Fusion of histogram based features for Human Action Recognition

Human action recognition is an active research topic which is having real time challenges. Some of the challenges are speed of action, background noise and shape of the performing action. To handle these problem, in this paper the following works are proposed. By the help of optical flow, Bag of Bag of histogram of optical flow (BoHOF) is proposed which is useful to differentiate actions varying with speed of action. BoHOF features are calculated from segmented human objects. To remove the shadow effect, sobel edge filter is used combingly in horizontal and vertical direction. Median filtering is applied to suppress background noise. Histogram of oriented gradients (HOG) features are extracted from 3D projected planes and combined with BoHOF to extract maximum advantages of both the features. Finally, the multi-class SVM-based classifier with radial basis kernel is applied to recognize different human actions. The experiments are conducted on the benchmark KTH dataset and the experimental findings concludes that the proposed HAR technique provides better performance compared to the state-of-the-art techniques.