Title :
Robust Action Recognition Based on a Hierarchical Model
Author :
Xinbo Jiang ; Fan Zhong ; Qunsheng Peng ; Xueying Qin
Author_Institution :
Sch. of Compute Sci. & Technol., Shandong Univ., Jinan, China
Abstract :
With the strong demand for human machine interaction, action recognition has attracted more and more attention in recent years. Traditional video-based approaches are very sensitive to background activity, and also lack the ability to discriminate complex 3D motion. With the emergence and development of commercial depth cameras, action recognition based on 3D skeleton joints is becoming more and more popular. However, a skeleton-based approach is still very challenging because of the large variation in human actions and temporal dynamics. In this paper, we propose a hierarchical model for action recognition. To handle confusing motions in a large feature space, a motion-based grouping method is first proposed, which can efficiently assign each video a group label, and then for each group, a pre-trained classifier is used for frame-labeling. Unlike previous methods, we adopt a bottom-up approach that first performs action recognition for each frame. The final action label is obtained by fusing the classification to its frames, with the effect of each frame being adaptively adjusted based on its local properties. The proposed method is evaluated using two challenge datasets captured by a Kinect. Experiments show that our method can perform more robustly than state-of-the-art approaches.
Keywords :
computer vision; feature extraction; human computer interaction; image classification; image fusion; image motion analysis; image sensors; image thinning; object recognition; video signal processing; 3D skeleton joints; Microsoft Kinect controller; classification fusion; commercial depth cameras; complex 3D motion discrimination; feature space; feature weighting; frame-labeling; hierarchical model; human machine interaction; motion-based grouping method; pretrained classifier; robust action recognition; video-based approaches; Feature extraction; Joints; Motion segmentation; Three-dimensional displays; Trajectory; Vectors; bottom-up approach; feature weighting; hierarchical model; robust action recognition;
Conference_Titel :
Cyberworlds (CW), 2013 International Conference on
Conference_Location :
Yokohama
Print_ISBN :
978-1-4799-2245-1