An incremental approach towards automatic model acquisition for human gesture recognition

The recognition of natural gestures typically involves: the collection of training examples; the generation of models; and the determination of a model that is most likely to have generated an observation sequence. The first step however, the collection of training examples, typically involves manual segmentation and hand labelling of image sequences. This is a time consuming and labour intensive process and is only feasible for a limited set of gestures. To overcome this problem we suggest that gestures can be viewed as a repetitive sequence of atomic movements, similar to phonemes in speech. We present an approach: to automatically segment an arbitrary observation sequence of a natural gesture, using only contextual information derived from the observation sequence itself; and to incrementally extract a set of atomic movements for the automatic model acquisition of natural gestures. Atomic components are modelled as semi-continuous hidden Markov models and the search for repetitive sequences is done using a discrete version of CONDENSATION that is no longer based on factored sampling.

[1]  Justine Cassell,et al.  Temporal classification of natural gesture and application to video coding , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Thad Starner,et al.  Visual Recognition of American Sign Language Using Hidden Markov Models. , 1995 .

[3]  Shaogang Gong,et al.  Learning Prior and Observation Augmented Density Models for Behaviour Recognition , 1999, BMVC.

[4]  Aaron F. Bobick,et al.  A state-based technique for the summarization and recognition of gesture , 1995, Proceedings of IEEE International Conference on Computer Vision.

[5]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[6]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Shaogang Gong,et al.  Gesture Recognition for Visually Mediated Interaction using Probabilistic Event Trajectories , 1998, BMVC.

[8]  Aaron F. Bobick,et al.  Realtime online adaptive gesture recognition , 1999, Proceedings International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems. In Conjunction with ICCV'99 (Cat. No.PR00378).

[9]  Ramesh C. Jain,et al.  Recursive identification of gesture inputs using hidden Markov models , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[10]  David C. Hogg,et al.  Learning Behaviour Models of Human Activities , 1999, BMVC.

[11]  Dimitris N. Metaxas,et al.  Toward Scalability in ASL Recognition: Breaking Down Signs into Phonemes , 1999, Gesture Workshop.

[12]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Michael J. Black,et al.  Recognizing temporal trajectories using the condensation algorithm , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[14]  Xuedong Huang,et al.  Semi-continuous hidden Markov models for speech signals , 1990 .