Multiple data cost-based stereo matching method to generate dense disparity maps from images under radiometric variations

Abstract

Stereo matching algorithms are capable of providing dense 3D information of the environment through two images taken simultaneously from a pair of cameras placed parallel to each other. Obtaining an accurate disparity map from a stereo image pair is a challenging task and also computationally expensive. If we take into consideration the environmental effect, then the difficulty of the task increases drastically. The authors try to overcome this problem by combining multiple stereo cost functions in the form of a linear equation. To reduce the computation time, a segmentation based cost aggregation method is followed in an attempt to produce an accurate disparity map even in the presence of radiometric variations in the images. The performance of the proposed algorithm is observed while varying the parameter ‘’ between the cost functions and the number of segments in the images. Different image pairs from the Middlebury stereo dataset were considered her