A área de recuperação de informação baseada em conteúdo visual vem ganhando importância graças ao volume de material visual existente (imagens e vídeo digitais), compartilhado e distribuído principalmente via Internet, e à capacidade de processamento alcançada pelos computadores pessoais na última década. Novas formas de consumo, manipulação e exploração de vídeo digital podem ser criadas através da organização e indexação apropriada desse material. A delimitação de tomadas fornece uma base para a abstração e estruturação de vídeo, agregando quadros contíguos em seqüências de mesmo contexto, isto é, trechos com unidade em termos de tempo e espaço. Nesta dissertação são apresentados os conceitos básicos de delimitação de tomadas e métodos tradicionais utilizados nesse tipo de segmentação, bem como vários resultados experimentais obtidos a partir de seqüências reais de TV. É analisada a distribuição das diferenças entre quadros sucessivos, calculada através de seus histogramas, na tentativa de caracterizar as transições entre tomadas e obter melhores parâmetros para a segmentação. Obtêm-se experimentalmente mais evidências que comprovam a superioridade da medida de intersecção de histogramas sobre outras medidas. A principal contribuição do trabalho consiste no desenvolvimento de um algoritmo baseado no método twin-comparison, que apresenta melhor desempenho que o método original na detecção dos limites de tomadas por utilizar análise local da variação visual entre os quadros do vídeo. / Visual content based information retrieval is an area of increasing importance due to the large volume of available material (digital images and videos), shared and distributed mainly by the internet, and the processing power achieved by personal computer in the last ten years. New ways to consume digital video and to manipulate and explore its visual information can be made by appropriately organizing and indexing this material. The shot boundary detection is a fundamental tool to video abstraction and structuring, combining near frames into sequences with similar context, segments with space and time unity. This work presents the basic concepts about shot boundary detection, traditional methods used and several experimental results obtained from a real TV data set. The distribution of differences of neighboring frames, calculated from histogram comparison, is used to define the transitions between frames and to obtain better parameters for segmentation. Our experimental results show the superiority of the histogram intersection method over other measures. Our main contribution is the development of a new algorithm based on the twin-comparison method, extended with local analysis of visual content variation between video frames. This algorithm was tested over hours of TV data, and performs better than the original method.

Proposed research object aims to develop and implement the novel imaging technique to delineate tissue boundaries based on electrical impedance of tissues.

A área de recuperação de informação baseada em conteúdo visual vem ganhando importância graças ao volume de material visual existente (imagens e vídeo digitais), compartilhado e distribuído principalmente via Internet, e à capacidade de processamento alcançada pelos computadores pessoais na última década. Novas formas de consumo, manipulação e exploração de vídeo digital podem ser criadas através da organização e indexação apropriada desse material. A delimitação de tomadas fornece uma base para a abstração e estruturação de vídeo, agregando quadros contíguos em seqüências de mesmo contexto, isto é, trechos com unidade em termos de tempo e espaço. Nesta dissertação são apresentados os conceitos básicos de delimitação de tomadas e métodos tradicionais utilizados nesse tipo de segmentação, bem como vários resultados experimentais obtidos a partir de seqüências reais de TV. É analisada a distribuição das diferenças entre quadros sucessivos, calculada através de seus histogramas, na tentativa de caracterizar as transições entre tomadas e obter melhores parâmetros para a segmentação. Obtêm-se experimentalmente mais evidências que comprovam a superioridade da medida de intersecção de histogramas sobre outras medidas. A principal contribuição do trabalho consiste no desenvolvimento de um algoritmo baseado no método twin-comparison, que apresenta melhor desempenho que o método original na detecção dos limites de tomadas por utilizar análise local da variação visual entre os quadros do vídeo. / Visual content based information retrieval is an area of increasing importance due to the large volume of available material (digital images and videos), shared and distributed mainly by the internet, and the processing power achieved by personal computer in the last ten years. New ways to consume digital video and to manipulate and explore its visual information can be made by appropriately organizing and indexing this material. The shot boundary detection is a fundamental tool to video abstraction and structuring, combining near frames into sequences with similar context, segments with space and time unity. This work presents the basic concepts about shot boundary detection, traditional methods used and several experimental results obtained from a real TV data set. The distribution of differences of neighboring frames, calculated from histogram comparison, is used to define the transitions between frames and to obtain better parameters for segmentation. Our experimental results show the superiority of the histogram intersection method over other measures. Our main contribution is the development of a new algorithm based on the twin-comparison method, extended with local analysis of visual content variation between video frames. This algorithm was tested over hours of TV data, and performs better than the original method.

No description available.

This paper describes the initial results of a project to create a self-supervised algorithm for learning object segmentation from video data. Developmental psychology and computational experience have demonstrated that the motion segmentation of objects is a simpler, more primitive process than the detection of object boundaries by static image cues. Therefore, motion information provides a plausible supervision signal for learning the static boundary detection task and for evaluating performance on a test set. A video camera and previously developed background subtraction algorithms can automatically produce a large database of motion-segmented images for minimal cost. The purpose of this work is to use the information in such a database to learn how to detect the object boundaries in novel images using static information, such as color, texture, and shape. / Singapore-MIT Alliance (SMA)

This thesis shows how to detect boundaries on the basis of motion information alone. The detection is performed in two stages: (i) the local estimation of motion discontinuities and of the visual flowsfield; (ii) the extraction of complete boundaries belonging to differently moving objects. For the first stage, three new methods are presented: the "Bimodality Tests,'' the "Bi-distribution Test,'' and the "Dynamic Occlusion Method.'' The second stage consists of applying the "Structural Saliency Method,'' by Sha'ashua and Ullman to extract complete and unique boundaries from the output of the first stage. The developed methods can successfully segment complex motion sequences.

