Human Action Recognition from Video Sequences by Enforcing Tri-view Constraints

Yang Wang, Wu. Lin, Xiaodi Huang, Xuemin Lin

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
26 Downloads (Pure)


Two-view methods have been well developed to identify human actions. However, in a case where the corresponding imaged points cannot induce distinguished measures, the performance of the methods deteriorates. For this reason, we propose a new view-invariant measure for human action recognition by enforcing tri-view constraints in this paper. This new measurement method can be tolerant to different rates of human actions and the anthropometric proportions. We apply our approach to video synchronization by imposing both the similarity ratio and the consistency in the trifocal tensor over entire video sequences. By testing on both synthetic and real data, our method has achieved higher tolerance to noise levels, as well as higher identification accuracy than the traditional two-view method. Experimental results demonstrate that our approach can identify human pose transitions, in spite of dynamic time-lines, different viewpoints and unknown camera parameters.
Original languageEnglish
Pages (from-to)1030-1040
Number of pages11
JournalComputer Journal
Issue number9
Publication statusPublished - Nov 2012


Dive into the research topics of 'Human Action Recognition from Video Sequences by Enforcing Tri-view Constraints'. Together they form a unique fingerprint.

Cite this