Computer Science Colloquium

The understanding of human motion is a diverse and complex subject that includes recognizing and tracking individual actions and multiperson interactions. Its scope ranges from understanding the actions of an isolated person to understanding the actions and interactions of a crowd. At The University of Texas at Austin, we are pursuing a number of projects on human motion. The talk will present an overview of the ongoing research. Discussion will address (i) the segmentation and recognition of continuous human activity into discrete action primitives, (ii) tracking and recognizing two-person interactions in outdoor image sequences, and (iii) recognizing two-person interactions in indoor image sequences. The issues considered in these problems will illustrate the richness and the difficulty associated with understanding human motion. Application of the above research to monitoring and surveillance will be discussed. In addition, Prof. Aggarwal will discuss the role of perceptual organization in the isolation of structure in images, and how this structure may be used in content-based image retrieval by query or classification.

J. K. Aggarwal has served on the faculty of The University of Texas at Austin since 1964 and is currently the Cullen Professor of Electrical and Computer Engineering and Director of the Computer and Vision Research Center. His research interests include computer vision and pattern recognition. A Fellow of IEEE since 1976 and IAPR since 1998, he received the Senior Research Award of the American Society of Engineering Education in 1992, and the Technical Achievement Award of the IEEE Computer Society in 1996. He has served as Chairman of the IEEE Computer Society Technical Committee on Pattern Analysis and Machine Intelligence (1987-1989); President of the International Association for Pattern Recognition (1992-94) and held several other offices. He has published extensively on motion since 1975 and is currently focusing on human motion.