Visual object tracking is the task of giving a unique ID to an object in a video frame, understanding whether it is present or not in a current frame and if it is present, precisely localizing its position. There are numerous challenges in object tracking, such as change of illumination, partial or full occlusion, change of target appearance, blurring caused by camera movement, presence of similar objects to the target, changes in video image quality through time, etc. Due to these challenges, traditional computer vision techniques cannot perform high-quality tracking, especially for long-term tracking. Almost all the state-of-the-art methods in object tracking use artificial intelligence nowadays, and more specifically, Convolutional Neural Networks. In this work, we present a Siamese based tracker which is different from previous works in two ways. Firstly, most of the Siamese based trackers takes the target in the first frame as the ground truth. Despite the success of such methods in previous years, it does not guarantee robust tracking as it cannot handle many of the challenges causing change in target appearance, such as blurring caused by camera movement, occlusion, pose variation, etc. In this work, while keeping the first frame as a template, we add five other additional templates that are dynamically updated and replaced considering target classification score in different frames. Diversity, similarity and recency are criteria to choose the members of the bag. We call it as a bag of dynamic templates. Secondly, many Siamese based trackers are vulnerable to mistakenly tracking another similar looking object instead of the intended target. Many researchers proposed computationally expensive approaches, such as tracking all the distractors and the given target and discriminate them in every frame. In this work, we propose an approach to handle this issue by estimate the next frame position by using the target's bounding box coordinates in previous frames. We use temporal network with past history of several previous frames, measure classification scores of candidates considering templates in the bag of dynamic templates and use tracker sequential confidence value which shows how confident the tracker has been in previous frames. We call it as robustifier that prevents the tracker from continuously switching between the target and possible distractors with this hypothesis in mind. Extensive experiments on OTB 50, OTB 100 and UAV20L datasets demonstrate the superiority of our work over the state-of-the-art methods.

There is an emerging class of applications that require long-term tracking and monitoring of mobile entities for characterising their contexts and behaviours using data from wireless sensors. Examples include monitoring animals in their natural habitat over the annual cycle; tracking shipping containers and their handling during transit; and monitoring air quality using sensors attached to bicycles used in public sharing schemes. All applications within this class require the acquisition of sensor data tagged with spatio-temporal information and uploaded wirelessly. Currently there is no solution targeting the entire class of applications, only point solutions focused on specific scenarios. This thesis presents a complete solution (firmware and hardware) for applications within this class that consists of attaching mobile sensor nodes to the entities for tracking and monitoring their behaviour, and deploying an infrastructure of base-stations for collecting the data wirelessly. The proposed solution is more energy efficient compared to the existing solutions that target specific scenarios, offering a longer deployment lifetime with a reduced size and weight of the devices. This is achieved mainly by using the VB-TDMA low-power data upload protocol proposed in this thesis. The mobile sensor nodes, consisting of the GPS and radio modules among others, and the base-stations are powered by batteries, and the optimisation of their energy usage is of primary concern. The presence of the GPS module, in particular its acquisition of accurate time, is used by the VB-TDMA protocol to synchronise the communication between nodes at no additional energy costs, resulting in an energy-efficient data upload protocol for sparse networks of mobile nodes, that can potentially be out of range of base-stations for extended periods of time. The VB-TDMA and an asynchronous data upload protocol were implemented on the custom-designed Prospeckz-5-based wireless sensor nodes. The protocols’ performances were simulated in the SpeckSim simulator and validated in real-world deployments of tracking and monitoring thirty-two Retuerta wild horses in the Doñana National Park in Spain, and a herd of domesticated horses in Edinburgh. The chosen test scenario of long-term wildlife tracking and monitoring is representative for the targeted class of applications. The VB-TDMA protocol showed a significantly lower power consumption than other comparable MAC protocols, effectively doubling the battery lifetime. The main contributions of the thesis are the development of the VB-TDMA data upload protocol and its performance evaluation, along with the development of simulation models for performance analysis of wireless sensor networks, validated using data from the two real-world deployments.

