Object‐based large‐scale terrain classification combined with segmentation optimization and terrain features: A case study in China
Object‐based large‐scale terrain classification combined with segmentation optimization and terrain features: A case study in China
复制标题
基于对象的大尺度地形分类结合分割优化和地形特征：以中国为例
DOI：
10.1111/tgis.12795
复制
发表时间：
2021-07
影响因子：
2.4
通讯作者：
Norbert Pfeifer
中科院分区：
文献类型：
--
作者：
Jiaming Na;Hu Ding;Wufan Zhao;Kai Liu;Guoan Tang;Norbert Pfeifer
地形分类是地貌学、景观调查、区域规划、灾害预测等领域的重要内容。大多数现有的方法是基于一个简单的阈值方法。然而，这种方法在准确性和鲁棒性方面受到限制，特别是对于大规模任务。为了克服这一局限性，本文提出了一种结合随机森林的基于对象的框架。首先利用谢菲尔德熵进行相关分析，筛选出地形起伏度、地表粗糙度、高程、高程系数变异、地形起伏度和累积曲率等6个地形因子。得到的分割结果，然后优化莫兰的我和加权方差，结合地形因素和纹理来自数字高程模型。然后，在地形因子及其灰度共生矩阵纹理中选择特征。最后，特征被送入随机森林分类器。划分了平原、丘陵、低山、低中山、高中山、高山、极高山7种地貌类型。在中国进行了一个案例研究，并实现了80.53%的整体精度与官方地形图，这是更好的性能相比，半自动方法。我们的框架的可移植性进一步证实了一个额外的应用程序在省级规模的地图与不同的分类系统。
Terrain classification involves essential tasks in geomorphology, landscape investigation, regional planning, and hazard prediction. Most existing methods are based on a simple thresholding approach. However, such an approach is limited in terms of accuracy and robustness, especially for large‐scale tasks. To overcome this limitation, this article proposes an object‐based framework combined with the random forest. Six terrain factors, namely terrain relief, surface roughness, elevation, elevation coefficient variation, shaded relief, and accumulative curvature, are first selected by correlation analysis using Sheffield's entropy. The obtained segmentation result is then optimized by Moran's I and the weighted variance, combining both terrain factors and textures derived from digital elevation models. Then, the features are selected among both terrain factors and their gray‐level co‐occurrence matrix textures. Finally, the features are fed into the random forest classifier. Seven landform types are classified, including plain, hill, low mountain, low‐middle mountain, high‐middle mountain, high mountain, and extremely high mountain. A case study in China was conducted and achieved an overall accuracy of 80.53% compared with the official landform atlas, which is better performance over the compared semi‐automatic methods. The transferability of our framework was further confirmed by an additional application in provincial‐scale mapping with a different classification system.
登录
查看更多内容
影响因子：
5.1
作者：
Alvioli, Massimiliano;Marchesini, Ivan;Guzzetti, Fausto
通讯作者：
Guzzetti, Fausto
考虑分段内和分段间异质性的区域合并：一种改进的混合遥感图像分割方法
影响因子：
5
作者：
Wang Yongji;Qi Qingwen;Meng Qingyan;Yang Jian;Liu Ying
通讯作者：
Liu Ying
影响因子：
3.9
作者：
R. Shruthi;N. Kerle;V. Jetten;A. Stein
通讯作者：
R. Shruthi;N. Kerle;V. Jetten;A. Stein
DOI：
10.1016/j.geomorph.2014.02.028
发表时间：
2014-06-01
期刊：
Geomorphology (Amsterdam, Netherlands)
影响因子：
--
作者：
Eisank C;Smith M;Hillier J
通讯作者：
Hillier J
DOI：
10.1111/j.1467-8306.1964.tb00470.x
发表时间：
1964-01-01
期刊：
ANNALS OF THE ASSOCIATION OF AMERICAN GEOGRAPHERS
影响因子：
--
作者：
HAMMOND, EH
通讯作者：
HAMMOND, EH