Abstract: Making Ground Autonomous Vehicles (GAVs) a reality as a service for the society is one of the major scientific and technological challenges of this century. The potential benefits of autonomous vehicles include reducing accidents, improving traffic congestion and better usage of road infrastructures, among others. These vehicles must operate in our cities, towns and highways, dealing with many different types of situations while respecting traffic rules and protecting human lives. GAVs are expected to deal with all types of scenarios and situations, coping with an uncertain and chaotic world.
Therefore, in order to fulfill these demanding requirements GAVs need to be endowed with the capability of understanding their surrounding at many different levels, by means of affordable sensors and artificial intelligence. This capacity to understand the surroundings and the current situation that the vehicle is involved in is called scene understanding. In this work we investigate novel techniques to bring scene understanding to autonomous vehicles by combining the use of cameras as the main source of information—due to their versatility and affordability—and algorithms based on computer vision and machine learning. We investigate different degrees of understanding of the scene, starting from basic geometric knowledge about where is the vehicle within the scene. A robust and efficient estimation of the vehicle location and pose with respect to a map is one of the most fundamental steps towards autonomous driving. We study this problem from the point of view of robustness and computational efficiency, proposing key insights to improve current solutions. Then we advance to higher levels of abstraction to discover what is in the scene, by recognizing and parsing all the elements present on a driving scene, such as roads, sidewalks, pedestrians, etc. We investigate this problem known as semantic segmentation, proposing new approaches to improve recognition accuracy and computational efficiency. We cover these points by focusing on key aspects such as: (i) how to leverage computation moving semantics to an offline process, (ii) how to train compact architectures based on deconvolutional networks to achieve their maximum potential, (iii) how to use virtual worlds in combination with domain adaptation to produce accurate models in a cost-effective fashion, and (iv) how to use transfer learning techniques to prepare models to new situations. We finally extend the previous level of knowledge enabling systems to reasoning about what has change in a scene with respect to a previous visit, which in return allows for efficient and cost-effective map updating.

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: Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, namely day and night time. Recent research has shown that the combination of visible and non-visible imaging modalities may increase detection accuracy, where the infrared spectrum plays a critical role. The goal of this paper is to assess the accuracy gain of different pedestrian models (holistic, part-based, patch-based) when training with images in the far infrared spectrum. Specifically, we want to compare detection accuracy on test images recorded at day and nighttime if trained (and tested) using (a) plain color images, (b) just infrared images and (c) both of them. In order to obtain results for the last item we propose an early fusion approach to combine features from both modalities. We base the evaluation on a new dataset we have built for this purpose as well as on the publicly available KAIST multispectral dataset.

Abstract: We propose an online domain adaptation method for the deformable part-based model (DPM). The online domain adaptation is based on a two-level hierarchical adaptation tree, which consists of instance detectors in the leaf nodes and a category detector at the root node. Moreover, combined with a multiple object tracking procedure (MOT), our proposal neither requires target-domain annotated data nor revisiting the source-domain data for performing the source-to-target domain adaptation of the DPM. From a practical point of view this means that, given a source-domain DPM and new video for training on a new domain without object annotations, our procedure outputs a new DPM adapted to the domain represented by the video. As proof-of-concept we apply our proposal to the challenging task of pedestrian detection. In this case, each instance detector is an exemplar classifier trained online with only one pedestrian per frame. The pedestrian instances are collected by MOT and the hierarchical model is constructed dynamically according to the pedestrian trajectories. Our experimental results show that the adapted detector achieves the accuracy of recent supervised domain adaptation methods (i.e., requiring manually annotated targetdomain data), and improves the source detector more than 10 percentage points.

Abstract: Robust and dense computation of depth information from stereo-camera systems is a computationally demanding requirement for real-time autonomous driving. Semi-Global Matching (SGM) [1] approximates heavy-computation global algorithms results but with lower computational complexity, therefore it is a good candidate for a real-time implementation. SGM minimizes energy along several 1D paths across the image. The aim of this work is to provide a real-time system producing reliable results on energy-efficient hardware. Our design runs on a NVIDIA Titan X GPU at 104.62 FPS and on a NVIDIA Drive PX at 6.7 FPS, promising for real-time platforms

Abstract: Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy-efficient GPU devices. Our design runs on a Tegra X1 at 41 frames per second for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.

Abstract: This paper presents the comparison of two nonlinear model-based control strategies for autonomous cars. A control oriented model of vehicle based on a bicycle model is used. The two control strategies use a model reference approach. Using this approach, the error dynamics model is developed. Both controllers receive as input the longitudinal, lateral and orientation errors generating as control outputs the steering angle and the velocity of the vehicle. The first control approach is based on a non-linear control law that is designed by means of the Lyapunov direct approach. The second approach is based on a sliding mode-control that defines a set of sliding surfaces over which the error trajectories will converge. The main advantage of the sliding-control technique is the robustness against non-linearities and parametric uncertainties in the model. However, the main drawback of first order sliding mode is the chattering, so it has been implemented a high order sliding mode control. To test and compare the proposed control strategies, different path following scenarios are used in simulation.

Abstract: It has recently been demonstrated that local feature descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Previous work on learning such descriptors has focused on exploiting pairs of positive and negative patches to learn discriminative CNN representations. In this work, we propose to utilize triplets of training samples, together with in-triplet mining of hard negatives.
We show that our method achieves state of the art results, without the computational overhead typically associated with mining of negatives and with lower complexity of the network architecture. We compare our approach to recently introduced convolutional local feature descriptors, and demonstrate the advantages of the proposed methods in terms of performance and speed. We also examine different loss functions associated with triplets.