Representation and Optimal Recognition of Human Activities

Towards the goal of realizing a generic automatichuman 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. A sequential occurrence several scenarios are recognized by an algorithm using a probabilistic finite-state automaton (a variant of structured HMM). The demonstration of the optimalityof these recognition method is discussed. Finally, the validityandthe effectiveness of our approach is demonstrated on both real-world and perturbed data.

• Type: Conference
• Year: 2000
• Where: CVPR
• Authors: François Brémond, Ramakant Nevatia, Somboon Hongeng
• Keywords: Activity Recognition System, Computer Vision, CVPR 2000, Image Features, Mobile Object Properties, Probabilistic Finite-state Automaton, Structured Hmm