Este trabalho apresenta um sistema de auxilio à navegação autônoma para veículos terrestres com foco em ambientes estruturados em um cenário agrícola. É gerada a estimativa das posições dos obstáculos baseado na fusão das detecções provenientes do processamento dos dados de duas câmeras, uma estéreo e outra térmica. Foram desenvolvidos três módulos de detecção de obstáculos. O primeiro módulo utiliza imagens monoculares da câmera estéreo para detectar novidades no ambiente através da comparação do estado atual com o estado anterior. O segundo módulo utiliza a técnica Stixel para delimitar os obstáculos acima do plano do chão. Por fim, o terceiro módulo utiliza as imagens térmicas para encontrar assinaturas que evidenciem a presença de obstáculo. Os módulos de detecção são fundidos utilizando a Teoria de Dempster-Shafer que fornece a estimativa da presença de obstáculos no ambiente. Os experimentos foram executados em ambiente agrícola real. Foi executada a validação do sistema em cenários bem iluminados, com terreno irregular e com obstáculos diversos. O sistema apresentou um desempenho satisfatório tendo em vista a utilização de uma abordagem baseada em apenas três módulos de detecção com metodologias que não tem por objetivo priorizar a confirmação de obstáculos, mas sim a busca de novos obstáculos. Nesta dissertação são apresentados os principais componentes de um sistema de detecção de obstáculos e as etapas necessárias para a sua concepção, assim como resultados de experimentos com o uso de um veículo real. / This work presents a support system to the autonomous navigation for ground vehicles with focus on structured environments in an agricultural scenario. The estimated obstacle positions are generated based on the fusion of the detections from the processing of data from two cameras, one stereo and other thermal. Three modules obstacle detection have been developed. The first module uses monocular images of the stereo camera to detect novelties in the environment by comparing the current state with the previous state. The second module uses Stixel technique to delimit the obstacles above the ground plane. Finally, the third module uses thermal images to find signatures that reveal the presence of obstacle. The detection modules are fused using the Dempster-Shafer theory that provides an estimate of the presence of obstacles in the environment. The experiments were executed in real agricultural environment. System validation was performed in well-lit scenarios, with uneven terrain and different obstacles. The system showed satisfactory performance considering the use of an approach based on only three detection modules with methods that do not prioritize obstacle confirmation, but the search for new ones. This dissertation presents the main components of an obstacle detection system and the necessary steps for its design as well as results of experiments with the use of a real vehicle.

Distributed target tracking (DTT) is desirable in wireless camera networks to achieve scalability and robustness to node or link failures. DTT estimates the target state via information exchange and fusion among cameras. This thesis proposes new DTT algorithms to handle five major challenges of DTT in wireless camera networks, namely non-linearity in the camera measurement model, temporary lack of measurements (benightedness) due to limited field of view, redundant information in the network, limited connectivity of the network due to limited communication ranges and asynchronous information caused by varying and unknown frame processing delays. The algorithms consist of two phases, namely estimation and fusion. In the estimation phase, the cameras process their captured frames, detect the target, and estimate the target state (location and velocity) and its uncertainty using the Extended Information Filter (EIF) that handles non-linearity. In the fusion phase, the cameras exchange their local target information with their communicative neighbours and fuse the information. The contributions of this thesis are as follows. The target states estimated by the EIFs undergo weighted fusion. The weights are chosen based on the estimated uncertainty (error covariance) and the number of nodes with redundant information such that the information of benighted nodes and the redundant information get lower weights. At each time step, only the cameras having the view of the target and the cameras that might have the view of the target in the next time step participate in the fusion (tracking). This reduces the energy consumption of the network. The algorithm selects the cameras dynamically by using a threshold on their shortest distances (in the communication graph) from the cameras having the view of the target. Before fusion, each camera predicts the target information of other cameras to temporally align its information with the (asynchronous) information received from other cameras. The algorithm predicts the target state using the latest estimated velocity of the target. The experimental results show that the proposed algorithms achieve higher tracking accuracy than the state of the art under the five DTT challenges.

