R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, Wonseok | - |
dc.contributor.author | Jeong, Hansaem | - |
dc.contributor.author | Kang, Kyungtae | - |
dc.contributor.author | Dutt, Nikil | - |
dc.contributor.author | Kim, Jong chan | - |
dc.date.accessioned | 2021-07-28T08:13:04Z | - |
dc.date.available | 2021-07-28T08:13:04Z | - |
dc.date.created | 2021-07-14 | - |
dc.date.issued | 2020-12 | - |
dc.identifier.issn | 1052-8725 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/105819 | - |
dc.description.abstract | For realizing safe autonomous driving, the end-to-end delays of real-time object detection systems should be thoroughly analyzed and minimized. However, despite recent development of neural networks with minimized inference delays, surprisingly little attention has been paid to their end-to-end delays from an object's appearance until its detection is reported. With this motivation, this paper aims to provide more comprehensive understanding of the end-to-end delay, through which precise best-and worst-case delay predictions are formulated, and three optimization methods are implemented: (i) on-demand capture, (ii) zero-slack pipeline, and (iii) contention-free pipeline. Our experimental results show a 76% reduction in the end-to-end delay of Darknet YOLO (You Only Look Once) v3 (from 1070 ms to 261 ms), thereby demonstrating the great potential of exploiting the end-to-end delay analysis for autonomous driving. Furthermore, as we only modify the system architecture and do not change the neural network architecture itself, our approach incurs no penalty on the detection accuracy. © 2020 IEEE. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kang, Kyungtae | - |
dc.identifier.doi | 10.1109/RTSS49844.2020.00027 | - |
dc.identifier.scopusid | 2-s2.0-85101995446 | - |
dc.identifier.bibliographicCitation | Proceedings - Real-Time Systems Symposium, pp.191 - 204 | - |
dc.relation.isPartOf | Proceedings - Real-Time Systems Symposium | - |
dc.citation.title | Proceedings - Real-Time Systems Symposium | - |
dc.citation.startPage | 191 | - |
dc.citation.endPage | 204 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Autonomous vehicles | - |
dc.subject.keywordPlus | Interactive computer systems | - |
dc.subject.keywordPlus | Network architecture | - |
dc.subject.keywordPlus | Neural networks | - |
dc.subject.keywordPlus | Object detection | - |
dc.subject.keywordPlus | Pipelines | - |
dc.subject.keywordPlus | Autonomous driving | - |
dc.subject.keywordPlus | Delay predictions | - |
dc.subject.keywordPlus | Detection accuracy | - |
dc.subject.keywordPlus | End to end delay | - |
dc.subject.keywordPlus | Object detection systems | - |
dc.subject.keywordPlus | Object detectors | - |
dc.subject.keywordPlus | Optimization method | - |
dc.subject.keywordPlus | System architectures | - |
dc.subject.keywordPlus | Real time systems | - |
dc.subject.keywordAuthor | Autonomous Driving | - |
dc.subject.keywordAuthor | Darknet | - |
dc.subject.keywordAuthor | End to End Delay | - |
dc.subject.keywordAuthor | R TOD | - |
dc.subject.keywordAuthor | Real Time Object Detection | - |
dc.subject.keywordAuthor | YOLO | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9355528 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG 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.