Abstract: Recent advances in endoscopic devices have increased their use for minimal invasive diagnostic and intervention procedures. Among all endoscopic modalities, bronchoscopy is one of the most frequent with around 261 millions of procedures per year. Although the use of bronchoscopy is spread among clinical facilities it presents some drawbacks, being the visual inspection for the assessment of anatomical measurements the most prevalent of them. In
particular, inaccuracies in the estimation of the degree of stenosis (the percentage of obstructed airway) decreases its diagnostic yield and might lead to erroneous treatments. An objective computation of tracheal stenosis in bronchoscopy videos would constitute a breakthrough for this non-invasive technique and a reduction in treatment cost.
This thesis settles the first steps towards on-line reliable extraction of anatomical information from videobronchoscopy for computation of objective measures. In particular, we focus on the computation of the degree of stenosis, which is obtained by comparing the area delimited by a healthy tracheal ring and the stenosed lumen. Reliable extraction of airway structures in interventional videobronchoscopy is a challenging task. This is mainly due to the large variety of acquisition conditions (positions and illumination), devices (different digitalizations) and in videos acquired at the operating room the unpredicted presence of surgical devices (such as probe ends). This thesis contributes to on-line stenosis assessment in several ways. We
propose a parametric strategy for the extraction of lumen and tracheal rings regions based on the characterization of their geometry and appearance that guide a deformable model. The geometric and appearance characterization is based on a physical model describing the way bronchoscopy images are obtained and includes local and global descriptions. In order to ensure a systematic applicability we present a statistical framework to select the optimal
parameters of our method. Experiments perform on the first public annotated database, show that the performance of our method is comparable to the one provided by clinicians and its computation time allows for a on-line implementation in the operating room.

Abstract: Optical Flow (OF) is the input of a wide range of decision support systems such as car driver assistance, UAV guiding or medical diagnose. In these real situations, the absence of ground truth forces to assess OF quality using quantities computed from either sequences or the computed optical flow itself. These quantities are generally known as Confidence Measures, CM. Even if we have a proper confidence measure we still need a way to evaluate its ability to discard pixels with an OF prone to have a large error. Current approaches only provide a descriptive evaluation of the CM performance but such approaches are not capable to fairly compare different confidence measures and optical flow algorithms. Thus, it is of prime importance to define a framework and a general road map for the evaluation of optical flow performance.
This thesis provides a framework able to decide which pairs “ optical flow – confidence measure” (OF-CM) are best suited for optical flow error bounding given a confidence level determined by a decision support system. To design this framework we cover the following points:
Descriptive scores. As a first step, we summarize and analyze the sources of inaccuracies in the output of optical flow algorithms. Second, we present several descriptive plots that visually assess CM capabilities for OF error bounding. In addition to the descriptive plots, given a plot representing OF-CM capabilities to bound the error, we provide a numeric score that categorizes the plot according to its decreasing profile, that is, a score assessing CM performance.
Statistical framework. We provide a comparison framework that assesses the best suited OF-CM pair for error bounding that uses a two stage cascade process. First of all we assess the predictive value of the confidence measures by means of a descriptive plot. Then, for a sample of descriptive plots computed over training frames, we obtain a generic curve that will be used for sequences with no ground truth. As a second step, we evaluate the obtained general curve and its capabilities to really reflect the predictive value of a confidence measure using the variability across train frames by means of ANOVA.
The presented framework has shown its potential in the application on clinical decision support systems. In particular, we have analyzed the impact of the different image artifacts such as noise and decay to the output of optical flow in a cardiac diagnose system and we have improved the navigation inside the bronchial tree on bronchoscopy.

