Image matching method based on feature detection

A matching method and a technology for testing images, which are applied in the field of pattern recognition and can solve problems such as difficulty in feature point detection and matching

Inactive Publication Date: 2010-07-14
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for computers, the detection and matching of feature points in images is a very difficult problem

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 matching method based on feature detection
  • Image matching method based on feature detection
  • Image matching method based on feature detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The various details involved in the technical method of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be pointed out that the described embodiments are only intended to facilitate the understanding of the present invention, rather than limiting it in any way.

[0038] The image matching algorithm based on image pose and illumination estimation improves the accuracy, stability and real-time performance of image matching. Using the estimation of pose and illumination, the present invention implements an image matching system, such as figure 1 The flow chart of the image matching algorithm based on image pose and illumination is shown. This method is divided into three parts: pose estimation and correction, illumination estimation and correction, and image matching:

[0039] The attitude estimation and correction part includes the steps of: extracting scale-invariant feature points for the reference image ...

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 an image matching method for based on a feature detection, which comprises the following steps: detecting algorithm by using a Harris function based feature of a reference image, and matching images to be detected by using nearest adjacent matching algorithm; acquiring a pose estimation of a detection image, relative to the reference image, and using the reference image to estimate the illumination of a goal of the diction image carried out the pose estimation; calculating the change of the illumination of the goal of the detection image, contained in the part of the reference image, carrying out the illumination transformation and correction on the illumination transformation function and the detection image carried out the pose estimation; gaining the detection image corrected by the illumination; carrying out a feature-based point detection and description on the detection image corrected by the illumination and the reference image to gain the feature point matching of the detection image corrected by the illumination; and combining the pose estimation of the detection image to gain the pose matching of the detection image corrected by the illumination. Image matching is an underlying problem of a computer vision, has important implication to typical problems of the computer vision, such as target tracking, scene modeling, image mosaic, image retrieval and the like.

Description

technical field [0001] The invention belongs to the field of pattern recognition and relates to technologies such as image processing and computer vision, in particular to feature detection, image matching, image splicing, image retrieval, three-dimensional reconstruction and augmented reality. Background technique [0002] Image matching is a basic problem in computer vision. Accurate and efficient image matching algorithms provide a solid underlying foundation for solving other problems. With the development of technology and the gradual reduction of hardware equipment prices, cameras and video cameras have become one of the widely used equipment in people's daily life. People's requirements for scene perception have changed from the original two-dimensional perception to three-dimensional perception, that is, to perceive the three-dimensional shape of objects in the real world and the three-dimensional posture of the scene. Due to the variety of objects in the real world...

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): G06K9/64
Inventor 谭铁牛黄凯奇余轶南
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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