基于WorldView-2的红树林种群分类——以深圳湾为例

Classification of Mangrove Population Based on WorldView-2——A Case Study of Shenzhen Bay

本文以WorldView-2多光谱遥感影像数据为数据源,选取深圳湾地区的红树林自然保护区为研究区域,基于ENVI5.3选用神经网络、支持向量机和随机森林三种分类方法对该区域的红树林进行种群分类,并对分类结果进行了对比分析。结果表明:随机森林分类法总体精度为73.6842%Kappa系数为0.6780,优于其余两种分类法。

In this paper,worldview-2 multi-spectral remote sensing image data was used as the data source,mangrove nature reserve in shenzhen bay area was selected as the research area,and three classification methods including neural network,support vector machine and random forest were used to classify mangrove population in this area based on ENVI5.3,and the classification results were compared and analyzed.The results show that the overall accuracy of random forest classification is 73.6842%and the Kappa coefficient is 0.6780,which is better than the other two classification methods.