An evaluation of feature matchers for fundamental matrix estimation

dc.contributor.authorBian, J.W.
dc.contributor.authorWu, Y.H.
dc.contributor.authorZhao, J.
dc.contributor.authorLiu, Y.
dc.contributor.authorZhang, L.
dc.contributor.authorCheng, M.M.
dc.contributor.authorReid, I.
dc.contributor.conferenceBritish Machine Vision Conference (BMVC) (9 Sep 2019 - 12 Sep 2019 : Cardiff, UK)
dc.date.issued2020
dc.description.abstractMatching two images while estimating their relative geometry is a key step in many computer vision applications. For decades, a well-established pipeline, consisting of SIFT, RANSAC, and 8-point algorithm, has been used for this task. Recently, many new approaches were proposed and shown to outperform previous alternatives on standard benchmarks, including the learned features, correspondence pruning algorithms, and robust estimators. However, whether it is beneficial to incorporate them into the classic pipeline is less-investigated. To this end, we are interested in i) evaluating the performance of these recent algorithms in the context of image matching and epipolar geometry estimation, and ii) leveraging them to design more practical registration systems. The experiments are conducted in four large-scale datasets using strictly defined evaluation metrics, and the promising results provide insight into which algorithms suit which scenarios. According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator. They show remarkable performances and have potentials to a large part of computer vision tasks. To facilitate future research, the full evaluation pipeline and the proposed methods are made publicly available.
dc.description.statementofresponsibilityJia-Wang Bian, Yu-Huan Wu, Ji Zhao, Yun Liu, Le Zhang, Ming-Ming Cheng, Ian Reid
dc.identifier.citationProceedings of the 30th British Machine Vision Conference (BMVC 2019), 2020, pp.1-14
dc.identifier.doi10.5244/C.33.89
dc.identifier.orcidBian, J.W. [0000-0003-2046-3363]
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.urihttps://hdl.handle.net/2440/132215
dc.language.isoen
dc.publisherBMVA
dc.publisher.placeonline
dc.rights© 2019. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
dc.source.urihttps://bmvc2019.org/wp-content/papers/0450.html
dc.titleAn evaluation of feature matchers for fundamental matrix estimation
dc.typeConference paper
pubs.publication-statusPublished

Files