Title :
Vision-based control using probabilistic geometry for objects reconstruction
Author :
Flandin, Grégory ; Chaumette, Francois
Author_Institution :
IRISA, Rennes, France
Abstract :
We first present a suitable object knowledge representation based on a mixture of stochastic and set membership models and consider an approximation resulting in ellipsoidal calculus by means of a normal assumption for stochastic laws and ellipsoidal over or inner bounding for uniform laws. Then we, build an efficient estimation process integrating visual data online and perform online and optimal exploratory motions for the camera. The control schemes are based on the maximization of the a posteriori predicted information
Keywords :
geometry; image reconstruction; motion estimation; probability; robot vision; set theory; state estimation; ellipsoidal calculus; object knowledge representation; objects reconstruction; optimal exploratory motions; probabilistic geometry; robot vision; set membership models; stochastic models; vision-based control; Calculus; Cameras; Geometry; Layout; Motion estimation; Robot vision systems; Solid modeling; State estimation; Stochastic processes; Uncertainty;
Conference_Titel :
Decision and Control, 2001. Proceedings of the 40th IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-7061-9
DOI :
10.1109/.2001.980833
