【摘要】 基于规则信息的无人机图像建筑物提取,首先要对待处理图像进行图像分割,经过大量的实验确定分割阈值为0.3,通过定义规则信息,解决了建筑物纹理特征与光谱特征与道路、裸地相似的问题,同时,将原始图像的提取结果和与进行主成分分析(PCA)处理后的图像的提取结果进行对比,证明了PCA后的图像提取精度高达85%。更多还原

【Abstract】 Based on the rule information, the UAV image building extraction firstly needs to process the image for image segmentation. After a large number of experiments, the segmentation threshold is 0.3. By defining the rule information, the problem that the texture features and spectral features of the building are similar to roads and bare land is solved.at the same time, comparing the extraction result of the original image with the extraction result of the image after performing principal component analysis(PCA), it is proved that the image accuracy after PCA is as high as 85%.更多还原