Image search and match optimizing method applied in model matching posture measurement

An optimization method, image search technology, applied in the field of image search matching optimization, can solve the problems of complex calculation and large amount of calculation, and achieve the effect of simplifying the matching process

Inactive Publication Date: 2014-03-26
NO 63921 UNIT OF PLA +1
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to provide an image search and matching optimization method applied to model matching attitude measurement to solve the problems of large amount of calculation and complex calculation in the prior art

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
  • Image search and match optimizing method applied in model matching posture measurement
  • Image search and match optimizing method applied in model matching posture measurement
  • Image search and match optimizing method applied in model matching posture measurement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The image search and matching optimization method of the present invention weakens the role of the imaging model, breaks away from the camera imaging error formula, completes iterative optimization from the perspective of the image, and finds the matching model projection image. For observation images and model projection images, target features on the images are used as objects for search matching optimization.

[0038] First, various specific descriptions are made to the features of the target in the image, and descriptors suitable for attitude measurement and feature matching are generated. The present invention uses chain codes, moment and Fourier descriptors. Normalize the descriptors to match feasible. Use the attitude prior knowledge to determine the initial attitude value. For chain codes and moment descriptors, direct optimization methods such as pattern search are used; for Fourier descriptors, learning-based optimization methods are used to solve feature-bas...

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 an image search and match optimizing method applied in model matching posture measurement, which solves the existing problems of large calculation quantity, complex calculation, etc. The image search and match optimizing method of the invention weakens the functions of an imaging model, gets rid of an imaging error formula of a camera, accomplishes iteration optimization from the angle of the image, and finds out the matched model projection image. As for an observation image and the model projection image, target characteristics of the images are used as a search and match optimizing object. In the iteration optimization, the invention avoids the connection between the camera imaging model and the error formula, and simplifies the calculation quantity in the matching process.

Description

technical field [0001] The invention relates to an image search matching optimization method applied to model matching pose measurement. Background technique [0002] Model matching pose measurement is to use the target observation image to match the images in the target model projection image cluster (library) to obtain the target's pose in the observation image. Image search matching of observed images to clusters of projected images is a major problem in pose measurement for model matching. The current search method mainly adopts the least squares iterative optimization method to establish the error equation. [0003] In the iterative optimization method, it is necessary to establish a camera imaging model to obtain the mathematical expression of the imaging error equation, then extract the contours in the observed target image and the model projection image, sample points on the contour of the observed image, and obtain the contour of the projected image. The normal or...

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 Patents(China)
IPC IPC(8): G06F17/30G06N3/02
Inventor 胡海滨唐慧君马彩文杜博军温佳冯志远李寅朱顺华
Owner NO 63921 UNIT OF PLA
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