Title :
Omnidirectional Depth Estimation by a Single Perspective Camera
Author :
Zhu, Feng ; Su, Liancheng
Author_Institution :
Shenyang Inst. of Autom., Chinese Acad. of Sci., Shenyang
Abstract :
Omnidirectional depth recovery in a novel omnidirectional stereo vision system was addressed. The stereo vision based on a common perspective camera coupled with two hyperbolic mirrors. Given two images of a same point acquired the system, the depth is calculated by means of triangulation. The calculation process aims at having corresponding incident rays intersecting at the same 3D point. As the hyperbolic mirrors ensure a single viewpoint (SVP) the incident light rays are easily found from the points of the image. The two hyperbolic mirrors are aligned coaxially and separately, share one focus that coincides with the camera center. So the geometry of the system naturally ensures matched epipolar lines in the two images of the scene. The separation between the two mirrors provides a large baseline and eventually leads to a precise result. The geometrical properties are derived and the experiments with real images are presented
Keywords :
cameras; computer vision; image sensors; mirrors; spatial variables measurement; stereo image processing; catadioptric sensor; coaxially aligned mirrors; epipolar lines; hyperbolic mirrors; incident light rays; incident rays; omnidirectional depth estimation; omnidirectional depth recovery; omnidirectional stereo vision system; single perspective camera; single viewpoint; triangulation; Automation; Cameras; Content addressable storage; Image sensors; Laboratories; Mirrors; Navigation; Optical imaging; Optical sensors; Stereo vision; Omnidirectional stereo vision; catadioptric sensor; depth recovery;
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
DOI :
10.1109/WCICA.2006.1713921