Dynamic textures for human movement recognition

Vili Kellokumpu, Guoying Zhao, Matti Pietikäinen
2010 Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10  
Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. movements with dynamic texture features. The proposed method is computationally simple and suitable for various applications such as action and gait recognition. We use Gentle AdaBoost to perform feature selection and build strong models f classifiers. We verify the performance of our methods on the challenging KTH and USF
more » ... ets, achieving high accuracy. Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. We describe human movements with dynamic texture features. The proposed method computationally simple and suitable for various applications We use Gentle AdaBoost to build strong models from weak verify the performance of our methods on the datasets, achieving high accuracy.
doi:10.1145/1816041.1816110 dblp:conf/civr/KellokumpuZP10 fatcat:otcl6wew5fafrkxid2c2np6z2u