Sequence of the most informative joints (SMIJ): A new representation for human skeletal action recognition
详细信息 查看全文
- 作者：Ferda Ofli ; Rizwan Chaudhry ; Gregorij Kurillo ; Ren茅 Vidal ; Ruzena Bajcsy
- 关键词：Human action representation ; Human action recognition ; Informative joints ; Bag-of-words ; Linear dynamical systems ; Normalized edit distance ; Cross-database generalization ; Berkeley MHAD ; HDM05 ; MSR Action3D
- 刊名：Journal of Visual Communication and Image Representation
- 出版年：January, 2014
- 年：2014
- 卷：25
- 期：1
- 页码：24-38
- 全文大小：987 K
文摘
Much of the existing work on action recognition combines simple features with complex classifiers or models to represent an action. Parameters of such models usually do not have any physical meaning nor do they provide any qualitative insight relating the action to the actual motion of the body or its parts. In this paper, we propose a new representation of human actions called sequence of the most informative joints (SMIJ), which is extremely easy to interpret. At each time instant, we automatically select a few skeletal joints that are deemed to be the most informative for performing the current action based on highly interpretable measures such as the mean or variance of joint angle trajectories. We then represent the action as a sequence of these most informative joints. Experiments on multiple databases show that the SMIJ representation is discriminative for human action recognition and performs better than several state-of-the-art algorithms.