Scholarlink

Cotton is the most important agricultural product in Burkina Faso, and it is farmed by 25% of the country's population. Cotton diseases, on the other hand, are a big issue for this crop, contributing considerably to output losses. These disorders are detected manually, which increases the time required for therapy. Artificial intelligence techniques can help enhance cotton production by automatically recognizing these diseases. This research aims to detect cotton diseases using UAV photos obtained in the field. We used the YOLOv7 detection model fine-tuned on the tomato leaves dataset and subsequently applied to the cotton leaves dataset. On the cotton dataset, experimental results from the YOLOv7 model yielded mAP@0.50 (mean average precision), f1score, Precision, and Recall of 50.7%, 55.4%, 53.7%, and 57.4%, respectively.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Cotton Disease Detection on UAV Images: A Deep Learning-Based Approach with YOLOv7

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zakaria Kinda,
  • Sadouanouan Malo,
  • Thierry Roger Bayala,
  • Issa Wonni

摘要

Cotton is the most important agricultural product in Burkina Faso, and it is farmed by 25% of the country's population. Cotton diseases, on the other hand, are a big issue for this crop, contributing considerably to output losses. These disorders are detected manually, which increases the time required for therapy. Artificial intelligence techniques can help enhance cotton production by automatically recognizing these diseases. This research aims to detect cotton diseases using UAV photos obtained in the field. We used the YOLOv7 detection model fine-tuned on the tomato leaves dataset and subsequently applied to the cotton leaves dataset. On the cotton dataset, experimental results from the YOLOv7 model yielded mAP@0.50 (mean average precision), f1score, Precision, and Recall of 50.7%, 55.4%, 53.7%, and 57.4%, respectively.