Building edge point detection method based on double-domain graph signal filtering

Abstract

The invention discloses a building edge point detection method based on double-domain graph signal filtering. The method comprises the following steps: collecting airborne laser radar data and generating three-dimensional point cloud data; based on the local feature statistical histogram and the elevation value of the vertex, constructing a double-domain signal graph of a spatial domain and a value domain; constructing a three-dimensional space weighted undirected signal graph model through a histogram cross kernel and a Gaussian function; carrying out edge perception smoothing on the signal graph model by utilizing bilateral filtering, and removing perigee and noise points; and based on the double-domain signal graph model, constructing a double-threshold high-pass filter to automaticallyextract building edge points. According to the invention, an airborne laser radar system and a POS system are used for collecting three-dimensional point cloud data of a surface building; and then athree-dimensional weighted double-domain signal graph is constructed based on a local feature statistical histogram, and bilateral filtering smoothing and double-threshold high-pass filtering edge detection is performed by using unused filters, thereby achieving the purpose of directly and accurately extracting building edge points from original point cloud data.

Description

technical field [0001] The invention relates to a laser radar data processing method, in particular to a method for directly detecting building edge points of laser radar data, and belongs to the technical field of laser radar data processing. Background technique [0002] LiDAR (Light Detection And Ranging, LiDAR) is an emerging technology that was first developed by Western countries in the early 1990s and put into commercial application. The ability to coordinate information. This technology has produced a major breakthrough in the real-time acquisition of three-dimensional spatial information, and provides a new technical means for obtaining spatial information with high temporal and spatial resolution. [0003] In recent years, LiDAR technology has become a common technical approach for geographic information system applications, photogrammetry, and cartographic production. A basic step in the analysis of research targets using LiDAR data is segmentation. Segmentation...

AI Technical Summary

Problems solved by technology

However, in this method, the conversion of LiDAR data from 3D point cloud to 2D image will cause information loss, and the final edge detection effect is not good.

Images