APP下载

城镇化背景下基于时序TM/NDVI的建成区检测方法

2016-04-06马丹刘曙光陈雯虹

土木建筑与环境工程 2016年1期

马丹 刘曙光 陈雯虹

摘要:对1990—2010年49景福州市TM时间序列影像进行处理,采用MODTRAN4+模型进行大气校正,得到研究区土地覆盖类型的NDVI值的多时相轨迹图。分析城镇化背景下建成区的变化特征和NDVI时间序列数据的季节特征,添加耕地发展为建设用地的地物特征到学习样本,比较不同数据组合对最大似然法、支持向量机、神经网络法、面向对象法对分类和检测城镇化背景下建设用地精度的影响,以及比较添加样本特征后对城镇化进程中建设用地检测方法的影响。结果表明,对于小样本数据集,面向对象法具有最高的分类精度,不同的数据组合与不同季节对面向对象法分类精度的影响分别达3.49%和5.22%,引入NDVI时间序列数据和添加变化地物的学习样本,总体分类精度提高了3.54%,建设用地的制图精度提高了4.24%。

关键词:土地覆盖;时序影像;面向对象法;福州

中图分类号:TP751.1

文献标志码:A文章编号:16744764(2016)01012906

Abstract:

Atmospheric corrections were conducted with the MODTRAN4+ model for 49 TM data from 1990 to 2010 in Fuzhou. Multitemporal trajectories of major land cover type were derived from NDVI images. The trends of Mean NDVI were analyzed. To investigate the influence of different data combination on the classification and detection accuraly of different methods,induding maximum likelihood classification, support vector machine, artificial neural network, and objectoriented methods, and compared the deteetion methods before and after adding a sample, the areas converted from cropland to builtup land were added to the learning sample. The results show that the objectoriented method is the most accurate method compared with other methods for a small sample. By using the method, the classification accuracy improves up to 3.53% and 4.24% for different data combination and different season respectively.Adding NDVI data and the sample of changing features improves 3.54% of the whole classification accuracy and 4.24% of drawing accuracy of the buidup land.

Keywords:land cover;time series of images;objectoriented methods;Fuzhou

遥感技术是监测城市发展和变化的主要手段。利用时间域与NDVI数据成为城镇化过程中建成区检测的发展趋势[17]。 过去,一般都是利用两到三景遥感图像,较少利用多个时间序列与季节的信息进行监测城镇化发展进程 [89]。城镇化过程中,一般发展为新城区的主要是耕地,其他土地类型比重很小,而且城区一般不太可能被转回为耕地。因此,主要关注耕地与建设用地的混分问题。一年中至少有一个季节会被种上植被的概率较高,通过多个年份和不同季节的数据可以区分城镇化过程中发展的新城区和休耕地。……

登录APP查看全文