynamically modify the feature space by appropriately weighting the descriptive features according to the users' perception of relevance. Extensive simulations showed that the proposed technique outperforms traditional deterministic RF approaches of the same class, thanks to its stochastic nature, which allows a better exploration of complex, nonlinear, and highly-dimensional solution spaces.

In this paper we propose a string-based approach to effectively represent trajectories in the 3D space. The strategy is coupled with a syntactical matching algorithm that allows evaluating the similarity of the retrieved data with pre-stored templates. The symbolic representation of the trajectory, is the core of the proposed system, which helps discriminating among different tracks using a modified version of the edit-distance. The hierarchical application of the algorithm on the spatial and temporal components helps detecting anomalous trajectories, and has proven to be robust in automatically learning new instances or classes of paths. We present the results achieved by performing a number of tests in an indoor lab used as a testbed for assisted living applications. The algorithm can discriminate among different classes of trajectories and can recognize actions and detect anomalies within the same class.

The paper presents a method for content-based image retrieval based on an evolutionary algorithm. Stochastic approaches have been applied with success in several optimization problems thanks to their capability to explore the solution space, in particular in complex, multidimensional spaces, avoiding local maxima of the target function. Here, we show how a Particle Swarm Optimization algorithm appropriately designed to exploit the user feedback in CBIR may outperform traditional Relevance Feedback approaches, showing a much higher precision/recall thanks to the capability of navigating the feature space and to move the swarm towards the most appropriate image cluster.

In this paper we present the application of a recently developed benchmarking tool to the comparison of watermarking algorithms. We carry out an extensive analysis to assess and compare robustness of digital image watermarking techniques by considering the perceptual quality of un-marked images in terms of Weighted PSNR. Such a benchmarking tool employs genetic algorithms, introduces a novel metric for robustness assessment based on perceptual quality measures and allows analysis and comparison of different techniques performances. Experimental results show the effectiveness of the proposed approach.

In this work we present a framework for physical rehabilitation, which is based on hand tracking. One particular requirement in physical rehabilitation is the capability of the patient to correctly reproduce a specific path, following an example provided by the medical staff. Currently, these assignments are typically performed manually, and a nurse or doctor, who supervises the correctness of the movement, constantly assists the patient throughout the whole rehabilitation process. With the proposed system, our aim is to provide medical institutions and patients with a low-cost and portable instrument to automatically assess the rehabilitation improvements. To evaluate the performance of the exercise, and to determine the distance between the trial and the reference path, we adopted the dynamic time warping (DTW) and the longest common sub-sequence (LCSS) as discriminating metrics. Trajectories and numerical values are then stored to track the history of the patient and appraise the improvements of the rehabilitation process over time. Thanks to the tests conducted with real patients, it has been possible to evaluate the quality of the proposed tool, in terms of both graphical interface and functionalities.

This paper presents a novel and flexible benchmarking tool based on genetic algorithms (GA) and designed to assess the robustness of any digital image watermarking system. The main idea is to evaluate robustness in terms of perceptual quality, measured by weighted peak signal-to-noise ratio. Through a stochastic approach, we optimize this quality metric, by finding the minimal degradation that needs to be introduced in a marked image in order to remove the embedded watermark. Given a set of attacks, chosen according to the considered application scenario, GA support the optimization of the parameters to be assigned to each processing operation, in order to obtain an unmarked image with perceptual quality as high as possible. Extensive experimental results demonstrate the effectiveness of the proposed evaluation tool.

In this paper we propose a novel approach for syntactic description and matching of object trajectories in digital video, suitable for classification and recognition purposes. Trajectories are first segmented by detecting the meaningful discontinuities in time and space, and are successively expressed through an ad-hoc syntax. A suitable metric is then proposed, which allows determining the similarity among trajectories, based on the so-called inexact or approximate matching. The metric mimics the algorithms used in bio-informatics to match DNA sequences, and returns a score, which allows identifying the analogies among different trajectories on both global and local basis. The tool can therefore be adopted for the analysis, classification, and learning of motion patterns, in activity detection or behavioral understanding.

An innovative approach based on an evolutionary stochastic algorithm, namely the Particle Swarm Optimizer (PSO), is proposed in this paper as a solution to the problem of intelligent retrieval of images in large databases. The problem is recast to an optimization one, where a suitable cost function is minimized through a customized PSO. Accordingly, the relevance-feedback is used in order to exploit the information of the user with the aim of both guiding the particles inside the search space and dynamically assigning different weights to the features.