Cette dissertation traite du problème du suivi d'objets visuels, dont le but est de localiser un objet et de déterminer sa trajectoire au cours du temps. En particulier, nous nous concentrons sur les scénarios difficiles, dans lesquels les objets subissent d'importantes déformations et occlusions, ou quittent le champs de vision. A cette fin, nous proposons deux méthodes robustes qui apprennent un modèle pour l'objet d'intérêt et le mettent à jour, afin de refléter ses changements au cours du temps.Notre première méthode traite du problème du suivi dans le cas où les objets subissent d'importantes transformations géométriques comme une rotation ou un changement d'échelle. Nous présentons un nouvel algorithme de sélection de propositions, qui étend l'approche traditionnelle de ``suivi par détection''. Cette méthode procède en deux étapes: proposition puis sélection. Dans l'étape de proposition, nous construisons un ensemble de candidats qui représente les localisations potentielles de l'objet en estimant de manière robuste les transformations géométriques. La meilleure proposition est ensuite sélectionnée parmi cet ensemble de candidats pour précisément localiser l'objet en utilisant des indices d'apparence et de mouvement.Dans un second temps, nous traitons du problème de la mise à jour de modèles dans le suivi visuel, c'est-à-dire de déterminer quand il est besoin de mettre à jour le modèle de la cible, lequel peut subir une occlusion, ou quitter le champs de vision. Pour résoudre cela, nous utilisons des indices de mouvement pour identifier l'état d'un objet de manière automatique et nous mettons à jour le modèle uniquement lorsque l'objet est entièrement visible. En particulier, nous utilisons des trajectoires à long terme ainsi qu'une technique basée sur la coup de graphes pour estimer les parties de l'objet qui sont visibles.Nous avons évalué nos deux approches de manière étendue sur différents bancs d'essai de suivi, en particulier sur le récent banc d'essai de suivi en ligne et le jeu de donnée du concours de suivi visuel. Nos deux approches se comparent favorablement à l'état de l'art et font montre d'améliorations significatives par rapport à plusieurs autres récents suiveurs. Notre soumission au concours de suivi d'objets visuels de 2015 a par ailleurs remporté l'une de ces compétitions. / In this dissertation we address the problem of visual object tracking, whereinthe goal is to localize an object and determine its trajectory over time. Inparticular, we focus on challenging scenarios where the object undergoessignificant transformations, becomes occluded or leaves the field of view. Tothis end, we propose two robust methods which learn a model for the object ofinterest and update it, to reflect its changes over time.Our first method addresses the tracking problem in the context of objectsundergoing severe geometric transformations, such as rotation, change in scale.We present a novel proposal-selection algorithm, which extends the traditionaldiscriminative tracking-by-detection approach. This method proceeds in twostages -- proposal followed by selection. In the proposal stage, we compute acandidate pool that represents the potential locations of the object byrobustly estimating the geometric transformations. The best proposal is thenselected from this candidate set to localize the object precisely usingmultiple appearance and motion cues.Second, we consider the problem of model update in visual tracking, i.e.,determining when to update the model of the target, which may become occludedor leave the field of view. To address this, we use motion cues to identify thestate of the object in a principled way, and update the model only when theobject is fully visible. In particular, we utilize long-term trajectories incombination with a graph-cut based technique to estimate parts of the objectsthat are visible.We have evaluated both our approaches extensively on several trackingbenchmarks, notably, recent online tracking benchmark and the visual objecttracking challenge datasets. Both our approaches compare favorably to thestate of the art and show significant improvement over several other recenttrackers. Specifically, our submission to the visual object tracking challengeorganized in 2015 was the winner in one of the competitions.

During the course of this thesis, two scenarios are considered. In the first one, we contribute to feature extraction algorithms. In the second one, we use features to improve object detection solutions and localization. The two scenarios give rise to into four thesis sub-goals. First, we present a new shape skeleton pruning algorithm based on contour approximation and the integer medial axis. The algorithm effectively removes unwanted branches, conserves the connectivity of the skeleton and respects the topological properties of the shape. The algorithm is robust to significant boundary noise and to rigid shape transformations. It is fast and easy to implement. While shape-based solutions via boundary and skeleton analysis are viable solutions to object detection, keypoint features are important for textured object detection. Therefore, we present a keypoint featurebased planar object detection framework for vision-based localization. We demonstrate that our framework is robust against illumination changes, perspective distortion, motion blur, and occlusions. We increase robustness of the localization scheme in cluttered environments and decrease false detection of targets. We present an off-line target evaluation strategy and a scheme to improve pose. Third, we extend planar object detection to a real-time approach for 3D object detection using a mobile and uncalibrated camera. We develop our algorithm based on two novel naive Bayes classifiers for viewpoint and feature matching that improve performance and decrease memory usage. Our algorithm exploits the specific structure of various binary descriptors in order to boost feature matching by conserving descriptor properties. Our novel naive classifiers require a database with a small memory footprint because we only store efficiently encoded features. We improve the feature-indexing scheme to speed up the matching process creating a highly efficient database for objects. Finally, we present a model-free long-term tracking algorithm based on the Kernelized Correlation Filter. The proposed solution improves the correlation tracker based on precision, success, accuracy and robustness while increasing frame rates. We integrate adjustable Gaussian window and sparse features for robust scale estimation creating a better separation of the target and the background. Furthermore, we include fast descriptors and Fourier spectrum packed format to boost performance while decreasing the memory footprint. We compare our algorithm with state-of-the-art techniques to validate the results.

This doctoral thesis deals with the analysis of ultrasound (US) video sequences. It specifically focuses on long-term tracking of the common carotid artery (CCA) in transversal section and measurement of its geometric parameters in a sequence of US images. The design and implementation of a system for automatic tracking of the artery is described in this thesis. The proposed system utilizes Viola-Jones detector and Hough transform to localize the artery in the image. Interest points are detected in the area of the artery wall. These points are then tracked using optical flow. The proposed system comprises a number of innovative methods which allow to perform accurate long-term measurement of parameters of CCA and store the results. A novel mathematical model describing the movement of CCA in transversal section during a cardiac cycle is defined afterwards taking the influence of breathing into consideration. A number of artificial sequences of US images based on this model have been created. These sequences were consequently used to evaluate the accuracy of the proposed system in terms of measuring the parameters of CCA. The sequences are unique because of their length which makes them suitable for evaluation of tracking accuracy even in long video sequences.

This thesis focuses on real-time visual object tracking with emphasis on problems caused by a long-term tracking task. Among theses problems belong primarily an occlusion problem, both the partial and the full one, and appearance changes of the object during the tracking. The work is also concerned with tracking objects of a very limited size and unsteady camera movements. These two particular problems are relatively common when tracking distant objects. A part of this work is also a summary of related work and a proposal of a system with high qualitative stability and robustness to problems mentioned. The proposed system was implemented and the evaluation demonstrated that it is capable of solving these problems partially.