Camellia oleifera Fruit Detection in Natural Scene Based on YOLO v5s

被引：0
|
作者：
Song H. [1 ,2 ]
Wang Y. [1 ,2 ]
Wang Y. [1 ,2 ]
Lü S. [1 ,2 ]
Jiang M. [1 ,2 ]
机构：
[1] College of Mechanical and Electronic Engineering, Northwest A&F University, Shaanxi, Yangling
[2] Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Shaanxi, Yangling
来源：
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2022年 / 53卷 / 07期
关键词：
Camellia oleifera fruits; data enhancement; deep learning; natural scene; object detection; YOLO v5s;
D O I：
10.6041/j.issn.1000-1298.2022.07.024
中图分类号：
学科分类号：
摘要：
In view of the characteristics of small size, dense distribution and changeable color of Camellia oleifera fruit, in order to realize the rapid and accurate identification of Camellia oleifera fruit in complex natural scene, and determine the appropriate clamping position for the automatic oscillating harvesting device according to the density distribution of the fruit, the YOLO v5s convolutional neural network model was used to carry out research on the image detection method of Camellia oleifera fruit in the natural scene. Through data enhancement, totally 3 296 Camellia oleifera fruit images were obtained to make the PASCAL VOC data set. After 150 rounds of training, the optimal weight model was got. The accurate rate was 90. 73%, the recall rate was 98. 38%, the comprehensive evaluation index was 94. 4%, the average detection accuracy was 98. 71%, the single image detection time was 12. 7 ms, and the memory size of the model was 14. 08 MB. Compared with the current mainstream first-stage detection algorithms YOLO v4 - tiny and RetinaNet, its accuracy rate was increased by 1. 99 percentage points and 4. 50 percentage points, the recall rate was increased by 9. 41 percentage points and 10. 77 percentage points, and the time was reduced by 96. 39% and 96. 25%, respectively. In addition, the weight file of the YOLO v5s model was small, indicating that its network was simpler and had the advantage of rapid deployment. It could be transplanted to edge devices in the future to provide algorithm reference for the vision system of the Camellia oleifera fruit automatic harvesting device. Through comparative experiment, the results also showed that the model can achieve high-precision recognition and positioning of fruits in dense, occluded, dim environments and fuzzy blur conditions, and it had strong robustness. The research results can provide a reference for the research of mechanical harvesting of Camellia oleifera fruit under the natural complex environment. © 2022 Chinese Society of Agricultural Machinery. All rights reserved.
引用
收藏
页码：234 / 242
页数：8
相关论文
共 28 条
  • [11] LI Lijun, YANG Hanjiang, Revised detection and localization algorithm for Camellia oleifera fruits based on convex hull theory [J], Transactions of the Chinese Society for Agricultural Machinery, 47, 12, pp. 285-292, (2016)
  • [12] ZHANG Xizhi, LI Lijun, Research of image recognition of Camellia oleifera fruit based on improved convolutional auto-encoder [J], Journal of Forestry Engineering, 4, 3, pp. 118-124, (2019)
  • [13] CHEN Bin, RAO Honghui, LIU Muhua, Recognition of Camellia oleifera fruit based on Fourier descriptor and Hu invariant moments [J], Journal of Zhejiang Agricultural Sciences, 61, 9, pp. 1876-1880, (2020)
  • [14] REDMON J, FARHADI A., YOLO 9000: better, faster, stronger [C], IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517-6525, (2017)
  • [15] REDMON J, DIVVALA S, GIRSHICK R, Et al., You only look once: unified, real-time object detection, IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [16] LI Juxia, LI Yanwen, NIU Fan, Et al., Pig diet behavior detection method based on YOLO v4 [J], Transactions of the Chinese Society for Agricultural Machinery, 52, 3, pp. 251-256, (2021)
  • [17] ZHAO Dean, WU Rendi, LIU Xiaoyang, Et al., Apple positioning based on YOLO deep convolutional neural network for picking robot in complex background [J], Transactions of the CSAE, 35, 3, pp. 164-173, (2019)
  • [18] XUE Yueju, HUANG Ning, TU Shuqin, Et al., Immature mango detection based on improved YOLO v2, Transactions of the CSAE, 34, 7, pp. 173-179, (2018)
  • [19] TIAN Yunong, YANG Guodong, WANG Zhe, Et al., Apple detection during different growth stages in orchards using the improved YOLO - V3 model [J], Computers and Electronics in Agriculture, 157, pp. 417-426, (2019)
  • [20] HE Dongjian, LIU Jiamin, XIONG Hongting, Et al., Individual identification of dairy cow based on improved YOLO v3 network [J], Transactions of the Chinese Society for Agricultural Machinery, 51, 4, pp. 250-260, (2020)
123