In the present work we propose a new approach to dynamically characterize trajectories for a syntactic spatio-temporal alignment that can be applied in the context of behavioral analysis and anomalous activity detection. The developed architecture is based on a symbolic representation of the trajectory, exploiting the framework of the so-called edit-distance. The acquired trajectory samples are filtered to identify the most significant spatio-temporal discontinuities: these key points are converted into a string-based domain where the matching of trajectory pairs can be expressed in terms of global alignment between symbols, similarly to DNA string matching algorithms. The extraction, characterization and alignment of trajectories have been tested in different environments, demonstrating the reliability of the achieved results and the viability of the solution for video surveillance and domotics applications.

The present paper proposes an asymmetric watermarking scheme suitable for fingerprinting and precision-critical applications. The method is based on linear algebra and is proved to be secure under projection attack. The problem of anonymous fingerprinting is also addressed, by allowing a client to get a watermarked image from a server without revealing her own identity. In particular, we consider the specific scenario where the client is a structured organization being trusted as a whole but involving possibly untrusted members. In such a context, where the watermarked copy can be made available to all members, but only authorized subgroups should be able to remove the watermark and recover a distortion-free image, a multilevel access to the embedding key is provided by applying Birkhoff polynomial interpolation. Extensive simulations demonstrate the robustness of the proposed method against standard image degradation operators.

In the recent years, MIMO MC-CDMA techniques have been proposed in order to increase system capacity over frequency-selective wireless channels. The key feature of MIMO MC-CDMA is the capability of exploiting diversity jointly in time, frequency and in the space domains. Very promising results have been achieved by STBC-MIMO MC-CDMA using receiver schemes targeted to maximize the signal-to-noise plus interference ratio (SINR) at the output of the diversity combiner. Such a concept turns on the minimum mean squared error (MMSE) combining criterion. Nevertheless, it is known by literature that MSE cost function is not always optimal in digital communications. In this work, we are proposing an adaptive multi-user detection approach based on a minimum-BER (M- BER) concept for a synchronous STBC-MIMO MC-CDMA system transmitting data over time-varying multipath fading channels. The practical implementation of the M-BER receiver relies on an adaptive least-mean-square (LMS)-like algorithm, periodically aided by a training sequence and working in decision-directed modality during a coherence time window. Experimental results have shown a performance improvement yielded by the proposed adaptive M-BER MUD with respect to MMSE adaptive MUD achieved by spending an affordable computational effort.

We introduce a novel asymmetric watermarking scheme, involving a private key for embedding and a public key for detection, and we detail its statistical analysis, relying on Neyman-Pearson criterion. The proposed scheme solves part of the problems connected to previous watermarking approaches based on linear algebra. In particular, special attention is paid at reducing the side information required at the detector, as well as at achieving higher robustness by enphasizing the contribution of the watermark in the detection phase.

Input peripherals such as mouse, tablet or touchscreen, significantly contributed to ease the attitude of humans towards computing machines. They reduce the need of a keyboard and make the interaction with the computer faster and more instinctive, in particular for unskilled users. Next step would be the complete removal of any tangible device, towards the concept of "disappearing computer". In this paper we propose an interactive virtual blackboard, based on a video processing and gesture recognition engine, which enables the user interacting almost seamlessly with the system giving commands, writing, and manipulating objects on a projected visual interface.

This letter aims at proposing the use of evolutionary computation methodologies (i.e., genetic algorithms) in order to solve the problem of the maximum-likelihood estimation of orthogonal frequency-division multiplexing symbols in the presence of nonlinear distortions. Experimental results can prove the effectiveness of the proposed detection algorithm achieved with a reasonable computational load

The possibility of adding several watermarks to the same image would enable many interesting applications such as multimedia document tracing, data usage monitoring, multiple property management. In this paper, we present a novel watermarking scheme which allows to insert and reliably detect multiple watermarks sequentially embedded into a digital image. The proposed method, based on elementary linear algebra, is asymmetric, secure under projection attack and robust against distortion due to basic operations such as storage, transmission, format conversion, etc

Edges are known to be a semantically rich representation of the contents of a digital image. Nevertheless, their use in practical applications is sometimes limited by computation and complexity constraints. In this paper, a new approach is presented that addresses the problem of matching visual objects in digital images by combining the concept of edge potential functions (EPF) with a powerful matching tool based on genetic algorithms (GAs). EPFs can be easily calculated starting from an edge map and provide a kind of attractive pattern for a matching contour, which is conveniently exploited by GAs. Several tests were performed in the framework of different image matching applications. The results achieved clearly outline the potential of the proposed method as compared to state of the art methodologies

