Title :
Binocular estimation of motion: A least-square solution using normal flows
Author :
Tak-Wai Hui ; Chung, Ronald
Author_Institution :
Dept. of Mech. & Autom. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Abstract :
We present a direct method for estimating general camera motion from a rectified stereo image sequence using merely normal flows. We require neither point-to-point feature correspondences nor special assumption about the imaged scene. It has a closed-form expression, requiring no iterative computation. Experimental results on both synthetic and real image data are provided to demonstrate the performance of the proposed method.
Keywords :
image sequences; least squares approximations; motion estimation; stereo image processing; binocular motion estimation; closed-form expression; general camera motion estimation; least-square solution; normal flows; point-to-point feature correspondences; real image data; rectified stereo image sequence; synthetic image data; Least-square solution; normal flows; optical flows; stereo motion;
Conference_Titel :
Image Processing (ICIP), 2013 20th IEEE International Conference on
Conference_Location :
Melbourne, VIC
DOI :
10.1109/ICIP.2013.6738789