A Stereo Matching Method Based on Improved Bidirectional Dynamic Programming
A technology of dynamic programming and stereo matching, applied in image data processing, instrumentation, computing, etc., can solve problems such as high error matching rate and "stripe defect", achieve high accuracy, speed up elimination, and reduce the effect of error matching rate
Active Publication Date: 2017-07-04
FUZHOU UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In view of this, the purpose of the present invention is to provide a stereo matching method based on improved two-way dynamic programming, the purpose is to solve the problem of "stripe" blemishes and high error matching rate in the disparity map obtained by the existing dynamic programming algorithm
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0035] like figure 1 As shown, the present invention provides a kind of stereo matching method based on improved two-way dynamic programming, comprises the following steps:
[0036] S01: Modify the adaptive weighted cost function;
[0037] S02: Use the modified adaptive weighted cost function to construct a new global energy function;
[0038] S03: Using the constructed global energy function, use the improved two-way dynamic programming algorithm to search for the parallax point matching path;
[0039] S04: Remove isolated erroneous disparity points using (simple) filtering methods and following three reliability criteria;
[0040] S05: Obtain the final dense disparity map.
[0041] Specifically, step S01: revise the adaptive weighted cost function.
[0042] Convert the color pixel value of an image pixel point into a CIELab value, Δc pq is the Euclidean distance between the CIELab values of pixel p and pixel q in the center of the window, Δg pq Indicates the Euclidea...
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
Login to View More Abstract
The invention relates to a three-dimensional matching method based on improved bidirectional dynamic programming. The three-dimensional matching method includes the steps: S01, correcting an adaptive support-weight cost function; S02, constructing a new global energy function by the aid of the corrected adaptive support-weight cost function; S03, searching a parallax error point matching path by the aid of the constructed global energy function and an improved bidirectional dynamic programming algorithm; S04, removing isolated incorrect parallax error points by a filtering method and by following three reliability criteria; S05, acquiring a final dense parallax error graph. Incorrect matching point removal is greatly accelerated by the aid of the three reliability criteria, global image matching accuracy is higher, mismatching rate can be reduced to be lower than 7%, a new column-wise smooth bound term strategy is made, and the method has remarkable improvement effects in terms of mismatching rate reduction and 'stripe' defect decrease.
Description
[0001] technology neighborhood [0002] The invention relates to the neighborhood of stereo matching algorithms, in particular to a stereo matching method based on improved bidirectional dynamic programming. Background technique [0003] Stereo vision technology is an important 3D display technology developed by people through the study of the visual system that captures the three-dimensional space information of objects, that is, by taking target images in multiple directions and synthesizing the depth parallax information of the target to complete the spatial target Stereoscopic scene information reconstruction. [0004] According to the difference of matching constraint objects, the stereo matching algorithm is usually divided into two categories. One is the local matching algorithm that formulates a constraint strategy for the local small neighborhood of pixels. The matching effect is poor; in response to this problem, some scholars have proposed another global matching a...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/32
Inventor 郭太良姚剑敏徐胜林金堂林志贤叶芸
Owner FUZHOU UNIV