基于DeepLabv3+语义分割的航空影像建筑物提取方法  

Building extraction method for aerial images based on DeepLabv3+semantic segmentation

作　　者：廖元晖 王敬东[1] 李浩然 杨衡 LIAO Yuanhui;WANG Jingdong;LI Haoran;YANG Heng(College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)

机构地区：[1]南京航空航天大学自动化学院,江苏南京211106

出　　处：《指挥控制与仿真》2024年第6期55-61,共7页Command Control & Simulation

摘　　要：航空影像可以提供丰富的地物信息,建筑物作为一种重要的地物信息,通过快速精确地识别航空影像中的建筑物,可以实现目标监测、位置定位,并进一步丰富特定区域的地理信息。针对语义分割算法在提取建筑物时存在的分割结果粘连、轮廓线条不规则的问题,通过改进特征融合结构、构建综合损失函数以及添加改进后的Douglas Peucker算法,提出了一种改进的基于DeepLabv3+的航空影像建筑物提取模型。实验结果表明,改进后的模型在测试集上交并比为0.794,相较于原模型提升了14.7%,有效地避免了近邻建筑物之间的粘连分割问题,使得分割边界更加规整,从而更精确地提取出建筑物的轮廓形状。Aerial imagery can provide rich geographic information.As an important ground object information,quickly and accurately extracting buildings from aerial images can achieve target monitoring,location positioning,and further enrich specific geographic information in a given area.To address the issues of segmentation result merging and irregular contour lines in semantic segmentation algorithms for building extraction,an improved model based on DeepLabv3+for aerial building extraction is proposed by improving the feature fusion structure,constructing a comprehensive loss function,and incorporating an improved Douglas Peucker algorithm.Experimental results show that the improved model achieves an IoU of 0.794 on the test set,a 14.7%improvement compared to the original model.It effectively avoids the problem of merged segmentation between neighboring buildings and results in more regular segmentation boundaries,enabling more accurate extraction of the building contours.

关 键 词：航空影像 建筑物提取 DeepLabv3+ 轮廓规则化 

分 类 号：P237[天文地球—摄影测量与遥感]