Abstract: Lung cancer is one of the most diagnosed cancers among men and women. Actually,
lung cancer accounts for 13% of the total cases with a 5-year global survival
rate in patients. Although Early detection increases survival rate from 38% to 67%, accurate diagnosis remains a challenge. Pathological confirmation requires extracting a sample of the lesion tissue for its biopsy. The preferred procedure for tissue biopsy is called bronchoscopy. A bronchoscopy is an endoscopic technique for the internal exploration of airways which facilitates the performance of minimal invasive interventions with low risk for the patient. Recent advances in bronchoscopic devices have increased their use for minimal invasive diagnostic and intervention procedures, like lung cancer biopsy sampling. Despite the improvement in bronchoscopic device quality, there is a lack of intelligent computational systems for supporting in-vivo clinical decision during examinations. Existing technologies fail to accurately reach the lesion due to several aspects at intervention off-line planning and poor intra-operative guidance at exploration time. Existing guiding systems radiate patients and clinical staff,might be expensive and achieve a suboptimlal 70% of yield boost. Diagnostic yield could be improved reducing radiation and costs by developing intra-operative support systems able to guide the bronchoscopist to the lesion during the intervention. The goal of this PhD thesis is to develop an image-based navigation systemfor intra-operative guidance of bronchoscopists to a target lesion across a path previously planned on a CT-scan. We propose a 3D navigation system which uses the anatomy of video bronchoscopy frames to locate the bronchoscope within the airways. Once the bronchoscope is located, our navigation system is able to indicate the bifurcation which needs to be followed to reach the lesion. In order to facilitate an off-line validation
as realistic as possible, we also present a method for augmenting simulated virtual bronchoscopies with the appearance of intra-operative videos. Experiments performed on augmented and intra-operative videos, prove that our algorithm can be speeded up for an on-line implementation in the operating room.

Abstract: Humans can effortlessly perceive faces, follow them over space and time, and decode their rich content, such as pose, identity and expression. However, despite many decades of research on automatic facial perception in areas like face detection, expression recognition, pose estimation and face recognition, and despite many successes, a complete solution remains elusive. This thesis is dedicated to three problems in automatic face perception, namely face detection, face tracking and pose estimation.
In face detection, an initial simple model is presented that uses pixel-based heuristics to segment skin locations and hand-crafted rules to determine the locations of the faces present in an image. Different colorspaces are studied to judge whether a colorspace transformation can aid skin color detection. The output of this study is used in the design of a more complex face detector that is able to successfully generalize to different scenarios.
In face tracking, a framework that combines estimation and control in a joint scheme is presented to track a face with a single pan-tilt-zoom camera. While this work is mainly motivated by tracking faces, it can be easily applied atop of any detector to track different objects. The applicability of this method is demonstrated on simulated as well as real-life scenarios.
The last and most important part of this thesis is dedicate to monocular head pose estimation. In this part, a method based on partial least squares (PLS) regression is proposed to estimate pose and solve the alignment problem simultaneously. The contributions of this work are two-fold: 1) demonstrating that the proposed method achieves better than state-of-the-art results on the estimation problem and 2) developing a technique to reduce misalignment based on the learned PLS factors that outperform multiple instance learning (MIL) without the need for any re-training or the inclusion of misaligned samples in the training process, as normally done in MIL.

Abstract: The release of challenging datasets with a vast number of images, requires the development of efficient image representations and algorithms which are able to manipulate these large-scale datasets efficiently. Nowadays the Bag-of-Words (BoW) is the most successful approach in the context of object and scene classification tasks. However, its main drawback is the absence of the important spatial information. Spatial pyramids (SP) have been successfully applied to incorporate spatial information into BoW-based image representation. Observing the remarkable performance of spatial pyramids, their growing number of applications to a broad range of vision problems, and finally its geometry inclusion, a question can be asked what are the limits of spatial pyramids. Within the SP framework, the optimal way for obtaining an image spatial representation, which is able to cope with it’s most foremost shortcomings, concretely, it’s high dimensionality and the rigidity of the resulting image representation, still remains an active research domain. In summary, the main concern of this thesis is to search for the limits of spatial pyramids and try to figure out solutions for them.

