Abstract: 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.

Abstract: Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features and shallow machine learning and, despite its unprecedented performance gains, the problem remains open within the deep learning paradigm due to its data-hungry nature. Best performing deep vision-based object detectors are trained in a supervised manner by relying on human-labeled bounding boxes which localize class instances (i.e. objects) within the training images. Thus, object detection is one of such tasks for which human labeling is a major bottleneck. In this article, we assess co-training as a semi-supervised learning method for self-labeling objects in unlabeled images, so reducing the human-labeling effort for developing deep object detectors. Our study pays special attention to a scenario involving domain shift; in particular, when we have automatically generated virtual-world images with object bounding boxes and we have real-world images which are unlabeled. Moreover, we are particularly interested in using co-training for deep object detection in the context of driver assistance systems and/or self-driving vehicles. Thus, using well-established datasets and protocols for object detection in these application contexts, we will show how co-training is a paradigm worth to pursue for alleviating object labeling, working both alone and together with task-agnostic domain adaptation.

Abstract: In this paper, a continuous head pose estimation system is proposed to estimate yaw and pitch head angles from raw facial images. Our approach is based on manifold learningbased methods, due to their promising generalization properties shown for face modelling from images. The method combines histograms of oriented gradients, generalized discriminative common vectors and continuous local regression to achieve successful performance. Our proposal was tested on multiple standard face datasets, as well as in a realistic scenario. Results show a considerable performance improvement and a higher consistence of our model in comparison with other state-of-art methods, with angular errors varying between 9 and 17 degrees.

Abstract: This manuscript evaluates the usage of fused cross-spectral images in a monocular visual odometry approach. Fused images are obtained through a Discrete Wavelet Transform (DWT) scheme, where the best setup is empirically obtained by means of a mutual information based evaluation metric. The objective is to have a flexible scheme where fusion parameters are adapted according to the characteristics of the given images. Visual odometry is computed from the fused monocular images using an off the shelf approach. Experimental results using data sets obtained with two different platforms are presented. Additionally, comparison with a previous approach as well as with monocular-visible/infrared spectra are also provided showing the advantages of the proposed scheme.

Abstract: This paper presents a novel method extracting biometric measures using depth sensors. Given a multi-part labeled training data, a new subject is aligned to the best model of the dataset, and soft biometrics such as lengths or circumference sizes of limbs and body are computed. The process is performed by training relevant pose clusters, defining a representative model, and fitting a 3D shape context descriptor within an iterative matching procedure. We show robust measures by applying orthogonal plates to body hull. We test our approach in a novel full-body RGB-Depth data set, showing accurate estimation of soft biometrics and better segmentation accuracy in comparison with random forest approach without requiring large training data.