Motion Retrieval Using Consistency Of Epipolar Geometry
Keywords
action alignment; action recognition; Animation; motion sequence retrieval; pose transition; view Invariance
Abstract
In this paper, we present an efficient method for motion retrieval method based on the consistency of the homographies with the epipolar geometry. We treat the body pose as body point triplets and use the fact that each homography obtained from corresponding body point triplets should be consistent with epipolar geometry to estimate the similarity of two poses. We show that our method is invariant to camera internal parameters and viewpoint. Experiments are performed on the CMU MoCap dataset, and IXMAS dataset testing testing view-invariance, and action recognition. The results demonstrate that our method can accurately identify human action from video sequences when they are observed from totally different viewpoints with different camera parameters.
Publication Date
12-9-2015
Publication Title
Proceedings - International Conference on Image Processing, ICIP
Volume
2015-December
Number of Pages
4219-4223
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICIP.2015.7351601
Copyright Status
Unknown
Socpus ID
84956626655 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84956626655
STARS Citation
Ashraf, Nazim and Foroosh, Hassan, "Motion Retrieval Using Consistency Of Epipolar Geometry" (2015). Scopus Export 2015-2019. 1979.
https://stars.library.ucf.edu/scopus2015/1979