Abstract
To make the cherry defect detection and identification system meet the real-time requirements, it was proposed to use the convolutional neural network model as the basis and used the SDSoC development platform to complete the design of FPGA for rapid detection and identification of cherry defects. By optimizing data transmission, multiplexing the general matrix multiplication function (GEMM) in the network model and parallelizing the design of the convolution operation, PL-side hardware acceleration was realized. Using the SDSoC platform, a high-level language mapping convolutional neural network model was used on the PS-side, which saved a lot of development time while achieving the required performance. The results showed that, compared with the pure software method, the speed based on the Zynq7020 hardware development platform had increased by more than 2.19 times. Compared with the CPU platform, the speed was almost the same.
Publication Date
2-18-2023
First Page
129
Last Page
134, 165
DOI
10.13652/j.issn.1003-5788.2020.08.023
Recommended Citation
Yue-kun, PEI; Yu, GU; and Ming-yue, LIAN
(2023)
"Design of fast cherry defect detection and recognition system based on FPGA,"
Food and Machinery: Vol. 36:
Iss.
8, Article 23.
DOI: 10.13652/j.issn.1003-5788.2020.08.023
Available at:
https://www.ifoodmm.cn/journal/vol36/iss8/23
References
[1] LAUER F,SUEN C Y,BLOCH G.A trainable feature extractor for handwritten digit recognition[J].Pattern Recognition,2007,40(6):1 816-1 824.
[2] SHUSTANOV A,YAKIMOV P.CNN design for real-time traffic sign recognition[J].Procedia Engineering,2017,201:718-725.
[3] 刘云,杨建滨,王传旭.基于卷积神经网络的苹果缺陷检测算法[J].电子测量技术,2017,40(3):108-112.
[4] 裴悦琨,连明月,姜艳超,等.基于机器视觉的樱桃缺陷检测与识别[J].食品与机械,2019,35(12):137-140,226.
[5] 伍锡如,雪刚刚,刘英璇.基于深度学习的水果采摘机器人视觉识别系统设计[J].农机化研究,2020,42(2):177-182,188.
[6] 秦东辉,周辉,赵雄波,等.基于卷积神经网络图像识别算法的加速实现方法[J].航天控制,2019,37(1):22-27.
[7] 王巍,周凯利,王伊昌,等.卷积神经网络(CNN)算法的FPGA并行结构设计[J].微电子学与计算机,2019,36(4):57-62,66.
[8] MA Yu-fei,SUDA N,CAO Yu,et al.ALAMO:FPGA acceleration of deep learning algorithms with a modularized RTL compiler[J].Integration,2018,62(6):14-23.
[9] 訾晶,张旭欣,金婕.基于FPGA动态重构的快速车牌识别系统[J].传感器与微系统,2019,38(12):69-72.
[10] DANOPOULOS D,KACHRIS C,SOUDRIS D.Acceleration of image classification with Caffe framework using FPGA[C]//2018 7th International Conference on Modern Circuits and Systems Technologies(MOCAST).Thessaloniki:IEEE,2018:1-4.
[11] RETTKOWSKI J,BOUTROS A,GHRINGER D.HW/SW Co-Design of the HOG algorithm on a Xilinx Zynq SoC[J].Journal of Parallel and Distributed Computing,2017,109(11):50-62.
[12] 吴进,赵隽,李聪,等.机器视觉中边缘检测算法的SDSoC加速实现[J].计算机工程与应用,2019,55(12):208-214.
[13] Vivado design suite user guide high-level synthesis UG902(v2017.3)[EB/OL].[2017-10-04].http://china.Xilinx.com/support/documentation.