Skip to main content

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

Publication ,  Conference
Mao, J; Yang, Q; Li, A; Li, H; Chen, Y
Published in: Proceedings - Design Automation Conference
June 2, 2019

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.

Duke Scholars

Published In

Proceedings - Design Automation Conference

DOI

ISSN

0738-100X

Publication Date

June 2, 2019
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Mao, J., Yang, Q., Li, A., Li, H., & Chen, Y. (2019). MobiEye: An efficient cloud-based video detection system for real-time mobile applications. In Proceedings - Design Automation Conference. https://doi.org/10.1145/3316781.3317865
Mao, J., Q. Yang, A. Li, H. Li, and Y. Chen. “MobiEye: An efficient cloud-based video detection system for real-time mobile applications.” In Proceedings - Design Automation Conference, 2019. https://doi.org/10.1145/3316781.3317865.
Mao J, Yang Q, Li A, Li H, Chen Y. MobiEye: An efficient cloud-based video detection system for real-time mobile applications. In: Proceedings - Design Automation Conference. 2019.
Mao, J., et al. “MobiEye: An efficient cloud-based video detection system for real-time mobile applications.” Proceedings - Design Automation Conference, 2019. Scopus, doi:10.1145/3316781.3317865.
Mao J, Yang Q, Li A, Li H, Chen Y. MobiEye: An efficient cloud-based video detection system for real-time mobile applications. Proceedings - Design Automation Conference. 2019.

Published In

Proceedings - Design Automation Conference

DOI

ISSN

0738-100X

Publication Date

June 2, 2019