北京测绘2024，Vol.38Issue(6)：930-935,6.DOI:10.19580/j.cnki.1007-3000.2024.06.019
基于无人机测绘图像的大面积地形变化特征提取方法
A method for extracting features of large-area terrain changes based on unmanned aerial vehicle surveying and mapping images
摘要
Abstract
In order to solve the problem of poor feature extraction performance for large-scale terrain changes,a feature extraction method for large-scale terrain changes based on unmanned aerial vehicle(UAV)surveying and mapping images was proposed.Image information captured by UAVs was collected using the information reconstruction method,and the terrain edge scale was calculated.The large-area images were preprocessed using image filtering algorithms.Terrain feature parameters were measured and calculated,and terrain change features were decomposed using weighted full polarization.The feature differentiation effect was enhanced through feature selection factors and feature judgment factors,and terrain features were classified using synthetic aperture radar(SAR)feature classification methods.The optimal weighted SAR feature dataset was processed through random forests and classifiers.Terrain change feature extraction was completed based on the voting results of the decision tree.Experiments have shown that after the application of the proposed method,the size of large-scale terrain features best matches the actual values,and the time required to extract features from mountainous and flat areas is shorter.The overall feature extraction effect is good,making it easy to quickly adjust the surveying and mapping path and parameters and thus achieving real-time monitoring of terrain changes.关键词
特征提取/数字高程模型/图像滤波算法/地形曲率/无人机测绘Key words
feature extraction/digital elevation model/image filtering algorithm/terrain curvature/unmanned aerial vehicle(UAV)surveying and mapping分类
天文与地球科学引用本文复制引用
邱龙..基于无人机测绘图像的大面积地形变化特征提取方法[J].北京测绘,2024,38(6):930-935,6.基金项目
国家自然科学基金(41431178) （41431178）
