ABSTRACT Semantic segmentation is an important method to implement fine-grained semantically understand for high-resolution remote sensing images by dividing images into pixel groupings which can then be labelled and classified. In the field of computer vision (CV), the methods based on fully convolutional network (FCN) are the hotspot and have achieved state-of-the-art results. Compared with popular datasets in CV such as PASCAL and COCO, class imbalance is a problem for multiclass semantic segmentation in remote sensing datasets. In this paper, an FCN-based model is proposed to implement pixel-wise classifications for remote sensing image in an end-to-end way, and an adaptive threshold algorithm is proposed to adjust the threshold of Jaccard index in each class. Experiments on DSTL dataset show that the proposed method produces accurate classifications in an end-to-end way. Results show that the adaptive threshold algorithm can increase the score of average Jaccard index from 0.614 to 0.636 and achieve better segmentation results.

中文翻译：

---

使用自适应阈值的全卷积网络对高分辨率遥感图像进行语义分割

摘要 语义分割是一种重要的方法，通过将图像划分为像素组，然后可以进行标记和分类，从而对高分辨率遥感图像实现细粒度语义理解。在计算机视觉（CV）领域，基于全卷积网络（FCN）的方法是热点，并取得了最先进的成果。与 CV 中流行的 PASCAL 和 COCO 等数据集相比，类不平衡是遥感数据集中多类语义分割的一个问题。在本文中，提出了一种基于FCN的模型以端到端的方式对遥感图像进行逐像素分类，并提出了一种自适应阈值算法来调整每个类别中Jaccard索引的阈值。在 DSTL 数据集上的实验表明，所提出的方法以端到端的方式产生准确的分类。结果表明，自适应阈值算法可以将平均Jaccard指数的得分从0.614提高到0.636，取得较好的分割效果。