Matches in SemOpenAlex for { <https://semopenalex.org/work/W2187968763> ?p ?o ?g. }
- W2187968763 endingPage "2813" @default.
- W2187968763 startingPage "2771" @default.
- W2187968763 abstract "We present a novel method for affine transformation estimation of image regions. We illustrate the benefits of using the proposed method in three realms: (1) locating large amounts of point matches with highly accurate localization; (2) producing very accurate affine transformation estimations of for each matched region; (3) effectively rejecting false matches. We show that this is achievable with low computational demand. Point matching is one of the most fundamental tasks in computer vision, being used extensively in applications such as object detection, object tracking, and structure from motion. The major challenge in point matching is to preserve large numbers of accurate matches between corresponding scene locations under different geometric and radiometric conditions, while keeping the number of false matches small. Recent publications have shown that applying the affine transformation model on local regions is a particularly suitable approach for point matching. Yet affine invariant methods are not used extensively for two reasons. First, these methods are computationally demanding; second, the derived affine estimations have limited accuracy. In this work, we propose a novel method of region expansion that enhances region matches detected by any state-of-the-art method. The method is based on accurate estimation of affine transformations, which is used to predict matching locations beyond initially detected matches. The suggested method achieves improved localization of the detected matches. The accuracy of local transformation estimations plays a crucial part in tasks that are based on geometric verification. We prove that expansion beyond local region matches is crucial for obtaining much more accurate local transformation estimations than previously possible. We utilize the improved estimations of affine transformations in order to locally verify tentative matches in an efficient way. We systematically reject false matches, while improving the localization of correct matches that are usually rejected by state-of-the-art methods." @default.
- W2187968763 created "2016-06-24" @default.
- W2187968763 creator A5027978582 @default.
- W2187968763 creator A5051835210 @default.
- W2187968763 date "2015-01-01" @default.
- W2187968763 modified "2023-09-27" @default.
- W2187968763 title "Geometric Expansion for Local Feature Analysis and Matching" @default.
- W2187968763 cites W1491719799 @default.
- W2187968763 cites W1607217798 @default.
- W2187968763 cites W1677409904 @default.
- W2187968763 cites W1995266040 @default.
- W2187968763 cites W2052094314 @default.
- W2187968763 cites W2066941820 @default.
- W2187968763 cites W2085261163 @default.
- W2187968763 cites W2106199912 @default.
- W2187968763 cites W2111308925 @default.
- W2187968763 cites W2124404372 @default.
- W2187968763 cites W2130103520 @default.
- W2187968763 cites W2151103935 @default.
- W2187968763 cites W2161576013 @default.
- W2187968763 cites W2172188317 @default.
- W2187968763 doi "https://doi.org/10.1137/140997671" @default.
- W2187968763 hasPublicationYear "2015" @default.
- W2187968763 type Work @default.
- W2187968763 sameAs 2187968763 @default.
- W2187968763 citedByCount "5" @default.
- W2187968763 countsByYear W21879687632017 @default.
- W2187968763 countsByYear W21879687632018 @default.
- W2187968763 countsByYear W21879687632019 @default.
- W2187968763 countsByYear W21879687632020 @default.
- W2187968763 countsByYear W21879687632023 @default.
- W2187968763 crossrefType "journal-article" @default.
- W2187968763 hasAuthorship W2187968763A5027978582 @default.
- W2187968763 hasAuthorship W2187968763A5051835210 @default.
- W2187968763 hasConcept C104317684 @default.
- W2187968763 hasConcept C105795698 @default.
- W2187968763 hasConcept C11413529 @default.
- W2187968763 hasConcept C115961682 @default.
- W2187968763 hasConcept C138885662 @default.
- W2187968763 hasConcept C153180895 @default.
- W2187968763 hasConcept C154945302 @default.
- W2187968763 hasConcept C165064840 @default.
- W2187968763 hasConcept C18516315 @default.
- W2187968763 hasConcept C185592680 @default.
- W2187968763 hasConcept C190470478 @default.
- W2187968763 hasConcept C200336642 @default.
- W2187968763 hasConcept C204241405 @default.
- W2187968763 hasConcept C207221997 @default.
- W2187968763 hasConcept C2524010 @default.
- W2187968763 hasConcept C2776401178 @default.
- W2187968763 hasConcept C28719098 @default.
- W2187968763 hasConcept C31972630 @default.
- W2187968763 hasConcept C33923547 @default.
- W2187968763 hasConcept C37914503 @default.
- W2187968763 hasConcept C41008148 @default.
- W2187968763 hasConcept C41895202 @default.
- W2187968763 hasConcept C55493867 @default.
- W2187968763 hasConcept C56435381 @default.
- W2187968763 hasConcept C6408098 @default.
- W2187968763 hasConcept C92757383 @default.
- W2187968763 hasConceptScore W2187968763C104317684 @default.
- W2187968763 hasConceptScore W2187968763C105795698 @default.
- W2187968763 hasConceptScore W2187968763C11413529 @default.
- W2187968763 hasConceptScore W2187968763C115961682 @default.
- W2187968763 hasConceptScore W2187968763C138885662 @default.
- W2187968763 hasConceptScore W2187968763C153180895 @default.
- W2187968763 hasConceptScore W2187968763C154945302 @default.
- W2187968763 hasConceptScore W2187968763C165064840 @default.
- W2187968763 hasConceptScore W2187968763C18516315 @default.
- W2187968763 hasConceptScore W2187968763C185592680 @default.
- W2187968763 hasConceptScore W2187968763C190470478 @default.
- W2187968763 hasConceptScore W2187968763C200336642 @default.
- W2187968763 hasConceptScore W2187968763C204241405 @default.
- W2187968763 hasConceptScore W2187968763C207221997 @default.
- W2187968763 hasConceptScore W2187968763C2524010 @default.
- W2187968763 hasConceptScore W2187968763C2776401178 @default.
- W2187968763 hasConceptScore W2187968763C28719098 @default.
- W2187968763 hasConceptScore W2187968763C31972630 @default.
- W2187968763 hasConceptScore W2187968763C33923547 @default.
- W2187968763 hasConceptScore W2187968763C37914503 @default.
- W2187968763 hasConceptScore W2187968763C41008148 @default.
- W2187968763 hasConceptScore W2187968763C41895202 @default.
- W2187968763 hasConceptScore W2187968763C55493867 @default.
- W2187968763 hasConceptScore W2187968763C56435381 @default.
- W2187968763 hasConceptScore W2187968763C6408098 @default.
- W2187968763 hasConceptScore W2187968763C92757383 @default.
- W2187968763 hasIssue "4" @default.
- W2187968763 hasLocation W21879687631 @default.
- W2187968763 hasOpenAccess W2187968763 @default.
- W2187968763 hasPrimaryLocation W21879687631 @default.
- W2187968763 hasRelatedWork W1502265686 @default.
- W2187968763 hasRelatedWork W1986076254 @default.
- W2187968763 hasRelatedWork W1988402223 @default.
- W2187968763 hasRelatedWork W2014157695 @default.
- W2187968763 hasRelatedWork W2047393684 @default.
- W2187968763 hasRelatedWork W2075867666 @default.
- W2187968763 hasRelatedWork W2115865553 @default.
- W2187968763 hasRelatedWork W2364279282 @default.