Appearance Based Behavior Recognition by Event Driven Selective Attention

Most of behavior recognition methods proposed so far share the limitations of bottom-up analysis, and singleobject assumption; the bottom-up analysis can be confused by erroneous and missing image features and the singleobject 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. 1 Introduction Motion understanding is essential for wide varieties of vision applications, such as visual surveillance, human interface and virtual reality. Motion understanding problems can be categorized into the following three levels: Physical m..