An Analysis of Errors in Graph-Based Keypoint Matching and Proposed Solutions

Abstract : An error occurs in graph-based keypoint matching when key-points in two different images are matched by an algorithm but do not correspond to the same physical point. Most previous methods acquire keypoints in a black-box manner, and focus on developing better algorithms to match the provided points. However to study the complete performance of a matching system one has to study errors through the whole matching pipeline, from keypoint detection, candidate selection to graph optimisation. We show that in the full pipeline there are six different types of errors that cause mismatches. We then present a matching framework designed to reduce these errors. We achieve this by adapting keypoint detectors to better suit the needs of graph-based matching, and achieve better graph constraints by exploiting more information from their keypoints. Our framework is applicable in general images and can handle clutter and motion discontinuities. We also propose a method to identify many mismatches a posteriori based on Left-Right Consistency inspired by stereo matching due to the asymmetric way we detect keypoints and define the graph.
Complete list of metadatas

Cited literature [37 references]  Display  Hide  Download

https://hal.inria.fr/hal-01221328
Contributor : Pablo Mesejo Santiago <>
Submitted on : Tuesday, October 27, 2015 - 5:30:31 PM
Last modification on : Thursday, January 11, 2018 - 6:23:32 AM
Long-term archiving on : Thursday, January 28, 2016 - 11:21:20 AM

File

proof.pdf
Files produced by the author(s)

Identifiers

Citation

Toby Collins, Pablo Mesejo, Adrien Bartoli. An Analysis of Errors in Graph-Based Keypoint Matching and Proposed Solutions. 13th European Conference on Computer Vision (ECCV’14), Sep 2014, Zurich, Switzerland. pp.138-153, ⟨10.1007/978-3-319-10584-0_10⟩. ⟨hal-01221328⟩

Share

Metrics

Record views

374

Files downloads

299