A Constrained Method for Extracting Building Facade Orthophoto Images

An orthophoto map and extraction method technology, which is applied in the field of building facade image algorithms, can solve the problems of low extraction accuracy, failure to consider the characteristics of the facade itself, and sensitive input parameters, etc., and achieve the effect of high extraction accuracy

Active Publication Date: 2021-09-17
SOUTHWEST PETROLEUM UNIV
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a constrained method for extracting building facade orthophoto images, so as to solve the problem of relying on manual segmentation and input and low extraction accuracy in the prior art for building facade orthophoto image extraction methods , sensitivity to input parameters and failure to consider the characteristics of the facade itself, etc., to achieve the purpose of efficiently and accurately extracting the orthophoto map of the building facade from the point cloud data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Constrained Method for Extracting Building Facade Orthophoto Images
  • A Constrained Method for Extracting Building Facade Orthophoto Images
  • A Constrained Method for Extracting Building Facade Orthophoto Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 A constrained method for extracting orthophoto images of building facades is shown, including:

[0065] Preprocess the 3D point cloud of the facade to be extracted;

[0066] Transform the 3D point cloud from the Euclidean space to the feature space;

[0067] Select the points exceeding the threshold in the feature space, convert the points exceeding the threshold back to the Euclidean space, and obtain the potential plane;

[0068] Create constraint conditions to constrain the potential plane, and obtain the plane satisfying the constraint conditions as the undetermined facade;

[0069] The pending facade is transformed into a vertical surface, and the corresponding point cloud is obtained as the final building facade point cloud;

[0070] The building facade point cloud is projected into the corresponding plane grid according to the plane equation, and the building facade orthophoto map is generated according to the number of point clouds contained...

Embodiment 2

[0072] Such as figure 2 A highly robust building facade orthophoto image extraction method with constraints is shown, which can accept 3D point cloud data input containing any number of planes; use 3D Hough transform to extract potential planes, which can be extracted at one time Identify all possible planes; create constraints based on building facade features to achieve merging of the same plane and removal of non-building facades; use RANSAC algorithm (random sampling consensus algorithm) to extract actual facade point clouds to achieve high-precision point cloud segmentation ; After point cloud segmentation, a vertical orthophoto map is generated for subsequent use. The specific steps are as follows:

[0073] S1. Point cloud preprocessing: Preprocessing the 3D point cloud used to extract the facade, mainly including point cloud denoising, point cloud thinning and coordinate transformation.

[0074] S2, 3D Hough Transform: Create a counter (accumulator), transform all po...

Embodiment 3

[0092] A constrained building facade orthophoto map extraction system, such as image 3 shown, including:

[0093] A preprocessing module is used to preprocess the 3D point cloud of the facade to be extracted;

[0094] The 3D Hough transform module, based on the 3D Hough transform, transforms the 3D point cloud from the Euclidean space to the feature space

[0095] The potential plane module is used to select points exceeding the threshold in the feature space of the Hough transform, and convert these points back to the Euclidean space to obtain the potential plane;

[0096] The facade constraint module is used to constrain the potential plane and obtain the plane satisfying the constraints as the undetermined facade;

[0097] The facade refinement module uses the RANSAC algorithm to transform the undetermined facade into a vertical surface, and obtains the point cloud corresponding to the refined plane as the final building facade point cloud;

[0098] The image generation...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for extracting orthophoto images of building facades with constraints, in order to solve the problem of relying on manual segmentation and input, low extraction accuracy, and poor The input parameters are sensitive and the characteristics of the facade are not considered, so as to achieve the purpose of extracting the orthophoto map of the building facade from the point cloud data with high efficiency and high precision. The purpose of the present invention is to provide a method for extracting building facade orthophoto maps with constraints, so as to solve the problem of relying on manual segmentation and input and low extraction accuracy in the prior art for building facade orthophoto map extraction methods , Sensitivity to input parameters and failure to consider the characteristics of the facade itself, etc., to achieve the purpose of extracting building facade orthophoto images from point cloud data with high efficiency and high precision.

Description

technical field [0001] The invention relates to the field of building facade image algorithms, in particular to a method for extracting building facade orthophoto images with constraints. Background technique [0002] Traditional building facade measurement often uses measurement methods such as total stations and GNSS, which cannot effectively solve the acquisition of facade information of large and complex buildings, and the measurement efficiency is very low, and there are problems such as long time and low efficiency. 3D laser point cloud extraction facade technology has become a hot method for building facade extraction due to its unique advantages. At present, the point cloud extraction facade algorithm is mainly based on a single algorithm, which has defects such as low extraction accuracy, sensitivity to input parameters, and failure to consider the characteristics of the facade itself. [0003] In the prior art, CN110111414A discloses "a method for generating ortho...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T17/20G01C15/00G01B11/24
CPCG01B11/24G01C15/002G06T17/20
Inventor 于冰胡金龙
Owner SOUTHWEST PETROLEUM UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap