您好，欢迎访问上海市农业科学院 机构知识库！
上海市农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

An Enhanced YOLOv5 Model for Greenhouse Cucumber Fruit Recognition Based on Color Space Features

文献类型： 外文期刊

作者： Wang, Ning 1 ; Qian, Tingting 2 ; Yang, Juan 2 ; Li, Linyi 2 ; Zhang, Yingyu 2 ; Zheng, Xiuguo 2 ; Xu, Yeying 2 ; Zhao, Hanqing 3 ; Zhao, Jingyin 3 ;

作者机构： 1.Shanghai Ocean Univ, Coll Informat Technol, Shanghai 201306, Peoples R China

2.Shanghai Acad Agr Sci, Inst Agr Sci & Technol Informat, Shanghai 201403, Peoples R China

3.Shanghai Engn Res Ctr Informat Technol Agr, Shanghai 201403, Peoples R China

4.Minist Agr & Rural Affairs, Key Lab Intelligent Agr Technol Changjiang Delta, Shanghai 201403, Peoples R China

5.Henan Agr Univ, Coll Informat & Management Sci, Zhengzhou 450046, Peoples R China

6.Shanghai Assoc Senior Scientists & Technicians, Shanghai 200070, Peoples R China

关键词： deep learning; color space; ReliefF characteristic analysis; near color recognition

期刊名称：AGRICULTURE-BASEL （ 影响因子：3.408； 五年影响因子：3.459 ）

ISSN：

年卷期： 2022 年 12 卷 10 期

页码：

收录情况： SCI

摘要： The identification of cucumber fruit is an essential procedure in automated harvesting in greenhouses. In order to enhance the identification ability of object detection models for cucumber fruit harvesting, an extended RGB image dataset (n = 801) with 3943 positive and negative labels was constructed. Firstly, twelve channels in four color spaces (RGB, YCbCr, HIS, La*b*) were compared through the ReliefF method to choose the channel with the highest weight. Secondly, the RGB image dataset was converted to the pseudo-color dataset of the chosen channel (Cr channel) to pre-train the YOLOv5s model before formal training using the RGB image dataset. Based on this method, the YOLOv5s model was enhanced by the Cr channel. The experimental results show that the cucumber fruit recognition precision of the enhanced YOLOv5s model was increased from 83.7% to 85.19%. Compared with the original YOLOv5s model, the average values of AP, F1, recall rate, and mAP were increased by 8.03%, 7%, 8.7%, and 8%, respectively. In order to verify the applicability of the pre-training method, ablation experiments were conducted on SSD, Faster R-CNN, and four YOLOv5 versions (s, l, m, x), resulting in the accuracy increasing by 1.51%, 3.09%, 1.49%, 0.63%, 3.15%, and 2.43%, respectively. The results of this study indicate that the Cr channel pre-training method is promising in enhancing cucumber fruit detection in a near-color background.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：上海市农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台