Full-waveform LiDAR point cloud classification method based on multi-wavelet support vector machine WSVM integration

Abstract

The invention discloses a full-waveform LiDAR point cloud classification method based on multi-wavelet support vector machine WSVM integration. The method comprises the following steps: firstly, decomposing full-waveform LiDAR data, extracting geometric and waveform characteristics of point cloud, constructing a plurality of wavelet support vector machine (WSVM) classifiers by utilizing differentwavelet kernel functions, and constructing an integrated system by taking the WSVM classifiers as base classifiers; performing parameter optimization in each WSVM classifier by adopting a particle swarm optimization PSO algorithm, and integrating the WSVM classifiers by adopting a bagging algorithm; and finally, adopting a wavelet support vector machine (WSVM) classifier integrated system to classify point clouds decomposed from the original full-waveform LiDAR data, and outputting a result. According to the invention, a good point cloud classification result can be obtained.

Description

technical field [0001] The invention belongs to the technical field of LiDAR data processing and application, in particular to a full-waveform LiDAR point cloud classification method based on multi-wavelet support vector machine WSVM integration. Background technique [0002] In recent years, with the development of LiDAR equipment and data processing technology, there are more and more researches on its data classification. As a new type of equipment, full waveform LiDAR can record the continuous echo waveform of the transmitted pulse at a small sampling interval. Compared with the traditional discrete point cloud LiDAR, it can extract waveform features for point cloud classification. LiDAR point clouds usually have a large number. As a commonly used machine learning classification method, Support Vector Machine (SVM) has great advantages in solving the problem of small training sample data and large data volume to be classified. It is often used for point cloud classifica...

AI Technical Summary

Problems solved by technology

However, the kernel function commonly used by SVM has the disadvantages of redundancy and lack of local analysis ability, which limits the ability to approximate complex functions.

Images