The main idea of this thesis is to de ne and formulate the role of bias estimation in multitarget{multisensor scenarios as a general framework for various measurement types. After a brief introduction of the work that has been done in this thesis, three main contributions are explained in detail, which exercise the novel ideas. Starting with radar measurements, a new bias estimation method that can estimate o set and scaling biases in large network of radars is proposed. Further, Cram er{Rao Lower Bound is calculated for the bias estimation algorithm to show the theoretical accuracy that can be achieved by the proposed method. In practice, communication loss is also part of the distributed systems, which sometimes can not be avoided. A novel technique is also developed to accompany the proposed bias estimation method in this thesis to compensate for communication loss at di erent rates by the use of tracklets. Next, bearing{only measurements are considered. Biases in this type of measurement can be di cult to tackle because the measurement noise and systematic biases are normally larger than in radar measurements. In addition, target observability is sensitive to sensor{target alignment and can vary over time. In a multitarget{ multisensor bearing{only scenario with biases, a new model is proposed for the biases that is decoupled form the bearing{only measurements. These decoupled bias measurements then are used in a maximum likelihood batch estimator to estimate the biases and then be used for compensation. The thesis is then expanded by applying bias estimation algorithms into video sensor measurements. Video sensor measurements are increasingly implemented in distributed systems because of their economical bene ts. However, geo{location and geo{registration of the targets must be considered in such systems. In last part of the thesis, a new approach proposed for modeling and estimation of biases in a two video sensor platform which can be used as a standalone algorithm. The proposed algorithm can estimate the gimbal elevation and azimuth biases e ectively. It is worth noting that in all parts of the thesis, simulation results of various scenarios with di erent parameter settings are presented to support the ideas, the accuracy, mathematical modelings and proposed algorithms. These results show that the bias estimation methods that have been conducted in this thesis are viable and can handle larger biases and measurement errors than previously proposed methods. Finally, the thesis conclude with suggestions for future research in three main directions. / Thesis / Doctor of Philosophy (PhD)

Simulated sensor data from active and passive sensors has numerous applications in target detection and tracking. Simulated data is particularly useful in performance evaluation of target tracking algorithms where the ground truth of a scenario must be known. For real sensor data it is impossible to know the ground truth so simulated data must be used. This paper discusses existing methods for simulation of data from active sensors and proposes a method that builds on existing techniques from the field of computer graphics. An extension to existing methods is proposed to accommodate the simulation of active sensor data for which timing and frequency information is required in addition to intensity. Results from an existing method of active sensor data simulation are compared to the results of the proposed method. Additionally, a cloud computing framework is proposed and its scalability evaluated to address the fairly large computational load of such a simulation. / Thesis / Master of Applied Science (MASc)

[pt] O rastreamento visual é uma etapa essencial em diversas aplicações de visão computacional. Em particular, o rastreamento facial é considerado uma tarefa desafiadora devido às variações na aparência da face, devidas à etnia, gênero, presença de bigode ou barba e cosméticos, além de variações na aparência ao longo da sequência de vídeo, como deformações, variações em iluminação, movimentos abruptos e oclusões. Geralmente, os rastreadores são robustos a alguns destes fatores, porém não alcançam resultados satisfatórios ao lidar com múltiplos fatores ao mesmo tempo. Uma alternativa é combinar as respostas de diferentes rastreadores para alcançar resultados mais robustos. Este trabalho se insere neste contexto e propõe um novo método para a fusão de rastreadores escalável, robusto, preciso e capaz de manipular rastreadores independentemente de seus modelos. O método prevê ainda a integração de detectores de faces ao modelo de fusão de forma a aumentar a acurácia do rastreamento. O método proposto foi implementado para fins de validação, tendo sido testado em diversas configurações que combinaram até cinco rastreadores distintos e um detector de faces. Em testes realizados a partir de quatro sequências de vídeo que apresentam condições diversas de imageamento o método superou em acurácia os rastreadores utilizados individualmente. / [en] Visual tracking is fundamental in several computer vision applications. In particular, face tracking is challenging because of the variations in facial appearance, due to age, ethnicity, gender, facial hair, and cosmetics, as well as appearance variations in long video sequences caused by facial deformations, lighting conditions, abrupt movements, and occlusions. Generally, trackers are robust to some of these factors but do not achieve satisfactory results when dealing with combined occurrences. An alternative is to combine the results of different trackers to achieve more robust outcomes. This work fits into this context and proposes a new method for scalable, robust and accurate tracker fusion able to combine trackers regardless of their models. The method further provides the integration of face detectors into the fusion model to increase the tracking accuracy. The proposed method was implemented for validation purposes and was tested in different configurations that combined up to five different trackers and one face detector. In tests on four video sequences that present different imaging conditions the method outperformed the trackers used individually.