Author(s): Ning, K (Ning, Ke); Zhao, MX (Zhao, Mingxin); Yao, CH (Yao, Chunhe); Zheng, XM (Zheng, Xuemin); Xu, MM (Xu, Mengmeng); Wu, NJ (Wu, Nanjian); Liu, LY (Liu, Liyuan); Yu, SM (Yu, Shuangming)

Source: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS Volume: 69 Issue: 3 Pages: 1677-1681 DOI: 10.1109/TCSII.2021.3125487 Published: MAR 2022

Abstract: With the development of artificial intelligence research, the convolutional neural networks (CNN) triumphantly continue to conquer diverse visual tasks, with lots of technical and practical problems emerging. When the detection networks need to meet the high-speed processing requirement and the low power consumption constraint in edge computing, dedicated circuits and algorithm optimization are necessary. In this brief, we propose a non-maximum suppression (NMS) coprocessor that cooperated with a Vision Processor (VP) to speed up the detection. It contains a parallel process unit and dynamic memory management to accelerate NMS processing. Meanwhile, the software workflow provides a comprehensive method to convert the one-stage detection network to our processor in a post-training manner. The experimental results show that our co-design solution reaches 166 FPS to run a MobileNet-SSD, promising to deploy in edge-computing scenarios. Moreover, the detection accuracy on the Airbus dataset is 88.6%, favorable in practical applications.

Accession Number: WOS:000770045800206

Author Identifiers:

Author        Web of Science ResearcherID        ORCID Number

Xu, Mengmeng                  0000-0001-6379-7940

ISSN: 1549-7747

eISSN: 1558-3791

Full Text: https://ieeexplore.ieee.org/document/9601285