新型语义分割D-UNet的建筑物提取

New building extraction method based on semantic segmentation

高分辨率遥感图像语义分割在航空图像分析领域中具有重要的理论价值和应用价值。但由于高分辨率遥感图像中建筑物语义的丰富性和图像背景的复杂性,以往的分割方法往往容易产生边缘模糊、细节信息丢失和分辨率低等缺点。为了解决高分辨率卫星图像语义分割边界模糊和信息丢失的问题,本文提出一种端到端的卷积神经网络Dilated-UNet(D-UNet)。首先,通过改进U-Net网络结构,采用Dilation技术拓展四通道的多尺度空洞卷积模块,每个通道采用不同的卷积扩张率来识别多尺度语义信息,从而提取更丰富的细节信息。其次,设计了一种交叉熵和Dice系数的联合损失函数,更好的训练模型以达到预期分割效果。最后,在Inria航空图像数据集上进行综合评估与检验。实验结果表明,本文提出的遥感图像分割方法能够有效地从高分辨率遥感图像中进行像素级城市建筑物的分割,与其他方法相比,分割精度更高,具有较高的实际应用价值。

Semantic segmentation of high-resolution remote sensing image has important theoretical and practical value in the field of aerial image analysis.However,the traditional segmentation methods are prone to edge blur,loss of detail information,and low resolution due to the richness of building semantics and the complexity of image background in high-resolution remote sensing images.An end-to-end convolutional neural network called Dilated-UNet(D-UNet)is proposed to solve the problem of fuzzy boundary and information loss in high-resolution satellite image semantic segmentation.First,the U-Net network structure is improved and the multiscale dilated convolution module of four channels is expanded using the division technology.Each channel uses different convolution expansion rates to identify the multiscale semantic information for extracting richer detailed information.Second,a joint loss function of cross entropy and Dice coefficient is designed to achieve the desired segmentation effect.The model is comprehensively evaluated and tested on the Inria aerial image dataset.Experimental results show that the proposed remote sensing image segmentation method can effectively segment urban buildings at pixel level from high-resolution remote sensing images,and the segmentation accuracy is higher and is therefore better than those of other methods.Our proposed D-UNet can deliver automatic building segmentation from high-resolution remote sensing images with high accuracy.Thus,it is a useful tool for practical application scenarios.