Title :
Appearance based behavior recognition by event driven selective attention
Author :
Wada, Toshikazu ; Matsuyama, Takashi
Author_Institution :
Dept. of Intelligence Sci. & Technol., Kyoto Univ., Japan
Abstract :
Most of behavior recognition methods proposed so far share the limitations of bottom-up analysis, and single-object assumption; the bottom-up analysis can be confused by erroneous and missing image features and the single-object assumption prevents us from analyzing image sequences including multiple moving objects. This paper presents a robust behavior recognition method free from these limitations. Our method is best characterized by 1) top-down image feature extraction by selective attention mechanism, 2) object discrimination by colored-token propagation, and 3) integration of multi-viewpoint images. Extensive experiments of human behavior recognition in real world environments demonstrate the soundness and robustness of our method
Keywords :
computer vision; feature extraction; image sequences; appearance based behavior recognition; bottom-up analysis; colored-token propagation; event driven selective attention; human behavior recognition; image sequences; multi-viewpoint images; multiple moving objects; real world environments; robust behavior recognition; robustness; selective attention mechanism; single-object assumption; soundness a; top-down image feature extraction; Electrical capacitance tomography; Feature extraction; Hidden Markov models; Image analysis; Image recognition; Image sequence analysis; Informatics; Motion analysis; Shape measurement; Surveillance;
Conference_Titel :
Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8497-6
DOI :
10.1109/CVPR.1998.698689