Physic object tracking and positioning method based on nature characteristics

A physical object, tracking and positioning technology, applied in image data processing, instruments, calculations, etc., can solve problems such as poor practicability, achieve good practicability, ensure accuracy and stability, and ensure automation

Inactive Publication Date: 2018-01-16
NORTHWESTERN POLYTECHNICAL UNIV
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of poor practicability of existing physical object tracking and positioni

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
  • Physic object tracking and positioning method based on nature characteristics
  • Physic object tracking and positioning method based on nature characteristics
  • Physic object tracking and positioning method based on nature characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] refer to Figure 1-5 . The specific steps of the physical object tracking and positioning method based on natural features of the present invention are as follows:

[0044] Step 1: 3D modeling of physical objects. Divided into the following 5 steps:

[0045] Step 1.1: Use the depth camera / binocular camera to collect multi-angle images of the physical object to obtain an image sequence of the physical object. Use the depth map or disparity map to obtain the local point cloud p corresponding to the image i .

[0046] Step 1.2: Use the iterative closest point algorithm to stitch and fuse the local 3D point cloud scene, complete the 3D reconstruction, and obtain the complete 3D point cloud scene including physical objects, and the translation matrix T of the image sequence relative to the reference coordinate system j and the rotation matrix R j . Calculate the Euler angles α, β, γ from the rotation matrix R, with the best angle interval, the present invention is ver...

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 physic object tracking and positioning method based on nature characteristics, solving a technical problem that the current physic object tracking and positioning method is poor in practicability. The physic object tracking and positioning method based on nature characteristics comprises steps of performing modeling on a physic object, introducing ORB characteristic descriptors, describing three-dimensional coordinator points under a physic object coordinate system, taking a camera coordinate system as an intermediate variable to perform calibration on a posture position relation between a physic object and a world coordinate system, and completing matching between two-dimensional image points and three-dimensional image points through ORB characteristic point matching so as to complete target tracking. The invention uses point cloud segmentation and the motion detection technology to guarantee automated proceeding of a tracking process, and uses a characteristic point matching algorithm based on a grid and rear end optimization of a tracking result to guarantee algorithm accuracy and stability. The physic object tracking and positioning method based on nature characteristics is applicable to the application of any reality enhancement product based on tracking and positioning and is good in practicability.

Description

technical field [0001] The invention relates to a physical object tracking and positioning method, in particular to a physical object tracking and positioning method based on natural features. Background technique [0002] Literature “Lima J P, Roberto R, F, et al.Markerless tracking system for augmented reality in the automotive industry[J].Expert Systems with Applications,2017,82:100-114."The public 3D modeling and tracking method based on natural features, using the natural feature points of physical objects, Combined with 3D reconstruction technology to complete the positioning and tracking of any physical object, but it relies on human manual selective operation when removing the background of the key frame, which affects the automation of the system; when tracking and positioning the target object, the previous data is not used as For reference, without back-end optimization, the tracking results will have error accumulation and poor stability. Contents of the inv...

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): G06T7/593G06T7/66G06T7/11G06T7/246
Inventor 何卫平刘洋陈永兴张旭
Owner NORTHWESTERN POLYTECHNICAL 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