Design and Experiment of Garlic Harvesting and Root Cutting Device Based on Deep Learning Target Determination

YANG Ke, HU Zhichao, YU Zhaoyang, PENG Baoliang, ZHANG Yanhua, GU Fengwei

Abstract

In order to study a suitable intelligent root cutting device for garlic combined harvesting, a non-contact bulb root (rutting method with machine vision was proposed, and a garlic root (rutting test bench based on a deep convolutional neural network was designed afterwards. Specially, the test bench adopted a deep learning theory to perform target detection on the collected images, through using the APP software in Matlab to complete the human-computer interaction. Then, the results presented that the deep convolutional neural network could determine the cutting position of the garlic root, and the motor control system could adjust the position of the double disc cutting automatically, ensuring the root cutting process completed by the root knife. Target comparison tests showed that bulb ( availability rate was 94. 79% , confidence score was 0. 976 97) was suitable for detecting, among the three kinds of bulb, root plate and garlic root. Comparison tests of detection models performed with ten models based on Faster R — CNN, SSD, YOLO v2, YOLO v3 and YOLO v4. The improved YOLO v2 model combined the detection speed and accuracy (the detection time in the test program was 0.052 3 s, and the confidence score was 0.968 49), where ResNet50 was selected as the feature extraction network; by using the improved YOLO v2 model, the root cutting test took bulbs as the targets (the confidence score was 0. 970 99, the availability rate was 96. 67% , the qualified rate of cutting roots was 95. 33% , and the detection time in the APP was 0. 088 7 s), (ran meet the requirements of garlic combined harvesting and cutting roots.

Keywords: convolutional neural network, YOLO, garlic harvester, root cutting device


Download Full Text:

PDF


References


YU Zhaoyang,HU Zhichao, YANG Ke,et al. Operation mechanism analysis and parameter optimization of garlic root floating cutting device[JJ. Transactions of the Chinese Society for Agricultural Machinery ,2021 ,52(5) : 11 1 - 1 19. (in Chinese)

ZHAO Dong,CAI Dongmei,QIN Lixiang,et al. Design and experiment of modularized garlic combine harvester [ J]. Transactions of the Chinese Society for Agricultural Machinery ,2020 ,51 (4) : 95 - 102. (in Chinese)

YU Zhaoyang,HU Zhichao, WANG Haiou,et al. Parameters optimization and experiment of garlic picking mechanism [ J ]. Transactions of the CSAE,2015 ,31 ( 1 ) ;40 -46. (in Chinese)

YU Zhaovang,HU Zhichao, Y ANG Ke,et al. Design and experiment of root cutting device in garlic combine harvesting [ J ]. Transactions of the CSAE,2016 ,32( 22 ) ; 77 -85. (in Chinese)

HOU JiaIin,HUANG Shenghai,NIU Ziru,et al. Mechanism analysis and test of adjusting garlics upwards using two duckbill devices[J]. Transactions of the Chinese Society for Agricultural Machinery ,2018 ,49( 1 1 ) :87 -96. ( in Chinese)

PENG Baoliang,L( Xiaolian, WANG Haiou,et al. Half-feed and self-propelled garlic combine harvester[ J ]. Transactions of the Chinese Society for Agricultural Machinery ,201 1 ,42(Supp. ) ; 138 - 141 ,146. (in Chinese)

W ANG Houxin,LI Tianhua,WU Yanqiang,et al. Research status and prospects of garlic harvesting machinery [ J ] . Journal of Chinese Agricultural Mechanization ,2018 ,39( 6 ) ; 102 - 107. (in Chinese)

YANG Ke. Research and optimization design of cutting mechanism in garlic combine harvesting [D]. Beijing;Chinese Academy of Agricultural Sciences,2015. (in Chinese)

YANG Ke,HU Zhichao,PENG Baoliang,et al. Research and test of garlic mechanical cutting roots technology[ J ]. Journal of Chinese Agricultural Mechanization ,2015 ,36( 3 ) ; 15 3 - 159. (in Chinese)

LI Xiang, DING Qing,SUN Jianqiao. Remaining useful life estimation in prognostics using deep convolution neural networks [J]. Reliability Engineering & System Safety ,2018 ,172 :1 - 11.

XU Huanliang, SUN Yunxiao, CAO Xuelian,et al. Apple quality detection based on photon transmission simulation and convolutional neural network[ J ]. Transactions of the Chinese Society for Agricultural Machinery ,2021 ,52(8) :338 -345. ( in Chinese)

YE Changwen,YU Zhenwei,KANG Rui,et al. An experimental study of stunned state detection for broiler chickens using an improved convolution neural network algorithm[ J ]. Computers and Electronics in Agriculture,2020 ,170 :105284.

WU Dihua,Lt) Shuaichao,JIANG Mei,et al. Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments [ J ]. Computers and Electronics in Agriculture, 2020, 178 :105742.

I10U Jialin,TIAN Lin,LI Tianhua,et al. Design and experiment of test bench for garlic bulbil adjustment and seeding based on bilateral image identification [ J ]. Transactions of the CSAE ,2020,36 ( 1 ) :50 -58. (in Chinese)

LI Yuhua,LIU Quancheng,LI Tianhua,et al. Design and experiments of garlic bulbil orientation adjustment device using Jetson Nano processor [J ]. Transactions of the CSAE,2021 ,37(7) : 35 -42. (in Chinese)

YUAN Peisen,SIIEN Chengji,XU Huanliang. Fine-grained mushroom phenotype recognition based on transfer learning and bilinear CNN [J]. Transactions of the Chinese Society for Agricultural Machinery,2021 ,52(7) : 151 - 158. (in Chinese)

HE Jinrong, SHI Yanxin, LIU Bin, et al. External quality grading method of Fuji apple based on deep learning [ J ]. Transactions of the Chinese Society for Agricultural Machinery,2021 ,52(7) :379 -385. (in Chinese)


Refbacks

  • There are currently no refbacks.