The paper proposes an adaptive retrieval approach based on the concept of relevance-feedback, which establishes a link between high-level concepts and low-level features, using the user's feedback not only to assign proper weights to the features, but also to dynamically select them within a large collection of parameters. The target is to identify a set of relevant features according to a user query while at the same time maintaining a small sized feature vector to attain better matching and lower complexity. To this end, the image description is modified during each retrieval by removing the least significant features and better specifying the most significant ones. The feature adaptation is based on a hierarchical approach. The weights are then adjusted based on previously retrieved relevant and irrelevant images without further user-feedback. The algorithm is not fixed to a given feature set. It can be used with different hierarchical feature sets, provided that the hierarchical structure is defined a priori. Results achieved on different image databases and two completely different feature sets show that the proposed algorithm outperforms previously proposed methods. Further, it is experimentally demonstrated that it approaches the results obtained by state-of-the-art feature-selection techniques having complete knowledge of the data set.

The possibility of adding several watermarks to the same image would enable many interesting applications such as multimedia document tracing, data usage monitoring, multiple property management. In this paper, we present a novel watermarking scheme which allows to insert and reliably detect multiple watermarks sequentially embedded into a digital image, while maintaining a good perceptual quality. The proposed method, based on elementary linear algebra, is asymmetric, secure under projection attack and robust against noise addition and JPEG compression.

In this work, a novel minimum-mean squared-error (MMSE) multi-user detector is proposed for MC-CDMA transmission systems working over mobile radio channels characterized by time-varying multipath fading. The proposed MUD algorithm is based on a genetic algorithm (GA)-assisted per-carrier MMSE criterion. The GA block works in two successive steps: a training-aided step aimed at computing the optimal receiver weights using a very short training sequence, and a decision-directed step aimed at dynamically updating the weights vector during a channel coherence period. Numerical results evidenced BER performances almost coincident with ones yielded by ideal MMSE-MUD based on the perfect knowledge of channel impulse response. The proposed GA-assisted MMSE-MUD outperforms state-of-the-art adaptive MMSE receivers based on deterministic gradient algorithms, especially for high number of users

In this paper the problem of transmitting embedded bitstreams over wireless packet networks is considered. In particular, the authors address the problem of joint usage of power control and forward error correction for optimizing video streams delivery, and analyze the performance in different scenarios. Experimental results, obtained for the transmission of MPEG-4 FGS bitstreams, show the impact of the proposed method in the case of different modulation schemes.

One of the main problems in content-based image retrieval is the query initialization and so-called "page-zero problem". The early solutions range from the use of similar images to definition of a user sketch (using color, texture, or shape information). The latter implies user's choice of a starting point, which can be achieved in different ways. In this paper a new approach to this problem is proposed based on relevance feedback. The objective is to provide a very simple interface, where at each iteration the user should make a binary decision based on two presented images. Experimental results show that the proposed approach performs very well compared to existing methods, while providing a very simple and intuitive interaction

In this paper, the problem of transmitting embedded bitstreams over wireless packet networks is considered. In particular, the authors address the problem of optimal energy allocation in video streams employing fixed-size packets, and analyze the performance under different modulation schemes. Results obtained for the transmission of MPEG-4 FGS bitstreams show the impact of the proposed method in different modulation schemes.

In this letter, a real-world working case of interfering signals coming to an antenna array with random arrivals modeled as a Poisson process is considered. A procedure based on a suitable genetic algorithm for adaptive array control is assessed by means of numerical simulations. Selected results clearly demonstrate the effectiveness and flexibility of the proposed procedure.

Multicarrier code division multiple access (MC-CDMA) techniques were originally proposed at mid of 90's for wideband multi-user communications in wireless environments characterised by hostile propagation characteristics. Problems still to be solved are related to the provision of efficient resource channel allocation in variable-bit-rate transmission. In this work, a strategy for medium access control in MC-CDMA systems for broadband WLAN indoor applications is considered. A great advantage of MC-CDMA lies in the capability of supporting asynchronous multi-user variable-bit-rate (VBR) transmission over multipath channel with conventional detection. This can be helpful in designing an efficient and real-time medium access control (MAC) strategy, since a significant number of VBR users can share the same bandwidth without relevant performance dropouts. Different classes of users will be labeled by the MAC level that has to plan a controlled access to the channel on the basis of the users' requests and to check the possibility of assuring to them a certain QoS degree. The paper presents some simulation results in order to discuss the feasibility of the proposed access control strategy.