Abstract: Automatic understanding of human activity and action is very important and challenging research area of Computer Vision with wide applications in video surveillance, motion analysis, virtual reality interfaces, video indexing, content based video retrieval, HCI and health care. This thesis presents a series of techniques to solve the problem of human action recognition in video. First approach towards this goal is based on a probabilistic optimization model of body parts using Hidden Markov Model. This strong model based approach is able to distinguish between similar actions by only considering the body parts having major contributions to the actions. In next approach, we apply a weak model based human detector and actions are represented by Bag-of-key poses model to capture the human pose changes during the actions. To tackle the problem of human action recognition in complex scenes, a selective spatio-temporal interest point (STIP) detector is proposed by using a mechanism similar to that of the non-classical receptive field inhibition that is exhibited by most oriented selective neuron in the primary visual cortex. An extension of the selective STIP detector is applied to multi-view action recognition system by introducing a novel 4D STIPs (3D space + time). Finally, we use our STIP detector on large scale continuous visual event recognition problem and propose a novel generalized max-margin Hough transformation framework for activity detection

Abstract: Single image super-resolution (SISR) is an important task in image processing which aims to enhance the resolution of imaging systems. Recently, SISR has witnessed great strides with the rapid development of deep learning. Recent advances in SISR are mostly devoted to designing deeper and wider networks to enhance their representation learning capacity. However, as the depth of networks increases, deep learning-based methods are faced with the challenge of computational complexity in practice. Moreover, most existing methods rarely leverage the intermediate features and also do not discriminate the computation of features by their frequencial components, thereby achieving relatively low performance. Aside from the aforementioned problems, another desired ability is to upsample images to arbitrary scales using a single model. Most current SISR methods train a dedicated model for each target resolution, losing generality and increasing memory requirements. In this thesis, we address the aforementioned issues and propose solutions to them: i) We present a novel frequency-based enhancement block which treats different frequencies in a heterogeneous way and also models inter-channel dependencies, which consequently enrich the output feature. Thus it helps the network generate more discriminative representations by explicitly recovering finer details. ii) We introduce OverNet which contains two main parts: a lightweight feature extractor that follows a novel recursive framework of skip and dense connections to reduce low-level feature degradation, and an overscaling module that generates an accurate SR image by internally constructing an overscaled intermediate representation of the output features. Then, to solve the problem of reconstruction at arbitrary scale factors, we introduce a novel multi-scale loss, that allows the simultaneous training of all scale factors using a single model. iii) We propose a directional variance attention network which leverages a novel attention mechanism to enhance features in different channels and spatial regions. Moreover, we introduce a novel procedure for using attention mechanisms together with residual blocks to facilitate the preservation of finer details. Finally, we demonstrate that our approaches achieve considerably better performance than previous state-of-the-art methods, in terms of both quantitative and visual quality.

Abstract: Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may – and to some extent already does – result in advantages regarding the representation’s structure, robustness, and generalizability to different tasks. In the long run, unsupervised methods are expected to surpass their supervised counterparts due to the reduction of human intervention and the inherently more general setup that does not bias the optimization towards an objective originating from specific annotation-based signals. While major advantages of unsupervised representation learning have been recently observed in natural language processing, supervised methods still dominate in vision domains for most tasks. In this dissertation, we contribute to the field of unsupervised (visual) representation learning from three perspectives: (i) Learning representations: We design unsupervised, backpropagation-free Convolutional Self-Organizing Neural Networks (CSNNs) that utilize self-organization- and Hebbian-based learning rules to learn convolutional kernels and masks to achieve deeper backpropagation-free models. Thereby, we observe that backpropagation-based and -free methods can suffer from an objective function mismatch between the unsupervised pretext task and the target task. This mismatch can lead to performance decreases for the target task. (ii) Evaluating representations: We build upon the widely used (non-)linear evaluation protocol to define pretext- and target-objective-independent metrics for measuring the objective function mismatch. With these metrics, we evaluate various pretext and target tasks and disclose dependencies of the objective function mismatch concerning different parts of the training and model setup. (iii) Transferring representations: We contribute CARLANE, the first 3-way sim-to-real domain adaptation benchmark for 2D lane detection. We adopt several well-known unsupervised domain adaptation methods as baselines and propose a method based on prototypical cross-domain self-supervised learning. Finally, we focus on pixel-based unsupervised domain adaptation and contribute a content-consistent unpaired image-to-image translation method that utilizes masks, global and local discriminators, and similarity sampling to mitigate content inconsistencies, as well as feature-attentive denormalization to fuse content-based statistics into the generator stream. In addition, we propose the cKVD metric to incorporate class-specific content inconsistencies into perceptual metrics for measuring translation quality.