This work presents a low-power embedded eye-tracking system based on Photosensor Oculography (PSOG) and evaluates lightweight calibration-driven distance-based classifiers for discrete gaze-zone estimation in smart eyewear.The proposed prototype integrates infrared LEDs and photodiodes within a commercial frame and uses sequential illumination to generate 32-dimensional feature vectors at 1 kHz with minimal computational cost.Distancebased classifiers, including Euclidean, standardized Euclidean, and Mahalanobis metrics, were first evaluated using a humanoid robot with human-like ocular geometry under controlled conditions.The selected methods were then extensively evaluated on a human dataset comprising 29 subjects under varying illumination conditions.Results show that the Mahalanobis distance achieves the highest accuracy, while dimensionality reduction improves robustness under changing lighting.A PCA-Mahalanobis configuration provided the best accuracy-complexity trade-off, while stronger feature reduction combined with Euclidean distance enabled competitive performance at very low computational cost, supporting deployment on both high-performance and embedded smart eyewear platforms.

This work presents a low-power wearable Photosensor Oculography (PSOG) gaze-tracking system for smart glasses, repurposing the MAX86181 optical analog front-end, originally designed for photoplethysmography (PPG) to measure periocular reflectance patterns. Infrared LEDs and photodiodes are arranged around the eyes, using time-multiplexed illumination to generate 32-element feature vectors (4 PDs × 4 LEDs × 2 eyes). The system’s integrated analog/digital ambient-light cancellation preserves signal integrity across indoor to outdoor conditions, as validated on a humanoid robot platform. A lightweight Mahalanobis distance-based classifier achieves ~\(97\%\) gaze-region classification accuracy for both 5-zone and 9-zone partitions in the controlled robotic evaluation at 58.6 μs integration time. Power consumption ranges from 11 mW at 50 fps to 18.5 mW at 150 fps, corresponding to an estimated operating time from approximately 34 hours to 20 hours, respectively, on a 100 mAh, 3.7 V LiPo battery under ideal conversion efficiency. These results demonstrate the feasibility of repurposing a PPG-derived optical front-end for low-power PSOG in smart-glasses form factors. While the present validation is limited to controlled experiments on a humanoid robot and coarse gaze-region classification, the approach represents a promising step toward always-on wearable eye tracking.

Pervasive eye-tracking technology for eyewear devices represents a major advancement in wearable computing, enabling intuitive interaction and improving accessibility. However, the low-power constraints of these devices present a significant challenge in balancing accuracy with limited computational capacity. This study focuses on developing and evaluating algorithms for a low-power wearable infrared eye-tracking system conceived to work 24/7. The system includes a custom-built prototype that integrates infrared LEDs and photodiodes, strategically positioned on smart eyewear to estimate gaze direction. A humanoid robot, Ami Desktop, was utilized to create a controlled and robust dataset. Two deep learning architectures were investigated: a Multi-Layer Perceptron (MLP) and a tailored Hierarchical Neural Network (HNN). Variants of these models incorporating dimensionality reduction techniques were implemented to optimize performance and efficiency for lowpower microcontrollers. The results demonstrate the superior accuracy and reasonable computational demands of the HNN models, highlighting their potential for continuous, real-time and portable eye-tracking applications.

Outdated infrastructure contributes to significant water wastage, where leaks can represent as much as 30% of urban water supply losses. Rapid and precise leak detection is therefore crucial for economic and environmental reasons. Data-driven methods have emerged as promising solutions to detect water leaks due to their accurate performance. However, they encounter obstacles like limited labeled datasets and adapting to various situations. To address these challenges, we explore Semi Supervised Learning (SSL) and Transfer Learning (TL) techniques in the context of water leak detection. We propose to address the problem of leak detection in case of limited labeled data, using a Convolutional Neural Network (CNN) trained on a laboratory-scale network, then adapted to work on real data. To do so, we compare three different domain adaptation techniques that leverage only a small amount of data from the new domain. Our results show that Self-Tuning techniques proves better than the others for this task, even with limited data.

