Files in this item
ROMA : run-time object detection to maximize real-time accuracy
Item metadata
dc.contributor.author | Lee, JunKyu | |
dc.contributor.author | Varghese, Blesson | |
dc.contributor.author | Vandierendonck, Hans | |
dc.contributor.editor | Berg, Tamara | |
dc.contributor.editor | Farrell, Ryan | |
dc.date.accessioned | 2023-02-23T13:30:01Z | |
dc.date.available | 2023-02-23T13:30:01Z | |
dc.date.issued | 2023-02-06 | |
dc.identifier | 283382900 | |
dc.identifier | a7e4e0ac-4eb7-4855-bfd2-29de84b0393b | |
dc.identifier | 85149023622 | |
dc.identifier.citation | Lee , 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/wacv56688.2023.00634 | en |
dc.identifier.citation | conference | en |
dc.identifier.isbn | 9781665493475 | |
dc.identifier.isbn | 9781665493468 | |
dc.identifier.issn | 2472-6737 | |
dc.identifier.other | Jisc: 902699 | |
dc.identifier.uri | https://hdl.handle.net/10023/27039 | |
dc.description | Funding: 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.abstract | This 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.extent | 10 | |
dc.format.extent | 1016561 | |
dc.language.iso | eng | |
dc.publisher | IEEE | |
dc.relation.ispartof | Proceedings 2023 IEEE/CVF winter conference on applications of computer vision (WACV) | en |
dc.relation.ispartofseries | 2023 IEEE/CVF winter conference on applications of computer vision (WACV) | en |
dc.subject | Applications: embedded sensing/real-time techniques | en |
dc.subject | QA75 Electronic computers. Computer science | en |
dc.subject | T-NDAS | en |
dc.subject | AC | en |
dc.subject | MCC | en |
dc.subject.lcc | QA75 | en |
dc.title | ROMA : run-time object detection to maximize real-time accuracy | en |
dc.type | Conference item | en |
dc.contributor.institution | University of St Andrews. School of Computer Science | en |
dc.identifier.doi | 10.1109/wacv56688.2023.00634 | |
dc.identifier.url | https://doi.org/10.1109/WACV56688.2023 | en |
dc.identifier.url | https://doi.org/10.48550/arXiv.2210.16083 | en |
dc.identifier.url | https://openaccess.thecvf.com/content/WACV2023/papers/Lee_ROMA_Run-Time_Object_Detection_To_Maximize_Real-Time_Accuracy_WACV_2023_paper.pdf | en |
This item appears in the following Collection(s)
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.