Show simple item record

Files in this item

Thumbnail

Item metadata

dc.contributor.authorLee, JunKyu
dc.contributor.authorVarghese, Blesson
dc.contributor.authorVandierendonck, Hans
dc.contributor.editorBerg, Tamara
dc.contributor.editorFarrell, Ryan
dc.date.accessioned2023-02-23T13:30:01Z
dc.date.available2023-02-23T13:30:01Z
dc.date.issued2023-02-06
dc.identifier283382900
dc.identifiera7e4e0ac-4eb7-4855-bfd2-29de84b0393b
dc.identifier85149023622
dc.identifier.citationLee , J , Varghese , B & Vandierendonck , H 2023 , ROMA : run-time object detection to maximize real-time accuracy . in T Berg & R Farrell (eds) , Proceedings 2023 IEEE/CVF winter conference on applications of computer vision (WACV) : 3-7 January 2023, Waikoloa, Hawaii . , 10030225 , 2023 IEEE/CVF winter conference on applications of computer vision (WACV) , IEEE , Piscataway, NJ , pp. 6394-6403 , IEEE/CVF Winter Conference on Applications of Computer Vision , Waikoloa , Hawaii , United States , 3/01/23 . https://doi.org/10.1109/wacv56688.2023.00634en
dc.identifier.citationconferenceen
dc.identifier.isbn9781665493475
dc.identifier.isbn9781665493468
dc.identifier.issn2472-6737
dc.identifier.otherJisc: 902699
dc.identifier.urihttps://hdl.handle.net/10023/27039
dc.descriptionFunding: This work is supported by the Engineering and Physical Sciences Research Council under grant agreement EP/T022345/1 and by CHIST-ERA under grant agreement CHIST-ERA-18-SDCDN-002 (DiPET).en
dc.description.abstractThis paper analyzes the effects of dynamically varying video contents and detection latency on the real-time detection accuracy of a detector and proposes a new run-time accuracy variation model, ROMA, based on the findings from the analysis. ROMA is designed to select an optimal detector out of a set of detectors in real time without label information to maximize real-time object detection accuracy. ROMA utilizing four YOLOv4 detectors on an NVIDIA Jetson Nano shows real-time accuracy improvements by 4 to 37% for a scenario of dynamically varying video con-tents and detection latency consisting of MOT17Det and MOT20Det datasets, compared to individual YOLOv4 detectors and two state-of-the-art runtime techniques.
dc.format.extent10
dc.format.extent1016561
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofProceedings 2023 IEEE/CVF winter conference on applications of computer vision (WACV)en
dc.relation.ispartofseries2023 IEEE/CVF winter conference on applications of computer vision (WACV)en
dc.subjectApplications: embedded sensing/real-time techniquesen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectT-NDASen
dc.subjectACen
dc.subjectMCCen
dc.subject.lccQA75en
dc.titleROMA : run-time object detection to maximize real-time accuracyen
dc.typeConference itemen
dc.contributor.institutionUniversity of St Andrews. School of Computer Scienceen
dc.identifier.doi10.1109/wacv56688.2023.00634
dc.identifier.urlhttps://doi.org/10.1109/WACV56688.2023en
dc.identifier.urlhttps://doi.org/10.48550/arXiv.2210.16083en
dc.identifier.urlhttps://openaccess.thecvf.com/content/WACV2023/papers/Lee_ROMA_Run-Time_Object_Detection_To_Maximize_Real-Time_Accuracy_WACV_2023_paper.pdfen


This item appears in the following Collection(s)

Show simple item record