An efficient Bayesian framework for on-line action recognition

Publication Type:
Conference Proceeding
Proceedings - International Conference on Image Processing, ICIP, 2009, pp. 3553 - 3556
Issue Date:
Full metadata record
On-line action recognition from a continuous stream of actions is still an open problem with fewer solutions proposed compared to time-segmented action recognition. The most challenging task is to classify the current action while finding its time boundaries at the same time. In this paper we propose an approach capable of performing on-line action segmentation and recognition by means of batteries of HMM taking into account all the possible time boundaries and action classes. A suitable Bayesian normalization is applied to make observation sequences of different length comparable and computational optimizations are introduce to achieve real-time performances. Results on a well known action dataset prove the efficacy of the proposed method. ©2009 IEEE.
Please use this identifier to cite or link to this item: