Title :
Adaptive estimation of 3-D motion parameters and optical flow
Author :
Park, Soon-Hyun ; Matsuo, Takami
Author_Institution :
Graduate Sch. of Eng., Oita Univ., Japan
Abstract :
The recovery of the 3-D motion parameters and structure of an object from its 2-D dynamic picture image is one of the most important problems in computer vision. First, we present a robust adaptive update law based on Riccati equation. Moreover, we design adaptive estimators of 3-D motion parameters and its optical flow from image sequences directly without differential operations. Finally, we demonstrate simulation results via Matlab/Simulink.
Keywords :
Riccati equations; adaptive estimation; computer vision; image sequences; motion estimation; nonlinear differential equations; parameter estimation; time-varying systems; 3D motion parameters; Matlab/Simulink; Riccati equation; adaptive estimation; computer vision; dynamic picture image; image processing; image sequences; motion estimation; optical flow field; robust adaptive update law; time-varying imagery; Adaptive estimation; Adaptive optics; Computational modeling; Computer vision; Image motion analysis; Image sequences; Motion estimation; Optical design; Riccati equations; Robustness;
Conference_Titel :
Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on
Print_ISBN :
0-7803-7866-0
DOI :
10.1109/CIRA.2003.1222183
