Unlock instant, AI-driven research and patent intelligence for your innovation.

Affine invariant image matching method

A technology of affine invariant and matching method, which is applied in the field of affine invariant image matching, and can solve problems such as inapplicability and large amount of calculation

Inactive Publication Date: 2014-03-05
康江科技(北京)有限责任公司
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although ASIFT and Fair-SURF proposed later have good affine invariance, the calculation process is not optimized, resulting in too much calculation, which cannot be applied to many occasions with high real-time requirements.

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
  • Affine invariant image matching method
  • Affine invariant image matching method
  • Affine invariant image matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0020] figure 1 Schematically shows a flow chart of an affine invariant image matching method according to a preferred embodiment of the present invention, the method includes the following steps:

[0021] Step 1: Perform perspective simulation on the original first image f and the second image g to be matched respectively, so as to obtain a first simulated image set and a second simulated image set.

[0022] Specifically, input the original two images to be matched, such as the first image and the second image, respectively denoted as and ;According to the angle between the camera optical axis and the normal vector of the target plane , and the angle between the camera optical axis and the x-coordinate of th...

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 affine invariant image matching method. The method comprises the steps that viewing angle simulation is conducted on an original first image f to be matched and an original second image g to be matched, so that a first simulation image set and a second simulation image set are obtained; cross enumeration is conducted on the first simulation image set and the second simulation image set, and an image pair set P is obtained; the similarity between the simulation images in the first simulation image set and the simulation images in the second simulation image set is calculated based on the matching algorithm, and an optimized image pair set is obtained; rough SIFT feature point matching is conducted on all the images in the image pair set, and matching point pairs are added into a point pair set; geometric constraint is added, the point pair set is screened, mistake matching is removed, and therefore an precise matching result is obtained.

Description

technical field [0001] Various embodiments of the present invention relate to the technical field of image matching in the field of pattern recognition and computer vision, and in particular to an affine invariant image matching method. Background technique [0002] Image matching is a basic problem in the field of computer vision, and has been widely used in applications such as stereo vision, object recognition, image stitching, three-dimensional reconstruction and tracking. The purpose of image matching is to establish point-to-point correspondences between input images. Classical image matching is based on robust local descriptors. The local descriptor can reflect the stable structure in the image and has strong invariance to geometric deformation. Traditional image matching techniques can be divided into three steps: detecting interest points, extracting descriptors, and matching. There are many ways to detect interest points. Generally, geometric corne...

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): G06T7/00
Inventor 不公告发明人
Owner 康江科技(北京)有限责任公司