Tracking of an object's full six degree-of-freedom (6-dof) position and orientation (pose) would allow a robotic system to autonomously perform a variety of complex tasks, such as docking from any preferred angle, surveillance of moving subjects, etc. Computer vision has been commonly advocated as an effective tool for 3D (i.e., 6-dof) tracking Objects of Interest (OIs). However, the vast majority of vision-based 6-dof pose trackers reported in the literature require a model of the OI to be provided a priori. Finding/selecting the OI to track is also essential to autonomous operation. A problem that has often been neglected. This Thesis proposes a novel, real-time object-tracking system that solves all of the aforementioned problems. The tracking procedure begins with OI selection. Since what constitutes an OI is application dependent, selection is achieved via a customizable framework of Interest Filters (IFs) that highlight regions of interest within an image. The region of greatest interest becomes the selected OI. Next, an approximate visual 3D model of the selected OI is built on-line by a real-time modeller. Unlike previously proposed techniques, this modeller can build the model of the OI even in the presence of background clutter; an essential task for tracking one object amongst many. Once a model is built, a real-time 6-dof tracker (i.e., the third sub-component) performs the actual 6-dof object tracking via 3D model projection and optical flow. Performing simultaneous modelling and tracking presents several challenges requiring novel solutions. For example, a novel data-reduction scheme based on colour-gradient redundancy is proposed herein that facilitates using colour input images whilst still maintaining real-time performance on current computer hardware. Likewise, a per-pixel occlusion-rejection scheme is proposed which enables tracking in the presence of partial occlusions. Various other techniques have also been developed within the framework of this Thesis in order to achieve real-time efficiency, robustness to lighting variations, ability to cope with high OI speeds, etc. Extensive experiments with both synthetic and real-world motion sequences have demonstrated the ability of the proposed object-tracking system to track a priori unknown objects. The proposed algorithm has also been tested within two target applications: autonomous convoying, and dynamic camera reconfiguration.

Tracking of an object's full six degree-of-freedom (6-dof) position and orientation (pose) would allow a robotic system to autonomously perform a variety of complex tasks, such as docking from any preferred angle, surveillance of moving subjects, etc. Computer vision has been commonly advocated as an effective tool for 3D (i.e., 6-dof) tracking Objects of Interest (OIs). However, the vast majority of vision-based 6-dof pose trackers reported in the literature require a model of the OI to be provided a priori. Finding/selecting the OI to track is also essential to autonomous operation. A problem that has often been neglected. This Thesis proposes a novel, real-time object-tracking system that solves all of the aforementioned problems. The tracking procedure begins with OI selection. Since what constitutes an OI is application dependent, selection is achieved via a customizable framework of Interest Filters (IFs) that highlight regions of interest within an image. The region of greatest interest becomes the selected OI. Next, an approximate visual 3D model of the selected OI is built on-line by a real-time modeller. Unlike previously proposed techniques, this modeller can build the model of the OI even in the presence of background clutter; an essential task for tracking one object amongst many. Once a model is built, a real-time 6-dof tracker (i.e., the third sub-component) performs the actual 6-dof object tracking via 3D model projection and optical flow. Performing simultaneous modelling and tracking presents several challenges requiring novel solutions. For example, a novel data-reduction scheme based on colour-gradient redundancy is proposed herein that facilitates using colour input images whilst still maintaining real-time performance on current computer hardware. Likewise, a per-pixel occlusion-rejection scheme is proposed which enables tracking in the presence of partial occlusions. Various other techniques have also been developed within the framework of this Thesis in order to achieve real-time efficiency, robustness to lighting variations, ability to cope with high OI speeds, etc. Extensive experiments with both synthetic and real-world motion sequences have demonstrated the ability of the proposed object-tracking system to track a priori unknown objects. The proposed algorithm has also been tested within two target applications: autonomous convoying, and dynamic camera reconfiguration.

With the advances of wireless communications and micro-electronic device technologies, wireless sensor networks have been applied in a wide spectrum of applications, including one of the killer applications--object tracking. Among numerous challenges in object tracking, one of the important issues is the energy management. One solution to the above issue is the mobile agent-based paradigm. Using the mobile agent in wireless sensor networks has many advantages over the client/server paradigm in terms of energy consumptions, networks band-width, etc. In this thesis, we adopt the mobile agent-based paradigm to support object track-ing in wireless sensor networks. Although using the mobile agents for object tracking can improve the overall perfor-mance, the hurdle is the determination of the mobile agent itinerary. The past studies on ob-ject tracking considered the object¡¦s movement behavior as randomness or the direction and the speed of the object remain constant for a certain period of time. However, in most real-world cases, the object movement behavior is often based on certain underlying events rather than randomness complete. With this assumption, the movements of objects are some-times predictable. Through the prediction, the mobile agent can determine which node to mi-grate in order to reduce energy consumption and increase the performance of object tracking. In this thesis, we develop a mining-based approach to discover the useful patterns from the object¡¦s movement behavior. This approach utilizes the discovered rules to choose the sensor node the mobile agent needs to migrate in order to reduce the number of wrong migration, to reduce total energy consumed by sensor nodes, and to prolong the lifetime of the wireless sensor network. Experimental results show the efficiency of the proposed approach.

