Study on the Detection of Defoliation Effect of an Improved YOLOv5x Cotton

被引:5
|
作者
Wang, Xingwang [1 ,2 ]
Wang, Xufeng [1 ,2 ]
Hu, Can [1 ,2 ]
Dai, Fei [2 ,3 ]
Xing, Jianfei [1 ,2 ]
Wang, Enyuan [1 ,2 ]
Du, Zhenhao [1 ,2 ]
Wang, Long [1 ,2 ]
Guo, Wensong [1 ,2 ]
机构
[1] Tarim Univ, Coll Mech & Elect Engn, Alar 843300, Peoples R China
[2] Tarim Univ, Modern Agr Engn Key Lab Univ Educ Dept Xinjiang U, Alar 843300, Peoples R China
[3] Gansu Agr Univ, Coll Mech & Elect Engn, Lanzhou 730070, Peoples R China
来源
AGRICULTURE-BASEL | 2022年 / 12卷 / 10期
关键词
defoliating agents; cotton detection; deep learning; defoliation effect;
D O I
10.3390/agriculture12101583
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
In order to study the detection effect of cotton boll opening after spraying defoliant, and to solve the problem of low efficiency of traditional manual detection methods for the use effect of cotton defoliant, this study proposed a cotton detection method improved YOLOv5x+ algorithm. Convolution Attention Module (CBAM) was embedded after Cony to enhance the network's feature extraction ability, suppress background information interference, and enable the network to focus better on cotton targets in the detection process. At the same time, the depth separable convolution (DWConv) was used to replace the ordinary convolution (Cony) in the YOLOv5x model, reducing the convolution kernel parameters in the algorithm, reducing the amount of calculation, and improving the detection speed of the algorithm. Finally, the detection layer was added to make the algorithm have higher accuracy in detecting small size cotton. The test results show that the accuracy rate P (%), recall rate R (%), and mAP value (%) of the improved algorithm reach 90.95, 89.16, and 78.47 respectively, which are 8.58, 8.84, and 5.15 higher than YOLOv5x algorithm respectively, and the convergence speed is faster, the error is smaller, and the resolution of cotton background and small target cotton is improved, which can meet the detection of cotton boll opening effect after spraying defoliant.
引用
收藏
页数:15
相关论文
共 50 条
  • [41] Road damage detection algorithm for improved YOLOv5
    Guo, Gege
    Zhang, Zhenyu
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [42] An improved lightweight object detection algorithm for YOLOv5
    Luo, Hao
    Wei, Jiangshu
    Wang, Yuchao
    Chen, Jinrong
    Li, Wujie
    PEERJ COMPUTER SCIENCE, 2024, 10
  • [43] Traffic Sign Detection Based on Improved YOLOv5
    Zhou, Hua-Ping
    Xu, Chen-Chen
    Sun, Ke-Lei
    Journal of Computers (Taiwan), 2023, 34 (03) : 63 - 73
  • [44] Outdoor Garbage Detection Based on Improved YOLOv5
    Chen Shengxuan
    Wang Aimin
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (22)
  • [45] Improved Traffic Sign Detection Method for YOLOv5
    Wei, Qiang
    Hu, Xiaoyang
    Zhao, Hongxin
    Computer Engineering and Applications, 2023, 59 (13) : 229 - 237
  • [46] Fire Detection Based on Improved-YOLOv5s
    Zhou, Mengdong
    Li, Jianjun
    Liu, Shuai
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT IV, 2022, 13532 : 88 - 100
  • [47] Helmet detection method based on improved YOLOv5
    Hou G.
    Chen Q.
    Yang Z.
    Zhang Y.
    Zhang D.
    Li H.
    Gongcheng Kexue Xuebao/Chinese Journal of Engineering, 2024, 46 (02): : 329 - 342
  • [48] Cow Detection Model Based on Improved YOLOv5
    Wang, Wei
    Xie, Mujun
    Jiang, Changhong
    Zheng, Zhong
    Bian, Heyu
    39TH YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION, YAC 2024, 2024, : 1704 - 1708
  • [49] Fish detection method based on improved YOLOv5
    Lei Li
    Guosheng Shi
    Tao Jiang
    Aquaculture International, 2023, 31 : 2513 - 2530
  • [50] Improved YOLOv5 for Small Object Detection Algorithm
    Yu, Jun
    Jia, Yinshan
    Computer Engineering and Applications, 2023, 59 (12) : 201 - 207