Saved in:
Bibliographic Details
Main Authors: Shi, Jianrui, Zhao, Yong, Cui, Zeyang, Shen, Xiaoming, Zeng, Minhang, Liu, Xiaojie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09465
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910786879750144
author Shi, Jianrui
Zhao, Yong
Cui, Zeyang
Shen, Xiaoming
Zeng, Minhang
Liu, Xiaojie
author_facet Shi, Jianrui
Zhao, Yong
Cui, Zeyang
Shen, Xiaoming
Zeng, Minhang
Liu, Xiaojie
contents Object detection plays a crucial role in smart video analysis, with applications ranging from autonomous driving and security to smart cities. However, achieving real-time object detection on edge devices presents significant challenges due to their limited computational resources and the high demands of deep neural network (DNN)-based detection models, particularly when processing high-resolution video. Conventional strategies, such as input down-sampling and network up-scaling, often compromise detection accuracy for faster performance or lead to higher inference latency. To address these issues, this paper introduces RE-POSE, a Reinforcement Learning (RL)-Driven Partitioning and Edge Offloading framework designed to optimize the accuracy-latency trade-off in resource-constrained edge environments. Our approach features an RL-Based Dynamic Clustering Algorithm (RL-DCA) that partitions video frames into non-uniform blocks based on object distribution and the computational characteristics of DNNs. Furthermore, a parallel edge offloading scheme is implemented to distribute these blocks across multiple edge servers for concurrent processing. Experimental evaluations show that RE-POSE significantly enhances detection accuracy and reduces inference latency, surpassing existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09465
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RE-POSE: Synergizing Reinforcement Learning-Based Partitioning and Offloading for Edge Object Detection
Shi, Jianrui
Zhao, Yong
Cui, Zeyang
Shen, Xiaoming
Zeng, Minhang
Liu, Xiaojie
Computer Vision and Pattern Recognition
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Object detection plays a crucial role in smart video analysis, with applications ranging from autonomous driving and security to smart cities. However, achieving real-time object detection on edge devices presents significant challenges due to their limited computational resources and the high demands of deep neural network (DNN)-based detection models, particularly when processing high-resolution video. Conventional strategies, such as input down-sampling and network up-scaling, often compromise detection accuracy for faster performance or lead to higher inference latency. To address these issues, this paper introduces RE-POSE, a Reinforcement Learning (RL)-Driven Partitioning and Edge Offloading framework designed to optimize the accuracy-latency trade-off in resource-constrained edge environments. Our approach features an RL-Based Dynamic Clustering Algorithm (RL-DCA) that partitions video frames into non-uniform blocks based on object distribution and the computational characteristics of DNNs. Furthermore, a parallel edge offloading scheme is implemented to distribute these blocks across multiple edge servers for concurrent processing. Experimental evaluations show that RE-POSE significantly enhances detection accuracy and reduces inference latency, surpassing existing methods.
title RE-POSE: Synergizing Reinforcement Learning-Based Partitioning and Offloading for Edge Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2501.09465