SODA: Similar 3D Object Detection Accelerator at Network Edge for Autonomous Driving

Offloading the 3D object detection from autonomous vehicles to MEC is appealing because of the gains on quality, latency, and energy. However, detection requests lead to repetitive computations since the multitudinous requests share approximate detection results. It is crucial to reduce such fuzzy r...

Full description

Saved in:
Bibliographic Details
Main Authors: Xu, Wenquan, Song, Haoyu, Hou, Linyang, Zheng, Hui, Zhang, Xinggong, Zhang, Chuwen, Hu, Wei, Wang, Yi, Liu, Bin
Format: Conference Proceeding
Language:English
Subjects:
Encoding
Image edge detection
Object detection
Partitioning algorithms
Redundancy
System performance
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Offloading the 3D object detection from autonomous vehicles to MEC is appealing because of the gains on quality, latency, and energy. However, detection requests lead to repetitive computations since the multitudinous requests share approximate detection results. It is crucial to reduce such fuzzy redundancy by reusing the previous results. A key challenge is that the requests mapping to the reusable result are only similar but not identical. An efficient method for similarity matching is needed to justify the use case. To this end, by taking advantage of TCAM's ap-proximate matching capability and NMC's computing efficiency, we design SODA, a first-of-its-kind hardware accelerator which sits in the mobile base stations between autonomous vehicles and MEC servers. We design efficient feature encoding and partition algorithms for SODA to ensure the quality of the similarity matching and result reuse. Our evaluation shows that SODA significantly improves the system performance and the detection results exceed the accuracy requirements on the subject matter, qualifying SODA as a practical domain-specific solution.
ISSN:2641-9874
DOI:10.1109/INFOCOM42981.2021.9488833