Skip to Main content Skip to Navigation
New interface
Conference papers

Automatic Line Matching across Views

Abstract : The paper presents a new method for matching individual line segments between images. The method uses both grey-level information and the multiple view geometric relations between the images. For image pairs epipolar geometry facilitates the computation of a cross-correlation based matching score for putative line correspondences. For image triplets cross-correlation matching scores are used in conjunction with line transfer based on the trifocal geometry. Algorithms are developed for both short and long range motion. In the case of long range motion the algorithm involves 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 different scene types. The three view algorithm eliminates all mismatches.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Wednesday, December 22, 2010 - 2:48:55 PM
Last modification on : Thursday, December 23, 2010 - 7:48:38 AM
Long-term archiving on: : Wednesday, March 23, 2011 - 2:36:44 AM


Files produced by the author(s)



Cordelia Schmid, Andrew Zisserman. Automatic Line Matching across Views. International Conference on Computer Vision & Pattern Recognition, Jun 1997, San Juan, Puerto Rico. pp.666--671, ⟨10.1109/CVPR.1997.609397⟩. ⟨inria-00548346⟩



Record views


Files downloads