Automatic Line matching across views

This paper presents a new method for matching individ-ual line segments between images. The method uses both greylevel information and the multiple view geometric rela-tions between the images. For image pairs epipolar geome-try facilitates the computation of a cross-correlation based matching score for putative line correspondences. For im-age triplets cross-correlation matching scores are used in conjunction with line transfer based on the trifocal geome-try. Algorithms are developed for both short and long range motion. In the case of long range motion the algorithm in-volves evaluating a one parameter family of plane induced homographies. The algorithms are robust to deficiencies in the line segment extraction and partial occlusion. Experimental results are given for image pairs and triplets, for varying motions between views, and for differ-ent scene types. The three view algorithm eliminates all mismatches. 1