ROMA: run-time object detection to maximize real-time accuracy

JunKyu Lee; Blesson Varghese; Hans Vandierendonck

doi:10.1109/wacv56688.2023.00634

ROMA: run-time object detection to maximize real-time accuracy

JunKyu Lee, Blesson Varghese, Hans Vandierendonck

School of Electronics, Electrical Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

92 Downloads (Pure)

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 contents and detection latency consisting of MOT17Det and MOT20Det datasets, compared to individual YOLOv4 detectors and two state-of-the-art runtime techniques.

Original language	English
Title of host publication	Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6394-6403
Number of pages	10
ISBN (Electronic)	9781665493468
ISBN (Print)	9781665493475
DOIs	https://doi.org/10.1109/wacv56688.2023.00634
Publication status	Published - 06 Feb 2023
Event	IEEE 2023 Winter Conference on Applications of Computer Vision - Waikoloa, United States Duration: 02 Jan 2023 → 07 Jan 2023

Publication series

Name	IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings
Publisher	IEEE
ISSN (Print)	2472-6737
ISSN (Electronic)	2642-9381

Conference

Conference	IEEE 2023 Winter Conference on Applications of Computer Vision
Abbreviated title	WACV 2023
Country/Territory	United States
City	Waikoloa
Period	02/01/2023 → 07/01/2023

Access to Document

10.1109/wacv56688.2023.00634Licence: Unspecified

ROMA: run-time object detection to maximize real-time accuracy
© 2023 IEEE. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 985 KBLicence: Unspecified

R1155CSC: DiPET: Distributed Stream Processing on Fog and Edge Systems via Transprecise Computing
Vandierendonck, H. (PI) & Varghese, B. (CoI)
07/04/2020 → …
Project: Research

Cite this

Lee, J., Varghese, B., & Vandierendonck, H. (2023). ROMA: run-time object detection to maximize real-time accuracy. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 (pp. 6394-6403). (IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/wacv56688.2023.00634

Lee, JunKyu ; Varghese, Blesson ; Vandierendonck, Hans. / ROMA: run-time object detection to maximize real-time accuracy. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 6394-6403 (IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings).

@inproceedings{17d7222640c7426ca1081332915983b4,

title = "ROMA: run-time object detection to maximize real-time accuracy",

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 contents and detection latency consisting of MOT17Det and MOT20Det datasets, compared to individual YOLOv4 detectors and two state-of-the-art runtime techniques. ",

author = "JunKyu Lee and Blesson Varghese and Hans Vandierendonck",

year = "2023",

month = feb,

day = "6",

doi = "10.1109/wacv56688.2023.00634",

language = "English",

isbn = "9781665493475",

series = "IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "6394--6403",

booktitle = "Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023",

address = "United States",

note = "IEEE 2023 Winter Conference on Applications of Computer Vision, WACV 2023 ; Conference date: 02-01-2023 Through 07-01-2023",

}

Lee, J, Varghese, B & Vandierendonck, H 2023, ROMA: run-time object detection to maximize real-time accuracy. in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 6394-6403, IEEE 2023 Winter Conference on Applications of Computer Vision, Waikoloa, Hawaii, United States, 02/01/2023. https://doi.org/10.1109/wacv56688.2023.00634

ROMA: run-time object detection to maximize real-time accuracy. / Lee, JunKyu; Varghese, Blesson; Vandierendonck, Hans.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 6394-6403 (IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - ROMA: run-time object detection to maximize real-time accuracy

AU - Lee, JunKyu

AU - Varghese, Blesson

AU - Vandierendonck, Hans

PY - 2023/2/6

Y1 - 2023/2/6

N2 - 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 contents and detection latency consisting of MOT17Det and MOT20Det datasets, compared to individual YOLOv4 detectors and two state-of-the-art runtime techniques.

AB - 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 contents and detection latency consisting of MOT17Det and MOT20Det datasets, compared to individual YOLOv4 detectors and two state-of-the-art runtime techniques.

U2 - 10.1109/wacv56688.2023.00634

DO - 10.1109/wacv56688.2023.00634

M3 - Conference contribution

SN - 9781665493475

T3 - IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings

SP - 6394

EP - 6403

BT - Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE 2023 Winter Conference on Applications of Computer Vision

Y2 - 2 January 2023 through 7 January 2023

ER -

Lee J, Varghese B, Vandierendonck H. ROMA: run-time object detection to maximize real-time accuracy. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 6394-6403. (IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings). doi: 10.1109/wacv56688.2023.00634

ROMA: run-time object detection to maximize real-time accuracy

Abstract

Publication series

Conference

Access to Document

Fingerprint

Projects

R1155CSC: DiPET: Distributed Stream Processing on Fog and Edge Systems via Transprecise Computing

Cite this