Abstract: Vision-based object detectors are crucial for different applications. They rely on learnt object models. Ideally, we would like to deploy our vision system in the scenario where it must operate, and lead it to self-learn how to distinguish the objects of interest, i.e., without human intervention. However, the learning of each object model requires labelled samples collected through a tiresome manual process. For instance, we are interested in exploring the self-training of a pedestrian detector for driver assistance systems. Our first approach to avoid manual labelling consisted in the use of samples coming from realistic computer graphics, so that their labels are automatically available [12]. This would make possible the desired self-training of our pedestrian detector. However, as we showed in [14], between virtual and real worlds it may be a dataset shift. In order to overcome it, we propose the use of unsupervised domain adaptation techniques that avoid human intervention during the adaptation process. In particular, this paper explores the use of the transductive SVM (T-SVM) learning algorithm in order to adapt virtual and real worlds for pedestrian detection (Fig. 1).

Abstract: Medial representations are powerful tools for describing and parameterizing the volumetric shape of anatomical structures. Existing methods show excellent results when applied to 2D objects, but their quality drops across dimensions. This paper contributes to the computation of medial manifolds in two aspects. First, we provide a standard scheme for the computation of medial manifolds that avoid degenerated medial axis segments; second, we introduce an energy based method which performs independently of the dimension. We evaluate quantitatively the performance of our method with respect to existing approaches, by applying them to synthetic shapes of known medial geometry. Finally, we show results on shape representation of multiple abdominal organs, exploring the use of medial manifolds for the representation of multi-organ relations.

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.