Due to the latest environmental concerns in keeping at bay contaminants emissions in urban areas, air pollution forecasting has been rising the forefront of all researchers around the world. When predicting pollutant concentrations, it is common to include the effects of environmental factors that influence these concentrations within an extended period, like traffic, meteorological conditions and geographical information. Most of the existing approaches exploit this information as past covariates, i.e., past exogenous variables that affected the pollutant but were not affected by it. In this paper, we present a novel forecasting methodology to predict NO2 concentration via both past and future covariates. Future covariates are represented by weather forecasts and future calendar events, which are already known at prediction time. In particular, we deal with air quality observations in a city-wide network of ground monitoring stations, modeling the data structure and estimating the predictions with a Spatiotemporal Graph Neural Network (STGNN). We propose a conditioning block that embeds past and future covariates into the current observations. After extracting meaningful spatiotemporal representations, these are fused together and projected into the forecasting horizon to generate the final prediction. To the best of our knowledge, it is the first time that future covariates are included in time series predictions in a structured way. Remarkably, we find that conditioning on future weather information has a greater impact than considering past traffic conditions. We release our code implementation at https://github.com/polimi-ispl/MAGCRN.

Water is a valuable resource that has to be handled appropriately. However, a significant volume of water is wasted annually due to leaks in Water Distribution Networks (WDNs). This emphasizes the necessity for reliable and effective leak detection and localization systems. Several types of solutions have been proposed during the last few years. Among these solutions, data-driven ones are gaining more traction due to their impressive performance. In this paper, we propose a new method for leak detection and localization. The method is based on water pressure measurements acquired at a series of nodes of a WDN. Our technique is a fully data-driven solution that makes only use of the knowledge of the WDN topology, and a series of pressure data acquisitions obtained in absence of leaks. The proposed solution is based on an autoencoder trained on no-leak data, so that leaks are detected as anomalies. The results achieved on the LeakDB dataset demonstrate that the proposed solution outperforms recent methods for leak detection and localization.

Biogenic Volatile Organic Compounds (BVOCs) play a critical role in biosphere-atmosphere interactions, being a key factor in the physical and chemical properties of the atmosphere and climate. Acquiring large and fine-grained BVOC emission maps is expensive and time-consuming, so most available BVOC data are obtained on a loose and sparse sampling grid or on small regions. However, high-resolution BVOC data are desirable in many applications, such as air quality, atmospheric chemistry, and climate monitoring. In this work, we investigate the possibility of enhancing BVOC acquisitions, further explaining the relationships between the environment and these compounds. We do so by comparing the performances of several state-of-the-art neural networks proposed for image Super-Resolution (SR), adapting them to overcome the challenges posed by the large dynamic range of the emission and reduce the impact of outliers in the prediction. Moreover, we also consider realistic scenarios, considering both temporal and geographical constraints. Finally, we present possible future developments regarding SR generalization, considering the scale-invariance property and super-resolving emissions from unseen compounds.

Water is a resource that has to be managed properly. Nevertheless, a sizable amount of water is lost each year because of leaks in Water Distribution Networks (WDNs). The need for trustworthy and efficient leak detection and localization systems is therefore an urgent necessity. For this reason, different solutions have been put out in recent years. Due to their outstanding performance, data-driven methods are among those that are gaining the most popularity. However, the performance of data-driven approaches depend on the coherence between data on which they are trained and data on which they are tested. For example, if the acquired test data look corrupted and incoherent with training ones due to sensor failure, the performance of the overall system may be severely hindered. In this work we present a resilient water leak detection and localization algorithm. It is based on two main steps: the first step analyzes acquired data to possibly recover corrupted ones by means of graph interpolation; the second step finds leaks exploiting an autoencoder-based anomaly detector proposed in the literature. The results show that the suggested approach for signal recovery by means of graph interpolation enables the detector to work in situations in which it would otherwise fail. In doing so, we address a problem that has so far received little attention in the literature: potential sensor failures when acquiring data.

