Abstract: Image values are the result of a combination of visual information coming from multiple sources. Recovering information from the multiple factors thatproduced an image seems a hard and ill-posed problem. However, it is important to observe that humans develop the ability to interpret images and recognize and isolate specific physical properties of the scene.
Images describing a single physical characteristic of an scene are called intrinsic images. These images would benefit most computer vision tasks which are often affected by the multiple complex effects that are usually found in natural images (e.g. cast shadows, specularities, interreflections...).
In this thesis we analyze the problem of intrinsic image estimation from different perspectives, including the theoretical formulation of the problem, the visual cues that can be used to estimate the intrinsic components and the evaluation mechanisms of the problem.

Abstract: 3D geometric information is essential for on-board perception in autonomous driving and driver assistance. Autonomous vehicles (AVs) are equipped with calibrated sensor suites. As part of these suites, we can find LiDARs, which are expensive active sensors in charge of providing the 3D geometric information. Depending on the operational conditions for the AV, calibrated stereo rigs may be also sufficient for obtaining 3D geometric information, being these rigs less expensive and easier to install than LiDARs. However, ensuring a proper maintenance and calibration of these types of sensors is not trivial. Accordingly, there is an increasing interest on performing monocular depth estimation (MDE) to obtain 3D geometric information on-board. MDE is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Moreover, a set of single cameras with MDE capabilities would still be a cheap solution for on-board perception, relatively easy to integrate and maintain in an AV.
Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Accordingly, the overall goal of this PhD is to study methods for improving CNN-based MDE accuracy under different training settings. More specifically, this PhD addresses different research questions that are described below. When we started to work in this PhD, state-of-theart methods for MDE were already based on CNNs. In fact, a promising line of work consisted in using image-based semantic supervision (i.e., pixel-level class labels) while training CNNs for MDE using LiDAR-based supervision (i.e., depth). It was common practice to assume that the same raw training data are complemented by both types of supervision, i.e., with depth and semantic labels. However, in practice, it was more common to find heterogeneous datasets with either only depth supervision or only semantic supervision. Therefore, our first work was to research if we could train CNNs for MDE by leveraging depth and semantic information from heterogeneous datasets. We show that this is indeed possible, and we surpassed the state-of-the-art results on MDE at the time we did this research. To achieve our results, we proposed a particular CNN architecture and a new training protocol.
After this research, it was clear that the upper-bound setting to train CNN-based MDE models consists in using LiDAR data as supervision. However, it would be cheaper and more scalable if we would be able to train such models from monocular sequences. Obviously, this is far more challenging, but worth to research. Training MDE models using monocular sequences is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. To alleviate these problems, we perform MDE by virtual-world supervision and real-world SfM self-supervision. We call our proposalMonoDEVSNet. We compensate the SfM self-supervision limitations by leveraging
virtual-world images with accurate semantic and depth supervision, as well as addressing the virtual-to-real domain gap. MonoDEVSNet outperformed previous MDE CNNs trained on monocular and even stereo sequences. We have publicly released MonoDEVSNet at <https://github.com/HMRC-AEL/MonoDEVSNet>.
Finally, since MDE is performed to produce 3D information for being used in downstream tasks related to on-board perception. We also address the question of whether the standard metrics for MDE assessment are a good indicator for future MDE-based driving-related perception tasks. By using 3D object detection on point clouds as proxy of on-board perception, we conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods which reflects relatively well the 3D object detection results we may expect.

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.

Abstract: Automatic face classification is currently a popular research area in Computer Vision. It involves several subproblems, such as subject recognition, gender classification or subject verification.
Current systems of automatic face classification need a large amount of training data to robustly learn a task. However, the collection of labeled data is usually a difficult issue. For this reason, the research on methods that are able to learn from a small sized training set is essential.
The dependency on the abundance of training data is not so evident in human learning processes. We are able to learn from a very small number of examples, given that we use, additionally, some prior knowledge to learn a new task. For example, we frequently find patterns and analogies from other domains to reuse them in new situations, or exploit training data from other experiences.
In computer science, Multitask Learning is a new Machine Learning approach that studies this idea of knowledge transfer among different tasks, to overcome the effects of the small sample sized problem.
This thesis explores, proposes and tests some Multitask Learning methods specially developed for face classification purposes. Moreover, it presents two more contributions dealing with the small sample sized problem, out of the Multitask Learning context. The first one is a method to extract external face features, to be used as an additional information source in automatic face classification problems. The second one is an empirical study on the most suitable face image resolution to perform automatic subject recognition.

