HMM based action recognition using oriented histograms of optical flow field

A simple and effective motion descriptor based on oriented histograms of optical flow field sequence is proposed. After dimensional reduction by principal component analysis, it is applicable to human action recognition using the hidden Markov model (HMM). Experiments with convincing recognition rate demonstrate the discriminative power of the proposed descriptor.

[1]  Luc Van Gool,et al.  Object Tracking with an Adaptive Color-Based Particle Filter , 2002, DAGM-Symposium.

[2]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Pietro Perona,et al.  Human action recognition by sequence of movelet codewords , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.

[4]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[5]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .