An improved Non-Local Cost Aggregation method for stereo matching based on color and boundary cue

Abstract

Recently, a novel Non-Local Cost Aggregation (NLCA) algorithm based on a minimum spanning tree (MST) has been proposed [1] for stereo matching providing extremely low computational complexity and outstanding performance. However, since the MST is constructed only based on color cue, this approach suffers from some improper connections at the boundaries of two objects with similar color distribution. In this paper, we propose a new weight function which includes not only the color cue but also the boundary cue of the reference image. Because the boundary cue is more discriminative than the color cue to distinguish the object from the background with similar color, the previous improper connections can be avoided and a more faithful MST can be constructed. Experimental results performed on Middlebury benchmark demonstrate the effectiveness of the improvements. The improved algorithm achieves rank 18th out of 143 submissions, while the original algorithm ranks 31th.