Scholarlink

<p>The excessive use of pesticides poses significant environmental and health risks. A real-time disease detection system can help mitigate this issue by identifying early infections and applying treatment only to affected areas. Building on the work of (P. P. Than), who conducted an exhaustive study on chilli anthracnose and the pathogenicity of Colletotrichum species, we utilize disease severity and spread indicators to enhance dataset annotation. Specifically, we classify infection levels based on affected areas, enabling precise disease detection. In this paper, we evaluate our method on a dataset of 6010 images, implementing a three-class classification system to determine the severity of fruit infections. This classification aids in calculating the optimal pesticide quantity required for specific areas. We assess the performance of YOLOv8 and YOLOv9 models in detecting infection levels, even in cases of minor disease spots. Among them, YOLOv8 demonstrated superior accuracy, achieving a mean average precision (mAP) of 92.7%, compared to YOLOv9’s 83.5%. The proposed method reduces pesticide usage by enabling targeted treatment and containment of infected areas. Furthermore, this enrichment improves plant disease understanding, optimizes workflows, and supports more informed decision-making in precision agriculture.</p>

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

Targeted detection of plant disease infection levels using YOLOv8 and YOLOv9 for agricultural monitoring and public healthcare support

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月21日

查看全文
  • Abdelkarim Lahmdani,
  • Abdessamad Elboushaki,
  • Sahar Saoud

摘要

The excessive use of pesticides poses significant environmental and health risks. A real-time disease detection system can help mitigate this issue by identifying early infections and applying treatment only to affected areas. Building on the work of (P. P. Than), who conducted an exhaustive study on chilli anthracnose and the pathogenicity of Colletotrichum species, we utilize disease severity and spread indicators to enhance dataset annotation. Specifically, we classify infection levels based on affected areas, enabling precise disease detection. In this paper, we evaluate our method on a dataset of 6010 images, implementing a three-class classification system to determine the severity of fruit infections. This classification aids in calculating the optimal pesticide quantity required for specific areas. We assess the performance of YOLOv8 and YOLOv9 models in detecting infection levels, even in cases of minor disease spots. Among them, YOLOv8 demonstrated superior accuracy, achieving a mean average precision (mAP) of 92.7%, compared to YOLOv9’s 83.5%. The proposed method reduces pesticide usage by enabling targeted treatment and containment of infected areas. Furthermore, this enrichment improves plant disease understanding, optimizes workflows, and supports more informed decision-making in precision agriculture.