您好，欢迎访问浙江省农业科学院 机构知识库！
浙江省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Implementing transfer learning for citrus Huanglongbing disease detection across different datasets using neural network

文献类型： 外文期刊

作者： Huang, Deyao 1 ; Xiao, Kangsong 1 ; Luo, Hairong 1 ; Yang, Biyun 3 ; Lan, Shiying 1 ; Jiang, Yutong 1 ; Li, You 4 ; Ye, Dapeng 1 ; Sun, Dawei 5 ; Weng, Haiyong 1 ;

作者机构： 1.Fujian Agr & Forestry Univ, Coll Mech & Elect Engn, Fuzhou 350002, Peoples R China

2.Fujian Key Lab Agr Informat Sensing Technol, Fuzhou 350002, Peoples R China

3.Coll Marine Mech & Elect Engn, Xiamen Ocean Vocat Coll, Xiamen 361012, Peoples R China

4.Fujian Agr & Forestry Univ, Coll Plant Protect, Fuzhou 350002, Peoples R China

5.Inst Agr Equipment, Zhejiang Acad Agr Sci, Hangzhou 310021, Peoples R China

关键词： Citrus Huanglongbing; Mask-RCNN; Transfer learning; Domain adaptation

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.9； 五年影响因子：9.3 ）

ISSN： 0168-1699

年卷期： 2025 年 238 卷

页码：

收录情况： SCI

摘要： Citrus Huanglongbing (HLB) is highly contagious, and timely detection and removal of HLB-infected citrus trees is extremely important to prevent its spread. However, the robustness of optical imaging-based models remains limited by the variations in data due to different plant varieties, geospatial conditions, and data collection dates, etc. This study aimed to propose a method for robust HLB detection via transfer learning with multispectralmulticolor imaging. Four lightweight neural networks, namely Yolov7, Yolov7-tiny, Yolov4-tiny, and MaskRCNN were introduced for citrus HLB disease detection across different datasets. Transfer learning on the Orah mandarin dataset was conducted using the Navel orange dataset for pre-training. The results showed that Mask-RCNN achieved the best performance with an mAP@0.5 of 91.65%. By replacing the backbone of MaskRCNN with MobileNetV3-large, the model Mask-RCNNV3 was established, with an mAP@0.5 of 93.37% and then used for transfer learning for other datasts. Further optimizing the number of transferred layers and sample size, it revealed the most favorable sample size was 20 per class, and the mAP@0.5 gradually increased at the first 9 layers. Mask-RCNNV3 under the best transfer learning parameters, called Mask-RCNNV3_best, achieved the mAP@0.5 of 93.14% for Orah mandarin, 91.82% for Blood orange and 92.36% for Ponkan, respectively. Compared to the original Mask-RCNN model, the training parameters (Params) and GFLOPs were reduced by 82.95% and 96.57%, respectivley. It demonstrated that a limited amount of labeled data proved sufficient to achieve satisfactory performance across the tested cultivars and growing conditions. The FPS of the model was also improved by 4 times compared to Mask-RCNN, illustrating the potential of the model for edge deployment for practical applications. These findings would bridge the gap between research and practical implementation, reduce costly labeling for model training and provide practical tools for citrus growers to use.

  • 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：浙江省农业科学院

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