Title :
Real-time closed-world tracking
Author :
Intille, Stephen S. ; Davis, James W. ; Bobick, Aaron E.
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
Abstract :
A real-time tracking algorithm that uses contextual information is described. The method is capable of simultaneously tracking multiple, non-rigid objects when erratic movement and object collisions are common. A closed-world assumption is used to adaptively select and weight image features used for correspondence. Results of algorithm testing and the limitations of the method are discussed. The algorithm has been used to track children in an interactive, narrative playspace
Keywords :
image matching; motion estimation; object recognition; real-time systems; tracking; algorithm testing; child tracking; closed-world assumption; contextual information; erratic movement; image correspondence; image feature selection; interactive narrative playspace; multiple nonrigid object tracking; object collisions; real-time closed-world tracking algorithm; Algorithm design and analysis; Cameras; Clustering algorithms; Foot; Games; Laboratories; Layout; Real time systems; Testing; Tracking;
Conference_Titel :
Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Conference_Location :
San Juan
Print_ISBN :
0-8186-7822-4
DOI :
10.1109/CVPR.1997.609402
