《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (10): 3332-3341.DOI: 10.11772/j.issn.1001-9081.2025091148

• 多媒体计算与计算机仿真 • 上一篇    

面向小目标优化的棉叶病害智能诊断模型

哈里旦木・阿布都克里木, 张耿荣, 梁宇涵, 魏安然, 阿布都克力木・阿布力孜()   

  1. 新疆财经大学 信息管理学院,乌鲁木齐 830012
  • 收稿日期:2025-09-28 修回日期:2025-12-19 接受日期:2025-12-24 发布日期:2026-01-21 出版日期:2026-10-10
  • 通讯作者: 阿布都克力木?阿布力孜
  • 作者简介:哈里旦木·阿布都克里木(1978—),女(维吾尔族),新疆伊宁人,教授,博士,CCF会员,主要研究方向:自然语言处理、农业人工智能
    张耿荣(2001—),女,山西长治人,硕士研究生,主要研究方向:农业人工智能
    梁宇涵(2001—),女,湖北十堰人,硕士研究生,主要研究方向:农业人工智能
    魏安然(2000—),男,山东济南人,硕士研究生,主要研究方向:农业人工智能
  • 基金资助:
    国家自然科学基金资助项目(62566061);国家自然科学基金资助项目(62366050)

Small-target-oriented intelligent diagnosis model for cotton leaf diseases

Abudukelimu HALIDANMU, Gengrong ZHANG, Yuhan LIANG, Anran WEI, Abulizi ABUDUKELIMU()   

  1. School of Information Management,Xinjiang University of Finance and Economics,Urumqi Xinjiang 830012,China
  • Received:2025-09-28 Revised:2025-12-19 Accepted:2025-12-24 Online:2026-01-21 Published:2026-10-10
  • Contact: Abulizi ABUDUKELIMU
  • About author:HALIDANMU Abudukelimu, born in 1978, Ph. D., professor. Her research interests include natural language processing, agricultural artificial intelligence.
    ZHANG Gengrong, born in 2001, M. S. candidate. Her research interests include agricultural artificial intelligence.
    LIANG Yuhan, born in 2001, M. S. candidate. Her research interests include agricultural artificial intelligence.
    WEI Anran, born in 2000, M. S. candidate. His research interests include agricultural artificial intelligence.
  • Supported by:
    National Natural Science Foundation of China(62566061)

摘要:

近年来农作物病害的智能治理已取得一定进展,但棉叶病害因目标尺度小、边界模糊仍面临重大挑战,且缺乏实现“识别?诊断?决策”一体化的模型。为解决上述问题,提出了棉叶病害智能诊断模型。首先,创建了包含1 320条数据的棉花种植问答数据集,为后续通义千问大语言模型的微调提供数据基础;其次,在YOLOv12n主干网络末端引入多尺度简单注意力模块(MSSimAM),以突出多尺度病害相关特征并抑制冗余信息;在检测头部采用自适应阈值焦点损失(ATFL)函数,以缓解难易样本不平衡问题,从而形成MN-YOLO模型;最后,集成MN-YOLO与微调后的通义千问大语言模型,基于检测结果生成病害防治方案。实验结果表明,MN-YOLO在保持较低参数量的情况下,交并比(IoU)阈值为0.5的平均精度均值(mAP50)达到96.9%,相较于YOLOv12n提升了2.0个百分点,精确率和召回率分别提升0.5和4.5个百分点。在不同数据集上的泛化实验中,所提模型也表现出较强的适应性和稳定性。该棉叶病害智能诊断模型集成了病害检测与防治方案推荐功能,在提升检测精度的同时,也为农业智能化提供了有效支撑。

关键词: 棉叶病害, YOLOv12, 小目标检测, 病害防治, 智慧农业

Abstract:

Recently, intelligent management of crop diseases has made considerable progress. However, cotton leaf disease still poses significant challenges due to small target sizes and blurred leaf boundaries, and there is a lack of models that integrate “recognition-diagnosis-decision-making.” Therefore, an intelligent diagnosis model for cotton leaf diseases was proposed. First, a dataset containing 1 320 entries of cotton cultivation question and answer was constructed to provide data basis for subsequent fine-tuning of the Tongyi Qianwen large language model. Second, the Multi-Scale Simple Attention Module (MSSimAM) was introduced at the end of the YOLOv12n backbone to highlight multi-scale disease-related features and suppress redundant information. Third, in the detection head, the Adaptive Threshold Focal Loss (ATFL) function was employed to address the imbalance between easy and hard samples, thereby forming the MN-YOLO model. Finally, MN-YOLO model was integrated with the fine-tuned Tongyi Qianwen large language model to generate disease prevention and treatment measure recommendations based on the detection results. Experimental results indicates that MN-YOLO model achieves a mean Average Precision at Intersection over Union (IoU) threshold of 0.5 (mAP50) of 96.9% while maintaining a low parameter count, representing increases of 2.0 percentage points in mAP50, 0.5 percentage points in precision, and 4.5 percentage points in recall compared with YOLOv12n. In generalization experiments, the proposed model also demonstrates strong adaptability and stability across different datasets. The results indicate that this diagnosis model for cotton leaf diseases combines disease detection and treatment measure recommendation, improving detection precision while providing effective support for smart agriculture.

Key words: cotton leaf disease, YOLOv12, small target detection, disease prevention and treatment, smart agriculture

中图分类号: