Forest species discrimination in an Alpine mountain area using a fuzzy classification of multi-temporal SPOT (HRV) data
Forest species discrimination in an Alpine mountain area using a fuzzy classification of multi-temporal SPOT (HRV) data
复制标题
使用多时相 SPOT (HRV) 数据的模糊分类识别高山地区的森林物种
DOI：
10.1109/igarss.2003.1294501
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
F. Giannetti
中科院分区：
文献类型：
--
作者：
V. Puzzolo;F. D. Natale;F. Giannetti
森林覆盖图显示不同森林类型的位置和范围，是森林监测和规划的基本工具。目前，遥感技术已成为不同尺度森林覆盖分类的重要手段之一。在本文中，中分辨率图像（SPOT HRV）的森林覆盖地图在当地规模的有用性进行了评估（1）和模糊分类方法进行了测试，以增加森林歧视在特定的水平（2）。这项研究是在位于意大利阿尔卑斯山东部的一个山区试验区进行的，该试验区是由意大利农业和森林部建立的RI.SELV.ITALIA项目的一部分。它所依据的是由两幅经过地形校正的SPOT图像和一些地面清单数据组成的一套数据。为了利用不同树种的物候特征提高万年青树种和落叶树种的可分离性，选择了夏秋两季的SPOT影像。首先将双时相图像合并为一幅多时相图像，然后采用最大似然法和模糊分类法对多时相图像进行分类。为了确定最佳的分类程序，两种分类的结果进行了评估，使用独立的地面清单数据，然后进行比较。模糊分类方法在森林物种判别中给出了更准确的结果，而最大似然算法在对地形崎岖和经常存在混交林的复杂景观中的森林覆盖进行分类时显示出一定的局限性。
Forest cover maps, showing the location and the extent of different forest types, are essential tools for forest monitoring and planning. Nowadays, remote sensing is one of the most important source of forest cover classifications at different scales. In this paper, the usefulness of middle resolution images (SPOT HRV) for forest cover mapping at local scale is evaluated (1) and a fuzzy classification approach is tested for increasing forest discrimination at the specific level (2). The study was carried out in a mountain test area located in the eastern Alps of Italy within the RI.SELV.ITALIA project founded by the Italian Ministry of Agriculture and Forests. It was based on a data-set composed of two SPOT images, topographically corrected, and some ground inventory data. The SPOT images, taken in summer and autumn, were selected in order to use the phenology characteristics of the different forest species for improving the separability between evergreen and deciduous species. The bi-temporal images were firstly combined in a single multi-temporal image which was later classified using both maximum likelihood and fuzzy classification methods. In order to identify the best classification procedure, the results of both classifications were evaluated using independent ground inventory data and then compared. The fuzzy classification approach gave more accurate results in forest species discrimination, while the maximum likelihood algorithm showed some limits in classifying the forest cover in such a complex landscapes characterized by rugged terrain and by the frequent presence of mixed forests.