In multi-camera surveillance, association of people detected in different camera views over time, known as person re-identification, is a fundamental task. Re-identification is a challenging problem because of changes in the appearance of people under varying camera conditions. Existing approaches focus on improving the re-identification accuracy, while no specific effort has yet been put into efficiently utilising the available resources that are normally limited in a camera network, such as storage, computation and communication capabilities. In this thesis, we aim to perform and improve the task of re-identification under constrained resources. More specifically, we reduce the data needed to represent the appearance of an object through a proposed feature selection method and a difference-vector representation method. The proposed feature-selection method considers the computational cost of feature extraction and the cost of storing the feature descriptor jointly with the feature's re-identification performance to select the most cost-effective and well-performing features. This selection allows us to improve inter-camera re-identification while reducing storage and computation requirements within each camera. The selected features are ranked in the order of effectiveness, which enable a further reduction by dropping the least effective features when application constraints require this conformity. We also reduce the communication overhead in the camera network by transferring only a difference vector, obtained from the extracted features of an object and the reference features within a camera, as an object representation for the association. In order to reduce the number of possible matches per association, we group the objects appearing within a defined time-interval in un-calibrated camera pairs. Such a grouping improves the re-identification, since only those objects that appear within the same time-interval in a camera pair are needed to be associated. For temporal alignment of cameras, we exploit differences between the frame numbers of the detected objects in a camera pair. Finally, in contrast to pairwise camera associations used in literature, we propose a many-to-one camera association method for re-identification, where multiple cameras can be candidates for having generated the previous detections of an object. We obtain camera-invariant matching scores from the scores obtained using the pairwise re-identification approaches. These scores measure the chances of a correct match between the objects detected in a group of cameras. Experimental results on publicly available and in-lab multi-camera image and video datasets show that the proposed methods successfully reduce storage, computation and communication requirements while improving the re-identification rate compared to existing re-identification approaches.

A utilização de detectores de radiação é de imensa importância na área de dosimetria, pois permite a quantificação da dose absorvida no meio. Uma técnica interessante para esta finalidade é o uso de detectores por cintilação. Estudos recentes com cintiladores plásticos e líquidos demonstraram a viabilidade do uso de detecção de cintilação por uma câmera digital com sensor CCD ou CMOS. Desse modo, este trabalho tem como objetivo desenvolver um dosímetro cintilador de baixo custo para viabilidade de seu uso e, de um sistema de detecção de cintilação através de uma câmera digital, para que assim pudesse ser realizada sua caracterização dosimétrica. O sistema dosimétrico foi construído a partir de um cintilador líquido a base de antraceno. Dosimetricamente verificou-se uma linearidade de resposta para a dose de 0,1 a 25,53 Gy, para a taxa de dose de 6,66 Gy/min e uma pequena diminuição da sensibilidade do dosímetro quando aumentada a taxa de dose de irradiação. Com relação à dependência energética, foi verificado um aumento na sensibilidade do dosímetro de 10,8% ao se variar a energia de 100 a 160 kVp. Quando comparado a um cintilador comercial, apresentou uma intensidade de sinal reduzida e, em uma análise de reprodutibilidade, obteve-se uma variação máxima de 2% em relação a repetição de uma mesma medida. O cintilador líquido apresentou baixa estabilidade pré e pós-irradiação, com uma variação de cor e redução do sinal ao decorrer dos dias. Para medidas bidimensionais o sistema montado mostrou-se promissor, uma vez que em medidas de deposição de dose com a profundidade para várias energias de feixes, verificou-se o aumento da penetração da radiação com o aumento da energia do feixe e as medidas de penumbra de um feixe parcialmente blindado com 2 mmPb apresentaram um valor de 1,79 cm, considerando o tipo de tubo gerador e blindagem utilizada. Por toda a caracterização realizada o sistema dosimétrico mostrou-se aplicável para dosimetria, desde que operado considerando as características apresentadas. / The utilization of radiation detector is important in the dosimetric area, because it allow the quantification of absortion dose in the medium. An interesting tehnique for this finalitypurpose is the use of scintillation detector. Recent studies with plastic scintillators and liquid scintillators have demonstrated the feasibility of using scintillation detection by a digital camera with CCD or CMOS sensors. Thus, this study is the intent to develop a low-cost scintillation dosimeter for the feasibility of its use and detection scintillation system through by a digital camera, with the finality of dosimetric characterization. The dosimetric system was constructed from using liquid scintilator based anthracene. A linearity dose response between 0.1 to 25.53 Gy was found for the dose rate of 6.66 Gy/min and the dosimeter sensibility was decreased when the dose rate increased. When varied the energy from 100 to 160 kVp, was verified an increased of 10.8% in the dosimeter sensibility, due the energy dependence. When compared to a commercial dosimeter, it shows signal intensity decreased and, the study of reproducibility, a maximum variation of 2% was obtained in relation to the repetition of the same measure. The liquid scintillator presented low stability before and after irradiation, with a color variation and signal reduction over the days. For two-dimensional measurements the assembled system proved to be promising, since in dose deposition measurements with the depth for several beam energies, the penetration of the radiation was increased with the increase of the beam energy and the penumbra measurements of a narrow beam with 2mmPb presented a value of 1.79 cm, considering the type of generator tube and narrow used. Throughout the characterization carried out the dosimetric system proved to be applicable for dosimetry, if operated considering the characteristics presented.

