数字农科院2.0

Fast and accurate detection of kiwifruits in the natural environment using improved YOLOv4

文献类型： 外文期刊

作者： Jin Peng Wang;Lei Xu;Song Mei;Hao Ruo Hu;Jia Liang Zhou;Qing Chen

作者机构：

关键词： fruit recognition;kiwifruits;natural environments;YOLOv4

期刊名称： International Journal of Agricultural and Biological Engineering

ISSN： 1934-6344

年卷期： 2024 年 17 卷 5 期

页码：

收录情况： SCIE（2024版） ; ; 农林核心（2020版）

摘要： Real-time detection of kiwifruits in natural environments is essential for automated kiwifruit harvesting. In this study, a lightweight convolutional neural network called the YOLOv4-GS algorithm was proposed for kiwifruit detection. The backbone network CSPDarknet-53 of YOLOv4 was replaced with GhostNet to improve accuracy and reduce network computation. To improve the detection accuracy of small targets, the upsampling of feature map fusion was performed for network layers 151 and 154, and the spatial pyramid pooling network was removed to reduce redundant computation. A total of 2766 kiwifruit images from different environments were used as the dataset for training and testing. The experiment results showed that the F1-score, average accuracy, and Intersection over Union (IoU) of YOLOv4-GS were 98.00%, 99.22%, and 88.92%, respectively. The average time taken to detect a 416×416 kiwifruit image was 11.95 ms, and the model’s weight was 28.8 MB. The average detection time of GhostNet was 31.44 ms less than that of CSPDarknet-53. In addition, the model weight of GhostNet was 227.2 MB less than that of CSPDarknet-53. YOLOv4-GS improved the detection accuracy by 8.39% over Faster R-CNN and 8.36% over SSD-300. The detection speed of YOLOv4-GS was 11.3 times and 2.6 times higher than Faster R-CNN and SSD-300, respectively. In the indoor picking experiment and the orchard picking experiment, the average speed of the YOLOv4-GS processing video was 28.4 fps. The recognition accuracy was above 90%. The average time spent for recognition and positioning was 6.09 s, accounting for about 29.03% of the total picking time. The overall results showed that the YOLOv4-GS proposed in this study can be applied for kiwifruit detection in natural environments because it improves the detection speed without compromising detection accuracy.

分类号：

  • 相关文献

[1]基于改进YOLOv4算法的苹果叶部病害缺陷检测研究. 王权顺,吕蕾,黄德丰,付思琴,余华云. 2022

[2]基于改进YOLOv4的田间密集小目标检测方法. 杨军奇,冯全,王书志,张建华,杨森. 2022

[3]Research on Flesh Texture and Quality Traits of Kiwifruit (cv. Xuxiang) with Fluctuating Temperatures during Cold Storage. Ranran Xu,Qian Chen,Yizhao Zhang,Jiali Li,Jiahua Zhou,Yunxiang Wang,Hong Chang,Fanxiang Meng,Baogang Wang. 2023

[4]Quantitative Proteomic Analysis for High- and Low-Aflatoxin-Yield Aspergillus flavus Strains Isolated From Natural Environments. Tao Li,Zhaowei Zhang,Yu Wang,Ying Li,Jiang Zhu, Rui Hu,Yunhuang Yang,Maili Liu. 2021

作者其他论文 更多>>