Adaptive Offloading and Enhancement for Low-Light Video Analytics on Mobile Devices

TL;DR

This paper proposes an adaptive system for low-light video analytics on mobile devices that intelligently offloads and enhances videos, improving accuracy by up to 20.83% through a novel quality assessment and genetic scheduling.

Contribution

It introduces a CAM-based enhancement quality assessment and a genetic scheduling algorithm for adaptive offloading in low-light video analytics on mobile devices.

Findings

Accuracy improved by up to 20.83%

Effective offloading and enhancement strategies under bandwidth constraints

Genetic algorithm achieves near-optimal scheduling in reasonable time

Abstract

In this paper, we explore adaptive offloading and enhancement strategies for video analytics tasks on computing-constrained mobile devices in low-light conditions. We observe that the accuracy of low-light video analytics varies from different enhancement algorithms. The root cause could be the disparities in the effectiveness of enhancement algorithms for feature extraction in analytic models. Specifically, the difference in class activation maps (CAMs) between enhanced and low-light frames demonstrates a positive correlation with video analytics accuracy. Motivated by such observations, a novel enhancement quality assessment method is proposed on CAMs to evaluate the effectiveness of different enhancement algorithms for low-light videos. Then, we design a multi-edge system, which adaptively offloads and enhances low-light video analytics tasks from mobile devices. To achieve the trade-off between the enhancement quality and the latency for all system-served mobile devices, we propose a genetic-based scheduling algorithm, which can find a near-optimal solution in a reasonable time to meet the latency requirement. Thereby, the offloading strategies and the enhancement algorithms are properly selected under the condition of limited end-edge bandwidth and edge computation resources. Simulation experiments demonstrate the superiority of the proposed system, improving accuracy up to 20.83\% compared to existing benchmarks.