Robust line segment matching via reweighted random walks on the homography graph.

• Matching line segments for stereo images can be employed relying only on the geometry constraint. • The association graph constructed with the epipolar constraint is invariant to the projective transformation. • Employing the random walk on the association graph enables ranking the candidate. • The proposed algorithm outperformed the state of the art methods in the experiments, especially in the scenes of the wide baseline, the steep viewpoint change, and the dense line segment. This paper presents a novel method for matching line segments between stereo images. Given the fundamental matrix, the local homography can be over determined with pairwise line segment candidates. We exploit this constraint to initialize the candidate and construct the novel homography graph. Because the constraint between the node is based on the epipolar geometry, the homography graph is invariant to the local projective transformation. We employ the reweighted random walk on the graph to rank the candidate, then, we propose the constrained-greedy algorithm to obtain the reliable match. To the best of our knowledge, this is the first study to embed the epipolar geometry into the graph matching theory for the line segment matching. When evaluated on the 32 image patches, our method outperformed the state of the art methods, especially in the scenes of the wide baseline, steep viewpoint changes and dense line segments. The proposed algorithm is available at https://github.com/weidong-whu/line-match-RRW. [ABSTRACT FROM AUTHOR]