In this paper, a new approach to the image retrieval problem is presented, that uses edge potential functions (EPF) and genetic algorithms (GA). The method allows a user to draw a rough sketch of the shape and to find or rank the images in a database that contain a similar shape at any position, rotation and scaling factor. It is explained how GAs allow to exploit the capability of EPFs to attract a sketch contour as a result, the algorithm provides the set of geometrical transformations corresponding to the best match, and a confidence factor about the presence of a matching object. The method has been widely tested achieving very satisfactory results.

Forest cover maps, showing the location and the extent of different forest types, are essential tools for forest monitoring and planning. Nowadays, remote sensing is one of the most important source of forest cover classifications at different scales. In this paper, the usefulness of middle resolution images (SPOT HRV) for forest cover mapping at local scale is evaluated (1) and a fuzzy classification approach is tested for increasing forest discrimination at the specific level (2). The study was carried out in a mountain test area located in the eastern Alps of Italy within the RI.SELV.ITALIA project founded by the Italian Ministry of Agriculture and Forests. It was based on a data-set composed of two SPOT images, topographically corrected, and some ground inventory data. The SPOT images, taken in summer and autumn, were selected in order to use the phenology characteristics of the different forest species for improving the separability between evergreen and deciduous species. The bi-temporal images were firstly combined in a single multi-temporal image which was later classified using both maximum likelihood and fuzzy classification methods. In order to identify the best classification procedure, the results of both classifications were evaluated using independent ground inventory data and then compared. The fuzzy classification approach gave more accurate results in forest species discrimination, while the maximum likelihood algorithm showed some limits in classifying the forest cover in such a complex landscapes characterized by rugged terrain and by the frequent presence of mixed forests.

A significant improvement of block-based motion estimation strategies is presented, which supports fast computation and VLBR coding. For each block, a spatio-temporal context is defined based on nearest neighbors in the current and previous frames, and a prediction list is built. Then, the best matching vector within the list is chosen as an estimation of the block motion. An additional correction vector can be sent when the prediction error exceeds a threshold. Bit rate saving is achieved through an adaptive sorting of the prediction list of each block, which allows one to reduce the entropy of the motion indexes. Tests demonstrate a speed up above 1:200 as compared to full search, and a coding gain above 2, with a negligible loss of accuracy.

Texture analysis based on the extraction of contrast features is very effective in terms of both computational complexity and discrimination capability. In this framework, max–min approaches have been proposed in the past as a simple and powerful tool to characterize a statistical texture. In the present work, a method is proposed that allows exploiting the potential of max–min approaches to efficiently solve the problem of detecting local alterations in a uniform statistical texture. Experimental results show a high defect discrimination capability, and a good attitude to real-time applications, which make it particularly attractive for the development of industrial visual inspection systems.

Current standards for video compression achieve good performances in terms of data compaction and signal-to-noise ratio of the decoded signal. Nevertheless, there are some known problems concerning the visual quality of reconstructed images, which can be partially solved using appropriate post-processing algorithms. The paper proposes a new adaptive anisotropic filter (AAF) that aims to unify the treatment of different sources of perceptive distortion in MPEG sequences. The process is driven by a local classification of blocks and single pixels of decoded frames, taking into account several parameters (distribution of DCT coefficient energy, presence of sharp variations, spatial position of DCT block boundaries). Experimental results show that the proposed algorithm outperforms existing enhancement approaches, in particular when constraints on complexity and real-time processing are compelling.

A significant improvement of block-based motion estimation strategies is presented, which provides fast computation and very low bitrate coding. For each block, a spatio-temporal context is defined based on nearest neighbors in the current and previous frames, and a prediction list is built. Then, the best matching vector within the list is chosen as an estimation of the block motion. Since coder and decoder are synchronous, only the index of the selected vector is needed at the decoder to reconstruct the motion field. To avoid the propagation of the error, an additional correction vector can be sent when prediction error exceeds a threshold. Furthermore, bitrate saving is achieved through an adaptive sorting of the prediction list of each block, which allows to reduce the entropy of the motion indexes. Tests demonstrate that the proposed method ensures a speed up over 1:200 as compared to full search, and a coding gain above 2, with a negligible loss of accuracy. This allows real-time implementation of VLBR software video coders on conventional PC platforms.

