CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2012 vol.34 Issue No.11 - Nov.
Issue No.11 - Nov. (2012 vol.34)
Mohamed-Bécha Kaâniche , Higher Sch. of Commun. of Tunis (Sup'Com), Univ. of Carthage, El Ghazala, Tunisia
François Brémond , INRIA, Sophia Antipolis, France
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2012.19
We introduce a new gesture recognition framework based on learning local motion signatures (LMSs) of HOG descriptors introduced by . 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)  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  and IXMAS . 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
Mohamed-Bécha Kaâniche, François Brémond, "Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 11, pp. 2247-2258, Nov. 2012, doi:10.1109/TPAMI.2012.19