State Key Laboratory of Resources and Environmental Information System, Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China.
PLoS One. 2013 Oct 28;8(10):e75852. doi: 10.1371/journal.pone.0075852. eCollection 2013.
The classification of land cover based on satellite data is important for many areas of scientific research. Unfortunately, some traditional land cover classification methods (e.g. known as supervised classification) are very labor-intensive and subjective because of the required human involvement. Jiang et al. proposed a simple but robust method for land cover classification using a prior classification map and a current multispectral remote sensing image. This new method has proven to be a suitable classification method; however, its drawback is that it is a semi-automatic method because the key parameters cannot be selected automatically. In this study, we propose an approach in which the two key parameters are chosen automatically. The proposed method consists primarily of the following three interdependent parts: the selection procedure for the pure-pixel training-sample dataset, the method to determine the key parameters, and the optimal combination model. In this study, the proposed approach employs both overall accuracy and their Kappa Coefficients (KC), and Time-Consumings (TC, unit: second) in order to select the two key parameters automatically instead of using a test-decision, which avoids subjective bias. A case study of Weichang District of Hebei Province, China, using Landsat-5/TM data of 2010 with 30 m spatial resolution and prior classification map of 2005 recognised as relatively precise data, was conducted to test the performance of this method. The experimental results show that the methodology determining the key parameters uses the portfolio optimisation model and increases the degree of automation of Jiang et al.'s classification method, which may have a wide scope of scientific application.
基于卫星数据的土地覆盖分类对于许多科学研究领域都非常重要。不幸的是，一些传统的土地覆盖分类方法（例如监督分类）由于需要人工参与，因此非常耗费人力并且具有主观性。蒋等人提出了一种使用先验分类图和当前多光谱遥感图像进行土地覆盖分类的简单但鲁棒的方法。事实证明，这种新方法是一种合适的分类方法；但是，其缺点是它是一种半自动方法，因为关键参数无法自动选择。在这项研究中，我们提出了一种自动选择两个关键参数的方法。该方法主要由以下三个相互依存的部分组成：纯像素训练样本数据集的选择过程，确定关键参数的方法以及最优组合模型。在这项研究中，所提出的方法既使用总体精度，也使用其 Kappa 系数（KC）和耗时（TC，单位：秒），以自动选择两个关键参数，而不是使用测试决策，从而避免了主观偏见。使用 2010 年具有 30 米空间分辨率的 Landsat-5/TM 数据和 2005 年的先验分类图对河北省围场县进行了案例研究，该分类图被认为是相对精确的数据，用于测试该方法的性能。实验结果表明，确定关键参数的方法使用投资组合优化模型，并增加了蒋等人的分类方法的自动化程度，这可能具有广泛的科学应用范围。
