Accurate segmentation of large areas from very high spatial-resolution (VHR) remote sensing imagery remains a challenging issue in image analysis. Existing supervised and unsupervised methods both suffer from the large variance of object sizes and the difficulty in scale selection, which often result in poor segmentation accuracies. To address the above challenges, we propose a deep learning-based region-merging method (DeepMerge) to handle the segmentation in large VHR images by integrating a Transformer with a multi-level embedding module, a segment-based feature embedding module and a region-adjacency graph model. In addition, we propose a modified binary tree sampling method to generate multi-level inputs from initial segmentation results, serving as inputs for the DeepMerge model. To our best knowledge, the proposed method is the first to use deep learning to learn the similarity between adjacent segments for region-merging. The proposed DeepMerge method is validated using a remote sensing image of 0.55m resolution covering an area of 5,660 km^2 acquired from Google Earth. The experimental results show that the proposed DeepMerge with the highest F value (0.9446) and the lowest TE (0.0962) and ED2 (0.8989) is able to correctly segment objects of different sizes and outperforms all selected competing segmentation methods from both quantitative and qualitative assessments.

翻译：从极高空间分辨率遥感影像中精确分割大面积区域仍是图像分析中的挑战性问题。现有监督与非监督方法均存在目标尺寸方差大、尺度选择困难等问题，导致分割精度欠佳。针对上述挑战，我们提出了一种基于深度学习的区域合并方法（DeepMerge），通过整合Transformer与多层次嵌入模块、基于分割的特征嵌入模块及区域邻接图模型，处理大尺度极高分辨率遥感影像分割任务。此外，我们提出改进的二叉树采样方法，从初始分割结果生成多层次输入，作为DeepMerge模型的输入。据我们所知，本方法是首次利用深度学习学习相邻分割区域间相似性以进行区域合并。采用Google Earth获取的0.55米分辨率、覆盖5660平方公里的遥感影像对DeepMerge方法进行验证。实验结果表明，所提出的DeepMerge方法在最高F值（0.9446）及最低TE（0.0962）和ED2（0.8989）指标上，能够正确分割不同尺寸目标，在定量与定性评估中均优于所有选定的对比分割方法。