Title :
Omni-directional structure from motion
Author :
Chang, Peng ; Hebert, Martial
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
In this paper, we describe our work on a robot navigation system using an omnidirectional camera as the primary sensor. An omnidirectional structure from motion algorithm is presented with its uncertainty analyzed. We evaluate the omnidirectional SFM on both synthetic data and on real image sequences. Comparison with the conventional camera is made and we show that in certain situations the omnidirectional SFM gives better results than the conventional one by taking advantage of its larger field of view
Keywords :
computer vision; image sequences; navigation; motion algorithm; omnidirectional camera; omnidirectional structure from motion; primary sensor; real image sequences; robot navigation system; uncertainty; Algorithm design and analysis; Cameras; Image motion analysis; Motion analysis; Navigation; Robot sensing systems; Robot vision systems; Sensor phenomena and characterization; Sensor systems; Uncertainty;
Conference_Titel :
Omnidirectional Vision, 2000. Proceedings. IEEE Workshop on
Conference_Location :
Hilton Head Island, SC
Print_ISBN :
0-7695-0704-2
DOI :
10.1109/OMNVIS.2000.853819
