Non-Anchor-Based Vehicle Detection for Traffic Surveillance Using Bounding Ellipses
DC Field | Value | Language |
---|---|---|
dc.contributor.author | YU, BYEONGHYEOP | - |
dc.contributor.author | SHIN, JOHYUN | - |
dc.contributor.author | KIM, GYEONGJUN | - |
dc.contributor.author | ROH, SEUNGBIN | - |
dc.contributor.author | SOHN, KEEMIN | - |
dc.date.accessioned | 2021-11-09T07:40:09Z | - |
dc.date.available | 2021-11-09T07:40:09Z | - |
dc.date.issued | 2021-08 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/51227 | - |
dc.description.abstract | Cameras for traffic surveillance are usually pole-mounted and produce images that reflect a birds-eye view. Vehicles in such images, in general, assume an ellipse form. A bounding box for the vehicles usually includes a large empty space when the vehicle orientation is not parallel to the edges of the box. To circumvent this problem, the present study applied bounding ellipses to a non-anchor-based, single-shot detection model (CenterNet). Since this model does not depend on anchor boxes, non-max suppression (NMS) that requires computing the intersection over union (IOU) between predicted bounding boxes is unnecessary for inference. The SpotNet that extends the CenterNet model by adding a segmentation head was also tested with bounding ellipses. Two other anchor-based, single-shot detection models (YOLO4 and SSD) were chosen as references for comparison. The model performance was compared based on a local dataset that was doubly annotated with bounding boxes and ellipses. As a result, the performance of the two models with bounding ellipses exceeded that of the reference models with bounding boxes. When the backbone of the ellipse models was pretrained on an open dataset (UA-DETRAC), the performance was further enhanced. Several data augmentation schemes also improved the performance of the proposed models. As a result, the best mAP score of a CenterNet exceeds 0.95 when augmenting heatmaps with bounding ellipses. © 2013 IEEE. | - |
dc.format.extent | 14 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Non-Anchor-Based Vehicle Detection for Traffic Surveillance Using Bounding Ellipses | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3109258 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.9, pp 123061 - 123074 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000696073800001 | - |
dc.identifier.scopusid | 2-s2.0-85115211466 | - |
dc.citation.endPage | 123074 | - |
dc.citation.startPage | 123061 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 9 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | Bounding ellipse | - |
dc.subject.keywordAuthor | deep-learning | - |
dc.subject.keywordAuthor | objects as points | - |
dc.subject.keywordAuthor | traffic surveillance | - |
dc.subject.keywordAuthor | vehicle detection | - |
dc.subject.keywordPlus | Security systems | - |
dc.subject.keywordPlus | Vehicles | - |
dc.subject.keywordPlus | Bounding box | - |
dc.subject.keywordPlus | Data augmentation | - |
dc.subject.keywordPlus | Ellipse model | - |
dc.subject.keywordPlus | Model performance | - |
dc.subject.keywordPlus | Reference models | - |
dc.subject.keywordPlus | Traffic surveillance | - |
dc.subject.keywordPlus | Vehicle detection | - |
dc.subject.keywordPlus | Vehicle orientation | - |
dc.subject.keywordPlus | Geometry | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
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.