Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Bidirectional closed mode stereoscopic vision full-field measurement method based on multi-source characteristic data control

A technology of characteristic data and closed mode, applied in the field of computer vision, can solve problems such as difficulty in ensuring the accuracy and stability of measurement results, low efficiency, and singleness of limited feature points, so as to overcome the problems of singleness and low efficiency, improve Accuracy and reliability, obtaining the effect of scheme optimization

Active Publication Date: 2020-09-25
HARBIN INST OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In target pose measurement for a large field of view, limited by the visual measurement model, the one-way transfer process from image data to spatial feature information is difficult to guarantee the accuracy and stability of the measurement results, such as large-scale aircraft pose measurement, wind tunnel test wait
[0006] These problems have led to the disadvantages of the singleness and inefficiency of limited feature points in the current visual measurement. It can be seen that the visual measurement based on point information control is no longer suitable for the characteristics of image data in the era of big data, and it is necessary to make full use of scene information and model libraries. Information and other data to ensure the reliability of the target pose measurement results

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
  • Bidirectional closed mode stereoscopic vision full-field measurement method based on multi-source characteristic data control
  • Bidirectional closed mode stereoscopic vision full-field measurement method based on multi-source characteristic data control
  • Bidirectional closed mode stereoscopic vision full-field measurement method based on multi-source characteristic data control

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0057] Such as Figure 1 to Figure 2 As shown, the present invention provides a kind of stereo vision full-field measurement method based on the two-way closed mode of multi-source feature data control, comprising the following steps:

[0058] A stereo vision full-field measurement method based on a two-way closed mode controlled by multi-source feature data, comprising the following steps:

[0059] Step 1: Establish a multi-source feature data fusion framework;

[0060] according to figure 1 As shown, the multi-source feature data fusion framework in step 1 includes: feature extraction digital base conversion layer, classification layer, feature data analysis layer, feature element integration layer, model library information layer, data convergence layer, attribute structure regularization layer , a lossless conversion layer, a measurement feature data alignment layer and a fusion function layer;

[0061] The feature extraction digital base conversion layer performs image...

specific Embodiment 2

[0094] exist image 3 The effect verification of the method of the present invention is carried out under the measurement scene shown. The system host is configured with a processor with a main frequency of 4.0GHz and a running memory of 4GB, and two sets of disk arrays are attached. The image resolution of the stereo camera is 2048×2048pixels, and the pixel size is du×dv=7.4×7.4μm 2 , the focal length of the camera is f=35mm, and the measurement space range is about 10m×6m×3m. The input data of the measurement system includes target feature information, image data and point cloud information. Point cloud information includes spatial point coordinates, sign features, database and scene information, etc.

[0095] This embodiment mainly involves the following multi-source data. First, the simulation device is fixed on the turntable to simulate the movement of the target. There are preset calibration points on the simulation device, and the mark points are detected by Hough tr...

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 bidirectional closed mode stereoscopic vision full-field measurement method based on multi-source characteristic data control. A multi-source feature data fusion framework is established; establishing a fusion function based on a multivariate feature data fusion framework, and fusing different types of feature data to obtain multi-source feature data; establishing a bidirectional closed vision measurement mode based on the multi-source feature data; and determining the minimum cost of the feature point cloud set based on a bidirectional closed vision measurement mode, and iteratively solving space target parameters by adopting a nonlinear iterative method. According to the invention, a one-way process from image data to spatial feature information transmission ina traditional visual measurement method is changed; the obtained or confirmed spatial data is returned to the measurement processing process as control information, a bidirectional closed measurementmode is constructed, efficient multi-source feature data fusion is carried out, the problems of singleness and low efficiency of feature points are solved, redundant information is added and resolved, and the overall measurement precision of a visual system is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, and relates to a two-way closed-mode stereo vision full-field measurement method based on multi-source feature data control. Background technique [0002] The non-contact measurement of the position and attitude of the target in space plays a very important role in the fields of aircraft performance testing, equipment calibration and process control. The visual measurement technology based on the combination of camera and computer technology is widely used in the measurement of target position and attitude. , by using the discrete feature points, feature lines or specific geometric shapes attached to the target, combined with the visual measurement model to perform pose calculation. The characteristics of the current visual measurement technology mainly include the selection of the feature image with the best quality, the relatively small range of the survey area, and the need for a speci...

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): G06T7/70G06K9/62G06T5/00
CPCG06T7/70G06T2207/10016G06F18/253G06T5/80
Inventor 张贵阳霍炬杨明薛牧遥王松艳朱子健魏亮
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com