No description available.

Pedestrian detection is one of the most researched areas in computer vision and is rapidly gaining importance with the emergence of autonomous vehicles and steering assistance technology. Much work has been done in this field, ranging from the collection of extensive datasets to benchmarking of new technologies, but all the research depends on high-quality hardware such as high-resolution cameras, Light Detection and Ranging (LIDAR) and radar. For detection in low-quality moving camera videos, we use image deblurring techniques to reconstruct image frames and use existing pedestrian detection algorithms and compare our results with the leading research done in this area.

This study focuses on hexagonally sampled images and grayscale morphology. We combine hexagonal image processing and grayscale morphology to develop hexagonal grayscale morphology, and propose an algorithm to detect and enhance edges. Hexagonal image processing consists of three important steps: conversion of hexagonally sampled images, processing, and display of processed images on simulated hexagonal grid. We construct four different sizes of hexagonal structuring elements to apply morphological operations on hexagonal images. In this study, we applied morphological gradient for edge detection and proposed algorithm for edge enhancement. Moreover, we developed six different shapes of structuring elements to find an optimum one. Finally, we assessed two methods to compare our results, and identified the best result and optimum structuring element. We expect that proposed algorithm will offer a useful tool of image processing on hexagonally sampled images.

Security cameras installed in public spaces or in private organizations continuously record video data with the aim of detecting and preventing crime. For that reason, video content analysis applications, either for real time (i.e. analytic) or post-event (i.e. forensic) analysis, have gained high interest in recent years. In this thesis, the primary focus is on two key aspects of video analysis, reliable moving object segmentation and carried object detection & identification. A novel moving object segmentation scheme by background subtraction is presented in this thesis. The scheme relies on background modelling which is based on multi-directional gradient and phase congruency. As a post processing step, the detected foreground contours are refined by classifying the edge segments as either belonging to the foreground or background. Further contour completion technique by anisotropic diffusion is first introduced in this area. The proposed method targets cast shadow removal, gradual illumination change invariance, and closed contour extraction. A state of the art carried object detection method is employed as a benchmark algorithm. This method includes silhouette analysis by comparing human temporal templates with unencumbered human models. The implementation aspects of the algorithm are improved by automatically estimating the viewing direction of the pedestrian and are extended by a carried luggage identification module. As the temporal template is a frequency template and the information that it provides is not sufficient, a colour temporal template is introduced. The standard steps followed by the state of the art algorithm are approached from a different extended (by colour information) perspective, resulting in more accurate carried object segmentation. The experiments conducted in this research show that the proposed closed foreground segmentation technique attains all the aforementioned goals. The incremental improvements applied to the state of the art carried object detection algorithm revealed the full potential of the scheme. The experiments demonstrate the ability of the proposed carried object detection algorithm to supersede the state of the art method.

