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

Wide baseline matching method and device

A matching method and matching device technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as wide baseline matching of structured scene images, and achieve scale invariance, strong stability, and rotation invariance.

Active Publication Date: 2017-12-12
ARMY ENG UNIV OF PLA
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a wide baseline matching method and device to solve the problem of wide baseline matching of existing structured scene images

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
  • Wide baseline matching method and device
  • Wide baseline matching method and device
  • Wide baseline matching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 The implementation flow of the wide baseline matching method provided by Embodiment 1 of the present invention is shown. As shown in the figure, the method may include the following steps:

[0035] Step S101, performing line segment detection on an input image to obtain a set of straight lines of the input image.

[0036] Here, the line segment detection method can be selected according to actual needs to perform line segment detection on the input image, for example, the LSD (Line Segment Detector, Line Segment Detector) line detection algorithm is used to perform line detection on the input image to obtain a single-pixel width line set of the input image.

[0037] Step S102, performing parallel straight line clustering on the set of straight lines to obtain parallel straight line groups of the input image.

[0038] Specifically, by using the property that parallel line segments intersect at the vanishing point, the above-mentioned set of straight lines is c...

Embodiment 2

[0075] In order to better understand the above method, an application example of the wide baseline matching method of the present invention will be described in detail below.

[0076] like Figure 7 As shown, this application example may include:

[0077] Step S701, using the LSD algorithm to detect the line segment of the input image, and obtain the set of single-pixel width straight lines represented by endpoints Ls={p 1 (x 1 i ,y 1 i ),p 2 (x 2 i ,y 2 i ), i=1,2,...,m}. LSD is a local line segment detection algorithm with fast operation speed and high precision.

[0078] Step S702, using the characteristic that parallel line segments intersect at the vanishing point, classify the line segment set Ls, and obtain the line segment grouping Ls={Ls j , j=1,2,...,N}, where Ls j Represents the jth subset Ls of the set of line segments j ={p j1 (x j1 i ,y j1 i ),p j2 (x j2 i ,y j2 i ), i=1,2,...,m}. Using the vanishing point detection and line segment class...

Embodiment 3

[0100] Corresponding to the wide baseline matching method described in the above embodiment, Figure 8 A structural block diagram of the wide-baseline matching device provided by the embodiment of the present invention is shown. For the convenience of description, only the parts related to this embodiment are shown.

[0101] refer to Figure 8 , the device includes a line segment detection module 801, a straight line clustering module 802, a straight line selection module 803, a straight line intersection obtaining module 804, a characteristic scale determination module 805, a feature point main direction determination module 806 and a wide baseline matching module 807.

[0102] The line segment detection module 801 is configured to perform line segment detection on the input image to obtain a straight line set of the input image.

[0103] Here, the line segment detection method can be selected according to actual needs to detect the line segment of the input image, for example...

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 is suitable for the technical field of computer vision and image processing, and provides a wide baseline matching method and device. The method comprises the following steps of: carrying out line segment detection on an input image to obtain a straight line set of the input image; carrying out parallel straight line clustering on the straight line set to obtain parallel straight line groups of the input image; randomly selecting two straight lines from different parallel straight line groups; obtaining non-parallel straight line intersection points of the input image according to the selected straight lines; determining a feature scale of each non-parallel straight line intersection point; determining a feature point main direction according to each feature scale; and carrying out wide baseline matching according to the feature point main direction and a preset matching method. The method has relatively strong robustness for image noise and illumination variation, and has invariance for image rotation and certain viewpoint and scale variation, so that a feasible method is provided for the matching of structured scenes under complicated illumination conditions.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image processing, and in particular relates to a wide baseline matching method and device. Background technique [0002] Image matching refers to finding the corresponding points of the same spatial point on images at different viewpoints. It is one of the basic technologies in the fields of image processing and computer vision. It has a wide range of applications in image stitching and fusion, stereo vision, image recognition, and target tracking. application. According to the density of matching points, image matching can be divided into sparse matching method and dense matching method. Dense matching performs point-by-point matching, and the obtained matching point pairs are dense. Dense matching is suitable for narrow baseline matching, that is, the changes in viewpoint, rotation and scale between images to be matched are small. The image to be matched is generally corrected by e...

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): G06T7/33
CPCG06T7/33
Inventor 翟优郭希维尉广军何鹏刘德亮谢建华赵慎王红云姚义
Owner ARMY ENG UNIV OF PLA
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