The multiple object tracking task (Pylyshyn and Storm, 1988) has long been a standard tool for use in understanding how we attend to multiple moving points in the visual field. In the current experiments, it is first demonstrated that this classical task can be adapted for use in a simulated driving environment, where it is commonly thought to apply. Standard requirements of driving (steering, maintaining headway) are shown to reduce tracking ability. Subsequent experiments (2a, 2b, 2c) investigate the way in which participants respond to events at target and distractor locations, and have bearing on Pylyshyn’s (1989) “indexing” hypothesis. The final experiment investigates the effect of the colour-composition of the tracking set on performance, and may have implications for our theoretical understanding of how tracking is performed. / AUTO21, NSERC, CANDrive

In this thesis, a novel Object Tracking Algorithm is proposed which tracks objects on Apple iPhone 4 platform in real-time. The system utilizes the colorspace of the frames provided by iPhone camera, in parallel with the motion data provided by iPhone motion sensors, to cancel the effect of iPhone rotations during tracking and matching different candidate tracks. The proposed system also adapts to changes in target appearance and size, thus leading to an object tracking robust to such changes. Several experiments conducted on actual video sequences are used to illustrate the functionality of the proposed approach.

In this thesis, a novel Object Tracking Algorithm is proposed which tracks objects on Apple iPhone 4 platform in real-time. The system utilizes the colorspace of the frames provided by iPhone camera, in parallel with the motion data provided by iPhone motion sensors, to cancel the effect of iPhone rotations during tracking and matching different candidate tracks. The proposed system also adapts to changes in target appearance and size, thus leading to an object tracking robust to such changes. Several experiments conducted on actual video sequences are used to illustrate the functionality of the proposed approach.

In this thesis, we propose a new aerial video dataset and benchmark for low altitude UAV target tracking, as well as, a photo-realistic UAV simulator that can be coupled with tracking methods. Our benchmark provides the first evaluation of many state of-the-art and popular trackers on 123 new and fully annotated HD video sequences captured from a low-altitude aerial perspective. Among the compared trackers, we determine which ones are the most suitable for UAV tracking both in terms of tracking accuracy and run-time. We also present a simulator that can be used to evaluate tracking algorithms in real-time scenarios before they are deployed on a UAV ”in the field”, as well as, generate synthetic but photo-realistic tracking datasets with free ground truth annotations to easily extend existing real-world datasets. Both the benchmark and simulator will be made publicly available to the vision community to further research in the area of object tracking from UAVs. Additionally, we propose a persistent, robust and autonomous object tracking system for unmanned aerial vehicles (UAVs) called Persistent Aerial Tracking (PAT). A computer vision and control strategy is applied to a diverse set of moving objects (e.g. humans, animals, cars, boats, etc.) integrating multiple UAVs with a stabilized RGB camera. A novel strategy is employed to successfully track objects over a long period, by ’handing over the camera’ from one UAV to another. We integrate the complete system into an off- 4 the-shelf UAV, and obtain promising results showing the robustness of our solution in real-world aerial scenarios.

The presented thesis deals with the design of a system capable of tracking the moving objects. The output of the thesis is the prototype layout of the device. Facility will be physically placed between the camera and the tripod in the dissertation and tested in real conditions. The role of this system is to automatically rolling the camera up the selected moving object.

Memoria para optar al título de Ingeniero Civil Eléctrico / En este trabajo se evaluarán distintos algoritmos de trackeo para el problema de seguimiento de peatones, donde teniendo un video obtenido de una camara de seguridad, nos interesa reconocer correctamente cada individuo a traves del tiempo, buscando minimizar la cantindad de etiquetas mal asignadas y objetos (peatones) no identificados. Para esto se ocuparán algorimos basados en el concepto de Conjuntos Aleatorios Finitos (Random Finite Sets - RFS), los cuales usan mediciones pasadas de los objetos para predecir posiciones futuras de todos ellos simultaneamente, mientras que también se consideran los casos de nacimientos y muertes de los objetos. Estos algoritmos fueron concebidos para el trackeo de objetos con movimientos simples y predecibles en condiciones de una gran cantidad ruido en las mediciones. mientras que las condiciones en las que se evaluarán son drasticamente opuestas, con un nivel muy alto de certeza en las mediciones pero con movimientos altamente no linear y muy impredecible. Se ocupará una libreria abierta creada por el investigador Ba Tuong Vo, donde están implementados varios de los más clásicos algoritmos en esta área. Es por esto que el trabajo se basará más en el análisis de los resultados en estas nuevas condiciones y observar como se comparán a los algoritmos actuales del area de Computer Vision (CV)/ Machine Learning (ML), usando tanto métricas de RFS como del área de CV.

Att spela brädspel är ett sätt för människor att interagera med varandra. Nyligen så påbörjade Egocentric Interaction Research Group (egocentrisk interaktions forskningsgrupp)på Malmö Universitet ett tvärvetenskapligt projekt kring den här typen av interaktion.Forskningen fokuserar på att analysera mellanmänsklig interaktion i en brädspelskontext.För att kunna dra slutsatser om interaktionen behövs empirisk data. I detta arbete presenteras processen kring utvecklingen av en prototyp för datainsamling i brädspelskontext.En kombination av 3D kamerateknik och 2D markörspårning används för att samla indata. Genom att kategorisera grundläggande händelser så som placering, förflyttning ochborttagning av 2D markörer samt kategorisera spelarnas rotationer i relation till bordetkan data samlas in och sparas i en databas. Systemet valideras genom en testsekvens. / Playing board games is one context where humans interact with each other. Recently theEgocentric Interaction Research Group at Malmö University piloted an interdisciplinaryproject to research this type of interaction. The research focus is to analyze the interactionbetween players while they are playing board games. However, empirical data needs tobe gathered from gameplay to be able to draw conclusions about the interaction. In thisthesis, the process of developing a prototype to collect event-based data is presented. Acombination of marker tracking technology and depth sensing is used for tracking 2Dmarkers as well as a single player in a tabletop environment. The system categorizes andstores basic events such as placing, removing, and changing the location of a 2D marker aswell as logging a player’s rotation in relation to the table. This empirical data is believedto be helpful for future studies by the Egocentric Interaction Research Group. The systemis validated through a test sequence.