LiDAR与航空影像的融合分类与精度分析

为了弥补单一数据源在地物分类时的不足,提出将机载激光扫描(LiDAR)数据与航空影像融合进行地物分类的思想,实现基于面向对象和单像元的复杂城区多级地物分类.将真彩色航空影像与机载激光扫描距离影像融合,采用光谱特征和空间特征将影像分割成若干同质区域;利用多源数据产生的各种信息建立分类规则并实现基于面向对象的地物分类,将植被信息和高差信息与分类结果叠加,实现基于单像元的分类结果纠正,然后再以对象内包含的建筑物直线段数量为约束条件对分类结果中的建筑物进行三级精化分类.实验表明该方法能够有效地自动分离建筑物、树木、草地和道路,其中建筑物的制图精度和用户精度分别是92.53%和95.79%,整个区域的分类精度为89.62%,该方法在复杂城区可行有效.

Classification and Accuracy analysis of LiDAR and Aerial Images

In order to make up the insufficiency of the single data source in the classification, an approach integrating light detection and ranging (LiDAR) and aerial image was proposed, and the multistage complex urban ground object classification was implemented based on object oriented and single pixel. Aerial image and LiDAR were merged and some homogeneous regions were divided into as the research object by combining spectrum and spatial characteristics. Ground points and non ground points were separated by filtering LiDAR, and the altitude difference was obtained based on twice return pulse heights and vegetation data from false color aerial image. The classification rules were established and the segmentation objects were classified by adopting object oriented method. Then, the mistake objects were defined again based on the above information, the second stage classification based on single pixel was finished. A further classification was put up to eliminate the mistake buildings by extracting the line segments of buildings. The result shows that the approach can automatically effectively separate buildings, woodland, grassland and road, the producer accuracy and user accuracy is respectively 92.53% and 95.79%, the whole classification accuracy is 89.62%. The study is a successful step in developing classification method for integrating LiDAR and aerial images.