A transição do sistema radiográfico convencional para os sistemas radiográficos digitais, ao longo de vinte anos, tem transformado as salas de laudos nos Serviços de Diagnóstico por Imagem tanto na Medicina quanto na Medicina Veterinária. Atualmente, com a introdução do sistema radiográfico computadorizado na rotina de alguns hospitais e laboratório de imagem, o uso das ferramentas do pós-processamento tem se tornado mais freqüente. Diante das vantagens e desvantagens destas ferramentas e da escassez de trabalhos a cerca dos filtros utilizados em imagens radiográficas digitais, o objetivo deste trabalho foi testar o uso dos filtros convencional, realce de borda e invertido, assim como a associação deles na detecção dos padrões pulmonares de cães e gatos. Foram selecionados 40 exames radiográficos do tórax de cães e gatos contendo as três projeções de eleição. Três observadores com diferentes graus de experiência e familiaridade com o sistema radiográfico computadorizado analisaram os filtros individualmente e depois em associação na detecção geral dos padrões pulmanres e individualmente. Obteve-se melhores valores de sensibilidade e especificidade, em geral, quando os observadores experientes utilizaram os três filtros em associação e, para o iniciante, os melhores resultados da sensibilidade e especificidade, em geral, foram no filtro convencional. Os resultados deste trabalho permitiram concluir que houve diferença estatística entre os observadores com distintos graus de experiência e familiaridade com o sistema digital. E que o uso em associação dos filtros pode incrementar o desempenho do radiologista na avaliação radiográfica do parênquima pulmonar. / The transition of the conventional radiographic system to the digital one has been transforming the radiographic routine human and veterinary medicine over the last twenty years. Currently, the introduction of the computed radiography system in some hospitals and imaging services has increased the use of post processing tools. Considering the advantages and disadvantages of these tools and the lack of knowledge about the filters used in digital radiographic images, the aim of this study was to test efficacy of the standard, edge enhancement and gray scale reversed filters and their association to detect pulmonary patterns of cats and dogs. This work selected forty canine and feline sets of thoracic radiographs, including three projections. Three different observers with different degrees of experience and familiarity with the computed radiographic system analyzed the filters individually and then associated in order to detect pulmonary patterns. The best results in sensibility and specificity were related to the more experienced observers using the three associated filters. However, for the beginner, the best sensibility and specificity results was reached with the use of the standard filter in general results. In conclusion were statistical differences between more experienced and familiarized observers with the digital system and the use of filters can increase the radiologist performance when evaluating the pulmonary patterns on the radiography.

A transição do sistema radiográfico convencional para os sistemas radiográficos digitais, ao longo de vinte anos, tem transformado as salas de laudos nos Serviços de Diagnóstico por Imagem tanto na Medicina quanto na Medicina Veterinária. Atualmente, com a introdução do sistema radiográfico computadorizado na rotina de alguns hospitais e laboratório de imagem, o uso das ferramentas do pós-processamento tem se tornado mais freqüente. Diante das vantagens e desvantagens destas ferramentas e da escassez de trabalhos a cerca dos filtros utilizados em imagens radiográficas digitais, o objetivo deste trabalho foi testar o uso dos filtros convencional, realce de borda e invertido, assim como a associação deles na detecção dos padrões pulmonares de cães e gatos. Foram selecionados 40 exames radiográficos do tórax de cães e gatos contendo as três projeções de eleição. Três observadores com diferentes graus de experiência e familiaridade com o sistema radiográfico computadorizado analisaram os filtros individualmente e depois em associação na detecção geral dos padrões pulmanres e individualmente. Obteve-se melhores valores de sensibilidade e especificidade, em geral, quando os observadores experientes utilizaram os três filtros em associação e, para o iniciante, os melhores resultados da sensibilidade e especificidade, em geral, foram no filtro convencional. Os resultados deste trabalho permitiram concluir que houve diferença estatística entre os observadores com distintos graus de experiência e familiaridade com o sistema digital. E que o uso em associação dos filtros pode incrementar o desempenho do radiologista na avaliação radiográfica do parênquima pulmonar. / The transition of the conventional radiographic system to the digital one has been transforming the radiographic routine human and veterinary medicine over the last twenty years. Currently, the introduction of the computed radiography system in some hospitals and imaging services has increased the use of post processing tools. Considering the advantages and disadvantages of these tools and the lack of knowledge about the filters used in digital radiographic images, the aim of this study was to test efficacy of the standard, edge enhancement and gray scale reversed filters and their association to detect pulmonary patterns of cats and dogs. This work selected forty canine and feline sets of thoracic radiographs, including three projections. Three different observers with different degrees of experience and familiarity with the computed radiographic system analyzed the filters individually and then associated in order to detect pulmonary patterns. The best results in sensibility and specificity were related to the more experienced observers using the three associated filters. However, for the beginner, the best sensibility and specificity results was reached with the use of the standard filter in general results. In conclusion were statistical differences between more experienced and familiarized observers with the digital system and the use of filters can increase the radiologist performance when evaluating the pulmonary patterns on the radiography.