Directionally-grouped CHLAC motion feature extraction and its application to sport motion analysis
Fumito Yoshikawa, Takumi Kobayashi, Kenji Watanabe, Nobuyuki Otsu · International Conference on Electronics, Hardware, Wireless and Optical Communications · 2011
In this paper, we propose a method for extracting motion direction of objects by directionally-grouped cubic higher-order local auto-correlation (DG-CHLAC) motion features. The DG-CHLAC motion features are obtained by classifying CHLAC feature components into predefined direction groups. By identifying the dominant feature component in DG-CHLAC with respect to magnitude, direction of motions can be simply detected. The experimental results on different motions in sport confirmed the effectiveness of the method.