一个基于YOLO的模型,用于在谷物块表面检测储存的谷物昆虫
Xueyan Zhu1, Dandan Li1,2, Yancheng Zheng3
1School of Technology, Beijing Forestry University, Beijing 100083, China.
Insects
|February 26, 2025
概括
一个新的YOLO-SGInsects模型准确地检测到谷物表面上的微小的储存谷物昆虫. 这种先进的系统通过提高检测和计数精度来改善综合性害虫管理 (IPM).
科学领域:
- 农业科学 农业科学
- 计算机视觉 计算机视觉
- 虫害管理 虫害管理 虫害管理
背景情况:
- 精确检测微小的储存谷物昆虫对于综合性害虫管理 (IPM) 至关重要.
- 现有的检测模型在谷物表面与小昆虫作斗争,并要求高计算资源.
- 需要有效和准确的方法来检测和计数储存的谷物中的昆虫.
研究的目的:
- 开发一种改进的深度学习模型,用于检测和计数在谷物散体表面上存储的微小谷物昆虫.
- 提高现有的物体检测模型的性能,用于在农业环境中小规模检测昆虫.
- 为监测和管理储存粮食害虫提供强大的技术解决方案.
主要方法:
- 一个新的YOLO-SGInsects模型是基于YOLOv8s.s的基础上开发的.
- 关键的修改包括在部添加一个微小的物体检测层 (TODL),一个非对称的特征金字塔网络 (AFPN),以及在脊柱中添加一个混合注意力变压器 (HAT) 模块.
- 该模型使用自定义的GrainInsects数据集进行了训练和验证.
主要成果:
- YOLO-SGInsects模型在存储的谷物中检测昆虫的平均精度 (mAP) 为94.2%.
- 该模型显示,计数中根二次平均误差 (RMSE) 为0.7913.
- 与基线YOLOv8s模型相比,观察到mAP的2.0%和RMSE的0.3067的显著改善.
结论:
- 与主流方法相比,YOLO-SGInsects模型在检测和计数微小的储存谷物昆虫方面提供了卓越的性能.
- 该模型有效地解决了在谷物散装表面检测小昆虫的挑战.
- 这项研究为检测和计数常见的储存谷物害虫提供了基础技术.
更多相关视频
07:36Visualizing Early Infection Sites of Rice Blast Disease Magnaporthe oryzae on Barley Hordeum vulgare Using a Basic Microscope and a Smartphone
Published on: March 17, 2023
1.5K
04:21Author Spotlight: Sieving Fruit Pulp to Detect Immature Tephritid Fruit Flies in the Field
Published on: July 28, 2023
1.6K
相关概念视频
00:48Optimal Foraging
How animals obtain and eat their food is called foraging behavior. Foraging can include searching for plants and hunting for prey and depends on the species and environment.
02:16Light Acquisition
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.