当前位置:
X-MOL 学术
›
arXiv.cs.PF
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Towards Performance Clarity of Edge Video Analytics
arXiv - CS - Performance Pub Date : 2021-05-18 , DOI: arxiv-2105.08694 Zhujun Xiao, Zhengxu Xia, Haitao Zheng, Ben Y. Zhao, Junchen Jiang
arXiv - CS - Performance Pub Date : 2021-05-18 , DOI: arxiv-2105.08694 Zhujun Xiao, Zhengxu Xia, Haitao Zheng, Ben Y. Zhao, Junchen Jiang
Edge video analytics is becoming the solution to many safety and management
tasks. Its wide deployment, however, must first address the tension between
inference accuracy and resource (compute/network) cost. This has led to the
development of video analytics pipelines (VAPs), which reduce resource cost by
combining DNN compression/speedup techniques with video processing heuristics.
Our measurement study on existing VAPs, however, shows that today's methods for
evaluating VAPs are incomplete, often producing premature conclusions or
ambiguous results. This is because each VAP's performance varies substantially
across videos and time (even under the same scenario) and is sensitive to
different subsets of video content characteristics. We argue that accurate VAP evaluation must first characterize the complex
interaction between VAPs and video characteristics, which we refer to as VAP
performance clarity. We design and implement Yoda, the first VAP benchmark to
achieve performance clarity. Using primitive-based profiling and a carefully
curated benchmark video set, Yoda builds a performance clarity profile for each
VAP to precisely define its accuracy/cost tradeoff and its relationship with
video characteristics. We show that Yoda substantially improves VAP evaluations
by (1) providing a comprehensive, transparent assessment of VAP performance and
its dependencies on video characteristics; (2) explicitly identifying
fine-grained VAP behaviors that were previously hidden by large performance
variance; and (3) revealing strengths/weaknesses among different VAPs and new
design opportunities.
中文翻译:
提升边缘视频分析的性能
边缘视频分析正在成为许多安全和管理任务的解决方案。但是,其广泛的部署必须首先解决推理准确性和资源(计算/网络)成本之间的矛盾。这导致了视频分析管道(VAP)的发展,该技术通过将DNN压缩/加速技术与视频处理启发式技术相结合来降低资源成本。但是,我们对现有VAP的测量研究表明,当今评估VAP的方法并不完整,常常会得出不成熟的结论或含糊不清的结果。这是因为每个VAP的性能会随视频和时间的不同而有很大差异(即使在相同的情况下),并且对视频内容特征的不同子集敏感。我们认为,准确的VAP评估必须首先表征VAP与视频特征之间的复杂交互,这就是我们所说的VAP性能清晰度。我们设计并实现了Yoda,这是第一个VAP基准测试,旨在实现性能的清晰度。Yoda使用基于原始的性能分析和精心策划的基准视频集,为每个VAP构建了性能清晰度配置文件,以精确定义其准确性/成本权衡以及与视频特性的关系。我们证明,尤达(1)通过提供对VAP性能及其对视频特性的依赖性的全面,透明的评估,大大提高了VAP评估。(2)明确识别以前由于较大的性能差异而隐藏的细粒度VAP行为;
更新日期:2021-05-19
中文翻译:
提升边缘视频分析的性能
边缘视频分析正在成为许多安全和管理任务的解决方案。但是,其广泛的部署必须首先解决推理准确性和资源(计算/网络)成本之间的矛盾。这导致了视频分析管道(VAP)的发展,该技术通过将DNN压缩/加速技术与视频处理启发式技术相结合来降低资源成本。但是,我们对现有VAP的测量研究表明,当今评估VAP的方法并不完整,常常会得出不成熟的结论或含糊不清的结果。这是因为每个VAP的性能会随视频和时间的不同而有很大差异(即使在相同的情况下),并且对视频内容特征的不同子集敏感。我们认为,准确的VAP评估必须首先表征VAP与视频特征之间的复杂交互,这就是我们所说的VAP性能清晰度。我们设计并实现了Yoda,这是第一个VAP基准测试,旨在实现性能的清晰度。Yoda使用基于原始的性能分析和精心策划的基准视频集,为每个VAP构建了性能清晰度配置文件,以精确定义其准确性/成本权衡以及与视频特性的关系。我们证明,尤达(1)通过提供对VAP性能及其对视频特性的依赖性的全面,透明的评估,大大提高了VAP评估。(2)明确识别以前由于较大的性能差异而隐藏的细粒度VAP行为;