Computer Science Bldg. Room 601
Dr. Sangho Park
The development of computer vision systems that are able to detect and recognize human activities has a broad impact on application areas such as motion analysis in sports and medicine, smart surveillance, virtual reality, user interfaces, and assistive technology for healthcare. These application areas can be viewed as intelligent systems in which humans and the systems (i.e., equipment, rooms, and infrastructures) collaborate with each other in a natural and seamless manner. The analysis of human activity is a diverse and complex subject that includes tracking and modeling human activity, and it often requires that video events be described at the semantic level. The scope ranges from understanding the actions of an isolated person to understanding the interactions between the persons and the environment. The objective of this talk is two-fold: to present a unified framework for human activity analysis that can seamlessly integrate multiple processing steps in video computing and to demonstrate the efficacy and scalability of the framework in diverse context of sensor-based intelligent systems. We illustrate our technical approach in intelligent video surveillance, driver behavior analysis in intelligent vehicles, and multi-level analysis of human activity in indoor and outdoor environments.
BIO: Dr. Sangho Park received his Bachelor of Science degree in electrical and computer engineering at Yonsei University, Seoul, Korea. He received his M.A. in cognitive psychology and Ph.D. in electrical and computer engineering from the University of Texas at Austin, specializing in computer vision and pattern recognition. He is a postdoctoral research scientist at the Computer Vision and Robotics Research Laboratory, the University of California at San Diego. His research interests include computer vision, pattern recognition, sensor-based intelligent systems, and human activity understanding. He is working on projects involving activity analysis in intelligent systems, video surveillance, and sensor-based enhancement of responses in unexpected crises.
Refreshments will be served at 10:45