A Lightweight Cherry Tomato Maturity Real-Time Detection Algorithm Based on Improved YOLOV5n

被引:19
|
作者
Wang, Congyue [1 ,2 ]
Wang, Chaofeng [1 ,2 ]
Wang, Lele [2 ]
Wang, Jing [1 ,2 ]
Liao, Jiapeng [1 ,2 ]
Li, Yuanhong [1 ,2 ]
Lan, Yubin [1 ,2 ,3 ,4 ]
机构
[1] South China Agr Univ, Coll Elect Engn, Coll Artificial Intelligence, Guangzhou 510642, Peoples R China
[2] South China Agr Univ, Natl Ctr Int Collaborat Res Precis Agr Aviat Pesti, Guangzhou 510642, Peoples R China
[3] South China Agr Univ, Guangdong Lab Lingnan Modern Agr, Guangzhou 510642, Peoples R China
[4] Texas A&M Univ, Dept Biol & Agr Engn, College Stn, TX 77843 USA
来源
AGRONOMY-BASEL | 2023年 / 13卷 / 08期
关键词
precision agriculture; YOLOv5; cherry tomato; maturity detection; CA; WIoU; COLOR;
D O I
10.3390/agronomy13082106
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
To enhance the efficiency of mechanical automatic picking of cherry tomatoes in a precision agriculture environment, this study proposes an improved target detection algorithm based on YOLOv5n. The improvement steps are as follows: First, the K-means++ clustering algorithm is utilized to update the scale and aspect ratio of the anchor box, adapting it to the shape characteristics of cherry tomatoes. Secondly, the coordinate attention (CA) mechanism is introduced to expand the receptive field range and reduce interference from branches, dead leaves, and other backgrounds in the recognition of cherry tomato maturity. Next, the traditional loss function is replaced by the bounding box regression loss with dynamic focusing mechanism (WIoU) loss function. The outlier degree and dynamic nonmonotonic focusing mechanism are introduced to address the boundary box regression balance problem between high-quality and low-quality data. This research employs a self-built cherry tomato dataset to train the target detection algorithms before and after the improvements. Comparative experiments are conducted with YOLO series algorithms. The experimental results indicate that the improved model has achieved a 1.4% increase in both precision and recall compared to the previous model. It achieves an average accuracy mAP of 95.2%, an average detection time of 5.3 ms, and a weight file size of only 4.4 MB. These results demonstrate that the model fulfills the requirements for real-time detection and lightweight applications. It is highly suitable for deployment in embedded systems and mobile devices. The improved model presented in this paper enables real-time target recognition and maturity detection for cherry tomatoes. It provides rapid and accurate target recognition guidance for achieving mechanical automatic picking of cherry tomatoes.
引用
收藏
页数:24
相关论文
共 50 条
  • [31] An improved lightweight and real-time YOLOv5 network for detection of surface defects on indocalamus leaves
    Zhe Tang
    Lin Zhou
    Fang Qi
    Huarong Chen
    Journal of Real-Time Image Processing, 2023, 20
  • [32] Real-time vehicle detection algorithm based on a lightweight You-Only-Look-Once (YOLOv5n-L) approach
    Bie, Minglin
    Liu, Yanyan
    Li, Guoning
    Hong, Jintao
    Li, Jin
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 213
  • [33] Real-Time Ship Detection Algorithm Based on Improved YOLOv8 Network
    Chen, Wei-Zhe
    Hao, Li-Ying
    Liu, Huiying
    Zhang, Yunze
    2023 IEEE 2ND INDUSTRIAL ELECTRONICS SOCIETY ANNUAL ON-LINE CONFERENCE, ONCON, 2023,
  • [34] Real-Time Jellyfish Classification and Detection Based on Improved YOLOv3 Algorithm
    Gao, Meijing
    Bai, Yang
    Li, Zhilong
    Li, Shiyu
    Zhang, Bozhi
    Chang, Qiuyue
    SENSORS, 2021, 21 (23)
  • [35] An improved YOLOv5n algorithm for detecting surface defects in industrial components
    Tian, Jia-Hui
    Feng, Xue-Feng
    Li, Feng
    Xian, Qing-Long
    Jia, Zhen-Hong
    Liu, Jie-Liang
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [36] Implementation of YOLOv5 for Real-Time Maturity Detection and Identification of Pineapples
    Trinh, Trung Hai
    Nguyen, Ha Huy Cuong
    TRAITEMENT DU SIGNAL, 2023, 40 (04) : 1445 - 1455
  • [37] Real-Time Detection Algorithm for Small-Target Traffic Signs Based on Improved YOLOv5
    Hu, Junping
    Wang, Hongshu
    Dai, Xiaobiao
    Gao, Xiaolin
    Computer Engineering and Applications, 59 (02): : 185 - 193
  • [38] Improved YOLOv5n Pipeline DR Defect Image Detection Method
    Shi, Yanan
    Chen, Zhiyuan
    Liu, Zhaoying
    Chen, Yingchun
    Zhang, Ting
    Fan, Xiaoli
    Miao, Rui
    Ye, Wei
    Computer Engineering and Applications, 2024, 60 (12) : 366 - 372
  • [39] YOLOv5s-Cherry: Cherry Target Detection in Dense Scenes Based on Improved YOLOv5s Algorithm
    Gai, Rongli
    Li, Mengke
    Wang, Zumin
    Hu, Lingyan
    Li, Xiaomei
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2023, 32 (12)
  • [40] Research on Real-Time Forestry Pest Detection Based on Improved YOLOv5
    Yu, Jipeng
    Tan, Taizhe
    Deng, Yaoyu
    ADVANCES IN COMPUTER GRAPHICS, CGI 2022, 2022, 13443 : 515 - 526