MobiEye: An efficient cloud-based video detection system for real-time mobile applications

Published

Conference Paper

© 2019 Association for Computing Machinery. 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.

Full Text

Duke Authors

Cited Authors

  • Mao, J; Yang, Q; Li, A; Li, H; Chen, Y

Published Date

  • June 2, 2019

Published In

International Standard Serial Number (ISSN)

  • 0738-100X

International Standard Book Number 13 (ISBN-13)

  • 9781450367257

Digital Object Identifier (DOI)

  • 10.1145/3316781.3317865

Citation Source

  • Scopus