Door and window point cloud shape detecting method and system based on laser point cloud data

Abstract

The invention provides a door and window point cloud shape detecting method and system based on laser point cloud data. The door and window point cloud shape detecting method based on the laser pointcloud data includes the steps of: pre-processing original point cloud data to obtain the point cloud data with gross errors removed and conducting edge extraction, determining the point cloud shape according to the result of edge extraction; projecting a 3D point cloud to 2D in the direction perpendicular to the plane of a door frame, dividing grids and extracting internal grids in the middle position, determining whether the number of points in the internal grids is greater than a preset corresponding threshold to know that the point cloud shape is a L shape if so and that the point cloud shape is another shape if not, splitting edge extraction results of the point cloud into four parts: up, down, left, and right, performing corresponding judgment fitting on the upper part and fitting theleft, right and bottom parts of the edge of the point cloud; fitting data and point cloud data to calculate fitting error point by point, calculating coefficient of determination, and extracting thefitting parameters of the coefficient of determination which meet the corresponding threshold. The door and window point cloud shape detecting method and system based on the laser point cloud data have the advantages of being simple, effective, high in precision, easy to implement and of important market value.

Description

technical field [0001] The invention belongs to the field of laser point cloud three-dimensional reconstruction, and in particular relates to a technical solution for realizing door and window shape detection and extraction by using point cloud data. Background technique [0002] Lidar is a new type of active remote sensing technology by measuring the propagation time of laser pulses and combining the positioning attitude data provided by the airborne positioning system to directly and quickly obtain high-precision dense lattice data. A notable feature of Lidar technology is that it can directly obtain 3D coordinates of ground objects. These points are distributed unevenly and discretely in space, and appear as "clouds", so they are called point clouds. The 3D reconstruction technology based on point cloud is a research field that intersects multiple disciplines such as computer graphics, virtual reality, and computer vision. Its main research is how to restore the geometri...

AI Technical Summary

Problems solved by technology

In the field of door and window measurement, the existing methods mainly use traditional manual measurement, which consumes manpower, material resources and time, especially for special-shaped doors and windows, the efficiency and accuracy of traditional measurement methods are very low

However, in the field of existing lidar applications, there is no algorithmic process for door and window shape detection.

Images