Action recognition using tri-view constraints

Yang Wang, Lin Wu, Xiaodi Huang

Research output: Book chapter/Published conference paperConference paperpeer-review

1 Citation (Scopus)
5 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. 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, despite of dynamic time-lines,different viewpoints, and unknown camera parameters
Original languageEnglish
Title of host publication2011 AVSS: Advanced Video and Signal-Based Surveillance - Proceedings
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781457708459
Publication statusPublished - 2011
Event8th IEEE International Conference on Advanced Video and Signal-Based Surveillance - Alpen-Adria Universität Klagenfurt, Wörthersee, Austria
Duration: 30 Aug 201102 Sept 2011


Conference8th IEEE International Conference on Advanced Video and Signal-Based Surveillance
Internet address


Dive into the research topics of 'Action recognition using tri-view constraints'. Together they form a unique fingerprint.

Cite this