Despite recent significant advances, object detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities, and a strong multiview (MV) classifier that accounts for different object views and poses. In this paper, we provide an extensive evaluation that gives insight into how each of these aspects (multicue, multimodality, and strong MV classifier) affect accuracy both individually and when integrated together. In the multimodality component, we explore the fusion of RGB and depth maps obtained by high-definition light detection and ranging, a type of modality that is starting to receive increasing attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the accuracy, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient.

Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multi-modality and strong multi-view classifier) affect performance both individually and when integrated together. In the multi-modality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.

This paper describes a general method to address partial occlusions for human detection in still images. The random subspace method (RSM) is chosen for building a classifier ensemble robust against partial occlusions. The component classifiers are chosen on the basis of their individual and combined performance. The main contribution of this work lies in our approach's capability to improve the detection rate when partial occlusions are present without compromising the detection performance on non occluded data. In contrast to many recent approaches, we propose a method which does not require manual labeling of body parts, defining any semantic spatial components, or using additional data coming from motion or stereo. Moreover, the method can be easily extended to other object classes. The experiments are performed on three large datasets: the INRIA person dataset, the Daimler Multicue dataset, and a new challenging dataset, called PobleSec, in which a considerable number of targets are partially occluded. The different approaches are evaluated at the classification and detection levels for both partially occluded and non-occluded data. The experimental results show that our detector outperforms state-of-the-art approaches in the presence of partial occlusions, while offering performance and reliability similar to those of the holistic approach on non-occluded data. The datasets used in our experiments have been made publicly available for benchmarking purposes.

Pedestrian detection is one of the most challenging tasks in computer vision, and has received a lot of attention in the last years. Recently, some authors have shown the advantages of using combinations of part/patch-based detectors in order to cope with the large variability of poses and the existence of partial occlusions. In this paper, we propose a pedestrian detection method that efficiently combines multiple local experts by means of a Random Forest ensemble. The proposed method works with rich block-based representations such as HOG and LBP, in such a way that the same features are reused by the multiple local experts, so that no extra computational cost is needed with respect to a holistic method. Furthermore, we demonstrate how to integrate the proposed approach with a cascaded architecture in order to achieve not only high accuracy but also an acceptable efficiency. In particular, the resulting detector operates at five frames per second using a laptop machine. We tested the proposed method with well-known challenging datasets such as Caltech, ETH, Daimler, and INRIA. The method proposed in this work consistently ranks among the top performers in all the datasets, being either the best method or having a small difference with the best one.

Multiple Instance Learning (MIL) has become a hot topic and many different algorithms have been proposed in the last years. Despite this fact, there is a lack of comparative studies that shed light into the characteristics of the different methods and their behavior in different scenarios. In this paper we provide such an analysis. We include methods from different families, and pay special attention to vocabulary-based approaches, a new family of methods that has not received much attention in the MIL literature. The empirical comparison includes seven databases from four heterogeneous domains, implementations of eight popular MIL methods, and a study of the behavior under synthetic conditions. Based on this analysis, we show that, with an appropriate implementation, vocabulary-based approaches outperform other MIL methods in most of the cases, showing in general a more consistent performance.

In this paper, we present a general guideline to find a better distance measure for similarity estimation based on statistical analysis of distribution models and distance functions. A new set of distance measures are derived from the harmonic distance, the geometric distance, and their generalized variants according to the Maximum Likelihood theory. These measures can provide a more accurate feature model than the classical Euclidean and Manhattan distances. We also find that the feature elements are often from heterogeneous sources that may have different influence on similarity estimation. Therefore, the assumption of single isotropic distribution model is often inappropriate. To alleviate this problem, we use a boosted distance measure framework that finds multiple distance measures which fit the distribution of selected feature elements best for accurate similarity estimation. The new distance measures for similarity estimation are tested on two applications: stereo matching and motion tracking in video sequences. The performance of boosted distance measure is further evaluated on several benchmark data sets from the UCI repository and two image retrieval applications. In all the experiments, robust results are obtained based on the proposed methods.