Texture boundary detection (or segmentation) is an important capability of the human visual system. Usually, texture segmentation is viewed as a 2D problem, as the definition of the problem itself assumes a 2D substrate. However, an interesting hypothesis emerges when we ask a question regarding the nature of textures: What are textures, and why did the ability to discriminate texture evolve or develop? A possible answer to this question is that textures naturally define physically distinct surfaces or objects, thus, we can hypothesize that 2D texture segmentation may be an outgrowth of the ability to discriminate surfaces in 3D. In this thesis, I investigated the relative difficulty of learning to segment textures in 2D vs. 3D configurations. It turns out that learning is faster and more accurate in 3D, very much in line with what was expected. Furthermore, I have shown that the learned ability to segment texture in 3D transfers well into 2D texture segmentation, but not the other way around, bolstering the initial hypothesis, and providing an alternative approach to the texture segmentation problem.

Texture boundary detection (or segmentation) is an important capability of the human visual system. Usually, texture segmentation is viewed as a 2D problem, as the definition of the problem itself assumes a 2D substrate. However, an interesting hypothesis emerges when we ask a question regarding the nature of textures: What are textures, and why did the ability to discriminate texture evolve or develop? A possible answer to this question is that textures naturally define physically distinct surfaces or objects, thus, we can hypothesize that 2D texture segmentation may be an outgrowth of the ability to discriminate surfaces in 3D. In this thesis, I investigated the relative difficulty of learning to segment textures in 2D vs. 3D configurations. It turns out that learning is faster and more accurate in 3D, very much in line with what was expected. Furthermore, I have shown that the learned ability to segment texture in 3D transfers well into 2D texture segmentation, but not the other way around, bolstering the initial hypothesis, and providing an alternative approach to the texture segmentation problem.

Boundary detection is an essential first-step for many computer vision applications. In practice, boundary detection is difficult because most images contain texture. Normally, texture-boundary detectors are complex, and so cannot run in real-time. On the other hand, the few texture boundary detectors that do run in real-time leave much to be desired in terms of quality. This thesis proposes two real-time texture-boundary detectors – the Variance Ridge Detector and the Texton Ridge Detector – both of which can detect high-quality texture-boundaries in real-time. The Variance Ridge Detector is able to run at 47 frames per second on 320 by 240 images, while scoring an F-measure of 0.62 (out of a theoretical maximum of 0.79) on the Berkeley segmentation dataset. The Texton Ridge Detector runs at 10 frames per second but produces slightly better results, with an F-measure score of 0.63. These objective measurements show that the two proposed texture-boundary detectors outperform all other texture-boundary detectors on either quality or speed. As boundary detection is so widely-used, this development could induce improvements to many real-time computer vision applications.

The wet zone – the lagg – that tends to form at the edge of ombrotrophic peatlands is believed to play an important role in promoting and maintaining the health of bog systems. The lagg is well-recognized by peatland scientists, yet empirical knowledge is surprisingly limited, and most of the characteristics associated with this ecotone come from qualitative observations. Understanding the role played by the lagg, and the potential impact its disturbance might have on the integrity of a raised bog system, is valuable for sustainable land management and peatland restoration science alike. This thesis explores and documents the basic ecohydrological characteristics of the lagg in the context of the neighbouring natural landscapes, and discusses the spatial properties of various types of laggs by exploring airborne LiDAR datasets to detect and position the ecotone. The specific objectives are 1) to describe the form and abiotic controls of the laggs and margins of bog peatlands, 2) to propose a conceptual model in cross-section of the “bog-lagg-mineral land” transition, 3) to explore the potential of data derived from aerial LiDAR (Light Detection And Ranging) to detect and locate laggs and lagg boundaries, and 4) to consider the spatial distribution of laggs around raised bog peatlands. Data were collected along 10 transects located within 6 relatively undisturbed bogs of the New Brunswick eastern lowlands, Canada. Each transect consisted of 4-6 wells, straddling the ombrotrophic bog and the adjacent mineral land, and of 3 nested piezometers in the center of each lagg. These instruments were used to monitor the position of the water table, to measure hydraulic gradient, hydraulic conductivity, and for water sampling. Dissimilarity analysis (edge-detection, split moving window) and similarity analysis (cluster, k-means) were used to test the delineation capacity of five variables derived from the LiDAR dataset; ground elevation (topography), vegetation height, topographic wetness index, and spatial frequency of both vegetation and ground LiDAR returns. The major abiotic control of the lagg appears to be topography. Two geomorphological categories were identified; confined and unconfined. The importance of topography is through the affect it has on water flow rates and direction, which in turn affect water chemistry, and most likely nutrient transport and availability, hence vegetation characteristics. Dissimilarity analysis of the five variables derived from LiDAR data revealed that some indicators were better at predicting the bog-lagg boundary (e.g. vegetation height), and others at finding the lagg-mineral land boundary (e.g. topography). In contrast, the similarity analysis gave more decisive influence to the topographic wetness index. When the lagg was confined between the bog and the adjacent upland, it took a linear form, parallel to the peatland’s edge. However, when the adjacent mineral land was flat or even sloping away, the lagg spatial distribution was discontinuous and intermittent around the bog. Our results confirms that laggs can take many forms, while suggesting two broad geomorphological categories from which they can more easily be studied and understood and highlight the potential offered by LiDAR technology in predicting their likely location around a raised bog. The results and conclusion from this research further our understanding of the goals to be achieved for ecological restoration, and favor sustainable management inclusive of the margins or bog peatlands.