Abstract: Multi-person tracking can be exploited in applications such as driver assistance, surveillance, multimedia and human-robot interaction. With the help of human detectors, particle filters offer a robust method able to filter noisy detections and provide temporal coherence. However, some traditional problems such as occlusions with other targets or the scene, temporal drifting or even the lost targets detection are rarely considered, making the systems performance decrease. Some authors propose to overcome these problems using heuristics not explained
and formalized in the papers, for instance by defining exceptions to the model updating depending on tracks overlapping. In this paper we propose to formalize these events by the use of a state-graph, defining the current state of the track (e.g., potential , tracked, occluded or lost) and the transitions between states in an explicit way. This approach has the advantage of linking track actions such as the online underlying models updating, which gives flexibility to the system. It provides an explicit representation to adapt the multiple parallel trackers depending on the context, i.e., each track can make use of a specific filtering strategy, dynamic model, number of particles, etc. depending on its state. We implement this technique in a single-camera multi-person tracker and test
it in public video sequences.

Abstract: Recognizing object categories in real world images is a challenging problem in computer vision. The deformable part based framework is currently the most successful approach for object detection. Generally, HOG are used for image representation within the part-based framework. For action recognition, the bag-of-word framework has shown to provide promising results. Within the bag-of-words framework, local image patches are described by SIFT descriptor. Contrary to object detection and action recognition, combining color and shape has shown to provide the best performance for object and scene recognition.
In the first part of this thesis, we analyze the problem of person detection in still images. Standard person detection approaches rely on intensity based features for image representation while ignoring the color. Channel based descriptors is one of the most commonly used approaches in object recognition. This inspires us to evaluate incorporating color information using the channel based fusion approach for the task of person detection.
In the second part of the thesis, we investigate the problem of object detection in still images. Due to high dimensionality, channel based fusion increases the computational cost. Moreover, channel based fusion has been found to obtain inferior results for object category where one of the visual varies significantly. On the other hand, late fusion is known to provide improved results for a wide range of object categories. A consequence of late fusion strategy is the need of a pure color descriptor. Therefore, we propose to use Color attributes as an explicit color representation for object detection. Color attributes are compact and computationally efficient. Consequently color attributes are combined with traditional shape features providing excellent results for object detection task.
Finally, we focus on the problem of action detection and classification in still images. We investigate the potential of color for action classification and detection in still images. We also evaluate different fusion approaches for combining color and shape information for action recognition. Additionally, an analysis is performed to validate the contribution of color for action recognition. Our results clearly demonstrate that combining color and shape information significantly improve the performance of both action classification and detection in still images.

Abstract: Pedestrian detection is of paramount interest for many applications, e.g. Advanced Driver Assistance Systems, Intelligent Video Surveillance and Multimedia systems. Most promising pedestrian detectors rely on appearance-based classifiers trained with annotated data. However, the required annotation step represents an intensive and subjective task for humans, what makes worth to minimize their intervention in this process by using computational tools like realistic virtual worlds. The reason to use these kind of tools relies in the fact that they allow the automatic generation of precise and rich annotations of visual information. Nevertheless, the use of this kind of data comes with the following question: can a pedestrian appearance model learnt with virtual-world data work successfully for pedestrian detection in real-world scenarios?. To answer this question, we conduct different experiments that suggest a positive answer. However, the pedestrian classifiers trained with virtual-world data can suffer the so called dataset shift problem as real-world based classifiers does. Accordingly, we have designed different domain adaptation techniques to face this problem, all of them integrated in a same framework (V-AYLA). We have explored different methods to train a domain adapted pedestrian classifiers by collecting a few pedestrian samples from the target domain (real world) and combining them with many samples of the source domain (virtual world). The extensive experiments we present show that pedestrian detectors developed within the V-AYLA framework do achieve domain adaptation. Ideally, we would like to adapt our system without any human intervention. Therefore, as a first proof of concept we also propose an unsupervised domain adaptation technique that avoids human intervention during the adaptation process. To the best of our knowledge, this Thesis work is the first demonstrating adaptation of virtual and real worlds for developing an object detector. Last but not least, we also assessed a different strategy to avoid the dataset shift that consists in collecting real-world samples and retrain with them in such a way that no bounding boxes of real-world pedestrians have to be provided. We show that the generated classifier is competitive with respect to the counterpart trained with samples collected by manually annotating pedestrian bounding boxes. The results presented on this Thesis not only end with a proposal for adapting a virtual-world pedestrian detector to the real world, but also it goes further by pointing out a new methodology that would allow the system to adapt to different situations, which we hope will provide the foundations for future research in this unexplored area.

Abstract: We present a region matching algorithm which establishes correspondences between regions from two segmented images. An abstract graph-based representation conceals the image in a hierarchical graph, exploiting the scene properties at two levels. First, the similarity and spatial consistency of the image semantic objects is encoded in a graph of commute times. Second, the cluttered regions of the semantic objects are represented with a shape descriptor. Many-to-many matching of regions is specially challenging due to the instability of the segmentation under slight image changes, and we explicitly handle it through high order potentials. We demonstrate the matching approach applied to images of world famous buildings, captured under different conditions, showing the robustness of our method to large variations in illumination and viewpoint.

Abstract: In this paper, we address the problem of reconstructing the background of a scene from a video sequence with occluding objects. The images are taken by hand-held cameras. Our method composes the background by selecting the appropriate pixels from previously aligned input images. To do that, we minimize a cost function that penalizes the deviations from the following assumptions: background represents objects whose distance to the camera is maximal, and background objects are stationary. Distance information is roughly obtained by a supervised learning approach that allows us to distinguish between close and distant image regions. Moving foreground objects are filtered out by using stationariness and motion boundary constancy measurements. The cost function is minimized by a graph cuts method. We demonstrate the applicability of our approach to recover an occlusion-free background in a set of sequences.

Abstract: This paper presents an evaluation framework for multimodal stereo matching, which allows to compare the performance of four similarity functions. Additionally, it presents details of a multimodal stereo head that supply thermal infrared and color images, as well as, aspects of its calibration and rectification. The pipeline includes a novel method for the disparity selection, which is suitable for evaluating the similarity functions. Finally, a benchmark for comparing different initializations of the proposed framework is presented. Similarity functions are based on mutual information, gradient orientation and scale space representations. Their evaluation is performed using two metrics: i) disparity error, and ii) number of correct matches on planar regions. In addition to the proposed evaluation, the current paper also shows that 3D sparse representations can be recovered from such a multimodal stereo head.