Real-time three-dimensional reconstruction method and system for large-scale scene based on line-of-sight updating algorithm

A real-time three-dimensional, large-scale technology, applied in radio wave measurement systems, calculations, electromagnetic wave re-radiation, etc., can solve problems such as poor accuracy and robustness, inability to achieve real-time three-dimensional reconstruction, and insufficient use of sensors in each frame. Achieve the effect of improved quality, real-time high-quality reconstruction

Active Publication Date: 2018-03-30
NANJING UNIV
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Image-based 3D reconstruction has poor accuracy and robustness in feature point matching, and cannot achieve real-time 3D reconstruction
[0004] At present, the reconstruction algorithm based on lidar mainly adopts the method of simplifying the point cloud and then triangulating it. I

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
  • Real-time three-dimensional reconstruction method and system for large-scale scene based on line-of-sight updating algorithm
  • Real-time three-dimensional reconstruction method and system for large-scale scene based on line-of-sight updating algorithm
  • Real-time three-dimensional reconstruction method and system for large-scale scene based on line-of-sight updating algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Such as figure 1 As shown, the present invention is based on the line-of-sight update algorithm for large-scale scene real-time three-dimensional reconstruction method, including the following steps:

[0042] Step 1: Calculate the external parameters of the sensor.

[0043] Use the absolute space coordinates obtained by the current global positioning system as the initial value, integrate the acceleration obtained by the inertial navigation unit (IMU), calculate the current sensor external parameter data, or perform feature point extraction and matching on each frame of radar point cloud , to calculate the extrinsic data of the lidar at this time.

[0044] Step 2: The line-of-sight algorithm calculates the symbol distance value.

[0045] Take the current spatial position of the lidar as the center, and voxelize the space within a certain range. Its body data structure is:

[0046] (p k，n , d k，n ,w k，n )

[0047] Among them, p k，n , representing the three-dimensi...

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 real-time three-dimensional reconstruction method and system for a large-scale scene based on a line-of-sight updating algorithm, and belongs to the field of computer visionand robots. The invention aims to solve a problem of providing a method in which a light of sight is generated according to the current three-dimensional point cloud, data updating is realized and thus real-time reconstruction is performed in allusion to a problem that general algorithms cannot realize real-time reconstruction for large-scale point cloud data of laser radar. The real-time three-dimensional reconstruction method mainly comprises the steps of acquiring three-dimensional point cloud, calculating external parameter data of a sensor, calculating a symbol distance value of an implicit surface based on a line-of-sight algorithm, performing weighted fusion on the symbol distance value, performing volume rendering on volume data, storing the volume data and displaying a reconstruction effect in real time. The implicit surface is updated in real time through introducing the line-of-sight updating algorithm, so that real-time reconstruction for a large-scale scene based on depthsensors such as radar is achieved. The real-time three-dimensional reconstruction method and system not only have great advantages in speed, but also acquire good effects in reconstruction quality.

Description

technical field [0001] The invention belongs to the field of computer vision and robots, and relates to a real-time three-dimensional reconstruction method and system for a large-scale scene based on a line-of-sight update algorithm. Background technique [0002] Real-time 3D reconstruction refers to the process of processing 3D point cloud or image data in real time and generating a 3D model. 3D reconstruction plays a very important role in the fields of computer vision and robotics, and is the basis for applications such as virtual reality, intelligent monitoring, and robot path planning. Since lidar can collect hundreds of thousands of points per second, the amount of data is huge, and the collected data contains relatively large noise. It is very challenging to reconstruct a 3D model of a large-scale scene in real time. [0003] 3D reconstruction is mainly divided into two categories: 3D reconstruction based on camera images and 3D reconstruction based on lidar. Image-...

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): G06T15/08G01S17/89
CPCG01S17/89G06T15/08
Inventor 周余章坚于耀
Owner NANJING 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