Markerless body part tracking for action recognition. (12th October 2010)

• Record Type: Journal Article
• Authors: Calderara, Simone; Prati, Andrea; Cucchiara, Rita
• Is Part Of: International journal of multimedia intelligence and security. Volume 1:Number 1(2010)
• Page Start: 76
• Page End: 89
• Publication Date: 2010-10-12
• Subjects: action recognition -- mean tracking -- mixture of Gaussians -- MoG -- dynamic programming -- body parts tracking -- human actions -- global alignment; Security systems -- Periodicals; Data protection -- Periodicals; Computer security -- Periodicals; Biometric identification -- Periodicals; 005.8
• Languages: English
• ISSNs: 2042-3462

Abstract

This paper presents a method for recognising human actions by tracking body parts without using artificial markers. A sophisticated appearance-based tracking able to cope with occlusions is exploited to extract a probability map for each moving object. A segmentation technique based on mixture of Gaussians (MoG) is then employed to extract and track significant points on this map, corresponding to significant regions on the human silhouette. The evolution of the mixture in time is analysed by transforming it in a sequence of symbols (corresponding to a MoG). The similarity between actions is computed by applying global alignment and dynamic programming techniques to the corresponding sequences and using a variational approximation of the Kullback-Leibler divergence to measure the dissimilarity between two MoGs. Experiments on publicly available datasets and comparison with existing methods are provided.