The Community for Technology Leaders
Green Image
Issue No. 11 - Nov. (2012 vol. 34)
ISSN: 0162-8828
pp: 2247-2258
Mohamed-Bécha Kaâniche , Higher Sch. of Commun. of Tunis (Sup'Com), Univ. of Carthage, El Ghazala, Tunisia
François Brémond , INRIA, Sophia Antipolis, France
We introduce a new gesture recognition framework based on learning local motion signatures (LMSs) of HOG descriptors introduced by [1]. Our main contribution is to propose a new probabilistic learning-classification scheme based on a reliable tracking of local features. After the generation of these LMSs computed on one individual by tracking Histograms of Oriented Gradient (HOG) [2] descriptor, we learn a codebook of video-words (i.e., clusters of LMSs) using k-means algorithm on a learning gesture video database. Then, the video-words are compacted to a code-book of codewords by the Maximization of Mutual Information (MMI) algorithm. At the final step, we compare the LMSs generated for a new gesture w.r.t. the learned code-book via the k-nearest neighbors (k-NN) algorithm and a novel voting strategy. Our main contribution is the handling of the N to N mapping between codewords and gesture labels within the proposed voting strategy. Experiments have been carried out on two public gesture databases: KTH [3] and IXMAS [4]. Results show that the proposed method outperforms recent state-of-the-art methods.
Tracking, Equations, Vectors, Feature extraction, Kalman filters, Trajectory, Clustering algorithms, probabilistic learning and classification, Gesture recognition, motion detection, HOG descriptors, feature tracking

M. Kaâniche and F. Brémond, "Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 2247-2258, 2012.
162 ms
(Ver 3.3 (11022016))