A method for automatically extracting plane patches from 3D laser point cloud data of foundation

Abstract

The invention discloses a method for automatically extracting plane patches from 3D laser point cloud data of foundation, which comprises the following steps: desampling 3D laser point cloud data of foundation; 2) calculating and quantifying point attribute; 3) clustering and selecting the seed point in the parameter domain; 4) clustering spatial domain planar patch; 5) performing least square plane parameter estimation and patch boundary calculation. That invention does not need manual intervention, has excellent anti-noise property, robustness, computational performance, and is very easy toparallelize, can be used for quickly extracting planar patch from a large range of mass point cloud data, meet the real-time processing requirements and processing accuracy requirements of building indoor and outdoor three-dimensional modeling.

Description

technical field [0001] The invention relates to the technical field of computer vision (three-dimensional reconstruction), in particular to a method for automatically extracting plane slices from ground-based three-dimensional laser point cloud data. Background technique [0002] Buildings (structures) are the most common and main features of the city (collectively referred to as buildings), and the interior of the building (indoor) is the main place for people to produce, live, or entertain. Different from the 3D point cloud (3D Point Cloud) on the city surface acquired by airborne lidar, the ground-based laser scanning system (TLS for short) can obtain more and more detailed building facade information, which can effectively and accurately , Rapidly and realistically reconstruct the 3D fine model of the digital city; for the indoor 3D modeling of buildings, TLS is an effective data acquisition tool. The 3D point cloud data produced by TLS can not only provide intuitive vi...

AI Technical Summary

Problems solved by technology

The plane in the three-dimensional Euclidean space contains four parameters, that is, its Hough attribute space is four-dimensional (it can be transformed into a three-dimensional attribute space by adding constraints), which requires a large amount of computer memory and low performance when programming. Difficult to process multiple planar slices in parallel

[0007] The main purpose of the present invention is to solve the shortcomings of the existing ground-based 3D point cloud plane slice extraction technology, that is, relying on the selection of seed points (insufficient robustness), low computational efficiency, and difficulty in processing point cloud data with uneven density distribution set etc.

Images