Early Representation and Analysis of Visual Spacetime

点击翻译按钮获取中文摘要

The research that my collaborators and I carry out is in the general area of computer vision, the attempt to endow machines with a sense of sight. From a theoretical point of view this is an important endeavor as it bears on fundamental issues in complex information processing, and may yield results that bear on our understanding of visual information processing in natural systems (e.g., humans), as well. From a practical point of view, machines that can see have the potential to interact with humans in a much more natural and useful fashion than is currently the case. Our particular studies of visual information provide insights into the fundamental properties of temporal sequences of image (e.g., video) and extend our technological capabilities by indicating novel applications. We use mathematical techniques to analyze images, develop processing algorithms based on our analyses and carry out empirical tests to evaluate their performance. This allows us to ask basic questions about temporal sequences of images, a pervasive source of information about our surround world. Questions of interest include: How can complex streams of video be parsed into meaningful components (e.g., persistent structures and moving objects)? How can multiple views of a captured scene be used to reconstruct a three-dimensional model of the scene? This research contributes to Canada in three important ways. First, it advances the discipline of computer vision as we expose basic properties of image information and develop corresponding algorithms for incorporation into vision machines; this allows Canada to compete successfully in a critical area of science and technology. Second, it provides students with hands on experience and skills in vital areas of investigation, computer vision and, more generally, computer science. Students go on to make careers in science, technology, teaching and elsewhere, taking with them the enrichment of having been involved in research. Third, it paves the way for novel ways to practically exploit image data. Applications of interest include video processing for everyday concerns ranging from the internet to personal handheld devices, video enhancement so that content is more readily interpretable and intelligent processing modules for robots.