Enhancing the resolution of Biogenic Volatile Organic Compound (BVOC) emission maps is a critical task in remote sensing. Recently, some Super-Resolution (SR) methods based on Deep Learning (DL) have been proposed, leveraging data from numerical simulations for their training process. However, when dealing with data derived from satellite observations, the reconstruction is particularly challenging due to the scarcity of measurements to train SR algorithms with. In our work, we aim at super-resolving low resolution emission maps derived from satellite observations by leveraging the information of emission maps obtained through numerical simulations. To do this, we combine a SR method based on DL with Domain Adaptation (DA) techniques, harmonizing the different aggregation strategies and spatial information used in simulated and observed domains to ensure compatibility. We investigate the effectiveness of DA strategies at different stages by systematically varying the number of simulated and observed emissions used, exploring the implications of data scarcity on the adaptation strategies. To the best of our knowledge, there are no prior investigations of DA in satellite-derived BVOC maps enhancement. Our work represents a first step toward the development of robust strategies for the reconstruction of observed BVOC emissions.

In recent years, the multimedia forensic community has put a great effort in developing solutions to assess the integrity and authenticity of multimedia objects, focusing especially on manipulations applied by means of advanced deep learning techniques. However, in addition to complex forgeries as the deepfakes, very simple yet effective manipulation techniques not involving any use of state-of-the-art editing tools still exist and prove dangerous. This is the case of audio splicing for speech signals, i.e., to concatenate and combine multiple speech segments obtained from different recordings of a person in order to cast a new fake speech. Indeed, by simply adding a few words to an existing speech we can completely alter its meaning. In this work, we address the overlooked problem of detection and localization of audio splicing from different models of acquisition devices. Our goal is to determine whether an audio track under analysis is pristine, or it has been manipulated by splicing one or multiple segments obtained from different device models. Moreover, if a recording is detected as spliced, we identify where the modification has been introduced in the temporal dimension. The proposed method is based on a Convolutional Neural Network (CNN) that extracts model-specific features from the audio recording. After extracting the features, we determine whether there has been a manipulation through a clustering algorithm. Finally, we identify the point where the modification has been introduced through a distance-measuring technique. The proposed method allows to detect and localize multiple splicing points within a recording.

In an era of complex networked parallel heterogeneous systems, simulating independently only parts, components, or attributes of a system-under-design is a cumbersome, inaccurate, and inefficient approach. Moreover, by considering each part of a system in an isolated manner, and due to the numerous and highly complicated interactions between the different components, the system optimization capabilities are severely limited. The presented fully-distributed simulation framework (called as COSSIM) is the first known open-source, high-performance simulator that can handle holistically system-of-systems including processors, peripherals and networks; such an approach is very appealing to both Cyber Physical Systems (CPS) and Highly Parallel Heterogeneous Systems designers and application developers. Our highly integrated approach is further augmented with accurate power estimation and security sub-tools that can tap on all system components and perform security and robustness analysis of the overall system under design—something that was unfeasible up to now. Additionally, a sophisticated Eclipse-based Graphical User Interface (GUI) has been developed to provide easy simulation setup, execution, and visualization of results. COSSIM has been evaluated when executing the widely used Netperf benchmark suite as well as a number of real-world applications. Final results demonstrate that the presented approach has up to 99% accuracy (when compared with the performance of the real system), while the overall simulation time can be accelerated almost linearly with the number of CPUs utilized by the simulator.

In an era of complex networked heterogeneous systems, simulating independently only parts, components or attributes of a system under design is not a viable, accurate or efficient option. The interactions are too many and too complicated to produce meaningful results and the optimization opportunities are severely limited when considering each part of a system in an isolated manner. The presented COSSIM simulation framework is the first known open-source, high-performance simulator that can handle holistically system-of-systems including processors, peripherals and networks; such an approach is very appealing to both CPS/IoT and Highly Parallel Heterogeneous Systems designers and application developers. Our highly integrated approach is further augmented with accurate power estimation and security sub-tools that can tap on all system components and perform security and robustness analysis of the overall networked system. Additionally, a GUI has been developed to provide easy simulation set-up, execution and visualization of results. COSSIM has been evaluated using real-world applications representing cloud (mobile visual search) and CPS systems (building management) demonstrating high accuracy and performance that scales almost linearly with the number of CPUs dedicated to the simulator.

