Abstract: In autonomous driving, artificial intelligence (AI) processes the traffic environment to drive the vehicle to a desired destination. Currently, there are different paradigms that address the development of AI-enabled drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception, maneuver planning, and control. On the other hand, we find end-to-end driving approaches that attempt to learn the direct mapping of raw data from input sensors to vehicle control signals. The latter are relatively less studied but are gaining popularity as they are less demanding in terms of data labeling. Therefore, in this thesis, our goal is to investigate end-to-end autonomous driving.
We propose to evaluate three approaches to tackle the challenge of end-to-end
autonomous driving. First, we focus on the input, considering adding depth information as complementary to RGB data, in order to mimic the human being’s
ability to estimate the distance to obstacles. Notice that, in the real world, these depth maps can be obtained either from a LiDAR sensor, or a trained monocular
depth estimation module, where human labeling is not needed. Then, based on
the intuition that the latent space of end-to-end driving models encodes relevant
information for driving, we use it as prior knowledge for training an affordancebased driving model. In this case, the trained affordance-based model can achieve good performance while requiring less human-labeled data, and it can provide interpretability regarding driving actions. Finally, we present a new pure vision-based end-to-end driving model termed CIL++, which is trained by imitation learning.
CIL++ leverages modern best practices, such as a large horizontal field of view and
a self-attention mechanism, which are contributing to the agent’s understanding of
the driving scene and bringing a better imitation of human drivers. Using training
data without any human labeling, our model yields almost expert performance in
the CARLA NoCrash benchmark and could rival SOTA models that require large amounts of human-labeled data.

Abstract: Manually annotating images to develop vision models has been a major bottleneck
since computer vision and machine learning started to walk together. This has
been more evident since computer vision falls on the shoulders of data-hungry
deep learning techniques. When addressing on-board perception for autonomous
driving, the curse of data annotation is exacerbated due to the use of additional
sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving
and, in fact, for any application requiring some sort of artificial perception. In the
last decade, it has been shown that leveraging from synthetic data is a paradigm
worth to pursue in order to minimizing manual data annotation. The reason is
that the automatic process of generating synthetic data can also produce different
types of associated annotations (e.g. object bounding boxes for synthetic images
and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly
using synthetic data for training deep perception models may not be the definitive
solution in all circumstances since it can appear a synth-to-real domain shift. In
this context, this work focuses on leveraging synthetic data to alleviate manual
annotation for three perception tasks related to driving assistance and autonomous
driving. In all cases, we assume the use of deep convolutional neural networks
(CNNs) to develop our perception models.
The first task addresses traffic sign recognition (TSR), a kind of multi-class
classification problem. We assume that the number of sign classes to be recognized
must be suddenly increased without having annotated samples to perform the
corresponding TSR CNN re-training. We show that leveraging synthetic samples of
such new classes and transforming them by a generative adversarial network (GAN)
trained on the known classes (i.e. without using samples from the new classes), it is
possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of
new/known sign classes. The second task addresses on-board 2D object detection,
focusing on vehicles and pedestrians. In this case, we assume that we receive a set
of images without the annotations required to train an object detector, i.e. without
object bounding boxes. Therefore, our goal is to self-annotate these images so
that they can later be used to train the desired object detector. In order to reach
this goal, we leverage from synthetic data and propose a semi-supervised learning
approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show
that co-training and GAN-based image-to-image translation complement each
other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from
human annotations. While in previous tasks we focus on vision-based perception,
the third task we address focuses on LiDAR pointclouds. Our initial goal was to
develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While
for images we may expect synth/real-to-real domain shift due to differences in
their appearance (e.g. when source and target images come from different camera
sensors), we did not expect so for LiDAR pointclouds since these active sensors
factor out appearance and provide sampled shapes. However, in practice, we have
seen that it can be domain shift even among real-world LiDAR pointclouds. Factors
such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce
a domain shift. We show it through comprehensive experiments with different
publicly available datasets and 3D detectors. This redirected our goal towards the
design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored
topic.
Finally, it is worth to mention that all the synthetic datasets used for these three
tasks, have been designed and generated in the context of this PhD work and will
be publicly released. Overall, we think this PhD presents several steps forward to
encourage leveraging synthetic data for developing deep perception models in the
field of driving assistance and autonomous driving.

