Abstract: Los sistemas actuales de reconocimiento automático del lenguaje oral se basan en dos etapas básicas de procesado: la parametrización, que extrae la evolución temporal de los parámetros que caracterizan la voz, y el reconocimiento propiamente dicho, que identifica la cadena de palabras de la elocución recibida con ayuda de los modelos que representan el conocimiento adquirido en la etapa de aprendizaje. Tomando como línea divisoria la palabra, dichos modelos son de tipo acústicofonético o gramatical. Los primeros caracterizan las palabras incluidas en el vocabulario de la aplicación o tarea a la que está orientado el sistema de reconocimiento, usando a menudo para ello modelos de unidades de habla de extensión inferior a la palabra, es decir, de unidades subléxicas. Por otro lado, la gramática incluye el conocimiento acerca de las combinaciones permitidas de palabras para formar las frases o su probabilidad. Queda fuera del esquema la denominada comprensión del habla, que utiliza adicionalmente el conocimiento semántico y pragmático para captar el significado de la elocución de entrada al sistema a partir de la cadena (o cadenas alternativas) de palabras que suministra el reconocedor.

Abstract: Put succinctly, the bag-of-words based image representation is the most successful approach for object and scene recognition. Within the bag-of-words framework the optimal fusion of multiple cues, such as shape, texture and color, still remains an active research domain. There exist two main approaches to combine color and shape information within the bag-of-words framework. The first approach called, early fusion, fuses color and shape at the feature level as a result of which a joint colorshape vocabulary is produced. The second approach, called late fusion, concatenates histogram representation of both color and shape, obtained independently. In the first part of this thesis, we analyze the theoretical implications of both early and late feature fusion. We demonstrate that both these approaches are suboptimal for a subset of object categories. Consequently, we propose a novel method for recognizing object categories when using multiple cues by separately processing the shape and color cues and combining them by modulating the shape features by category specific color attention. Color is used to compute bottom-up and top-down attention maps. Subsequently, the color attention maps are used to modulate the weights of the shape features. Shape features are given more weight in regions with higher attention and vice versa. The approach is tested on several benchmark object recognition data sets and the results clearly demonstrate the effectiveness of our proposed method. In the second part of the thesis, we investigate the problem of obtaining compact spatial pyramid representations for object and scene recognition. Spatial pyramids have been successfully applied to incorporate spatial information into bag-of-words based image representation. However, a major drawback of spatial pyramids is that it leads to high dimensional image representations. We present a novel framework for obtaining compact pyramid representation. The approach reduces the size of a high dimensional pyramid representation upto an order of magnitude without any significant reduction in accuracy. Moreover, we also investigate the optimal combination of multiple features such as color and shape within the context of our compact pyramid representation. Finally, we describe a novel technique to build discriminative visual words from multiple cues learned independently from training images. To this end, we use an information theoretic vocabulary compression technique to find discriminative combinations of visual cues and the resulting visual vocabulary is compact, has the cue binding property, and supports individual weighting of cues in the final image representation. The approach is tested on standard object recognition data sets. The results obtained clearly demonstrate the effectiveness of our approach.

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: Recent advances in thermal infrared imaging (LWIR) has allowed its use in applications beyond of the military domain. Nowadays, this new family of sensors is included in different technical and scientific applications. They offer features that facilitate tasks, such as detection of pedestrians, hot spots, differences in temperature, among others, which can significantly improve the performance of a system where the persons are expected to play the principal role. For instance, video surveillance applications, monitoring, and pedestrian detection.
During this dissertation the next question is stated: Could a couple of sensors measuring different bands of the electromagnetic spectrum, as the visible and thermal infrared, be used to extract depth information? Although it is a complex question, we shows that a system of these characteristics is possible as well as their advantages, drawbacks, and potential opportunities.
The matching and fusion of data coming from different sensors, as the emissions registered at visible and infrared bands, represents a special challenge, because it has been showed that theses signals are weak correlated. Therefore, many traditional techniques of image processing and computer vision are not helpful, requiring adjustments for their correct performance in every modality.
In this research an experimental study that compares different cost functions and matching approaches is performed, in order to build a multimodal stereovision system. Furthermore, the common problems in infrared/visible stereo, specially in the outdoor scenes are identified. Our framework summarizes the architecture of a generic stereo algorithm, at different levels: computational, functional, and structural, which can be extended toward high-level fusion (semantic) and high-order (prior).The proposed framework is intended to explore novel multimodal stereo matching approaches, going from sparse to dense representations (both disparity and depth maps). Moreover, context information is added in form of priors and assumptions. Finally, this dissertation shows a promissory way toward the integration of multiple sensors for recovering three-dimensional information.