A multi‐camera rig calibration algorithm based on a double sided planar target is proposed. Due to their inherently simple realisation, low cost and accuracy, planar calibration targets came out as one of the most largely adopted calibration tools both for intrinsic and extrinsic camera parameters. However, concerning the estimation of extrinsic parameters, one of the major drawbacks of these targets is their requirement for distinct target visibility from both cameras. This prevents many configurations from being adopted where, e.g. two cameras are facing each other. An inexpensive solution could be based on printing/pasting a planar pattern on both target sides, however, the relative misalignment between the patterns on the two sides and the target thickness could be unknown. The authors propose a solution where double‐sided target displacement error is estimated together with the extrinsic parameters allowing the reuse of all the available planar calibration tools in less constrained configurations. To assess their approach the authors tested the system in two scenarios, one using two professional 4K cameras and one using two smartphones.

We propose an infrared (IR) stereo-vision system for estimating the 3D model of the pinna, based on low-cost devices. A commercial IR calibrated stereo camera is used in conjunction with a structured IR light projector, to acquire highly textured snapshots of the pinna. A point cloud is computed for each snapshot by triangulating the stereo correspondences detected in the acquired IR images. A complete 3D model is computed by aligning and merging the point clouds, and then creating a polygonal mesh surface. The nominal accuracy of the proposed system turns to be about 1 mm, which enables an accurate prediction of the Head Related Transfer Function (HRTF) through numerical acoustic simulation.

Lens distortion is a well-known problem for camera calibration. In particular in applications where a large amount of low-quality acquisition devices is adopted, like, e.g. embedded systems or Cyber-Physical Systems (CPS), a complete re-sectioning and undistortion in different operating conditions (e.g. autofocus, zooming) could not be feasible and accurate. Usually undistortion is obtained building a proper invertible geometrical distortion model with a specific number of parameters, but, unfortunately with the actually available low cost wide-angle and ultra wide-angle lenses a simple mathematical model for a global closed form solution can be ineffective in practical cases in particular in the peripheral image regions. In order to account for these problems we present a novel local correction approach based on the planarity and orthogonality constrains for a planar target (a checkerboard) where a Look-Up Table (LUT) is built to provide the minimum displacement for every pixel in the target region minimizing interpolation and residual distortion. The proposed method can also be considered a preliminary step in order to recognize image elements before global undistortion e.g. for features matching in images stitching.

This work deals with the definition of a framework for interpreting, modeling and classifying sequences of body movements into a pre-defined vocabulary of actions. Starting from sequences of volumetric reconstructions of the actor pose in each frame, we split action recognition into three separated tasks. The first task is the representation of the four-dimensional patterns reconstructed from each sequence, the second task is the extraction of motion descriptors, and the third task is the classification into action classes. In particular, we extract the curve skeleton from the reconstructed volumes in order to underly the actor movements and to reduce the system dependence from the actor gender and the body shape. The proposed method increases the action recognition rate.

The use of iris as biometric trait has emerged as one of the most preferred method because of its uniqueness, lifetime stability and regular shape. Moreover it shows public acceptance and new user-friendly capture devices are developed and used in a broadened range of applications. Currently, iris recognition systems work well with frontal iris images from cooperative users. Nonideal iris images are still a challenge for iris recognition and can significantly affect the accuracy of iris recognition systems. In this paper, we propose a method to correct off-angle iris image. Taking into account the eye morphology and the reflectance properties of the external transparent layers, we can evaluate the distorting effect that is present in the acquired image. The correction algorithm proposed includes a first modeling phase of the human eye, a segmentation of the acquired image, and a simulation phase where the acquisition geometry is reproduced and the distortions are evaluated. Finally we obtain an image which does not contain the distorting effects due to jumps in the refractive index. We show how this correction process reduce the intra-class variations for off-angle iris images.

