AMS-YOLO:用于针对玉米害虫的智能植物保护的多级特征集成
Leilei Deng1,2, Di Fang1, Aziz Ullah1
1College of Information and Technology, Jilin Agricultural University, Changchun, China.
Frontiers in plant science
|October 20, 2025
概括
这项研究介绍了AMS-YOLO,这是一个先进的AI模型,用于准确检测玉米害虫,提高作物产量和质量. 这种轻量级模型在资源有限的农业环境中提供了高性能.
科学领域:
- 农业科学 农业科学
- 计算机视觉 计算机视觉
- 人工智能的人工智能
背景情况:
- 玉米是全球重要的粮食作物,受到害虫威胁,影响产量和质量.
- 目前的害虫检测方法与各种害虫外观,相似性和复杂的现场条件作斗争.
- 准确有效地识别害虫对于有效的农业管理和可持续的作物保护至关重要.
研究的目的:
- 开发一种针对玉米害虫的增强检测模型,克服现有方法的局限性.
- 在具有挑战性的农业环境中提高玉米害虫识别的准确性和效率.
- 为精准农业应用创建一个轻量级和可部署的模型.
主要方法:
- 开发了AMS-YOLO,这是一个基于YOLOv8n的增强检测模型.
- 集成了三个协同作用的模块:SMCA注意力机制,MSBlock多尺度特征融合,以及AMConv优化下采样.
- 在13种常见的玉米害虫的数据集上训练和评估模型,跨越发展阶段.
主要成果:
- AMS-YOLO实现了90.0%的精度,89.8%的回忆率和94.2%的mAP50,表现优于YOLOv8n.
- 与其他最先进的方法 (如SSD和RT-DETR) 相比,表现出卓越的性能.
- 该模型重量轻 (5.3MB),参数和计算要求降低,适用于Jetson Nano等边缘设备.
结论:
- 通过有针对性的架构改进,AMS-YOLO有效地解决了玉米害虫检测方面的挑战.
- 该模型的轻量级设计和高精度使其能够在资源有限的环境中进行现场部署.
- 这一进步支持精确的农药应用,资源优化和智能植物保护,以实现可持续农业.
相关概念视频
Light Acquisition
9.4K
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.
9.4K
Plant Breeding and Biotechnology
21.4K
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.
21.4K
Defenses Against Pathogens and Herbivores
29.5K
Plants present a rich source of nutrients for many organisms, making it a target for herbivores and infectious agents. Plants, though lacking a proper immune system, have developed an array of constitutive and inducible defenses to fend off these attacks.
29.5K


