Abstract: This paper presents a preliminary study on the registration and fusion of cross-spectral imaging. The objective is to evaluate the validity of widely used computer vision approaches when they are applied at different
spectral bands. In particular, we are interested in merging images from the infrared (both long wave infrared: LWIR and near infrared: NIR) and visible spectrum (VS). Experimental results with different data sets are presented.

Abstract: This paper presents a novel model to estimate human activities — a human activity is defined by a set of human actions. The proposed approach is based on the usage of Recurrent Neural Networks (RNN) and Bayesian inference through the continuous monitoring of human actions and its surrounding environment. In the current work human activities are inferred considering not only visual analysis but also additional resources; external sources of information, such as context information, are incorporated to contribute to the activity estimation. The novelty of the proposed approach lies in the way the information is encoded, so that it can be later associated according to a predefined semantic structure. Hence, a pattern representing a given activity can be defined by a set of actions, plus contextual information or other kind of information that could be relevant to describe the activity. Experimental results with real data are provided showing the validity of the proposed approach.

Abstract: 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, multimodality and strong multi-view classifier) affect performance both individually and when integrated together. In the multimodality 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.

Abstract: Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos.

Abstract: In this paper, we present a novel methodology to compute a 3D scene
representation. The algorithm uses macro scale polygonal primitives to model the scene. This means that the representation of the scene is given as a list of large scale polygons that describe the geometric structure of the environment. Results show that the approach is capable of producing accurate descriptions of the scene. In addition, the algorithm is very efficient when compared to other techniques.

Abstract: Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and generate samples that preserve global structure but tend to suffer from image blurriness. PixelCNNs model sharp contours and details very well, but lack an explicit latent representation and have difficulty modeling large-scale structure in a computationally efficient way. In this paper, we present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN. The resulting architecture achieves state-of-the-art log-likelihood on binarized MNIST. We extend PixelVAE to a hierarchy of multiple latent variables at different scales; this hierarchical model achieves competitive likelihood on 64x64 ImageNet and generates high-quality samples on LSUN bedrooms.

Abstract: Pedestrian detection for autonomous driving is one of the hardest tasks within computer vision, and involves huge computational costs. Obtaining acceptable real-time performance, measured in frames per second (fps), for the most advanced algorithms is nowadays a hard challenge. Taking the work in [1] as our baseline, we propose a CUDA implementation of a pedestrian detection system that includes LBP and HOG as feature descriptors and SVM and Random forest as classifiers. We introduce significant algorithmic adjustments and optimizations to adapt the problem to the NVIDIA GPU architecture. The aim is to deploy a real-time system providing reliable results.

Abstract: Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. The irruption of deep convolutional neural networks (DCNNs) allows to foresee obtaining reliable classifiers to perform such a visual task. However, DCNNs require to learn many parameters from raw images; thus, having a sufficient amount of diversified images with this class annotations is needed. These annotations are obtained by a human cumbersome labour specially challenging for semantic segmentation, since pixel-level annotations are required. In this paper, we propose to use a virtual world for automatically generating realistic synthetic images with pixel-level annotations. Then, we address the question of how useful can be such data for the task of semantic segmentation; in particular, when using a DCNN paradigm. In order to answer this question we have generated a synthetic diversified collection of urban images, named SynthCity, with automatically generated class annotations. We use SynthCity in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments on a DCNN setting that show how the inclusion of SynthCity in the training stage significantly improves the performance of the semantic segmentation task