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.
@article{arxiv.2210.16083,
title = {ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy},
author = {JunKyu Lee and Blesson Varghese and Hans Vandierendonck},
journal= {arXiv preprint arXiv:2210.16083},
year = {2024}
}
Comments
Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023