Mapping per-pixel predicted accuracy of classified remote sensing images
Mapping per-pixel predicted accuracy of classified remote sensing images
复制标题
DOI：
10.1016/j.rse.2017.01.025
复制
发表时间：
2017-03-15
影响因子：
13.5
通讯作者：
Stehman, Stephen V.
中科院分区：
文献类型：
--
作者：
Khatami, Reza;Mountrakis, Giorgos;Stehman, Stephen V.
传统的基于误差矩阵的地图精度评估方法不能反映分类精度的空间变化。这里，提出了基于来自测试样本的内插精度值的每像素精度预测方法，在测试样本中，已经确定了每个采样像素的参考类。基于四个因素开发了不同的准确度预测方法：预测域（空间与光谱），插值函数（常数，线性，高斯和逻辑），类信息的合并（分别插值每个类与将它们分组在一起），和样本量。与以前基于空间域的努力相比，使用谱域开发精度图是一种新方法。使用分布在美国各地的26个10公里x10公里大小的试验块对预测方法的性能进行了评价。每个区块都有由口译员人工提取的完整覆盖范围参考数据和使用决策树分类法从大地遥感卫星图像生成的土地覆盖图。然后将全景图与相应的参考图进行比较，以产生每个块的完整覆盖精度信息。预测准确度图是从参考数据的样本（即，测试数据集）。使用受试者工作特征的曲线下面积（AUC）评价基于样本的准确度预测的性能。相对于现有的准确性预测方法，我们提出的方法导致AUC提高了0.15或更高。对组成准确度预测方法的四个因素的评价表明：i）应单独对每个类别进行插值，而不是将所有类别分组在一起; ii）如果使用所有类别方法，则光谱域将导致比空间域大得多的AUC; iii）对于较小的样本量和每个类别的预测，光谱域和空间域产生相似的AUC; iv）对于较大的样本量（即，非常密集的空间样本）和每类预测，空间域产生了更大的AUC; v）增加样本量提高了预测的准确性，对空间域产生了更大的益处;以及vi）用于插值的函数对AUC的影响最小。总而言之，生成每像素精度预测并生成易于理解的精度地图的能力为各种学科中遥感产品的误差传播开辟了新的可能性。(C)2017爱思唯尔公司All rights reserved.
The traditional approach of map accuracy assessment based on an error matrix does not capture the spatial variation in classification accuracy. Here, per-pixel accuracy prediction methods are proposed based on interpolating accuracy values from a test sample in which the reference class of each sampled pixel has been determined. Different accuracy prediction methods were developed based on four factors: predictive domain (spatial versus spectral), interpolation function (constant, linear, Gaussian, and logistic), incorporation of class information (interpolating each class separately versus grouping them together), and sample size. Developing accuracy maps using the spectral domain is a new approach in contrast to previous efforts based on the spatial domain. Performance of the prediction methods was evaluated using 26 test blocks, with 10 km x 10 km dimensions, dispersed throughout the United States. Each block had complete coverage reference data manually extracted by interpreters and a land-cover map produced from Landsat imagery using a decision tree classification. The full scene maps were then compared to the corresponding reference maps to produce complete coverage accuracy information for each block. The predicted accuracy maps were produced from a sample of the reference data (i.e., the test dataset). The performance of the sample-based accuracy predictions was evaluated using the area under the curve (AUC) of the receiver operating characteristic. Relative to existing accuracy prediction methods, our proposed methods resulted in improvements of AUC of 0.15 or greater. Evaluation of the four factors comprising the accuracy prediction methods demonstrated that: i) interpolations should be done separately for each class instead of grouping all classes together; ii) if an all-classes approach is used, the spectral domain will result in substantially greater AUC than the spatial domain; iii) for the smaller sample size and per-class predictions, the spectral and spatial domain yielded similar AUC; iv) for the larger sample size (i.e., very dense spatial sample) and per-class predictions, the spatial domain yielded larger AUC; v) increasing the sample size improved accuracy predictions with a greater benefit accruing to the spatial domain; and vi) the function used for interpolation had the smallest effect on AUC. To conclude, the ability to produce per-pixel accuracy predictions yielding simple to understand accuracy maps opens up new possibilities for error propagation of remotely sensed products in a variety of disciplines. (C) 2017 Elsevier Inc. All rights reserved.