This study compares some different types of spectral domain transformations for convolutional neural network (CNN)-based land cover classification. A novel approach was proposed, which transforms one-dimensional (1-D) spectral vectors into two-dimensional (2-D) features: Polygon graph images (CNN-Polygon) and 2-D matrices (CNN-Matrix). The motivations of this study are that (1) the shape of the converted 2-D images is more intuitive for human eyes to interpret when compared to 1-D spectral input; and (2) CNNs are highly specialized and may be able to similarly utilize this information for land cover classification. Four seasonal Landsat 8 images over three study areas—Lake Tapps, Washington, Concord, New Hampshire, USA, and Gwangju, Korea—were used to evaluate the proposed approach for nine land cover classes compared to several other methods: Random forest (RF), support vector machine (SVM), 1-D CNN, and patch-based CNN. Oversampling and undersampling approaches were conducted to examine the effect of the sample size on the model performance. The CNN-Polygon had better performance than the other methods, with overall accuracies of about 93%–95 % for both Concord and Lake Tapps and 80%–84% for Gwangju. The CNN-Polygon particularly performed well when the training sample size was small, less than 200 per class, while the CNN-Matrix resulted in similar or higher performance as sample sizes became larger. The contributing input variables to the models were carefully analyzed through sensitivity analysis based on occlusion maps and accuracy decreases. Our result showed that a more visually intuitive representation of input features for CNN-based classification models yielded higher performance, especially when the training sample size was small. This implies that the proposed graph-based CNNs would be useful for land cover classification where reference data are limited.

中文翻译：

---

基于卷积神经网络和多时相卫星图像的土地利用分类的不同光谱域变换

这项研究比较了基于卷积神经网络（CNN）的土地覆盖分类的一些不同类型的谱域转换。提出了一种新颖的方法，该方法将一维（1-D）光谱向量转换为二维（2-D）特征：多边形图图像（CNN-Polygon）和二维矩阵（CNN-Matrix）。这项研究的动机是：（1）与一维光谱输入相比，转换后的二维图像的形状对于人眼来说更直观。（2）CNN高度专业化，可以类似地利用此信息进行土地覆盖分类。与其他几种方法相比，我们使用了三个研究区域（美国华盛顿州，新罕布什尔州康科德湖和韩国光州的三个地区）的四个Landsat 8季节性影像，来评估九种土地覆盖类别的拟议方法：随机森林（RF），支持向量机（SVM），一维CNN和基于补丁的CNN。进行了过采样和欠采样方法来检查样本大小对模型性能的影响。CNN-Polygon的性能优于其他方法，对于Concord和Lake Tapps而言，总体精度约为93％–95％，而对于光州，总体精度约为80％–84％。当训练样本量较小（每个班级少于200个）时，CNN-Polygon的性能特别好，而样本量变大时，CNN-Matrix的性能相似或更高。通过基于遮挡图的敏感性分析对模型的贡献输入变量进行了仔细分析，从而降低了准确性。我们的结果表明，对于基于CNN的分类模型，输入特征的更直观直观的表示产生了更高的性能，尤其是在训练样本量较小时。这意味着，所提出的基于图的CNN对于参考数据有限的土地覆盖分类很有用。