Land cover classification using moderate resolution satellite imagery and random forests with post-hoc smoothing
Land cover classification using moderate resolution satellite imagery and random forests with post-hoc smoothing
复制标题
DOI：
10.1080/14498596.2013.819600
复制
发表时间：
2013-09-01
影响因子：
1.9
通讯作者：
Zhu, Xuan
中科院分区：
文献类型：
--
作者：
Zhu, Xuan
目前已有多种影像分类方法用于土地覆盖制图。其中，分类树及其新的改进，如随机森林(RF)，已被证明是有效的。然而，这些基于树的方法通常执行每个像素的分类，这通常会产生分散的错误分类的次优结果。本文建议应用平滑技术来解决这一问题，并将后自组织平滑与RF相结合，用于使用中分辨率遥感图像和辅助数据进行土地覆盖分类。利用Rf为每种类型的土地覆盖生成概率图，使用平滑技术对概率图进行平滑，然后对平滑后的概率图应用最大概率规则，通过将每个像素分配到类别概率最高的类别来生成土地覆盖图。利用Landsat Theme Mapper(TM)影像和地形数据，将该方法应用于中国九寨沟自然保护区的土地覆盖分类，并对各向异性扩散、高斯、均值和中值滤波等几种不同平滑方法的分类精度进行了评估和比较。结果表明，与未经平滑处理的土地覆盖分类相比，RF结合后自组织平滑处理的土地覆盖分类的总体精度提高了6%，Kappa统计量提高了9%，在5%的显著水平上，所有平滑后的土地覆盖图与未平滑的土地覆盖图相比，基于Kappa的精度差异有统计学意义。
Various image classification methods have been developed for land cover mapping. Among them, classification trees and their new modifications, such as random forests (RF), have proven effective. However, these tree-based methods typically perform per-pixel classification, which often produces suboptimal results with scattered misclassifications. This paper recommends applying smoothing techniques to address the problem and combines post-hoc smoothing with RF for land cover classification using moderate resolution remote sensing imagery and ancillary data. RF is used to produce probability maps for each type of land cover, a smoothing technique is employed to smooth the probability maps and then a maximum probability rule is applied on the smoothed probability maps to generate a land cover map by assigning each pixel to the class with highest class probability. This method was applied to classify land cover in the Jiuzhaigou Nature Reserve in China using Landsat Thematic Mapper (TM) Images and topographic data, and the classification accuracies with several different smoothing techniques, including anisotropic diffusion, Gaussian, mean and median filtering, were assessed and compared. The results demonstrated that RF combined with post-hoc smoothing improved the overall accuracy by up to 6 percent and the Kappa statistic by up to 9 percent over the land cover classification without a smoothing process, and at the 5 percent significance level, all the smoothed land cover maps had a statistically significant difference in accuracy based on Kappa compared with the unsmoothed map.