How2Compress: Scalable and Efficient Edge Video Analytics via Adaptive Granular Video Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yuheng, Nguyen, Thanh-Tung, Liebe, Lucas, Tau, Quang, Campos, Pablo Espinosa, Cheng, Jinghan, Lee, Dongman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915566473707520
author Wu, Yuheng
Nguyen, Thanh-Tung
Liebe, Lucas
Tau, Quang
Campos, Pablo Espinosa
Cheng, Jinghan
Lee, Dongman
author_facet Wu, Yuheng
Nguyen, Thanh-Tung
Liebe, Lucas
Tau, Quang
Campos, Pablo Espinosa
Cheng, Jinghan
Lee, Dongman
contents With the rapid proliferation of the Internet of Things, video analytics has become a cornerstone application in wireless multimedia sensor networks. To support such applications under bandwidth constraints, learning-based adaptive quantization for video compression have demonstrated strong potential in reducing bitrate while maintaining analytical accuracy. However, existing frameworks often fail to fully exploit the fine-grained quality control enabled by modern blockbased video codecs, leaving significant compression efficiency untapped. In this paper, we present How2Compress, a simple yet effective framework designed to enhance video compression efficiency through precise, fine-grained quality control at the macroblock level. How2Compress is a plug-and-play module and can be seamlessly integrated into any existing edge video analytics pipelines. We implement How2Compress on the H.264 codec and evaluate its performance across diverse real-world scenarios. Experimental results show that How2Compress achieves up to $50.4\%$ bitrate savings and outperforms baselines by up to $3.01\times$ without compromising accuracy, demonstrating its practical effectiveness and efficiency. Code is available at https://github.com/wyhallenwu/how2compress and a reproducible docker image at https://hub.docker.com/r/wuyuheng/how2compress.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18409
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How2Compress: Scalable and Efficient Edge Video Analytics via Adaptive Granular Video Compression
Wu, Yuheng
Nguyen, Thanh-Tung
Liebe, Lucas
Tau, Quang
Campos, Pablo Espinosa
Cheng, Jinghan
Lee, Dongman
Multimedia
Networking and Internet Architecture
With the rapid proliferation of the Internet of Things, video analytics has become a cornerstone application in wireless multimedia sensor networks. To support such applications under bandwidth constraints, learning-based adaptive quantization for video compression have demonstrated strong potential in reducing bitrate while maintaining analytical accuracy. However, existing frameworks often fail to fully exploit the fine-grained quality control enabled by modern blockbased video codecs, leaving significant compression efficiency untapped. In this paper, we present How2Compress, a simple yet effective framework designed to enhance video compression efficiency through precise, fine-grained quality control at the macroblock level. How2Compress is a plug-and-play module and can be seamlessly integrated into any existing edge video analytics pipelines. We implement How2Compress on the H.264 codec and evaluate its performance across diverse real-world scenarios. Experimental results show that How2Compress achieves up to $50.4\%$ bitrate savings and outperforms baselines by up to $3.01\times$ without compromising accuracy, demonstrating its practical effectiveness and efficiency. Code is available at https://github.com/wyhallenwu/how2compress and a reproducible docker image at https://hub.docker.com/r/wuyuheng/how2compress.
title How2Compress: Scalable and Efficient Edge Video Analytics via Adaptive Granular Video Compression
topic Multimedia
Networking and Internet Architecture
url https://arxiv.org/abs/2510.18409