MobiEye: An Efficient Cloud-based Video Detection System for Real-Time Mobile Applications
MobiEye: An Efficient Cloud-based Video Detection System for Real-Time Mobile Applications
复制标题
DOI：
10.1145/3316781.3317865
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Jiachen Mao;Qing Yang;Ang Li;H. Li;Yiran Chen
中科院分区：
文献类型：
--
作者：
Jiachen Mao;Qing Yang;Ang Li;H. Li;Yiran Chen
近年来，机器学习的研究在很大程度上将重点从云转移到了边缘。虽然由此产生的算法和硬件级别的优化使边缘设备上的大多数深度神经网络(DNN)能够在本地执行，但与实时视频检测工作负载相关的DNN的巨大规模迫使它们保持在云中远程执行。当与这些工作负载相结合的严格延迟要求结合在一起时，这是有问题的，并带来了一组在以前的工作中没有直接解决的独特挑战。在这项工作中，我们设计了MobiEye，这是一个基于云的视频检测系统，针对实时移动应用进行了优化。与视频检测系统的传统实现相比，MobiEye能够在仅略微降低精度的情况下实现高达32%的延迟减少。
In recent years, machine learning research has largely shifted focus from the cloud to the edge. While the resulting algorithm-and hardware-level optimizations have enabled local execution for the majority of deep neural networks (DNNs) on edge devices, the sheer magnitude of DNNs associated with real-time video detection workloads has forced them to remain relegated to remote execution in the cloud. This problematic when combined with the strict latency requirements that are coupled with these workloads, and imposes a unique set of challenges not directly addressed in prior works. In this work, we design MobiEye, a cloud-based video detection system optimized for deployment in real-time mobile applications. MobiEye is able to achieve up to a 32% reduction in latency when compared to a conventional implementation of video detection system with only a marginal reduction in accuracy.