Real-time Robust Object Detection Using an Adjacent Feature Fusion-based Single Shot Multibox Detector
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Donggeun | - |
dc.contributor.author | Park, Sangwoo | - |
dc.contributor.author | Kang, Donggoo | - |
dc.contributor.author | Paik, Joonki | - |
dc.date.available | 2020-04-10T03:21:11Z | - |
dc.date.issued | 2020-02 | - |
dc.identifier.issn | 2287-5255 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/38233 | - |
dc.description.abstract | A single shot multibox detector (SSD) is used as a baseline for many object detection networks, since it can provide sufficiently high accuracy in real time. However, it cannot deal with objects of various sizes, because features used in an SSD are not robust to multi-scale objects. To solve this problem, we present an improved feature pyramid for using multi-scale context information. The proposed feature pyramid fuses only adjacent features of the conventional SSD to achieve high accuracy without decreasing the processing speed. Our detector, with a 320×320 input, achieved 79.1% mean average precision (mAP) at 63 frames per second on a Pascal Visual Object Classes Challenge 2007 test set using a single Nvidia 1080 Ti graphics processing unit. This result shows better performance than existing SSDs. | - |
dc.format.extent | 6 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | 대한전자공학회 | - |
dc.title | Real-time Robust Object Detection Using an Adjacent Feature Fusion-based Single Shot Multibox Detector | - |
dc.type | Article | - |
dc.identifier.doi | 10.5573/IEIESPC.2020.9.1.022 | - |
dc.identifier.bibliographicCitation | IEIE Transactions on Smart Processing & Computing, v.9, no.1, pp 22 - 27 | - |
dc.identifier.kciid | ART002559711 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85087447203 | - |
dc.citation.endPage | 27 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 22 | - |
dc.citation.title | IEIE Transactions on Smart Processing & Computing | - |
dc.citation.volume | 9 | - |
dc.publisher.location | 대한민국 | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | Feature pyramid | - |
dc.subject.keywordAuthor | Pascal VOC | - |
dc.subject.keywordAuthor | SSD | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
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.