Airborne multispectral LiDAR data land coverage classification method based on super voxel

Abstract

The invention discloses an airborne multispectral LiDAR data land coverage classification method based on a super voxel, and the method comprises the steps: firstly carrying out the abnormal data elimination and multiband LiDAR point cloud fusion of multispectral LiDAR data, and obtaining the spatial position of a fused multispectral LiDAR point cloud and the single point cloud data of multiband spectral information corresponding to the fused multispectral LiDAR point cloud; then, on the basis of the principle of minimum information loss, carrying out voxelization on the data, and assigning values to the voxels; then, by utilizing a simple linear iterative clustering algorithm SLIC, merging voxels which are close in space and spectrum into super voxels, and performing feature extraction and standardization processing on the super voxels; and finally, adopting a support vector machine (SVM) classifier training data set to construct a one-to-many super-voxel-oriented SVM classification model, and completing the classification of ground features. The method has the advantages of being visual in principle and easy to implement, the better and more efficient classification effect is achieved, and a good foundation is laid for application such as urban basic geographic space information obtaining and updating.

Description

technical field [0001] The invention relates to the technical field of ground object classification, in particular to a method for land cover classification of airborne multi-spectral LiDAR data based on super voxels. Background technique [0002] Airborne multispectral LiDAR data is a new type of data source. The multiple single-band LiDAR data contained in it have consistency in time phase, scene, and resolution, and are located in the same coordinate system. The multi-band spectral information of the scene point cloud obtained by the reflection intensity information can obtain the point cloud data containing both spectrum and three-dimensional (3Dimension, 3D) spatial information, which can well avoid the shortcomings of image and single-band LiDAR fusion data, so it is the current It is the most ideal data source for the study of object classification. [0003] The research on object classification methods has always been a research hotspot in the field of photogrammetr...

AI Technical Summary

Problems solved by technology

This method loses a lot of positional relationship information between points in the point cloud when the point cloud is interpolated into an image. Build the 3D geometry of the target

(2) Poor feature integrity or reliability

(3) The influence of the classifier, the performance of the classifier is limited

The classifier must be classified according to the input features, but as mentioned earlier, the available features of the point- and pixel-oriented classifiers are limited, which is not enough to accurately distinguish all ground objects

Images