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: In this dissertation, we explore different ways to perform human action recognition in video clips. We focus on data efficiency, proposing new approaches that alleviate the need for laborious and time-consuming manual data annotation. In the first part of this dissertation, we start by analyzing previous state-of-the-art models, comparing their differences and similarities in order to pinpoint where their real strengths come from. Leveraging this information, we then proceed to boost the classification accuracy of shallow models to levels that rival deep neural networks. We introduce hybrid video classification architectures based on carefully designed unsupervised representations of handcrafted spatiotemporal features classified by supervised deep networks. We show in our experiments that our hybrid model combine the best of both worlds: it is data efficient (trained on 150 to 10,000 short clips) and yet improved significantly on the state of the art, including deep models trained on millions of manually labeled images and videos. In the second part of this research, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. It contains a total of 39,982 videos, with more than 1,000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We then introduce deep multi-task representation learning architectures to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, outperforming fine-tuning state-of-the-art unsupervised generative models of videos.

Abstract: Road traffic crashes have become a major cause of death and injury throughout the world.
Hence, in order to improve road safety, the automobile manufacture is moving towards the
development of vehicles with autonomous functionalities such as keeping in the right lane, safe distance keeping between vehicles or regulating the speed of the vehicle according to the traffic conditions. A key component of these systems is vision–based road detection that aims to detect the free road surface ahead the moving vehicle. Detecting the road using a monocular vision system is very challenging since the road is an outdoor scenario imaged from a mobile platform. Hence, the detection algorithm must be able to deal with continuously changing imaging conditions such as the presence ofdifferent objects (vehicles, pedestrians), different environments (urban, highways, off–road), different road types (shape, color), and different imaging conditions (varying illumination, different viewpoints and changing weather conditions). Therefore, in this thesis, we focus on vision–based road detection using a single color camera. More precisely, we first focus on analyzing and grouping pixels according to their low–level properties. In this way, two different approaches are presented to exploit
color and photometric invariance. Then, we focus the research of the thesis on exploiting context information. This information provides relevant knowledge about the road not using pixel features from road regions but semantic information from the analysis of the scene.
In this way, we present two different approaches to infer the geometry of the road ahead
the moving vehicle. Finally, we focus on combining these context and appearance (color)
approaches to improve the overall performance of road detection algorithms. The qualitative and quantitative results presented in this thesis on real–world driving sequences show that the proposed method is robust to varying imaging conditions, road types and scenarios going beyond the state–of–the–art.

Abstract: For millennia, the study of the couple brain-mind has fascinated the humanity in order to understand the complex nature of cognitive states. A cognitive state is the state of the mind at a specific time and involves cognition activities to acquire and process information for making a decision, solving a problem, or achieving a goal.
While normal cognitive states assist in the successful accomplishment of tasks; on the contrary, abnormal states of the mind can lead to task failures due to a reduced cognition capability. In this thesis, we focus on the assessment of cognitive states by means of the analysis of ElectroEncephaloGrams (EEG) signals using deep learning methods. EEG records the electrical activity of the brain using a set of electrodes placed on the scalp that output a set of spatiotemporal signals that are expected to be correlated to a specific mental process.
From the point of view of artificial intelligence, any method for the assessment of cognitive states using EEG signals as input should face several challenges. On the one hand, one should determine which is the most suitable approach for the optimal combination of the multiple signals recorded by EEG electrodes. On the other hand, one should have a protocol for the collection of good quality unambiguous annotated data, and an experimental design for the assessment of the generalization and transfer of models. In order to tackle them, first, we propose several convolutional neural architectures to perform data fusion of the signals recorded by EEG electrodes, at raw signal and feature levels. Four channel fusion methods, easy to incorporate into any neural network architecture, are proposed and assessed. Second, we present a method to create an unambiguous dataset for the prediction of cognitive mental workload using serious games and an Airbus-320 flight simulator. Third, we present a validation protocol that takes into account the levels of generalization of models based on the source and amount of test data.
Finally, the approaches for the assessment of cognitive states are applied to two use cases of high social impact: the assessment of mental workload for personalized support systems in the cockpit and the detection of epileptic seizures. The results obtained from the first use case show the feasibility of task transfer of models trained to detect workload in serious games to real flight scenarios. The results from the second use case show the generalization capability of our EEG channel fusion methods at k-fold cross-validation, patient-specific, and population levels.

