Pattern Recognition in Video Center for （模式识别的视频中心）.pdf

Pattern Recognition in Video Rama Chellappa, Ashok Veeraraghavan, and Gaurav Aggarwal University of Maryland, College Park MD 20742, USA, {rama,vashok,gaurav}@ WWW home page: /~rama Abstract. Images constitute data that lives in a very high dimensional space, typically of the order of hundred thousand dimensions. Drawing inferences from data of such high dimensions soon becomes intractable. Therefore traditionally several of these problems like face recognition, object recognition, scene understanding etc. have been approached us- ing techniques in pattern recognition. Such methods in conjunction with methods for dimensionality reduction have been highly popular and suc- cessful in tackling several image processing tasks. Of late, the advent of cheap, high quality video cameras has generated new interests in extend- ing still image-based recognition methodologies to video sequences. The added temporal dimension in these videos makes problems like face and gait-based human recognition, event detection, activity recognition ad- dressable. Our research has focussed on solving several of these problems through a pattern recognition approach. Of course, in video streams pat- terns refer to both patterns in the spatial structure of image intensities around interest points and temporal patterns that arise either due to camera motion or object motion. In this paper, we discuss the applica- tions of pattern recognition in video to problems like tracking, face and gait-based human recognition, activity recognition and activity based person identification. 1 Introduction Pattern recognition is the art of being able to look at raw data and cateoga