Modeling of 3D scenes is a hot topic in computer vision from more that thirty years, and probably its history is longer than a century considering also photogrammetry. In the recent years the rapid technological improvements that characterized the acquisition devices (photo-cameras, video-cameras, ..), illumination devices (lasers, structured light sources) and computational units allowed the application of 3D shape estimation methods, based on image analysis techniques, in a wide set of applications. Furthermore real-time 3D analysis is becoming a common tool in virtual and augmented reality contexts. Aim of this presentation is a rapid description of recent major advances on geometric and radiometric modeling of 3D scenes based on image analysis.

This paper focuses on the generation of physically valid views from two or more uncalibrated images acquired by standard cameras. The problem is faced without trying to yield a three dimensional reconstruction of the imaged scene, which would be unfeasible without the exact knowledge of the positions of the cameras in the Euclidean frame where the scene is to be described. Instead, starting from the previous works of Shashua and Navab on relative affine structure (1996) and the article of Fusiello on views synthesis from uncalibrated views (2007) we propose a novel approach that does not require the presence of a plane at infinity to define the homography between two views but merely the parallelism between couples of planes. This allows our approach to be applied to numerous scenes where two parallel planes can be defined (indoor scenes, straight streets and avenues). Experiments with synthetic images illustrate the approach.

In this paper we present a novel approach to 3-D human action classification based on the analysis of volumetric data obtained form the joint processing of video sequences acquired by a multiple-camera system. The use of volumetric data makes the system very robust and avoids problems related the typical human body self-occlusions and motion ambiguities, very common in an independent camera-by-camera analysis. A shape descriptor of a human body is obtained in order to capture only posture-dependent characteristics and its outputs at each time instant are collected together in action feature matrices. The use of dynamic time warping approach for action template matching accounts for possible temporal nonlinear distortions among different instances of the same gesture and allows gesture classification

In this paper we present a complete method to retrieve reliable correspondences among wide baseline images, that is images of the same scene/object acquired from very different viewpoints. We propose a solution based on matching of affine co-variant features, composed by the following four steps: interest region detection, normalization, description and matching. In our method we implemented improved versions of some techniques recently introduced in the literature: the MSER detector (maximally stable extremal regions) and SIFT and RIFT descriptors (scale/rotation invariant feature transform). After a general introduction to the wide baseline problems and a summary of the recent state-of-the-art solutions, we illustrate the proposed method detailing the added improvements, then we present some experimental results obtained on wide baseline images.

This paper presents a robust method for fast visual tags reading, suitable for augmented reality (AR) environments. Tag detection is based on well known tools of image-processing, but their combination, together with the use of colored markers, allows a robust recognition even with low-cost CMOS or CCD cameras and in poorly illuminated environments. In particular the color mix and the structure of the tag are quite unusual in common environments and can be easily detected with color filtering and geometric analysis. The proposed tag carries binary information encoded in its structure: in the presented implementation a 32-bit code with 12 parity bits is encoded in the tag but extensions to longer codes can be easily devised.

We propose a human action clustering method based on a 3D representation of the body in terms of volumetric coordinates. Features representing body postures are extracted directly from 3D data, making the system inherently insensitive to viewpoint dependence, motion ambiguities and self-occlusions. An invariant shape descriptor of human body is obtained in order to capture only posture-dependent characteristics, despite possible differences in translation, orientation, scale and body size. Frame-by-frame descriptions, generated from a gesture sequence, are collected together in matrices. Clustering of action matrices is eventually performed, and through a dynamic time warping (while computing the distance metric), we gain independence from possible temporal nonlinear distortions among different instances of the same gesture.

In the past few years several systems for object reconstruction based on the analysis of 2D images have been proposed. In order for such systems to be of practical use, the 3D data extraction process is expected to be fast and reliable. In this paper we propose a general approach for the reconstruction of complete 3D objects based on a mesh fusion algorithm. Every surface patch is obtained as a depth map using an algorithm based on graph cuts theory. Each depth map is then triangulated before using it in a fusion algorithm based on a voxel-set carving approach. The result of the process is a closed mesh representing the object surface with sub-voxel resolution.