Understanding Video of Crowded Environments

点击翻译按钮获取中文摘要

The automated monitoring and surveillance of crowded scenes is a remarkable challenge for current image and video understanding technology. It has application in areas such as homeland security, natural disaster prevention, research on insect behavior, and monitoring of animal populations, among others. It has recently acquired strong societal significance, due to the possibility of terrorist attacks on events involving large concentrations of people, a problem for which there are currently no effective solutions. This project lays the foundation for the technology that will enable the automated monitoring and surveillance of crowded scenes, by modeling their video as a visual texture that deforms itself in stochastic but predictable ways, in response to certain events. In particular, the project aims to produce 1) a suite of generative probabilistic models for the video produced by various types of crowded scenes, and optimal algorithms for the estimation of their parameters, 2) a family of classifiers that build on these models to design detectors of important events, 3) a collection of algorithms for crowd video stabilization, segmentation, and parsing, and 4) a large database of video examples, that will establish a common experimental framework for the evaluation of future research in the field. Educationally, the project will provide research opportunities to both undergraduate students and students of underrepresented backgrounds.The URL address is: www.svcl.ucsd.edu/crowds