AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge

TL;DR

AyE-Edge is a novel development tool that automates deployment space search to achieve high-accuracy, power-efficient, real-time object detection on edge devices, significantly reducing power consumption while maintaining performance.

Contribution

This paper introduces AyE-Edge, the first tool to automate deployment space exploration for edge object detection, balancing accuracy, power efficiency, and real-time performance.

Findings

Achieves real-time object detection with high accuracy on mobile devices.

Reduces power consumption by 96.7% compared to SOTA methods.

Demonstrates effectiveness through extensive real-world experiments.

Abstract

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.