Design and Experiment of Precision Spray-type Adaptive Weeder for Paddy Fields

WANG Jinfeng, ZHU Pengyun, CHU Yuhang, XU Chen, SONG Yuling, WANG Yijia

Abstract

Weed control in paddy fields is a key agronomic measure to improve rice yield, and chemical weed control is widely used because of its high efficiency. Traditional chemical weed control relies on manual operation and often uses large area spraying, which increases the operation cost and causes negative problems such as environmental pollution. Based on this background, a precision spraying type paddy weeder for adaptive weeding operation was designed. The weeder spraying device and system were constructed, and the weed detection system with MS YOLO v7 as the core framework was designed based on the constructed diversified paddy field weed dataset. The MS YOLO v7 model combined the backbone network with MobileOne, and replaced the CIoU loss function with the SIoU loss function. The model performance was verified by ablation test and different model comparison test, and the results showed that the model recognition accuracy was 95.65% , the mean average precision ( mAP) was 92.67% , and the real-time performance reached 51.29 f / s. The IR model was reasoned by using OpenVINO on Raspberry Pi, and the detection of a single paddy field weed image took 0.806 s. The constructed spraying system can instantly capture and analyze the transmission signals from the weed detection system, and then realize the precise regulation of the weed spraying device. The results of the field test showed that the precision spraying type paddy field adaptive weeder had a seedling injury rate of 2.95% , a target application accuracy of 94.98% , and a coefficient of variation of 0.128% , which met the agronomic requirements for weed control in paddy fields. The weeder realized the unmanned operation of paddy field weeding and it can provide technical reference for the intelligent development of agriculture.

 

Keywords: paddy weeder, precision spraying, adaptive, deep learning, YOLO v7

 

Download Full Text:

PDF


References


JABRAN К, CHAU HAN В S. Weed management in aerobic rice systems [J ]. Crop Protection, 2015, 78: 151 -163.

KHATUN A, WATERS D L E, LIU L. A review of rice starch digestibility: effect of composition and heat-moisture processing [J]. Starch-Starke, 2019 , 71(9-10): 1900090.

YU F H, JIN Z Y, GUO S E, et al. Research on weed identification method in rice fields based on UAV remote sensing [J]. Frontiers in Plant Science, 2022, 13; 1037760.

ZHANG Weirong. The identification technology research of corn seedlings and weeds based on machine vision to target application system[ D]. Shihezi: Shihezi University, 2021. (in Chinese)

YIN Dongfu, CHEN Shuren, MAO Hanping,et al. Weed control system for variable target spraying based on fuzzy control [J].Transactions of the Chinese Society for Agricultural Machinery, 2011, 42(4): 179 -183. (in Chinese)

QUAN Longzhe, ZHANG Jingyu, JIANG Wei,et al. Development and experiment of intra-row weeding robot system based on protection of maize root system [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2021 , 52(12): 115 - 123. (in Chinese)

GENZE N, AJEKWE R, GUERELI Z, et al. Deep learning-based early weed segmentation using motion blurred UAV images of sorghum fields [J]. Computers and Electronics in Agriculture, 2022, 202: 107388.

JI Wenli, LIU Zhou, XING Haihua. Lightweight method for identifying farmland weeds based on YOLO 5 [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55( 1) : 212 -222, 293. (in Chinese)

CAO Yingli, ZHAO Yuwei, YANG Lulu, et al. Weed identification method in rice field based on improved DeepLabv3 + [ J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54( 12) : 242 -252. (in Chinese)

XIAO Ke, HAO Vi, GAO Guandong. Design and experiment of automatic variable-distance precison spraying system in orchard) [J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53( 10) ; 137 - 145. (in Chinese)

HAN Changjie, ZHENG Kang, ZHAO Xueguan, et al. Design and experiment of row identification and row-oriented spray control system for field cabbage crops [J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(6): 89 - 101. (in Chinese)

WU Bing. The acquisition of weed phenotype information based on instance segmentation and development of target application system [D]. Harbin: Northeast Agricultural University, 2021. (in Chinese)

THENMOZH1 K, REDDY U S. Crop pest classification based on deep convolutional neural network and transfer learning [J]. Computers and Electronics in Agriculture, 2019, 164: 104906.

ZHAl Zhaoyu,ZHANG Zihan, XU Huanliang, et al. Review of applying YOLO family algorithms to analyze animal and plant phenotype [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2024,55(11) : 1 -20. (in Chinese)

WANG С Y, BOCHKOVSKIY A, LIAO H Y M. YOLO v7; trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C] // Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2023: 7464 -7475.

ZHANG Zhen, ZHOU Jun, JIANG Zizhen, et al. Lightweight apple recognition method in natural orchard environment based on improved YOLO v7 model [J] . Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(3) : 231 -242. (in Chinese)

LI Z Y, LI B, N1 H J, et al. An effective surface defect classification method based on RepVGG with CBAM attention mechanism ( RepVGG - CBAM) for aluminum profiles[ J ]. Metals, 2022, 12(11): 1809.

WANG Hongle, YE Quanzhou, WANG Xinglin, et al. Rice panicles counting method based on YOLO v7 using unmanned aerial vehicles images[J] . Guangdong Agricultural Sciences, 2023, 50(7) ; 74 -82. (in Chinese)


Refbacks

  • There are currently no refbacks.