Three-dimensional matching method based on interactive image segmentation

A technology for image segmentation and stereo matching, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of insufficient utilization of segmentation information, complex calculation framework, and high difficulty in implementation, so as to reduce the amount of calculation and increase sub-pixel accuracy , reduce the effect of building nodes

Inactive Publication Date: 2015-10-28
SHAANXI NORMAL UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of previous stereo matching methods based on image segmentation, such as large amount of calculation, complex calculation framework, high difficulty in implementation, and insufficient use of segmentation information, the present invention proposes a fast image segmentation method based on interaction to obtain sense Objects of interest, a stereo matching method based on interactive image segmentation that only performs stereo matching on the foreground template of the object of interest, with small computation and accurate matching 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
  • Three-dimensional matching method based on interactive image segmentation
  • Three-dimensional matching method based on interactive image segmentation
  • Three-dimensional matching method based on interactive image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] Taking the Tsukaba image pair as an example, the test environment is Windows 7 64-bit system, the CPU is 3.0GHz, the memory is 8G, and the compiler is Visual Studio 2010.

[0060] Carry out stereo matching according to the method of the present invention, concrete steps are as follows:

[0061] (1) The segmentation of the target of interest, the process is as follows figure 1 shown.

[0062] (1.1) The user sets the seed points in the left and right views of the Tsukaba image respectively according to the needs, marks the foreground image and the background image, marks the background part as blue, and the foreground part as red; figure 2 , image 3 .

[0063] (1.2) In the left and right views, the image segmentation method based on the color index value is used to segment the object of interest to the user;

[0064] The image segmentation method based on the color index value refers to the paper "One-time Fast Graph Cut Algorithm" (Tang M, Gorelick L, Veksler O, et...

Embodiment 2

[0083] In this embodiment, step (1.3) is specifically: the user judges that the segmented object of interest meets the needs, if the segmentation result is not satisfactory, then return to step (1.1) to reset the seed point; if the segmentation result is satisfactory, obtain the segmentation template , proceed to the next step.

[0084] The graph cut algorithm called in step (2.3) can also refer to the Fulkerson maximum flow algorithm (Ford‐Fulkerson algorithm) invented by L.R. Ford and D.R. Fulkerson in 1956.

[0085] Other steps are the same as in Embodiment 1 to obtain a disparity map.

Embodiment 3

[0087] In this embodiment, taking the sawtooth image pair as an example, stereo matching is performed according to the method of the present invention, and the specific steps are as follows:

[0088] (1) Segmentation of the target of interest, specifically:

[0089] (1.1) The user sets the seed points in the left and right views of the sawtooth image according to the needs, marks the foreground image and the background image, and marks the background part as blue and the foreground part as red; Figure 12 , Figure 13 .

[0090] (1.2) In the left and right views, the image segmentation method based on the color index value is used to segment the object of interest to the user;

[0091] The image segmentation method based on the color index value refers to the paper "One-time Fast Graph Cut Algorithm" (Tang M, Gorelick L, Veksler O, et al. GrabCut in One Cut) published at the International Computer Vision Conference in 2013 [C] / / Computer Vision (ICCV), 2013IEEE International...

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 present invention relates to a three-dimensional matching method based on interactive image segmentation. An object in which a user is interested is segmented by adopting a graph-cut algorithm based on the interactive image segmentation; an optimal network graph is generated by a segmentation template; the graph-cut algorithm is called to carry out minimum segmentation calculation on the network graph; a disparity image is generated; and a three-dimensional matching result is obtained. According to the present invention, segmentation information is effectively utilized; the calculation is reduced; the accurate matching result is obtained by utilizing the characteristic of global optimum of the graph-cut algorithm; an experiment result shows that the method disclosed by the present invention obtains excellent effects on shielding, depth discontinuity, illumination variation, low texture, no-texture regions and the like and is obviously improved on the aspects of operation time and operation accuracy.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, in particular to a stereo matching method based on interactive image segmentation. Background technique [0002] Stereo matching technology is a difficult point and hot spot that has been widely concerned in the computer field in recent years. Its purpose is to obtain a disparity map by matching two or more images, and recover the depth information of the corresponding pixel from the proportional relationship between the disparity map and depth, so that It can calculate the three-dimensional information in the scene, and has a wide range of applications in robot navigation, industrial control, driverless cars, etc. [0003] Because the graph cut algorithm has good performance of combinatorial optimization, the quality of the disparity map has been significantly improved, and it can better deal with low texture areas and occluded pixels. In recent years, domestic and foreign scho...

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
CPCG06T2207/20104G06T2207/20228
Inventor 刘侍刚王雅宁
Owner SHAANXI NORMAL UNIV
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