使用深度学习从无人机遥感图像中识别田杂草
Zhonghui Guo1,2,3, Dongdong Cai1,2,3, Yunyi Zhou1,2,3
1School of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang, 110866, China.
Plant methods
|July 16, 2024
概括
这项研究介绍了RMS-DETR,这是一种用于增强大米田杂草检测的新型网络. 该模型在复杂的环境中准确识别杂草,有助于精准农业和可变速率喷雾系统.
科学领域:
- 计算机视觉 计算机视觉
- 农业技术 农业技术
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 准确的田杂草检测对于农业中精确喷至关重要.
- 传统方法在复杂的农场环境中与小,封闭或密集的杂草作斗争.
研究的目的:
- 提出一个多尺度功能增强的DETR网络 (RMS-DETR) 改进田杂草识别.
- 解决现有物体检测模型在现实世界农业场景中的局限性.
主要方法:
- 在DETR模型上实现了多级特征提取分支.
- 利用变压器来获取高层次的上下文信息,使用CNN来获取低层次的细节.
- 采用部分卷积 (Pconv) 来优化模型计算和推理速度.
主要成果:
- 在定制数据集上,RMS-DETR的平均识别精度提高了3.6%,在DOTA数据集上提高了4.4%.
- 平均准确度分别为0.792和0.851 .
- 性能优于经典的DETR变体,平均精度显著提高.
结论:
- 在复杂的现实条件下,RMS-DETR准确地识别了田杂草.
- 为农业中的精密喷雾和可变速率喷雾系统提供必要的技术支持.
相关概念视频
Light Acquisition
8.4K
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.
8.4K
Responses to Drought and Flooding
10.6K
Water plays a significant role in the life cycle of plants. However, insufficient or excess of water can be detrimental and pose a serious threat to plants.
10.6K