Abstract: From the early stages of Computer Vision, scene reconstruction has been one of the most studied topics leading to a wide variety of new discoveries and applications. Object grasping and manipulation, localization and mapping, or even visual effect generation are different examples of applications in which scene reconstruction has taken an important role for industries such as robotics, factory automation, or audio visual production. However, scene reconstruction is an extensive topic that can be approached in many different ways with already existing solutions that effectively work in controlled environments. Formally, the problem of scene reconstruction can be formulated as a sequence of independent processes which compose a pipeline. In this thesis, we analyse some parts of the reconstruction pipeline from which we contribute with novel methods using Convolutional Neural Networks (CNN) proposing innovative solutions that consider the optimisation of the methods in an end-to-end fashion. First, we review the state of the art of classical local features detectors and descriptors and contribute with two novel methods that inherently improve pre-existing solutions in the scene reconstruction pipeline.
It is a fact that computer science and software engineering are two fields that usually go hand in hand and evolve according to mutual needs making easier the design of complex and efficient algorithms. For this reason, we contribute with Kornia, a library specifically designed to work with classical computer vision techniques along with deep neural networks. In essence, we created a framework that eases the design of complex pipelines for computer vision algorithms so that can be included within neural networks and be used to backpropagate gradients throw a common optimisation framework. Finally, in the last chapter of this thesis we develop the aforementioned concept of designing end-to-end systems with classical projective geometry. Thus, we contribute with a solution to the problem of synthetic view generation by hallucinating novel views from high deformable cloths objects using a geometry aware end-to-end system. To summarize, in this thesis we demonstrate that with a proper design that combine classical geometric computer vision methods with deep learning techniques can lead to improve pre-existing solutions for the problem of scene reconstruction.

Abstract: Pedestrian detection continues to be an extremely challenging problem in real scenarios, in which situations like illumination changes, noisy images, unexpected objects, uncontrolled scenarios and variant appearance of objects occur constantly. All these problems force the development of more robust detectors for relevant applications like vision-based autonomous vehicles, intelligent surveillance, and pedestrian tracking for behavior analysis. Most reliable vision-based pedestrian detectors base their decision on features extracted using a single sensor capturing complementary features, e.g., appearance, and texture. These features usually are extracted from the current frame, ignoring temporal information, or including it in a post process step e.g., tracking or temporal coherence. Taking into account these issues we formulate the following question: can we generate more robust pedestrian detectors by introducing new information sources in the feature extraction step?
In order to answer this question we develop different approaches for introducing new information sources to well-known pedestrian detectors. We start by the inclusion of temporal information following the Stacked Sequential Learning (SSL) paradigm which suggests that information extracted from the neighboring samples in a sequence can improve the accuracy of a base classifier.
We then focus on the inclusion of complementary information from different sensors like 3D point clouds (LIDAR – depth), far infrared images (FIR), or disparity maps (stereo pair cameras). For this end we develop a multi-modal framework in which information from different sensors is used for increasing detection accuracy (by increasing information redundancy). Finally we propose a multi-view pedestrian detector, this multi-view approach splits the detection problem in n sub-problems.
Each sub-problem will detect objects in a given specific view reducing in that way the variability problem faced when a single detectors is used for the whole problem. We show that these approaches obtain competitive results with other state-of-the-art methods but instead of design new features, we reuse existing ones boosting their performance.