This Article 
 Bibliographic References 
 Add to: 
Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors
Nov. 2012 (vol. 34 no. 11)
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.
Index Terms:
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 and Machine Intelligence, vol. 34, no. 11, pp. 2247-2258, Nov. 2012, doi:10.1109/TPAMI.2012.19
Usage of this product signifies your acceptance of the Terms of Use.