结合深度学习和图割法的遥感影像建筑物检测

提出一种基于卷积神经网络和图割法的自动提取高分影像建筑物的方法。首先，通过卷积神经网络定位与检测建筑物的位置，逐一提取单个建筑物轮廓，利用检测结果分别建立建筑物和非建筑物的高斯混合模型（GMM），然后结合最大流最小割的图像分割方式实现全局优化，完成建筑物初步提取，最后用形态学进行优化。通过试验证明了该方法的可行性。

Remote sensing image building extraction based on deep learning and graph cut

A method for automatically extracting buildings on high-resolution images based on convolutional neural networks and graph cuts is proposed. Firstly, the location of the contour of the building is located and detected by the convolutional neural network, and the outlines of the individual buildings are extracted one by one. The Gaussian mixture model (GMM) of the building and the non-building is respectively established by the detection result, and the minimum flow is minimized. The cut image segmentation method achieves global optimization, completes the preliminary extraction of the building, and finally optimizes with morphology. The feasibility of the method is proved by experiments.