Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382655128> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4382655128 endingPage "785" @default.
- W4382655128 startingPage "774" @default.
- W4382655128 abstract "Image registration is a fundamental problem in computer vision and robotics. Recently, learning-based image registration methods have made great progress. However, these methods are sensitive to abnormal transformation and have insufficient robustness, which leads to more mismatched points in the actual environment. In this paper, we propose a new registration framework based on ensemble learning and dynamic adaptive kernel. Specifically, we first use a dynamic adaptive kernel to extract deep features at the coarse level to guide fine-level registration. Then we added an adaptive feature pyramid network based on the integrated learning principle to realize the fine-level feature extraction. Through different scale, receptive fields, not only the local geometric information of each point is considered, but also its low texture information at the pixel level is considered. According to the actual registration environment, fine features are adaptively obtained to reduce the sensitivity of the model to abnormal transformation. We use the global receptive field provided in the transformer to obtain feature descriptors based on these two levels. In addition, we use the cosine loss directly defined on the corresponding relationship to train the network and balance the samples, to achieve feature point registration based on the corresponding relationship. Extensive experiments on object-level and scene-level datasets show that the proposed method outperforms existing state-of-the-art techniques by a large margin. More critically, it has the best generalization ability in unknown scenes with different sensor modes." @default.
- W4382655128 created "2023-07-01" @default.
- W4382655128 creator A5013806533 @default.
- W4382655128 creator A5017033250 @default.
- W4382655128 creator A5038336906 @default.
- W4382655128 creator A5045391965 @default.
- W4382655128 creator A5051098098 @default.
- W4382655128 creator A5071301036 @default.
- W4382655128 date "2023-08-01" @default.
- W4382655128 modified "2023-10-14" @default.
- W4382655128 title "A continuation method for image registration based on dynamic adaptive kernel" @default.
- W4382655128 cites W1491719799 @default.
- W4382655128 cites W1532362218 @default.
- W4382655128 cites W2042255844 @default.
- W4382655128 cites W2056935845 @default.
- W4382655128 cites W2085261163 @default.
- W4382655128 cites W2111308925 @default.
- W4382655128 cites W2151103935 @default.
- W4382655128 cites W2312890204 @default.
- W4382655128 cites W2320444803 @default.
- W4382655128 cites W2623455008 @default.
- W4382655128 cites W2910963390 @default.
- W4382655128 cites W2963881378 @default.
- W4382655128 cites W3080980548 @default.
- W4382655128 cites W3092135995 @default.
- W4382655128 cites W3166975282 @default.
- W4382655128 cites W3167684723 @default.
- W4382655128 cites W4224229959 @default.
- W4382655128 cites W4226488683 @default.
- W4382655128 cites W4280538209 @default.
- W4382655128 doi "https://doi.org/10.1016/j.neunet.2023.06.025" @default.
- W4382655128 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37418860" @default.
- W4382655128 hasPublicationYear "2023" @default.
- W4382655128 type Work @default.
- W4382655128 citedByCount "0" @default.
- W4382655128 crossrefType "journal-article" @default.
- W4382655128 hasAuthorship W4382655128A5013806533 @default.
- W4382655128 hasAuthorship W4382655128A5017033250 @default.
- W4382655128 hasAuthorship W4382655128A5038336906 @default.
- W4382655128 hasAuthorship W4382655128A5045391965 @default.
- W4382655128 hasAuthorship W4382655128A5051098098 @default.
- W4382655128 hasAuthorship W4382655128A5071301036 @default.
- W4382655128 hasConcept C104317684 @default.
- W4382655128 hasConcept C115961682 @default.
- W4382655128 hasConcept C153180895 @default.
- W4382655128 hasConcept C154945302 @default.
- W4382655128 hasConcept C166704113 @default.
- W4382655128 hasConcept C185592680 @default.
- W4382655128 hasConcept C31972630 @default.
- W4382655128 hasConcept C32990609 @default.
- W4382655128 hasConcept C41008148 @default.
- W4382655128 hasConcept C52622490 @default.
- W4382655128 hasConcept C55493867 @default.
- W4382655128 hasConcept C56435381 @default.
- W4382655128 hasConcept C63479239 @default.
- W4382655128 hasConceptScore W4382655128C104317684 @default.
- W4382655128 hasConceptScore W4382655128C115961682 @default.
- W4382655128 hasConceptScore W4382655128C153180895 @default.
- W4382655128 hasConceptScore W4382655128C154945302 @default.
- W4382655128 hasConceptScore W4382655128C166704113 @default.
- W4382655128 hasConceptScore W4382655128C185592680 @default.
- W4382655128 hasConceptScore W4382655128C31972630 @default.
- W4382655128 hasConceptScore W4382655128C32990609 @default.
- W4382655128 hasConceptScore W4382655128C41008148 @default.
- W4382655128 hasConceptScore W4382655128C52622490 @default.
- W4382655128 hasConceptScore W4382655128C55493867 @default.
- W4382655128 hasConceptScore W4382655128C56435381 @default.
- W4382655128 hasConceptScore W4382655128C63479239 @default.
- W4382655128 hasFunder F4320321001 @default.
- W4382655128 hasFunder F4320321470 @default.
- W4382655128 hasFunder F4320335777 @default.
- W4382655128 hasLocation W43826551281 @default.
- W4382655128 hasLocation W43826551282 @default.
- W4382655128 hasOpenAccess W4382655128 @default.
- W4382655128 hasPrimaryLocation W43826551281 @default.
- W4382655128 hasRelatedWork W2009466720 @default.
- W4382655128 hasRelatedWork W2035976912 @default.
- W4382655128 hasRelatedWork W2087122453 @default.
- W4382655128 hasRelatedWork W2146076056 @default.
- W4382655128 hasRelatedWork W2167923216 @default.
- W4382655128 hasRelatedWork W2541791370 @default.
- W4382655128 hasRelatedWork W2811390910 @default.
- W4382655128 hasRelatedWork W2921707373 @default.
- W4382655128 hasRelatedWork W3094187672 @default.
- W4382655128 hasRelatedWork W3163375306 @default.
- W4382655128 hasVolume "165" @default.
- W4382655128 isParatext "false" @default.
- W4382655128 isRetracted "false" @default.
- W4382655128 workType "article" @default.