Asphalt pavement rutting is one of the most common and destructive pavement distresses observed on U.S. roads, particularly in the urban environment at intersections. They are an important indicator of the structural integrity of the pavement as well as having an impact on road user safety. For these reasons, most road agencies regularly monitor the levels of rut depths on their pavement. There are four technologies used for estimating rut depth in automated measurement way: ultrasonics, point lasers, scanning lasers, Optical. This thesis will focus on the development of the laser scanner rut depth measurement system, including the improvement of the hardware design, the software development and data analysis. In order to evaluate the accuracy and correction of the laser scanner system, the researcher used it to measure different pavement in different situations. This research focused on the performance measures, such as correlativity, repeatability. From field experiments and data analysis, the following results had been obtained: 1. Laser scanner showed satisfactory repeatability performances; 2. Laser scanner has good correlations with manual rut data. 3. High power laser scanner in dark asphalt has good correlations with in light pavement. The findings of this research will contribute to the development of laser system in the measurement of pavement rutting.

<p>This thesis presents work done within the EC-founded project VISATEC. Due to the different directions of the VISATEC project this thesis has a few different threads.</p><p>A novel presentation scheme for medium level vision features applied to range sensor data and to image sequences. Some estimation procedures for this representation have been implemented and tested. The representation is tensor based and uses higher order tensors in a projective space. The tensor can hold information on several local structures including their relative position and orientation. This information can also be extracted from the tensor.</p><p>A number of well-known techniques are combined in a novel way to be able to perform object pose estimation under changes of the object in position, scale and rotation from a single 2D image. The local feature used is a patch which is resampled in a log-polar pattern. A number of local features are matched to a database and the k nearest neighbors vote an object state parameters. This most probable object states are found through mean-shift clustering.</p><p>A system using multi-cue integration as a means of reaching a higher level of system-level robustness and a higher lever of accuracy is developed and evaluated in an industrial-like-setting. The system is based around a robotic manipulator arm with an attached camera. The system is designed to solve parts of the bin-picking problem. The above mentioned 2D technique for object pose estimation is also evaluated within this system.</p>

<p>Buildings, maps and objects et cetera, can be modeled using a computer or reconstructed in 3D by data from different kinds of cameras or laser scanners. This thesis concerns the latter. The recent improvements of Time-of-Flight cameras have brought a number of new interesting research areas to the surface. Registration of several ToF camera point clouds is such an area.</p><p>A literature study has been made to summarize the research done in the area over the last two decades. The most popular method for registering point clouds, namely the Iterative Closest Point (ICP), has been studied. In addition to this, an error relaxation algorithm was implemented to minimize the accumulated error of the sequential pairwise ICP.</p><p>A few different real-world test scenarios and one scenario with synthetic data were constructed. These data sets were registered with varying outcome. The obtained camera poses from the sequential ICP were improved by loop closing and error relaxation.</p><p>The results illustrate the importance of having good initial guesses on the relative transformations to obtain a correct model. Furthermore the strengths and weaknesses of the sequential ICP and the utilized error relaxation method are shown.</p>

Thesis (M.A.)--University of North Carolina at Greensboro, 2006. / Title from PDF title page screen. Advisor: Kenneth Allan; submitted to the Dept. of Sociology. Includes bibliographical references (p. 81-85).

