【摘要】 探讨应用高分辨率遥感影像提取城市地区绿地信息。利用自相关函数计算30个绿地样区,结果表明在影像位移2像元时,自相关系数还能达到0.95,从而确定纹理窗口大小为5*5。纹理值计算是在全色影像灰度共生矩阵的基础上,方向取45°、135°、225°、315°4个方向的平均值,计算5个纹理参数:M ean、variance、hom ogeneity、contrast、second m om ent。对全色影像和5个纹理影像进行多分辨率分割,对分割所形成的目标根据绿地5个纹理特征设定阈值,提取出绿地信息,通过精度评定正确率达92.8%。结果表明所采取的方法在高分辨率遥感影像的城市绿地信息的提取上具有很好的应用性。更多还原

【Abstract】 This paper discusses about the extraction of urban green space from high resolution remote sensing image.Computation 30 green space samples using autocorrelation function,the results shows that movement two pixels,the autocorrelation index is up to 0.95,which to ensure texture window as 5*5.Based on panchromatic image grey co-occurrence matrix,selected 45°,135°,225°,315° four directions means,computation five texture parameter : Mean,variance,homogeneity,contrast,second moment.Applicability multi-resolution segmentation panchromatic image and five texture images,according green space five texture feature to select threshold of image objects that after segmentation,extraction green space information,after accuracy appraisal the right up to 92.8%.The result indicated that the method adopted has good utility on extraction urban green space information from high resolution remote sensing image.更多还原