Large-scene airborne point cloud semantic modeling method

A modeling method and technology for large scenes, applied in 3D modeling, image data processing, instruments, etc., can solve the problems of weakening the salience of the model boundary, seldom considering the global structural expression of the building, sacrificing the geometric accuracy of the model, etc.

Active Publication Date: 2019-08-13
NANJING FORESTRY UNIV
View PDF4 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) Boundary expression modeling does not make full use of the reliable characteristics of point cloud surface information, so that the geometric accuracy of the created 3D model at key points and boundary lines is not high;
[0006] (2) Strict prior assumption modeling can improve the abstract granularity and regularity of the model, but at the same time it will sacrifice the geometric accuracy of the model, which is not conducive to the reconstruction of complex structural buildings with various shapes in large-scale point clouds;
[0007] (3) Although the dimensionality reduction modeling idea simplifies the modeling problem and improves the robustness and scalability of the algorithm, it weakens the com

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
  • Large-scene airborne point cloud semantic modeling method
  • Large-scene airborne point cloud semantic modeling method
  • Large-scene airborne point cloud semantic modeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0106] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0107] Such as figure 1 The overall framework of the airborne point cloud semantic modeling method for large scenes is composed of four parts: ALS point cloud scene classification, architectural semantic identification, architectural semantic reconstruction and accuracy evaluation.

[0108] (1) ALS point cloud scene classification:

[0109] In order to realize the classification of ALS point clouds, the present invention establishes a three-dimensional capsule network deep learning model based on multi-level objects, and obtains a multi-level classification framework of ALS point clouds. With the help of the capsule network model with more robust performance in deep learning theory, the framework makes full use of the advantages of deep learning in salient feature expression, and designs a deep learning feature expression method based on mult...

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 provides a large-scene airborne point cloud semantic modeling method. The large-scene airborne point cloud semantic modeling method specifically comprises the following steps: 1) classifying ALS point cloud scenes; (2) building semantic element identifiers; (3) building semantic element identifiers; (4) making precision evaluation. The method has the advantages of (1) fusing multiplecurrent modeling ideas to reflect flexibility of a modeling method, (2) improving the possibility of processing large-scale point cloud data through an algorithm, and (3) guaranteeing the integrity of model information in the aspects of geometry, topology and semantics.

Description

technical field [0001] The invention relates to a large-scene airborne point cloud semantic modeling method, which belongs to the technical field of architectural model measurement and construction. Background technique [0002] Extracting the geometric model of buildings is the foundation and key of building a digital smart city, and it is also the focus of current digital city construction. LiDAR technology (Light Detection And Ranging, LiDAR), especially Airborne Laser Scanning technology (Airborne Laser Scanning, ALS), as an important means of collecting large-scale three-dimensional spatial information of buildings, has the advantages of short data acquisition cycle, high precision and timeliness With the characteristics of high precision, strong initiative, and large scanning scenes, it has gradually become an important way to collect 3D architectural data in large scenes. With the development of laser payload hardware technology and storage technology, the accuracy a...

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): G06T17/20
CPCG06T17/20
Inventor 陈动杨强王玉亮郑加柱曹伟曹震李春成
Owner NANJING FORESTRY 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