The posture of the recognition under the numerous and disorderly background anti-interference method research and implementation

Numerous and disorderly background is the background which has multiple moving targets. Specific moving targets detection and anti-interference technology are the key technologies in recognition of posture under the numerous and disorderly background. For the case that the identifying target is easily affected by other moving targets, an anti-interference method that can identify specific body gestures in numerous and disorderly scene is proposed. This method combines inter-frame difference method and LK optical flow method. Eventually this anti-interference method is realized and proved to be efficient at the platform of Kinect.

[1]  Hironobu Fujiyoshi,et al.  Moving target classification and tracking from real-time video , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[2]  Ioannis Pavlidis,et al.  Urban surveillance systems: from the laboratory to the commercial world , 2001, Proc. IEEE.

[3]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Gerald Schaefer,et al.  Robust codebook-based video background subtraction , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Niloofar Gheissari,et al.  Evaluation of Background Subtraction Methods , 2008, 2008 Digital Image Computing: Techniques and Applications.