地理空间信息2024，Vol.22Issue(8)：41-44,4.DOI:10.3969/j.issn.1672-4623.2024.08.009
利用U-Net神经网络的多光谱图像草地特征提取
Grass Feature Extraction for Multi-spectral Images Based on U-Net Neural Network
王德传1
作者信息
- 1. 中煤浙江测绘地理信息有限公司,浙江 杭州 310021
- 折叠
摘要
Abstract
In this paper,we proposed a feature analysis method incorporating U-Net neural network for grass recognition in multi-spectral imag-es,which addressed the problems of fusion of waveband information,large amount of computational data and easy confusion of contextual se-mantic information in feature extraction of UAV multi-spectral images.Firstly,we preprocessed the images,and eliminated undesirable interfer-ences through HO correction,radiation correction and image alignment.Then,we used principal component analysis and correlation analysis to select the feature bands.Finally,we built a U-Net neural network to extract grass features and identify the extent of grass in the sample images.The simulation experiments show that the method has high feature recognition and extraction accuracy and is feasible.关键词
多光谱图像/草地特征提取/U-Net神经网络/语义信息辨识Key words
multi-spectral image/grass feature extraction/U-Net neural network/semantic information recognition分类
天文与地球科学引用本文复制引用
王德传..利用U-Net神经网络的多光谱图像草地特征提取[J].地理空间信息,2024,22(8):41-44,4.
