Context-aware image compression optimization for visual analytics offloading

Context-aware image compression optimization for visual analytics offloading
复制标题

用于视觉分析卸载的上下文感知图像压缩优化

DOI:
10.1145/3524273.3528178
复制
发表时间:
2022
期刊:
MMSys '22: Proceedings of the 13th ACM Multimedia Systems Conference
影响因子:
--
通讯作者:
Nahrstedt, Klara
Nahrstedt, Klara
中科院分区:
--
文献类型:
--
作者:
Chen, Bo;Yan, Zhisheng;Nahrstedt, Klara

文献摘要

参考文献

被引文献

相似文献

卷积神经网络(CNN)在互联网边缘产生了许多可视化分析应用。图像通常由摄像头捕获,然后实时流传输到边缘服务器进行分析,因为在计算受限的终端设备上运行CNN的成本过高。确保通过低带宽网络进行低延迟和准确的视觉分析卸载的关键组件是图像压缩,该压缩可最大限度地减少要卸载的视觉数据量,并最大限度地提高用于分析的突出像素的解码质量。尽管JPEG标准和传统图像压缩被广泛采用,但它们并不能解决分析任务的准确性问题,从而导致视觉分析卸载的压缩效果不佳。虽然最近的以机器为中心的图像压缩技术利用复杂的神经网络模型或硬件架构来支持准确性-带宽权衡,但它们在视觉分析卸载管道中引入了过多的延迟。本文介绍了CICO,一个上下文感知的图像压缩优化框架,以实现低带宽和低延迟的视觉分析卸载。CICO通过采用易于计算的低级图像特征来理解不同图像区域对视觉分析任务的重要性,从而将图像压缩用于卸载。因此,CICO可以优化压缩大小和分析准确性之间的权衡。大量的实际实验表明,CICO在分析精度相当的情况下,将现有压缩方法的带宽消耗减少了40%。在低延迟支持方面,CICO比最先进的压缩技术实现了高达2倍的加速。
Convolutional Neural Networks (CNN) have given rise to numerous visual analytics applications at the edge of the Internet. The image is typically captured by cameras and then live-streamed to edge servers for analytics due to the prohibitive cost of running CNN on computation-constrained end devices. A critical component to ensure low-latency and accurate visual analytics offloading over low bandwidth networks is image compression that minimizes the amount of visual data to offload and maximizes the decoding quality of salient pixels for analytics. Despite the wide adoption, JPEG standard and traditional image compression do not address the accuracy of analytics tasks, leading to ineffective compression for visual analytics offloading. Although recent machine-centric image compression techniques leverage sophisticated neural network models or hardware architecture to support the accuracy-bandwidth trade-off, they introduce excessive latency in the visual analytics offloading pipeline. This paper presents CICO, a Context-aware Image Compression Optimization framework to achieve low-bandwidth and low-latency visual analytics offloading. CICO contextualizes image compression for offloading by employing easily-computable low-level image features to understand the importance of different image regions for a visual analytics task. Accordingly, CICO can optimize the trade-off between compression size and analytics accuracy. Extensive real-world experiments demonstrate that CICO reduces the bandwidth consumption of existing compression methods by up to 40% under a comparable analytics accuracy. In terms of the low-latency support, CICO achieves up to a 2x speedup over state-of-the-art compression techniques.
DOI: 10.1145/3387514.3405874
发表时间: 2020-07
期刊: Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication
影响因子: --
作者:
Yuanqi Li;Arthi Padmanabhan;Pengzhan Zhao;Yufei Wang;G. Xu;R. Netravali
通讯作者: Yuanqi Li;Arthi Padmanabhan;Pengzhan Zhao;Yufei Wang;G. Xu;R. Netravali
DOI: --
发表时间: 2019-06
期刊: ArXiv
影响因子: --
作者:
Shinya Suzuki;Shion Takeno;T. Tamura;Kazuki Shitara;Masayuki Karasuyama
通讯作者: Shinya Suzuki;Shion Takeno;T. Tamura;Kazuki Shitara;Masayuki Karasuyama
DOI: 10.1007/978-3-642-21292-5_3
发表时间: 2010-03
期刊: --
影响因子: --
作者:
Eunsuk Kang;Ethan K. Jackson;Wolfram Schulte
通讯作者: Eunsuk Kang;Ethan K. Jackson;Wolfram Schulte
MOBOpt - 多目标贝叶斯优化
DOI: --
发表时间: 2020
期刊: SoftwareX
影响因子: 3.4
作者:
P. Galuzio;E. H. V. Segundo;L. Coelho;V. Mariani
通讯作者: V. Mariani
DOI: --
发表时间: 2016
期刊: 2016 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
影响因子: --
作者:
S. C. Smithson;Guang Yang;W. Gross;B. Meyer
通讯作者: B. Meyer