融合LiDAR数据与高分影像特征信息的建筑物提取方法

A Method for Building Extraction by Fusing Feature Information from LiDAR Data and High-Resolution Imagery

建筑物是城市环境中的主要地物类型,从高分影像等数据中自动提取建筑物对于提升土地利用变化检测、城市规划与土地执法等业务的质量与效率具有重要意义。本文针对现有建筑物提取方法存在的边界提取不精确的问题以及采用手工特征表达图像信息的局限性,融合LiDAR数据与高分影像两种数据源的特征信息,提出一种基于SegNet语义模型的建筑物提取新方法。首先,对LiDAR数据预处理得到数字表面模型(DSM)、数字地形模型(DTM)、归一化数字表面模型(nDSM),利用高分影像NDVI值去除n DSM中部分树木点,得到结果影像nDSM_en;其次,分别获取LiDAR数据回波强度、表面曲率以及高分影像NDVI值3个特征构建特征图像训练SegNet语义模型,利用训练得到的模型完成建筑物初始提取;最后,采用阈值法分割nDSM_en得到影像对象,利用影像对象约束建筑物初始提取结果,完成建筑物精提取。在以ISPRS官方提供的标准数据集(数据采集的地理区域为德国Vaihingen,采集时间2008年7—8月)为样本的实验中,本文方法在像素层次的平均查全率、平均查准率和提取质量分别为96.4%、94.8%和91.7%;针对面积大于50 m2的建筑物对象,上述3个指标均为100%。实验结果表明:本文提出与实现的建筑物提取方法更好地利用了反映建筑物与非建筑物本质差异的特征信息,有效地实现了2种数据源的相对优势互补,提高了建筑物的检测与提取精度。

One of the main feature types in urban areas is building;automatic building extraction from high-resolution imagery or other data has great significance for improving the quality and efficiency of land use change detection,urban planning,land law enforcement,and so on.To deal with the problem of boundary inaccuracy of extracted buildings and the limitation caused by expressing image information with artificial features,this paper proposed a new building extraction method based on the SegNet semantic model,which fused feature information from LiDAR data and high-resolution imagery.Firstly,LiDAR data were preprocessed to obtain Digital Surface Model(DSM),Digital Terrain Model(DTM),and normalized Digital Surface Model(nDSM).The resulted image nDSM_en was acquired by removing tree points from nDSM with Normalized Differential Vegetation Index(NDVI)values derived from high-resolution imagery.Secondly,three features-LiDAR data echo intensity,and surface curvature from LiDAR data,and NDVI from high-resolution imagery were obtained to construct feature images for training the SegNet semantic model.Initial extraction of buildings was completed with the trained model.Finally,the threshold segmentation algorithm was executed with nDSM_en for generating image objects,which were used to refine the initially extracted buildings through boundary constraints.In the experiment which utilized the Standard Dataset as a sample,the average completeness,correctness,and extract quality of the proposed method at the pixel level were 96.4%,94.8%,and 91.7%respectively.For building objects with area larger than 50 m2,the above three indicators were 100%.Our findings suggest that the proposed building extraction method makes better use of the feature information which reflects the essential difference between buildings and non-buildings,integrates effectively the relative advantages of the two data sources,and can increase the accuracy of building detection and extraction.