作者简介: 孙小芳(1973- ) , 女, 博士生, 现主要从事遥感图像处理及应用方面的研究。Extraction of Green Space in Urban High Resolution Remote Sensing Image

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53 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:Mean、variance、homogeneity、contrast、secondmomen t。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。

Extraction of Green Space in Urban High Resolution Remote Sensing Image

This paper discusses about the extraction of urban green space from high resolution remote sensing image. Computation 30 green space samples using au tocorrelation function, the results shows that movement two pixels, the autocorrelation index is up to 0. 95, which to ensure texture window as 53 5.Based on panchromatic image grey cooccurrence at rix, selected 45°, 135°, 225°, 315°four directions means, computation five textu reparameter : Mean, variance, mogeneity, contrast, secondmoment.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.