Title :
Representation and optimal recognition of human activities
Author :
Hongeng, Somboon ; Brémond, Francois ; Nevatia, Ramakant
Author_Institution :
Inst. for Robotics & Intelligent Syst., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
Towards the goal of realizing a generic automatic human activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation using three type of entities: image features, mobile object properties and scenarios. Taking image features of tracked moving regions from an image sequence as input, mobile object properties are first computed by specific methods while noise is suppressed by statistical methods. Scenarios are recognized from mobile object properties based on Bayesian analysis. Several scenarios are recognized by an algorithm using a probabilistic finite-state automaton (a variant of structured HMM). A demonstration of the optimality of this recognition method is discussed. Finally, the validity and the effectiveness of our approach is demonstrated on both real-world and perturbed data
Keywords :
Bayes methods; feature extraction; finite automata; image motion analysis; image recognition; image representation; image sequences; Bayesian analysis; chained hierarchical representation; generic automatic human activity recognition system; image features; image sequence; mobile object properties; noise suppression; optimal recognition; probabilistic finite-state automaton; representation; scenarios; statistical methods; tracked moving regions; Automata; Bayesian methods; Computer vision; Electrical capacitance tomography; Event detection; Humans; Image recognition; Image sequences; Intelligent robots; Mobile computing;
Conference_Titel :
Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on
Conference_Location :
Hilton Head Island, SC
Print_ISBN :
0-7695-0662-3
DOI :
10.1109/CVPR.2000.855905
