您好，欢迎访问湖南省农业科学院 机构知识库！

A Multi-Modal Open Object Detection Model for Tomato Leaf Diseases with Strong Generalization Performance Using PDC-VLD

文献类型： 外文期刊

作者： Li, Jinyang 1 ; Zhao, Fengting 1 ; Zhao, Hongmin 1 ; Zhou, Guoxiong 1 ; Xu, Jiaxin 1 ; Gao, Mingzhou 2 ; Li, Xin 3 ; Dai, Weisi 1 ; Zhou, Honliang 1 ; Hu, Yahui 4 ; He, Mingfang 1 ;

作者机构： 1.Cent South Univ Forestry & Technol, Changsha 410004, Hunan, Peoples R China

2.Inner Mongolia Agr Univ, Hohhot 010010, Inner Mongolia, Peoples R China

3.Inner Mongolia Univ, Hohhot 010021, Inner Mongolia, Peoples R China

4.Hunan Acad Agr Sci, Plant Protect Inst, Changsha 410125, Hunan, Peoples R China

期刊名称：PLANT PHENOMICS （ 影响因子：6.4； 五年影响因子：7.1 ）

ISSN： 2643-6515

年卷期： 2024 年 6 卷

页码：

收录情况： SCI

摘要： Precise disease detection is crucial in modern precision agriculture, especially in ensuring the health of tomato crops and enhancing agricultural productivity and product quality. Although most existing disease detection methods have helped growers identify tomato leaf diseases to some extent, these methods typically target fixed categories. When faced with new diseases, extensive and costly manual annotation is required to retrain the dataset. To overcome these limitations, this study proposes a multimodal model PDC-VLD based on the open-vocabulary object detection (OVD) technology within the VLDet framework, which can accurately identify new tomato leaf diseases without manual annotation by using only imagetext pairs. First, we developed a progressive visual transformer-convolutional pyramid module (PVT-C) that effectively extracts tomato leaf disease features and optimizes anchor box positioning using the self-supervised learning algorithm DINO, suppressing interference from irrelevant backgrounds. Then, a context feature guided module (CFG) was adopted to address the low adaptability and recognition accuracy of the model in data-scarce environments. To validate the model's effectiveness, we constructed a tomato leaf disease image dataset containing 4 base classes and 2 new categories. Experimental results show that the PDC-VLD model achieved 61.2% on the main evaluation metric mAP50 novel, and 56.4% on mAP75 novel, 87.7% on mAP50 base, 81.0% on mAP50 all, and 45.5% on average recall, outperforming existing OVD models. Our research provides an innovative solution for efficiently and accurately detecting new diseases, substantially reducing the need for manual annotation, and offering critical technical support and practical reference for agricultural workers.

  • 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：湖南省农业科学院

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