Classification method based on vehicle lidar point cloud data

Abstract

The invention discloses a classification method based on vehicle-mounted LiDAR point cloud data. The normal vector, curvature and density of the point cloud are calculated during the process; the preprocessed point cloud data is classified, and the power lines, building facade points and tree points are extracted according to the normal vector, curvature and density of the point cloud. The classification method of the present invention is simple, has a small amount of calculation, is quick and effective, and paves the way for the extraction of street view patches, making the extraction of the patches more accurate.

Description

Technical field [0001] The invention relates to the technical field of vehicle-mounted LiDAR point cloud data processing, in particular to a classification method based on vehicle-mounted LiDAR point cloud data that can effectively extract building points, power lines and tree points. Background technique [0002] With the digitization of cities and the increasing demand for informatization, street view maps are developing more and more rapidly. As an advanced measurement method, vehicle-mounted laser scanning not only has the characteristics of fast, no contact with the measured object, real-time, dynamic, active, high-density and high-precision, but also can collect large-area three-dimensional spatial data and obtain buildings and roads. The surface information of urban features such as, vegetation, etc., which provides ideas for the extraction of street scene patches. Therefore, how to quickly and accurately classify the vehicle-mounted laser point cloud data has become one ...

AI Technical Summary

Problems solved by technology

[0004] Foreign countries have developed a relatively ideal automatic classification and recognition algorithm for point cloud data in this field: such as an algorithm for classifying laser scanning point cloud data into different groups according to the point spatial distribution characteristics (geometric features, dispersion degree and density information) of cross-sectional scanning points , but the algorithm’s recognition of mixed arrangement points is relatively complicated; the point cloud data feature extraction method based on building semantics aims to construct walls, doors, windows, and building protrusions by extracting semantic features from ground point cloud data and recessed parts, as well as the digital model of parts such as the roof, the processing process is also more complicated

Images