The transmission of block-coded visual information over packet networks introduces fidelity problems in terms of data losses, which result in wrong reconstruction of block sequences at the decoder. Concealment techniques aim at masking the visual effect of these errors, by exploiting either spatial or temporal available information. Both temporal and spatial approaches present drawbacks: the first is in general inefficient in handling complex or fast objects' motion, while the second is computationally expensive and is not able to recover high-frequency contents and small details. In this paper, a new solution is proposed that combines temporal and spatial approaches. The technique first replaces the lost block with the best matching pattern in a previously decoded frame (BMA), using the border information, and then applies a mesh-based warping (MBW) that reduces the artifacts caused by fast movements, rotations or deformations. The first step is achieved by a fast matching algorithm, for a high precision is not needed, while the second step uses an affine transform applied to a deformable mesh structure. Experimental results show that significant improvements can be achieved in comparison with traditional spatial or temporal concealment approaches, in terms of both subjective and objective reconstruction quality.

Most widespread video coding algorithms (such as MPEG, H.261, H.263) employ DCT coding for data compression but introduce annoying artefacts due mainly to the independent quantization of the coefficients in each block, that are especially visible at medium and low bitrates. Within this framework, post-processing appears to be a practical solution for visual enhancement of compressed video. In this paper, an adaptive anisotropic spatial-variant FIR filtering procedure is proposed. The filter kernels are selected on the basis of a pixel classification procedure that performs a block-DCT coefficients energy analysis and an edge extraction. The analysis of the transform coefficients matrix allows one to extract information about spatial characteristics, while the edge information provide the basis for the estimation of the position of the local visual artifact. Accurate filtering results were obtained during experiments that outperform those obtained with other existing approaches.

In this paper, the problem of DCT information recovery in the transmission of coded visual data over packet networks is addressed. The loss of a packet conveying coded block data leads to the unsuccessful reconstruction of the relevant area, with consequent degradation of the received image quality. The proposed method allows recovery of a subset of the missing DCT coefficients sufficient to achieve good reconstruction quality of the lost block, based on the available surrounding information. To this purpose, a neural predictor was carefully designed and suitably trained with an appropriate set of synthetic and natural patterns. An extensive testing phase, performed on a large set of images with different frequency characteristics, revealed that the method provides very good reconstruction capabilities.

In this paper, a mechanism for the recovery of lost data in the transmission of JPEG coded images over packet networks is presented. The loss of a packet conveying coded block data brings to the unsuccessful reconstruction of the relevant picture area. The proposed method allows to recover a subset of DCT coefficients by exploiting the structure of the correctly received neighboring blocks, in the very critical case when the loss concerns all the block coefficients. For this purpose a neural predictor was specifically designed and suitably trained with a set of carefully studied synthetic patterns. It directly works in the transformed domain, allowing a real time reconstruction of damaged blocks. The results achieved show that the method has very good reconstruction capability both on synthetic and natural test data.

The paper presents a comparison of the principal lossy compression algorithms, vector quantization (VQ), JPEG and wavelets (WV) posterior KLT applied to multispectral remotely sensed images and evaluated by the classification algorithm K-NN (K-nearest neighbor). The main goal of the compression of remotely sensed images is a reduction of the huge requirements for downlink and storage. The Karhunen Loeve transform first removes the interband correlation to produce the principal components of the image which are then compressed by the principal algorithms. The quality evaluation was done by a supervised classification with the well known algorithm K-NN for remote sensing applications and the MSE for visual aspects. The obtained results of these accurate and particular analysis of the current compression techniques are quite surprisingly compared to other previous works.

This paper presents an original approach to the lossless encoding of an exhaustive image partition. The method is based on a preliminary quad-tree description of the partition that associates adaptive sized blocks to the leaves of the tree. The generated blocks can have a minimum dimension of one pixel, in order to fit every possible region shape. Using such a preliminary quad-tree, coded with just a few bits, we univocally describe the partition using some additional information that relates together the leaves. Every leaf of the quad-tree is given a label, with the rule that two neighboring leaves share the same label only if they belong to the same region. By exploiting a classical result of the planar geometry, known as the four colors theorem, it is possible to reduce the number of labels (i.e., colors) to a theoretical limit of four. A simple and efficient color allocation algorithm is also proposed, which uses more than four colors, but that reduces the entropy to less than 2 bits per color. The achieved representation is particularly useful in region-based image coders, for it greatly reduces the code dimension as compared to classical edge-based methods.

