Region-based Content Enhancement for Efficient Video Analytics at the Edge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Weijun, Mi, Liang, Cen, Shaowei, Dai, Haipeng, Li, Yuanchun, Fu, Xiaoming, Liu, Yunxin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908297623240704
author Wang, Weijun
Mi, Liang
Cen, Shaowei
Dai, Haipeng
Li, Yuanchun
Fu, Xiaoming
Liu, Yunxin
author_facet Wang, Weijun
Mi, Liang
Cen, Shaowei
Dai, Haipeng
Li, Yuanchun
Fu, Xiaoming
Liu, Yunxin
contents Video analytics is widespread in various applications serving our society. Recent advances of content enhancement in video analytics offer significant benefits for the bandwidth saving and accuracy improvement. However, existing content-enhanced video analytics systems are excessively computationally expensive and provide extremely low throughput. In this paper, we present region-based content enhancement, that enhances only the important regions in videos, to improve analytical accuracy. Our system, RegenHance, enables high-accuracy and high-throughput video analytics at the edge by 1) a macroblock-based region importance predictor that identifies the important regions fast and precisely, 2) a region-aware enhancer that stitches sparsely distributed regions into dense tensors and enhances them efficiently, and 3) a profile-based execution planer that allocates appropriate resources for enhancement and analytics components. We prototype RegenHance on five heterogeneous edge devices. Experiments on two analytical tasks reveal that region-based enhancement improves the overall accuracy of 10-19% and achieves 2-3x throughput compared to the state-of-the-art frame-based enhancement methods.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Region-based Content Enhancement for Efficient Video Analytics at the Edge
Wang, Weijun
Mi, Liang
Cen, Shaowei
Dai, Haipeng
Li, Yuanchun
Fu, Xiaoming
Liu, Yunxin
Networking and Internet Architecture
Video analytics is widespread in various applications serving our society. Recent advances of content enhancement in video analytics offer significant benefits for the bandwidth saving and accuracy improvement. However, existing content-enhanced video analytics systems are excessively computationally expensive and provide extremely low throughput. In this paper, we present region-based content enhancement, that enhances only the important regions in videos, to improve analytical accuracy. Our system, RegenHance, enables high-accuracy and high-throughput video analytics at the edge by 1) a macroblock-based region importance predictor that identifies the important regions fast and precisely, 2) a region-aware enhancer that stitches sparsely distributed regions into dense tensors and enhances them efficiently, and 3) a profile-based execution planer that allocates appropriate resources for enhancement and analytics components. We prototype RegenHance on five heterogeneous edge devices. Experiments on two analytical tasks reveal that region-based enhancement improves the overall accuracy of 10-19% and achieves 2-3x throughput compared to the state-of-the-art frame-based enhancement methods.
title Region-based Content Enhancement for Efficient Video Analytics at the Edge
topic Networking and Internet Architecture
url https://arxiv.org/abs/2407.16990