This paper presents an efficient object-class recognition approach based on a new type of image descriptor: the Class-Specific Binary Correlogram (CSBC). In our representation, the image is described by a collection of CSBCs, where each one encodes the spatial distribution of class-specific features around a particular reference point. This representation is obtained by first performing an automatic selection of class-specific features from a vocabulary, and then extracting collections of binary correlograms that encode, at the same time, detected object parts and their spatial distribution around multiple points of the image. Our descriptors live in high-dimensional spaces (in the order of 10K dimensions), but they are very sparse. We show that efficient learning and matching procedures can be obtained for such a representation if we use, first, fast feature selection techniques specific for binary features, and then Boosting integrated with an appropriate Inverted File data organization. The proposed strategy works with weak supervision, outperforms state-of-the-art bag-of-feature methods, and it is more accurate and computationally more efficient than well-known geometrical-based methods, including our previous work on Generalized Correlograms (GCs) [1]. 1

We present a novel approach for retrieval of object categories based on a novel type of image representation: the Generalized Correlogram (GC). In our image representation, the object is described as a constellation of GCs where each one encodes information about some local part and the spatial relations from this part to others (i.e., the part's context). We show how such a representation can be used with fast procedures that learn the object category with weak supervision and efficiently match the model of the object against large collections of images. In the learning stage, we show that by integrating our representation with Boosting the system is able to obtain a compact model that is represented by very few features, where each feature conveys key properties about the object's parts and their spatial arrangement. In the matching step, we propose direct procedures that exploit our representation for efficiently considering spatial coherence between the matching of local parts. Combined with an appropriate data organization such as Inverted Files, we show that thousands of images can be evaluated efficiently. The framework has been applied to different standard databases and we show that our results are favorably compared against state-of-the-art methods in both computational cost and accuracy.

In this paper, we present a general guideline to establish the relation between a distribution model and its corresponding similarity estimation. A rich set of distance metrics, such as harmonic distance and geometric distance, is derived according to Maximum Likelihood theory. These metrics can provide a more accurate feature model than the conventional Euclidean distance (SSD) and Manhattan distance (SAD). Because the feature elements are from heterogeneous sources and may have different influence on similarity estimation, the assumption of single isotropic distribution model is often inappropriate. We propose a novel boosted distance metric that not only finds the best distance metric that fits the distribution of the underlying elements but also selects the most important feature elements with respect to similarity. We experiment with different distance metrics for similarity estimation and compute the accuracy of different methods in two applications: stereo matching and motion tracking in video sequences. The boosted distance metric is tested on fifteen benchmark data sets from the UCI repository and two image retrieval applications. In all the experiments, robust results are obtained based on the proposed methods.

Distance metric is widely used in similarity estimation. In this paper we find that the most popular Euclidean and Manhattan distance may not be suitable for all data distributions. A general guideline to establish the relation between a distribution model and its corresponding similarity estimation is proposed. Based on maximum likelihood theory, we propose new distance metrics, such as harmonic distance and geometric distance. Because the feature elements may be from heterogeneous sources and usually have different influence on similarity estimation, it is inappropriate to model the distribution as isotropic. We propose a novel boosted distance metric that not only finds the best distance metric that fits the distribution of the underlying elements but also selects the most important feature elements with respect to similarity. The boosted distance metric is tested on fifteen benchmark data sets from the UCI repository and two image retrieval applications. In all the experiments, robust results are obtained based on the proposed methods

We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized correlograms that integrate both information of local parts and their spatial relations. Incorporating the spatial relations into our constellation of descriptors, we show that an exhaustive search for the best matching can be avoided. Combining the contextual descriptors with boosting, the system simultaneously learns the information that characterize each part of the object along with their characteristic mutual spatial relations. The proposed framework includes a matching step between homologous parts in the training set, and learning the spatial pattern after matching. In the matching part two approaches are provided: a supervised algorithm and an unsupervised one. Our results are favorably compared against state-of-the-art results.

We present a content-based image retrieval system of medical images of bodies with high elasticity, that is, high inter- and intrasubject variability in shape. The system is based on a rich feature space that is able to describe all the relevant aspects of an image, including local, global, and contextual information. For including relative spatial relations between the structures (i.e., contextual information) we do not need to obtain very accurate segmentations of the image, in contrast to the majority of methods employed for this kind of description. We also obtain invariance to spatial deformations of the same type of object along different instances. This is achieved by applying efficient registrations of the images before their comparison. The incorporation of all these components represents an innovative and powerful way of comparing and retrieving medical images. Validated results are reported on a database of 168 intravascular ultrasound images, showing the appropriateness of our approach for images of such high complexity. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 541–559, 2005.