Abstract: Intestinal motility assessment with video capsule endoscopy arises as a novel and challenging clinical fieldwork. This technique is based on the analysis of the patterns of intestinal contractions obtained by labelling all the motility events present in a video provided by a capsule with a wireless micro-camera, which is ingested by the patient. However, the visual analysis of these video sequences presents several im- portant drawbacks, mainly related to both the large amount of time needed for the visualization process, and the low prevalence of intestinal contractions in video.
In this work we propose a machine learning system to automatically detect the intestinal contractions in video capsule endoscopy, driving a very useful but not fea- sible clinical routine into a feasible clinical procedure. Our proposal is divided into two different parts: The first part tackles the problem of the automatic detection of phasic contractions in capsule endoscopy videos. Phasic contractions are dynamic events spanning about 4-5 seconds, which show visual patterns with a high variability. Our proposal is based on a sequential design which involves the analysis of textural, color and blob features with powerful classifiers such as SVM. This approach appears to cope with two basic aims: the reduction of the imbalance rate of the data set, and the modular construction of the system, which adds the capability of including domain knowledge as new stages in the cascade. The second part of the current work tackles the problem of the automatic detection of tonic contractions. Tonic contrac- tions manifest in capsule endoscopy as a sustained pattern of the folds and wrinkles of the intestine, which may be prolonged for an undetermined span of time. Our proposal is based on the analysis of the wrinkle patterns, presenting a comparative study of diverse features and classification methods, and providing a set of appro- priate descriptors for their characterization. We provide a detailed analysis of the performance achieved by our system both in a qualitative and a quantitative way.

Abstract: Latest advances in digitization techniques have fostered the interest in creating digital copies of collections of documents. Digitized documents permit an easy maintenance, loss-less storage, and efficient ways for transmission and to perform information retrieval processes. This situation has opened a new market niche to develop systems able to automatically extract and analyze information contained in these collections, specially in the ambit of the business activity.
Due to the great variety of types of documents this is not a trivial task. For instance, the automatic extraction of numerical data from invoices differs substantially from a task of text recognition in historical documents. However, in order to extract the information of interest, is always necessary to identify the area of the document where it is located. In the area of Document Analysis we refer to this process as layout analysis, which aims at identifying and categorizing the different entities that compose the document, such as text regions, pictures, text lines, or tables, among others. To perform this task it is usually necessary to incorporate a prior knowledge about the task into the analysis process, which can be modeled by defining a set of contextual relations between the different entities of the document. The use of context has proven to be useful to reinforce the recognition process and improve the results on many computer vision tasks. It presents two fundamental questions: What kind of contextual information is appropriate for a given task, and how to incorporate this information into the models.
In this thesis we study several ways to incorporate contextual information to the task of document layout analysis, and to the particular case of handwritten text line segmentation. We focus on the study of Probabilistic Graphical Models and other mechanisms for this purpose, and propose several solutions to these problems. First, we present a method for layout analysis based on Conditional Random Fields. With this model we encode local contextual relations between variables, such as pair-wise constraints. Besides, we encode a set of structural relations between different classes of regions at feature level. Second, we present a method based on 2D-Probabilistic Context-free Grammars to encode structural and hierarchical relations. We perform a comparative study between Probabilistic Graphical Models and this syntactic approach. Third, we propose a method for structured documents based on Bayesian Networks to represent the document structure, and an algorithm based in the Expectation-Maximization to find the best configuration of the page. We perform a thorough evaluation of the proposed methods on two particular collections of documents: a historical collection composed of ancient structured documents, and a collection of contemporary documents. In addition, we present a general method for the task of handwritten text line segmentation. We define a probabilistic framework where we combine the EM algorithm with variational approaches for computing inference and parameter learning on a Markov Random Field. We evaluate our method on several collections of documents, including a general dataset of annotated administrative documents. Results demonstrate the applicability of our method to real problems, and the contribution of the use of contextual information to this kind of problems.

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.