Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model

被引:0
|
作者
Li, Zehua [1 ,2 ]
Lin, Yongjun [1 ]
Pan, Yihui [1 ]
Ma, Xu [3 ]
Wu, Xiaola [4 ]
机构
[1] South China Agr Univ, Coll Math & Informat, Guangzhou 510642, Peoples R China
[2] Minist Agr & Rural Affairs, Key Lab Smart Agr Technol Trop South China, Guangzhou 510642, Peoples R China
[3] South China Agr Univ, Sch Engn, Guangzhou 510642, Peoples R China
[4] South China Agr Univ, Zhujiang Coll, Sch Artificial Intelligence, Guangzhou 510900, Peoples R China
来源
AGRONOMY-BASEL | 2024年 / 14卷 / 12期
基金
中国国家自然科学基金;
关键词
seedling density estimation; deep learning; object detection; classification of seedlings; mechanized seedling cultivation;
D O I
10.3390/agronomy14123066
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
In seedling cultivation of hybrid rice, fast estimation of seedling density is of great significance for classifying seedling cultivation. This research presents an improved YOLOv8 model for estimating seedling density at the needle leaf stage. Firstly, the auxiliary frame technology was used to address the problem of locating the detection area of seedlings. Secondly, the Standard Convolution (SConv) layers in the neck network were replaced by the Group Shuffle Convolution (GSConv) layer to lightweight the model. A dynamic head module was added to the head network to enhance the capability of the model to identify seedlings. The CIoU loss function was replaced by the EIoU loss function, enhancing the convergence speed of the model. The results showed that the improved model achieved an average precision of 96.4%; the parameters and floating-point computations (FLOPs) were 7.2 M and 2.4 G. In contrast with the original model, the parameters and FLOPs were reduced by 0.9 M and 0.6 G, and the average precision was improved by 1.9%. Compared with state-of-the-art models such as YOLOv7 et al., the improved YOLOv8 achieved preferred comprehensive performance. Finally, a fast estimation system for hybrid rice seedling density was developed using a smartphone and the improved YOLOv8. The average inference time for each image was 8.5 ms, and the average relative error of detection was 4.98%. The fast estimation system realized portable real-time detection of seedling density, providing technical support for classifying seedling cultivation of hybrid rice.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] A Soybean Pod Accuracy Detection and Counting Model Based on Improved YOLOv8
    Jia, Xiaofei
    Hua, Zhenlu
    Shi, Hongtao
    Zhu, Dan
    Han, Zhongzhi
    Wu, Guangxia
    Deng, Limiao
    AGRICULTURE-BASEL, 2025, 15 (06):
  • [42] Lightweight construction safety behavior detection model based on improved YOLOv8
    Kan Huang
    Mideth B. Abisado
    Discover Applied Sciences, 7 (4)
  • [43] Wheat Seed Detection and Counting Method Based on Improved YOLOv8 Model
    Ma, Na
    Su, Yaxin
    Yang, Lexin
    Li, Zhongtao
    Yan, Hongwen
    SENSORS, 2024, 24 (05)
  • [44] A Method for Tomato Ripeness Recognition and Detection Based on an Improved YOLOv8 Model
    Yang, Zhanshuo
    Li, Yaxian
    Han, Qiyu
    Wang, Haoming
    Li, Chunjiang
    Wu, Zhandong
    HORTICULTURAE, 2025, 11 (01)
  • [45] A Lightweight Forest Pest Image Recognition Model Based on Improved YOLOv8
    Jiang, Tingyao
    Chen, Shuo
    APPLIED SCIENCES-BASEL, 2024, 14 (05):
  • [46] RCT-YOLOv8: A Tuna Detection Model for Distant-Water Fisheries Based on Improved YOLOv8
    Zhou, Qingyi
    Liu, Yuqing
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2024, 28 (06) : 1273 - 1283
  • [47] AppleYOLO: Apple yield estimation method using improved YOLOv8 based on Deep OC-SORT
    Tan, Shiting
    Kuang, Zhufang
    Jin, Boyu
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 272
  • [48] Improved Target Detection With YOLOv8 for GAN Augmented Polarimetric Images Using MIRNet Denoising Model
    Dey, Jaydeep
    Anandan, P.
    Rajagopal, Sonaa
    Mani, Muralikrishnan
    IEEE ACCESS, 2024, 12 : 166885 - 166910
  • [49] A lightweight algorithm for steel surface defect detection using improved YOLOv8
    Ma, Shuangbao
    Zhao, Xin
    Wan, Li
    Zhang, Yapeng
    Gao, Hongliang
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [50] Classification of Ground penetrating radar data using YOLOv8 model
    Goyal, Pramod
    Tarai, Sangeeta
    Maiti, Dr Subrata
    Chongder, Prasun
    2024 IEEE SPACE, AEROSPACE AND DEFENCE CONFERENCE, SPACE 2024, 2024, : 1100 - 1103