Saved in:
Bibliographic Details
Main Authors: Wu, Chao, Gong, Yifan, Liu, Liangkai, Li, Mengquan, Wu, Yushu, Shen, Xuan, Li, Zhimin, Yuan, Geng, Shi, Weisong, Wang, Yanzhi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.05363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911983724396544
author Wu, Chao
Gong, Yifan
Liu, Liangkai
Li, Mengquan
Wu, Yushu
Shen, Xuan
Li, Zhimin
Yuan, Geng
Shi, Weisong
Wang, Yanzhi
author_facet Wu, Chao
Gong, Yifan
Liu, Liangkai
Li, Mengquan
Wu, Yushu
Shen, Xuan
Li, Zhimin
Yuan, Geng
Shi, Weisong
Wang, Yanzhi
contents Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the deployment dilemma of simultaneously achieving high accuracy, excellent power efficiency, and meeting strict real-time requirements. To tackle this dilemma, we propose AyE-Edge, the first-of-this-kind development tool that explores automated algorithm-device deployment space search to realize Accurate yet power-Efficient real-time object detection on the Edge. Through a collaborative exploration of keyframe selection, CPU-GPU configuration, and DNN pruning strategy, AyE-Edge excels in extensive real-world experiments conducted on a mobile device. The results consistently demonstrate AyE-Edge's effectiveness, realizing outstanding real-time performance, detection accuracy, and notably, a remarkable 96.7% reduction in power consumption, compared to state-of-the-art (SOTA) competitors.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05363
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge
Wu, Chao
Gong, Yifan
Liu, Liangkai
Li, Mengquan
Wu, Yushu
Shen, Xuan
Li, Zhimin
Yuan, Geng
Shi, Weisong
Wang, Yanzhi
Computer Vision and Pattern Recognition
Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the deployment dilemma of simultaneously achieving high accuracy, excellent power efficiency, and meeting strict real-time requirements. To tackle this dilemma, we propose AyE-Edge, the first-of-this-kind development tool that explores automated algorithm-device deployment space search to realize Accurate yet power-Efficient real-time object detection on the Edge. Through a collaborative exploration of keyframe selection, CPU-GPU configuration, and DNN pruning strategy, AyE-Edge excels in extensive real-world experiments conducted on a mobile device. The results consistently demonstrate AyE-Edge's effectiveness, realizing outstanding real-time performance, detection accuracy, and notably, a remarkable 96.7% reduction in power consumption, compared to state-of-the-art (SOTA) competitors.
title AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.05363