Supercharge Your Innovation With Domain-Expert AI Agents!

Lightweight reconstruction method and device for Manhattan structure building

A building and lightweight technology, applied in 3D modeling, instrumentation, computing, etc., can solve the problem of inability to achieve lightweight reconstruction of Manhattan structures, and achieve the effect of shortened overall running time and low cost

Pending Publication Date: 2022-08-05
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Embodiments of the present invention provide a method and device for lightweight reconstruction of Manhattan structure buildings, to at least solve the technical problem that the prior art cannot realize lightweight reconstruction of Manhattan structure buildings

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
  • Lightweight reconstruction method and device for Manhattan structure building
  • Lightweight reconstruction method and device for Manhattan structure building
  • Lightweight reconstruction method and device for Manhattan structure building

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] According to an embodiment of the present invention, a lightweight reconstruction method for a Manhattan structure building is provided, comprising the following steps:

[0086] Apply recovery-from-motion reconstruction to image sequences to obtain camera poses and sparse point clouds, and perform line-segment-based reconstruction to obtain line clouds;

[0087] The line cloud is clustered, and the sampling points are obtained by sampling on the line cloud, and added to the sparse point cloud;

[0088] Detect planes from line clouds, and cut corners by finding orthogonal planes;

[0089] Starting from the corner points, the point cloud is fitted by changing the parameters of the corner points, and the final cube model is obtained;

[0090] Perform image-based registration for cubes that do not converge to the correct size.

[0091] In the light-weight reconstruction method of Manhattan structure buildings in the embodiment of the present invention, recovery and recons...

Embodiment 2

[0192] According to another embodiment of the present invention, a lightweight reconstruction device for a Manhattan structure building is provided, comprising:

[0193] The reconstruction unit is used to apply the recovery-from-motion reconstruction to the image sequence, obtain the camera pose and sparse point cloud, and perform line-segment-based reconstruction to obtain the line cloud;

[0194] The clustering unit is used to cluster the line cloud, and sample the line cloud to obtain sampling points, which are added to the sparse point cloud;

[0195] The detection unit is used to detect the plane from the line cloud, and obtain the corner points by finding the orthogonal plane cutting;

[0196] The fitting unit is used to fit the point cloud by changing the parameters of the corner points from the corner points to obtain the final cube model;

[0197] Registration unit for image-based registration of cubes that do not converge to the correct size.

[0198] The light-wei...

Embodiment 3

[0252] A storage medium storing a program file capable of implementing any one of the above-mentioned lightweight reconstruction methods for Manhattan structures.

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 relates to a lightweight reconstruction method and device for a Manhattan structure building. According to the method and the device, firstly, an image sequence is recovered and reconstructed from motion to obtain a camera pose and a sparse point cloud, and reconstruction based on line segments is executed to obtain a line cloud; clustering the line clouds, sampling on the line clouds to obtain sampling points, and adding the sampling points into sparse point clouds; a plane is detected from the line cloud, and angular points are obtained by searching an orthogonal plane for cutting; starting from the angular points, fitting the point cloud by changing the parameters of the angular points to obtain a final cube model; and carrying out image-based registration on cubes which are not converged to the correct size. According to the method, the plane is obtained by using the line cloud, dense point cloud is not needed, the method for extracting the plane by using the line cloud is superior to the prior art in the aspect of plane extraction robustness, and the cost for obtaining the sparse point cloud and the line cloud is lower than that of the dense point cloud, so that the total operation time of the method is shortened, and the cost is lower.

Description

technical field [0001] The present invention relates to a method and device for lightweight reconstruction of Manhattan structure buildings. Background technique [0002] As a common artificial landscape, the 3D model of urban scene has a wide range of applications in GIS systems, virtual reality, digital games, autonomous driving, smart cities and other fields. Urban scenes are mainly composed of buildings, streets and other objects. Although most of these objects have simple geometric structures, it is still a very challenging task to construct a large-scale 3D urban scene model. Due to the huge scale of the city, the corresponding amount of data is huge, and at the same time, due to the occlusion of buildings and the limitation of angle in the actual data collection, the application of traditional modeling methods in urban modeling is not only slow but also the reconstruction effect is not good. Therefore, exploring Efficient urban scene modeling methods have great resea...

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
IPC IPC(8): G06T17/05G06V10/762G06K9/62
CPCG06T17/05G06F18/23Y02A30/60
Inventor 程章林何振邦
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com