Robust human action recognition using improved BOW and hybrid features

Abstract

Recognizing human action in video has many applications in computer vision and robotics. It is a challenging task not only because of the variations produced by general factors like illumination, background clutter, occlusion or intra-class variation, but also because of subtle behavioral patterns among interacting people or between people and objects in images as well as attracts many attentions in activity in recently years. However, these researches are not yet fully realized due to the lack of an effective feature to present human action. In this paper, we present a novel for human action representation based on hybrid features from local and global features. Firstly, a local-based feature descriptor is combined by motion and SURF. Secondly, improved BOW with kmeans++ and soft-weighting scheme are used to yield the histogram of word occurrences (HoWO) to present for action in video. Thirdly, HOG/HOF features are extracted from video for global features. Next, hybrid features is created by concatenating HoWO and HOG/HOF. Lastly, Support Vector Machine is used for classification on KTH, Weizmann and YouTube datasets. The experimental results also indicated that the extraction of features is effective and shows the feasibility of our proposal. In addition, compared with other approaches our approach is more robust, more flexible, easier to implement and simpler to comprehend.