Abstract: Autonomous vehicles are now considered as an assured asset in the future. Literally, all the relevant car-markers are now in a race to produce fully autonomous vehicles. These car-makers usually make use of modular pipelines for designing autonomous vehicles. This strategy decomposes the problem in a variety of tasks such as object detection and recognition, semantic and instance segmentation, depth estimation, SLAM and place recognition, as well as planning and control. Each module requires a separate set of expert algorithms, which are costly specially in the amount of human labor and necessity of data labelling. An alternative, that recently has driven considerable interest, is the end-to-end driving. In the end-to-end driving paradigm, perception and control are learned simultaneously using a deep network. These sensorimotor models are typically obtained by imitation learning fromhuman demonstrations. The main advantage is that this approach can directly learn from large fleets of human-driven vehicles without requiring a fixed ontology and extensive amounts of labeling. However, scaling end-to-end driving methods to behaviors more complex than simple lane keeping or lead vehicle following remains an open problem. On this thesis, in order to achieve more complex behaviours, we
address some issues when creating end-to-end driving system through imitation
learning. The first of themis a necessity of an environment for algorithm evaluation and collection of driving demonstrations. On this matter, we participated on the creation of the CARLA simulator, an open source platformbuilt from ground up for autonomous driving validation and prototyping. Since the end-to-end approach is purely reactive, there is also the necessity to provide an interface with a global planning system. With this, we propose the conditional imitation learning that conditions the actions produced into some high level command. Evaluation is also a concern and is commonly performed by comparing the end-to-end network output to some pre-collected driving dataset. We show that this is surprisingly weakly correlated to the actual driving and propose strategies on how to better acquire data and a better comparison strategy. Finally, we confirmwell-known generalization issues
(due to dataset bias and overfitting), new ones (due to dynamic objects and the
lack of a causal model), and training instability; problems requiring further research before end-to-end driving through imitation can scale to real-world driving.

Abstract: During the last decade vision-based human detection systems have started to play a key rolein multiple applications linked to driver assistance, surveillance, robot sensing and home automation.
Detecting humans is by far one of the most challenging tasks in Computer Vision.
This is mainly due to the high degree of variability in the human appearanceassociated to
the clothing, pose, shape and size. Besides, other factors such as cluttered scenarios, partial occlusions, or environmental conditions can make the detection task even harder.
Most promising methods of the state-of-the-art rely on discriminative learning paradigms which are fed with positive and negative examples. The training data is one of the most
relevant elements in order to build a robust detector as it has to cope the large variability of the target. In order to create this dataset human supervision is required. The drawback at this point is the arduous effort of annotating as well as looking for such claimed variability.
In this PhD thesis we address two recurrent problems in the literature. In the first stage,we aim to reduce the consuming task of annotating, namely, by using computer graphics.
More concretely, we develop a virtual urban scenario for later generating a pedestrian dataset.
Then, we train a detector using this dataset, and finally we assess if this detector can be successfully applied in a real scenario.
In the second stage, we focus on increasing the robustness of our pedestrian detectors
under partial occlusions. In particular, we present a novel occlusion handling approach to increase the performance of block-based holistic methods under partial occlusions. For this purpose, we make use of local experts via a RandomSubspaceMethod (RSM) to handle these cases. If the method infers a possible partial occlusion, then the RSM, based on performance statistics obtained from partially occluded data, is applied. The last objective of this thesis
is to propose a robust pedestrian detector based on an ensemble of local experts. To achieve this goal, we use the random forest paradigm, where the trees act as ensembles an their nodesare the local experts. In particular, each expert focus on performing a robust classification ofa pedestrian body patch. This approach offers computational efficiency and far less design complexity when compared to other state-of-the-artmethods, while reaching better accuracy