Repulsion Distance Intersection over Union Loss for Crowd Scene Detection
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, YuChul | - |
dc.contributor.author | Lee, Eunju | - |
dc.contributor.author | Jang, Soojin | - |
dc.contributor.author | Kim, Youngbin | - |
dc.contributor.author | Kwon, JuneHyoung | - |
dc.date.accessioned | 2022-12-09T05:40:46Z | - |
dc.date.available | 2022-12-09T05:40:46Z | - |
dc.date.issued | 2022-02 | - |
dc.identifier.issn | 2288-9248 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59529 | - |
dc.description.abstract | The detection of many people or crowds increases the false-positive prediction rate owing to the creation of more bounding boxes. In this study, a loss function that reduces the false positive predictions of an object detection model is proposed. The proposed loss function induces not only the bounding box to be closer to the ground truth (GT) box but also the center point distance between the GT box and the overlapped adjacent object or other bounding boxes to be longer. In addition, a balanced feature pyramid was introduced to enhance the precision of object prediction. Applying the proposed method, the log-average miss rate on false positive per image in [10^(-2),100] was 1.89% lower while average precision and Jaccard index were 0.5% and 0.58% higher, respectively, than those of the conventional method, which indicates that it effectively reduces false positive predictions. | - |
dc.format.extent | 4 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | 중앙대학교 영상콘텐츠융합연구소 | - |
dc.title | Repulsion Distance Intersection over Union Loss for Crowd Scene Detection | - |
dc.type | Article | - |
dc.identifier.doi | 10.15323/techart.2022.2.9.1.27 | - |
dc.identifier.bibliographicCitation | TechArt, v.9, no.1, pp 27 - 30 | - |
dc.identifier.kciid | ART002896849 | - |
dc.description.isOpenAccess | N | - |
dc.citation.endPage | 30 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 27 | - |
dc.citation.title | TechArt | - |
dc.citation.volume | 9 | - |
dc.publisher.location | 대한민국 | - |
dc.subject.keywordAuthor | Crowd detection | - |
dc.subject.keywordAuthor | Pedestrian detection. | - |
dc.description.journalRegisteredClass | kciCandi | - |
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.