Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Mingxuan, Wang, Yi, Xiao, Xuedou, Luo, Zhiqing, He, Jianhua, Wang, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910385601249280
author Yan, Mingxuan
Wang, Yi
Xiao, Xuedou
Luo, Zhiqing
He, Jianhua
Wang, Wei
author_facet Yan, Mingxuan
Wang, Yi
Xiao, Xuedou
Luo, Zhiqing
He, Jianhua
Wang, Wei
contents Offloading computing to edge servers is a promising solution to support growing video understanding applications at resource-constrained IoT devices. Recent efforts have been made to enhance the scalability of such systems by reducing inference costs on edge servers. However, existing research is not directly applicable to pixel-level vision tasks such as video semantic segmentation (VSS), partly due to the fluctuating VSS accuracy and segment bitrate caused by the dynamic video content. In response, we present Penance, a new edge inference cost reduction framework. By exploiting softmax outputs of VSS models and the prediction mechanism of H.264/AVC codecs, Penance optimizes model selection and compression settings to minimize the inference cost while meeting the required accuracy within the available bandwidth constraints. We implement Penance in a commercial IoT device with only CPUs. Experimental results show that Penance consumes a negligible 6.8% more computation resources than the optimal strategy while satisfying accuracy and bandwidth constraints with a low failure rate.
format Preprint
id arxiv_https___arxiv_org_abs_2402_14326
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation
Yan, Mingxuan
Wang, Yi
Xiao, Xuedou
Luo, Zhiqing
He, Jianhua
Wang, Wei
Multimedia
Offloading computing to edge servers is a promising solution to support growing video understanding applications at resource-constrained IoT devices. Recent efforts have been made to enhance the scalability of such systems by reducing inference costs on edge servers. However, existing research is not directly applicable to pixel-level vision tasks such as video semantic segmentation (VSS), partly due to the fluctuating VSS accuracy and segment bitrate caused by the dynamic video content. In response, we present Penance, a new edge inference cost reduction framework. By exploiting softmax outputs of VSS models and the prediction mechanism of H.264/AVC codecs, Penance optimizes model selection and compression settings to minimize the inference cost while meeting the required accuracy within the available bandwidth constraints. We implement Penance in a commercial IoT device with only CPUs. Experimental results show that Penance consumes a negligible 6.8% more computation resources than the optimal strategy while satisfying accuracy and bandwidth constraints with a low failure rate.
title Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation
topic Multimedia
url https://arxiv.org/abs/2402.14326