Small object segmentation with fully convolutional network based on overlapping domain decomposition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jinhee | - |
dc.contributor.author | Kwon, Dokyeong | - |
dc.contributor.author | Choi, Bo Won | - |
dc.contributor.author | Kim, Ga Young | - |
dc.contributor.author | Kim, Kwang Yong | - |
dc.contributor.author | Kwon, Junseok | - |
dc.date.available | 2019-08-09T07:58:56Z | - |
dc.date.issued | 2019-06 | - |
dc.identifier.issn | 0932-8092 | - |
dc.identifier.issn | 1432-1769 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/32753 | - |
dc.description.abstract | We propose a new segmentation algorithm based on deep learning. To segment ice hockey players, a fully convolutional network (FCN) is adopted and fine-tuned with our augmented training data. The original FCN has difficulty segmenting small-size objects. To solve this problem, our method divides an input image into four overlapping sub-images and each image is fed into the deep learning network. After obtaining segmentation results from all sub-images, we combine them into a single result. The segmentation results should be consistent over time in video. Thus, our method tracks segments over time and removes false positives that appear for brief periods. Mathematically, we show that our overlapping subdivision process can be interpreted as overlapping domain decomposition methods, which enable the FCN to regularize over consecutive sub-images in training time. Experimental results demonstrate that our method accurately segments ice hockey players when they appear small and when there exists severe background clutter. Our method shows real-time performance. | - |
dc.format.extent | 10 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | SPRINGER | - |
dc.title | Small object segmentation with fully convolutional network based on overlapping domain decomposition | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/s00138-019-01023-x | - |
dc.identifier.bibliographicCitation | MACHINE VISION AND APPLICATIONS, v.30, no.4, pp 707 - 716 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 000469483000012 | - |
dc.identifier.scopusid | 2-s2.0-85064181315 | - |
dc.citation.endPage | 716 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 707 | - |
dc.citation.title | MACHINE VISION AND APPLICATIONS | - |
dc.citation.volume | 30 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | Small object segmentation | - |
dc.subject.keywordAuthor | Fully convolutional network | - |
dc.subject.keywordAuthor | Overlapping domain decomposition | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Cybernetics | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.