Three-dimensional matching method based on improved bidirectional dynamic programming
A dynamic programming algorithm and dynamic programming technology, applied in image data processing, instruments, calculations, etc., can solve the problems of high false matching rate, "stripe defects", etc., to achieve high accuracy, speed up elimination, and reduce the effect of false matching rate.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] Such as 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:
[0035] S01: Modify the adaptive weighted cost function;
[0036] S02: Use the modified adaptive weighted cost function to construct a new global energy function;
[0037] S03: Using the constructed global energy function, use the improved two-way dynamic programming algorithm to search for the parallax point matching path;
[0038] S04: Remove isolated erroneous disparity points using (simple) filtering methods and following three reliability criteria;
[0039] S05: Obtain the final dense disparity map.
[0040] Specifically, step S01: revise the adaptive weighted cost function.
[0041] 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 Eucli...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 