File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Fully convolutional line parsing

TitleFully convolutional line parsing
Authors
KeywordsFully convolutional network
Line detection
Single stage method
Issue Date2022
Citation
Neurocomputing, 2022, v. 506, p. 1-11 How to Cite?
AbstractWe present a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images. The proposed network is very simple and flexible with variations that gracefully trade off between speed and accuracy for different applications. F-Clip detects line segments in an end-to-end fashion by predicting each line's center position, length, and angle. We further customize the design of convolution kernels of our fully convolutional network to effectively exploit the statistical priors of the distribution of line angles in real image datasets. We conduct extensive experiments and show that our method achieves a significantly better trade-off between efficiency and accuracy, resulting in a real-time line detector at up to 73 FPS on a single GPU. Such inference speed makes our method readily applicable to real-time tasks without compromising any accuracy of previous methods. Moreover, when equipped with a performance-improving backbone network, F-Clip is able to significantly outperform all state-of-the-art line detectors on accuracy at a similar or even higher frame rate. In other word, under same inference speed, F-Clip always achieving best accuracy compare with other methods. Source code https://github.com/Delay-Xili/F-Clip.
Persistent Identifierhttp://hdl.handle.net/10722/327785
ISSN
2023 Impact Factor: 5.5
2023 SCImago Journal Rankings: 1.815
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorDai, Xili-
dc.contributor.authorGong, Haigang-
dc.contributor.authorWu, Shuai-
dc.contributor.authorYuan, Xiaojun-
dc.contributor.authorYi, Ma-
dc.date.accessioned2023-05-08T02:26:47Z-
dc.date.available2023-05-08T02:26:47Z-
dc.date.issued2022-
dc.identifier.citationNeurocomputing, 2022, v. 506, p. 1-11-
dc.identifier.issn0925-2312-
dc.identifier.urihttp://hdl.handle.net/10722/327785-
dc.description.abstractWe present a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images. The proposed network is very simple and flexible with variations that gracefully trade off between speed and accuracy for different applications. F-Clip detects line segments in an end-to-end fashion by predicting each line's center position, length, and angle. We further customize the design of convolution kernels of our fully convolutional network to effectively exploit the statistical priors of the distribution of line angles in real image datasets. We conduct extensive experiments and show that our method achieves a significantly better trade-off between efficiency and accuracy, resulting in a real-time line detector at up to 73 FPS on a single GPU. Such inference speed makes our method readily applicable to real-time tasks without compromising any accuracy of previous methods. Moreover, when equipped with a performance-improving backbone network, F-Clip is able to significantly outperform all state-of-the-art line detectors on accuracy at a similar or even higher frame rate. In other word, under same inference speed, F-Clip always achieving best accuracy compare with other methods. Source code https://github.com/Delay-Xili/F-Clip.-
dc.languageeng-
dc.relation.ispartofNeurocomputing-
dc.subjectFully convolutional network-
dc.subjectLine detection-
dc.subjectSingle stage method-
dc.titleFully convolutional line parsing-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.neucom.2022.07.026-
dc.identifier.scopuseid_2-s2.0-85135693588-
dc.identifier.volume506-
dc.identifier.spage1-
dc.identifier.epage11-
dc.identifier.eissn1872-8286-
dc.identifier.isiWOS:000914170300001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats