Yuanyi He, Peng Yang, Tian Qin, Jiawei Hou, Ning Zhang
{"title":"移动设备低照度视频分析的自适应卸载和增强","authors":"Yuanyi He, Peng Yang, Tian Qin, Jiawei Hou, Ning Zhang","doi":"arxiv-2409.05297","DOIUrl":null,"url":null,"abstract":"In this paper, we explore adaptive offloading and enhancement strategies for\nvideo analytics tasks on computing-constrained mobile devices in low-light\nconditions. We observe that the accuracy of low-light video analytics varies\nfrom different enhancement algorithms. The root cause could be the disparities\nin the effectiveness of enhancement algorithms for feature extraction in\nanalytic models. Specifically, the difference in class activation maps (CAMs)\nbetween enhanced and low-light frames demonstrates a positive correlation with\nvideo analytics accuracy. Motivated by such observations, a novel enhancement\nquality assessment method is proposed on CAMs to evaluate the effectiveness of\ndifferent enhancement algorithms for low-light videos. Then, we design a\nmulti-edge system, which adaptively offloads and enhances low-light video\nanalytics tasks from mobile devices. To achieve the trade-off between the\nenhancement quality and the latency for all system-served mobile devices, we\npropose a genetic-based scheduling algorithm, which can find a near-optimal\nsolution in a reasonable time to meet the latency requirement. Thereby, the\noffloading strategies and the enhancement algorithms are properly selected\nunder the condition of limited end-edge bandwidth and edge computation\nresources. Simulation experiments demonstrate the superiority of the proposed\nsystem, improving accuracy up to 20.83\\% compared to existing benchmarks.","PeriodicalId":501480,"journal":{"name":"arXiv - CS - Multimedia","volume":"75 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Adaptive Offloading and Enhancement for Low-Light Video Analytics on Mobile Devices\",\"authors\":\"Yuanyi He, Peng Yang, Tian Qin, Jiawei Hou, Ning Zhang\",\"doi\":\"arxiv-2409.05297\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we explore adaptive offloading and enhancement strategies for\\nvideo analytics tasks on computing-constrained mobile devices in low-light\\nconditions. We observe that the accuracy of low-light video analytics varies\\nfrom different enhancement algorithms. The root cause could be the disparities\\nin the effectiveness of enhancement algorithms for feature extraction in\\nanalytic models. Specifically, the difference in class activation maps (CAMs)\\nbetween enhanced and low-light frames demonstrates a positive correlation with\\nvideo analytics accuracy. Motivated by such observations, a novel enhancement\\nquality assessment method is proposed on CAMs to evaluate the effectiveness of\\ndifferent enhancement algorithms for low-light videos. Then, we design a\\nmulti-edge system, which adaptively offloads and enhances low-light video\\nanalytics tasks from mobile devices. To achieve the trade-off between the\\nenhancement quality and the latency for all system-served mobile devices, we\\npropose a genetic-based scheduling algorithm, which can find a near-optimal\\nsolution in a reasonable time to meet the latency requirement. Thereby, the\\noffloading strategies and the enhancement algorithms are properly selected\\nunder the condition of limited end-edge bandwidth and edge computation\\nresources. Simulation experiments demonstrate the superiority of the proposed\\nsystem, improving accuracy up to 20.83\\\\% compared to existing benchmarks.\",\"PeriodicalId\":501480,\"journal\":{\"name\":\"arXiv - CS - Multimedia\",\"volume\":\"75 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.05297\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.05297","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Adaptive Offloading and Enhancement for Low-Light Video Analytics on Mobile Devices
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.