Pfinder Real-Time Tracking of the Human Body人体的实时跟踪.pdfVIP

780 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 19, NO. 7, JULY 1997 Pfinder: Real-Time Tracking of the Human Body Christopher Richard Wren, Ali Azarbayejani, Trevor Darrell, and Alex Paul Pentland Abstract—Pfinder is a real-time system for tracking people and interpreting their behavior. It runs at 10Hz 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 (a) 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. Index Terms—Blobs, blob tracking, real-time, person tracking, 3D person tracking, segmentation, gesture recognition, mixture model, MDL. ———————— ———————— 1 INTRODUCTION APPLICATIONS such as video databases, wireless virtual reality interfaces, smart rooms, very-low-bandwidth video compression, and security monitoring all have in common the need to track and (b) interpret human behavior. The ability to find and follow people’s head, hands, and body is therefore an important visual problem. To address this need we have developed a real-time system called Pfinder (“person finder”) that substantially solves the problem for arbitrarily complex but single-person, fixed-camera situations. Use of image-to-image registration techniques [1], [10], as a prepro