Self-adaptive weight three-dimensional matching method based on SIFT descriptor

An adaptive weight, stereo matching technology, applied in image data processing, instruments, calculations, etc., can solve the problems of low matching accuracy and cannot meet the needs, and achieve the effect of overcoming the low matching accuracy and wide application prospects.

Active Publication Date: 2015-10-07
天津渤化南港码头仓储有限公司
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above algorithms can achieve ideal matching results in high-texture areas, but in low-texture areas, occlusion areas, and depth discontinuous areas such as object boundaries, the matching accuracy is not high, which cannot meet the needs of practical applications.

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
  • Self-adaptive weight three-dimensional matching method based on SIFT descriptor
  • Self-adaptive weight three-dimensional matching method based on SIFT descriptor
  • Self-adaptive weight three-dimensional matching method based on SIFT descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] 101: Obtain the adaptive aggregation window of each center point through the similarity area judgment criterion;

[0028] 102: Perform adaptive weight calculation through the L1 norm of the SIFT descriptor at each point, and complete the optimization of the matching cost according to the initial joint matching cost and the adaptive aggregation window;

[0029] 103: For the optimized matching cost, use the WTA strategy to select the optimal disparity value for each point, then use the left-right consistency detection method to detect the optimal disparity value, and use the background filling method to perform Padding to get the final disparity map.

[0030] Among them, the initial joint matching cost is specifically:

[0031] Using the magnitude and phase of the gradient field of the left and right views, the matching cost is calculated for the left and right views, and the initial joint matching cost is obtained.

[0032] Among them, the judgment criterion of the sim...

Embodiment 2

[0041] 201: Using the magnitude and phase of the gradient field of the left and right views, calculate the matching cost for the left and right views, and obtain the initial joint matching cost;

[0042] Among them, the traditional stereo matching algorithm uses the color difference of pixels, or the method based on census transformation and rank transformation to calculate the matching cost, which is easily affected by noise and local illumination changes. In view of the strong robustness of the gradient domain to noise and local illumination changes, the embodiment of the present invention uses the magnitude and phase of the gradient domain to calculate the matching cost, so as to improve the robustness of the algorithm.

[0043] For any pixel (x, y) in the view to be matched ， When the disparity value is d, its gradient domain-based joint matching cost function is defined as:

[0044] C(x,y,d)=α·min(C c (x,y,d), T c )+β·min((C g (x,y,d),T g )+μ·min(C p (x,y,d),T p ))...

Embodiment 3

[0087] The technical solutions in Embodiment 1 and Embodiment 2 of the present invention will be further described in detail below in conjunction with specific examples.

[0088] The present invention selects the stereoscopic image database provided by the Computer Vision Research Center of Middlebury University in the United States: http: / / vision.middlebury.edu / stereo as the test picture. The image database covers various situations that are likely to cause false matching, including low-textured areas. , depth discontinuity area, occlusion area, etc., to verify the effectiveness of the method of the present invention.

[0089] image 3 They are the experimental results of VariableCross algorithm, SNCC algorithm, HistoAggr algorithm and the present invention respectively. Among them: picture (a) is 4 standard test images, picture (b) is the real disparity map of 4 standard test pictures, picture (c) is the disparity map obtained by using SNCC algorithm, picture (d) is using V...

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 discloses a self-adaptive weight three-dimensional matching method based on an SIFT descriptor. The self-adaptive weight three-dimensional matching method comprises the following steps: obtaining a self-adaptive aggregation window of each center point through a similarity area decision criterion; performing self-adaptive weight calculation through an L1 norm of an SIFT descriptor of each point, and optimizing a matching cost according to an initial combined matching cost and the self-adaptive aggregation window; for the optimized matching cost, selecting the optimal parallax value of each point through a WTA strategy, then detecting the optimal parallax value by adopting a left-right consistency detection method, and filling detected mismatching points by using a background filling method to obtain a final parallax image. The self-adaptive weight three-dimensional matching method of the present invention realizes aggregation of the matching costs in a three-dimensional matching process, can obtain a parallax image with high accuracy, overcomes the problems that a traditional algorithm has low matching accuracy in a depth discontinuous area and a low texture area, and has wide application prospect.

Description

technical field [0001] The invention relates to the field of stereo matching, in particular to an adaptive weight stereo matching method based on a SIFT (Scale Invariant Feature Transform) descriptor. Background technique [0002] Stereo matching is to find the corresponding matching points from two or more images obtained from the same scene, and use the matching algorithm to calculate the depth information of each point in the image, so as to achieve the purpose of three-dimensional reconstruction. At present, stereo matching technology has been widely used in various fields, such as video surveillance, 3D tracking and robot control, etc., and has received extensive attention. [0003] In recent years, scholars from various countries have conducted in-depth research in the field of stereo matching, and proposed many algorithms, which can be divided into two categories: stereo matching algorithms based on local constraints and stereo matching algorithms based on global cons...

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
CPCG06T2207/10012
Inventor 何凯王晓文葛云峰姚静娴
Owner 天津渤化南港码头仓储有限公司
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