GPU and depth camera based indoor 3D reconstruction method

A depth camera and 3D reconstruction technology, applied in the field of indoor 3D reconstruction based on GPU and depth camera, can solve the problems of complex calculation, prone to offset, large amount of calculation, etc., and achieve the effect of accurate map, simple cost and less noise.

Active Publication Date: 2017-06-23
HANGZHOU LANXIN TECH CO LTD
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, SfM is prone to offset for larger scenes, and the calculation is complicated and the calculation amount is large

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
  • GPU and depth camera based indoor 3D reconstruction method
  • GPU and depth camera based indoor 3D reconstruction method
  • GPU and depth camera based indoor 3D reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the embodiments and the accompanying drawings.

[0027] like figure 1 As shown, the technical solution of the present invention is a kind of indoor three-dimensional reconstruction method based on GPU and depth camera, comprising the following steps:

[0028] Step 1: Calibration of the camera and the dual wheels of the intelligent mobile platform

[0029] The depth camera is installed on the intelligent mobile platform, and the bottom of the intelligent mobile platform is equipped with two driving wheels driven by a motor and a universal wheel, and an encoder is installed on the motor; the present invention uses a depth camera, and Microsoft Kinect can be selected Or ASUS Xtion. Before data collection, the camera and the dual wheels of the intelligent mobile platform need to be calibrated. The calibration method of the depth camera adopts the ChessBoard method provided by OpenCV. The camera mod...

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 GPU and depth camera based indoor 3D reconstruction method. The method comprises the following steps of (1) calibration of a camera and double wheels of an intelligent moving platform; (2) data collection; (3) key frame selection; (4) GPU based map generation; and (6) map optimization. According to the invention, data is obtained according to speedometer information of the depth camera and the double wheels of the platform, the camera is positioned, a GPU acceleration method is used, and 3D reconstruction of an indoor scene is completed at a higher speed. A map is accurate, the cost is low, and noises are fewer. A universal interface is provided, and expansion and visualization are easy to implement.

Description

technical field [0001] The invention relates to the technical fields of computer vision, three-dimensional reconstruction, GPU and artificial intelligence, in particular to an indoor three-dimensional reconstruction method based on a GPU and a depth camera. Background technique [0002] 3D scene reconstruction technology includes laser scanner reconstruction, computer vision method reconstruction and other technologies. Among them, laser scanning technology can scan the structure of three-dimensional objects more accurately, but it is more suitable for the reconstruction of a single object, and the laser scanner is relatively expensive. In the field of computer vision technology, the reconstruction method is mainly SfM (Structure from Motion), and its difficulty lies in the process of matching feature points of multi-view images and triangulating feature points. However, SfM is prone to offset for larger scenes, and the calculation is complicated and the calculation amount ...

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 Applications(China)
IPC IPC(8): G06T17/00G06T7/00G06T3/40G01C22/00
CPCG01C22/00G06T3/4038G06T17/00G06T2207/10028
Inventor 时岭高勇
Owner HANGZHOU LANXIN TECH CO LTD
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