This paper presents a new strategy that exploits artificial neural networks (ANNs) for a direct selection of edge points from an image. First, a spatial filtering for edge enhancement (the Canny filter) is used to obtain a set of candidate edge points which turn out to be the local maxima of the filtered image (MPS). A preliminary coarse selection of these points that exploits neighborhood information is performed to produce an extended pseudo-edges set (PES). Then, a features vector is extracted from the PES and is used by a neural classifier to decide whether or not a point belongs to the target edge set (TES).

Simple approaches to texture discrimination based on histogram analysis are useful in real-time applications but often yield inadequate results. On the other hand, methods based on higher-order statistics (e.g., co-occurrence matrices) provide a more complete statistical characterisation but are extremely time-consuming. In this paper, methods based on first order statistical analysis are reviewed and the significance of the relevant representative features analyzed. Then, rank functions are considered and appropriate distance functions are introduced that prove to have substantial advantages over classical histogram-based approaches.

This paper presents a novel predictive coding scheme for image-data compression by vector quantization (VQ). On the basis of a prediction, further compression is achieved by using a dynamic codebook-reordering strategy that allows a more efficient Huffman encoding of vector addresses. The proposed method is lossless, for it increases the compression performances of a baseline vector quantization scheme, without causing any further image degradation. Results are presented and a comparison with Cache-VQ is made.

The paper focuses on a new method for block based disparity estimation (BBDE) that is specially suited for real time coding of stereo sequences. The estimation is performed by exploiting a preliminary disparity field, obtained from the coarsest level of a multiresolution pyramid, and its successive refinements in the finer ones. A strong correction strategy for wrong estimates has been implemented by using an appropriate propagation of disparity vectors from one level to the next one and an adaptive search range. Finally, a variable-resolution disparity field is achieved stopping the propagation at an intermediate level of resolution, if a vector allows a good reconstruction quality of its block.

The paper presents an adaptive scheme for image-data compression. It is a region-based approach that suitably integrates two different approaches to image coding, vector quantization (VQ) and polynomial approximation (PA). The scheme is adaptive from the point of view of the human observer: the perceptually most significant areas are those near edges or details. In smoothed areas, PA can be used with notable results, but there VQ must be employed to ensure high fidelity. The two techniques exhibit a complementarity in both advantages and drawbacks. PA is not efficient in compressing high-frequency areas, but yields the best results when applied to highly correlated data. VQ is unable to reach high-compression ratios because of its low adaptability, but is quite suitable for compressing uncorrelated data. The means to achieve the integration of the two techniques is a control image containing information about edge and texture locations. In the paper, edge encoding and restoration are also addressed, which are closely related to the proposed hybrid scheme; block prediction is also utilized to further reduce the residual redundancy between VQ blocks. The exploitation of the best features of both approaches results in high compression factors, and in perceivable good quality. In particular, bit rates range from 0.15 to 0.07 bpp. Main applications of this compression scheme are in the areas of very-low bit rate image transmission and image archiving.>

A novel approach to video coding at very low bit rates is presented, which differs significantly from most of previous approaches, as it uses a spline-like interpolation scheme in a spatiotemporal domain. This operator is applied to a non-uniform 3D grid (built on sets of consecutive frames) so as to allocate the information adaptively. The proposed method allows a full exploitation of intra/inter-frame correlations and a good objective and visual quality of the reconstructed sequences.>

A new strategy for video coding at very low bit rates is proposed in the paper, where an image sequence is encoded in a two-source way. The main difference from state-of-the-art approaches lies in the use of a 3D spatio-temporal interpolation, based on a non-uniform grid (frames are processed in overlapped blocks), in order to allocate the information in an adaptive way. Experimental results show a good fidelity of the decoded sequences, without blocking effect.>

A system for the processing and interpretation of underwater images acquired with an acoustic sensor is presented. As a first objective, the system aims to recognize simple objects with known characteristics located at different positions so as to create a scenario. The proposed recognition system exhibits the features of a knowledge-based system, as it is based on ideal models (provided by an expert) of the possible objects present in the scene, and the matching of such models with the real objects detected by processing data coming from the acquisition system. The numerical data provided by different types of sensors are first processed by some low-level modules. The high-level modules operate a matching of the objects detected with the models, according to criteria of maximum fuzzy reliability. Results are presented and discussed.>

The authors discuss with the development of a coding system able to reach high compressions of picture data, without notable distortion, by integrating vector quantization and polynomial approximation. The whole process is driven by the latter, while the former is used in textured areas only. The polynomial approximation module is described in depth, together with its integration with the other module. Results obtained on standard images are presented and discussed.>