A Maximum Disparity Estimation Algorithm Based on CLG-TV Optical Flow Method

Special Issues Editor (Nottingham Tent University, United Kingdom (Great Britain))

Disparity range estimation is a very important part of stereo vision system in machine vision. In order to estimate the disparity range effectively, a new algorithm based on CLG-TV optical flow method is proposed. For the computation of the maximum disparity, the algorithm improves data item and smooth item of optical flow method. The position estimation of the maximum disparity is obtained by using the coarse-to-fine method at low resolution, then the image is cut in the position to carry out the accurate optical flow calculation, and finally the optical flow field is analysed to obtain the maximum disparity. Experimental results show that the proposed algorithm has a high accuracy in real images and synthetic sequences, and the maximum disparity can be effectively estimated in a short time.

Journal: International Journal of Simulation: Systems, Science & Technology, IJSSST V17

Published: Jul 14, 2016

DOI: 10.5013/IJSSST.a.17.26.24