SODA: Similar 3D object detection accelerator at network edge for autonomous driving

Xu，Wenquan1; Song，Haoyu2; Hou，Linyang1; Zheng，Hui3; Zhang，Xinggong3; Zhang，Chuwen1; Hu，Wei3; Wang，Yi4,5; Liu，Bin1,5

10.1109/INFOCOM42981.2021.9488833

2021-05-10

0743-166X

978-1-6654-3131-6

Proceedings - IEEE INFOCOM

2021-May

1-10

10-13 May 2021

Vancouver, BC, Canada

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.

Three-dimensional displays System performance Image edge detection Redundancy Object detection Encoding Partitioning algorithms

其他

英语

CPCI-S ; EI

Computer Science ; Engineering ; Telecommunications

Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Telecommunications

WOS:000702210400167

20213210732796

Autonomous vehicles ; Chemical detection ; Object recognition

Data Processing and Image Processing:723.2 ; Chemistry:801

2-s2.0-85111921013

Scopus

1.Tsinghua University,China
2.Futurewei Technologies,United States
3.Peking University,China
4.Southern University of Science and Technology,China
5.Peng Cheng Laboratory,China

Xu，Wenquan,Song，Haoyu,Hou，Linyang,et al. SODA: Similar 3D object detection accelerator at network edge for autonomous driving[C],2021:1-10.