Title :
Pfinder: real-time tracking of the human body
Author :
Wren, Christopher Richard ; Azarbayejani, Ali ; Darrell, Trevor ; Pentland, Alex Paul
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
fDate :
7/1/1997 12:00:00 AM
Abstract :
Pfinder is a real-time system for tracking people and interpreting their behavior. It runs at 10 Hz on a standard SGI Indy computer, and has performed reliably on thousands of people in many different physical locations. The system uses a multiclass statistical model of color and shape to obtain a 2D representation of head and hands in a wide range of viewing conditions. Pfinder has been successfully used in a wide range of applications including wireless interfaces, video databases, and low-bandwidth coding
Keywords :
image coding; image colour analysis; image representation; image segmentation; video signal processing; 2D representation; Pfinder; behavior interpretation; human body; low-bandwidth coding; multiclass statistical model; people tracking; real-time system; standard SGI Indy computer; video databases; wireless interfaces; Biological system modeling; Communication system security; Hardware; Head; Humans; Image segmentation; Pixel; Real time systems; Video compression; Virtual reality;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
