ABSTRACT

Convolutional Neural Network (CNN) is widely used for semantic segmentation and land-use and land-cover (LULC) mapping of very high-resolution (VHR) remote sensing images. The convolution operation is a powerful method for VHR classification, but the loss of high-frequency detail information caused during its operation decreases the classification accuracy, particularly in the boundary. Thus, it is necessary to supply additional boundary information to the CNN for alleviating this situation. In the classification task (and in LULC mapping), providing more effective information generates a better classification result. Current methods regard the boundary of images as the same category object and process it uniformly, which loses a notable amount of useful information because of the different properties, such as ambiguity and transition, between remote sensing images and their boundaries. Thus, a semantic segmentation method with category boundary for LULC mapping is proposed in this paper. First, a multi-task CNN called the category boundary detection network (CBDN) is designed to extract the boundary information of different category objects. Second, this category boundary and VHR images are used for initial semantic segmentation. Finally, the category boundary and the initial semantic segmentation result (ISSR) are fused to obtain the final LULC map by a two-step strategy, including the explicit fusion and the boundary attention loss function. To verify whether category boundary improved the classification accuracy, a set of comparative experiments were conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam datasets. The method in this paper was compared with a semantic segmentation method with no boundary information and a semantic segmentation method with global boundary. The results showed that the proposed method in this paper achieved good performances in the Vaihingen (overall accuracy (OA) = 0.924, Kappa coefficient (K) = 0.898, mean F1 score (mF1) = 0.896 and mean Intersection over Union (mIoU) = 0.817) and Potsdam datasets (OA = 0.890, K = 0.857, mF1 = 0.923, and mIoU = 0.860) based on the eroded labels.

摘要

卷积神经网络（CNN）被广泛用于超高分辨率（VHR）遥感图像的语义分割以及土地使用和土地覆盖（LULC）映射。卷积运算是VHR分类的有力方法，但是在其操作过程中引起的高频细节信息的丢失会降低分类精度，尤其是在边界上。因此，有必要向CNN提供其他边界信息以减轻这种情况。在分类任务（和LULC映射）中，提供更有效的信息会产生更好的分类结果。当前的方法将图像的边界视为同一类别对象并对其进行统一处理，由于诸如歧义性和过渡性等不同属性，图像的边界会损失大量有用信息。在遥感影像及其边界之间。因此，本文提出了一种用于LULC映射的具有类别边界的语义分割方法。首先，设计了一个多任务CNN，称为类别边界检测网络（CBDN），以提取不同类别对象的边界信息。其次，此类别边界和VHR图像用于初始语义分割。最后，通过两步策略融合类别边界和初始语义分割结果（ISSR），以获得最终的LULC图，包括显式融合和边界注意力损失函数。为了验证类别边界是否提高了分类精度，在国际摄影测量与遥感学会（ISPRS）的Vaihingen和波茨坦数据集上进行了一组比较实验。将该方法与没有边界信息的语义分割方法和具有全局边界的语义分割方法进行了比较。结果表明，本文提出的方法在Vaihingen上取得了良好的性能（整体精度（OA）= 0.924，Kappa系数（K）= 0.898，平均F1分数（mF1）= 0.896，平均交叉口数（mIoU）= 0.817）和波茨坦数据集（OA = 0.890，K = 0.857，mF1 = 0.923，mIoU = 0.860） 。