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
  • [21] Microalgae detection based on improved YOLOv5
    Duan, Ziqiang
    Xie, Ting
    Wang, Lucai
    Chen, Yang
    Wu, Jie
    IET IMAGE PROCESSING, 2024, 18 (10) : 2602 - 2613
  • [22] BDC-YOLOv5: a helmet detection model employs improved YOLOv5
    Lihong Zhao
    Turdi Tohti
    Askar Hamdulla
    Signal, Image and Video Processing, 2023, 17 : 4435 - 4445
  • [23] BDC-YOLOv5: a helmet detection model employs improved YOLOv5
    Zhao, Lihong
    Tohti, Turdi
    Hamdulla, Askar
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (08) : 4435 - 4445
  • [24] YOLOv5-OCDS: An Improved Garbage Detection Model Based on YOLOv5
    Sun, Qiuhong
    Zhang, Xiaotian
    Li, Yujia
    Wang, Jingyang
    ELECTRONICS, 2023, 12 (16)
  • [25] Improved YOLOv5 Smoke Detection Model
    Zheng, Yuanpan
    Xu, Boyang
    Wang, Zhenyu
    Computer Engineering and Applications, 2023, 59 (07): : 214 - 221
  • [26] DDVC-YOLOv5: An Improved YOLOv5 Model for Road Defect Detection
    Zhong, Shihao
    Chen, Chunlin
    Luo, Wensheng
    Chen, Siyuan
    IEEE ACCESS, 2024, 12 : 134008 - 134019
  • [27] Improved YOLOv5 for Road Disease Detection
    Wu, Guangfu
    Liangl, Longxin
    Liu, Hao
    Li, Yun
    2024 6TH INTERNATIONAL CONFERENCE ON DATA-DRIVEN OPTIMIZATION OF COMPLEX SYSTEMS, DOCS 2024, 2024, : 781 - 786
  • [28] Improved YOLOv5 Method for Fall Detection
    Peng, Jun
    He, Yuanmin
    Jin, Shangzhu
    Dai, Haojun
    Peng, Fei
    Zhang, Yuhao
    2022 IEEE 17TH CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), 2022, : 504 - 509
  • [29] Weed detection in cotton farming by YOLOv5 and YOLOv8 object detectors
    Kanade, Aditya Kamalakar
    Potdar, Milind P.
    Kumar, Aravinda
    Balol, Gurupada
    Shivashankar, K.
    EUROPEAN JOURNAL OF AGRONOMY, 2025, 168
  • [30] An Improved YOLOv5x-Based Algorithm for IC Pin Welding Defects Detection
    Wang, Xueying
    Li, Mengyun
    Hu, Xiaofeng
    Guo, Bin
    INFORMATION TECHNOLOGY AND CONTROL, 2024, 53 (02): : 509 - 521