Successful treatment of myocardial infarction requires anearly and accurate diagnosis. Recent studies have shown thatacute myocardial scintigraphy has a high predictive value forprognosis of myocardial events. Three dimensional (3D)perfusion data obtained with SPECT are however very rare in theemergency department (ED). We have developed a mobile tomographic system for myocardialscintigraphy, which can be used in the ED. The objectives ofthe studies presented were:     To develop software and hardware for a mobile tomographicgamma camera system: the Cardiotom     To demonstrate that a mobile tomographic system can beused in a clinical situation     To evaluate the limitations of Ectomography when usingfiltered back projection for reconstruction     To develop a method of reconstruction that compensatesfor the incomplete data acquisition associated with theacquisition geometry of Ectomography Three prototypes of a mobile tomographic gamma camera systemhave been designed and built at the Division of MedicalEngineering, which all have been used in a clinical setting.The systems are based on Ectomography, a limited view anglemethod, also developed by us. Instead of rotating the entiregamma camera detector around the patient as in SPECT, a slanthole collimator is rotated in front of a stationary detector.Since short imaging times are important in the ED and the heartonly occupies a small area of the detector, system sensitivityhas been increased by dividing the collimator into segmentswith different projection directions. In myocardial imaging, 4segments are used and within 10 minutes from the start ofacquisition, reconstructed short axis view sections areavailable for interpretation. Using the Cardiotom in an experimental animal study, weverified that the system could be used to quantify myocardialarea at risk and final infarct size. This conclusion was madefrom a comparison of images obtained from the Cardiotom andpathological staining of the myocardium, analysedpost-mortem. Inherent limitations of Ectomography were evaluated withboth phantom studies and computer simulated data, reconstructedusing filtered back-projection Results show that moderatedeviation from optimal position of the detector with respect tothe myocardium will have little or no influence on thediagnostic information when assessed from short axis sectionimages and polar tomograms. However, long axis section imagesappear elongated when reconstructed using filteredback-projection. We have shown that this elongation distortion can besuppressed using iterative reconstructions techniques, and wehave implemented such an algorithm, called three-dimensionalTotal Variation Expectation Maximisation (3DTV-EM). Resultswere that elongation distortion was reduced and depthresolution improved. The reconstruction technique was alsoevaluated for SPECT reconstruction and was found to decreasethe noise in reconstructed images, when compared to thetwo-dimensional TV-EM algorithm. Noise pattern were also foundto be more uniform for the 3DTV-EM algorithm compared totwo-dimensional TV-EM. In conclusion, we have shown that the Cardiotom may beuseful in a clinical acute setting, providing valuablediagnostic information. Rapid positioning is possible, sincemoderate deviation from optimal positioning will cause few orno artefacts. Image quality can be improved if iterativetechniques are used for image reconstruction instead offiltered back-projection. <b>Keywords</b>: acute studies, myocardial infarction,scintigraphy, mobile gamma camera, tomography.

Buildings, maps and objects et cetera, can be modeled using a computer or reconstructed in 3D by data from different kinds of cameras or laser scanners. This thesis concerns the latter. The recent improvements of Time-of-Flight cameras have brought a number of new interesting research areas to the surface. Registration of several ToF camera point clouds is such an area. A literature study has been made to summarize the research done in the area over the last two decades. The most popular method for registering point clouds, namely the Iterative Closest Point (ICP), has been studied. In addition to this, an error relaxation algorithm was implemented to minimize the accumulated error of the sequential pairwise ICP. A few different real-world test scenarios and one scenario with synthetic data were constructed. These data sets were registered with varying outcome. The obtained camera poses from the sequential ICP were improved by loop closing and error relaxation. The results illustrate the importance of having good initial guesses on the relative transformations to obtain a correct model. Furthermore the strengths and weaknesses of the sequential ICP and the utilized error relaxation method are shown.