Title :
Further constraints on visual articulated motions
Author :
Sinclair, D. ; Zesar, K.
Author_Institution :
Inst. for Comput. Graphics, Tech. Univ. Graz, Austria
Abstract :
This paper derives what we term the Euclidean hinge constraint for projective reconstruction of objects displaying articulated motion. A Euclidean hinge is defined here to be an articulation axis with the proviso that any plane perpendicular to the articulation axis in link 1 has a coincident plane which is perpendicular to the articulation ads in link 2 and that these planes remain coincident under articulated motion. This constraint permits the independent projective reconstructions of two adjacent articulated links to be placed in a common frame. The constraint may be expressed mathematically by considering what we define as circular parallax. Additionally the existence of a Euclidean hinge permits the permits the projective frame to be brought nearer to a Euclidean frame for the reconstructed object. A brief reprise of the method of articulation axis estimation is given together with a more extensive series of experimental results
Keywords :
computational geometry; image reconstruction; object recognition; Euclidean hinge constraint; articulated links; articulation axis; circular parallax; epipolar geometry; fundamental matrix; projective reconstruction; projective structure recovery; visual articulated motions; Computer graphics; Constraint theory; Fasteners; Geometry; Humans; Image reconstruction; Layout; Motion detection; Vehicle dynamics; Wheels;
Conference_Titel :
Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-8186-7259-5
DOI :
10.1109/CVPR.1996.517059