Prioritizing in segment matching
A part of the pixel, part of the boundary technology, applied in the direction of image analysis, equipment, television, etc., can solve the problem of time-consuming and expensive calculation, and the solution is not accurate enough
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0017] In the following example of the invention, the matching of two images will be explained. These images may be consecutive images from a video stream, but the invention is not limited thereto. These images are digital images containing image pixels and are defined as two 2-dimensional digital images I 1 (x, y) and I 2 (x, y). Among them, x and y indicate the coordinates of each independent pixel in the image.
[0018] The matching of these two images involves computing a pair of functions M=M x (x,y) and M=M y (x, y). The definition of M is the same as before, that is, the image I 1 Each pixel in the image I is mapped to 2 A pixel in .
[0019] I 1 (x, y) = I 2 (x+M x (x, y), y+M y (x, y))
[0020] According to the invention, the construction method of M is modified so that for groups of pixels with similar motion, the function M is constant, and the previous definition of M is modified as:
[0021] I 1 (x, y) = I 2 (x+M x (G(x,y)), y+M y (G(x,y)))
[0...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 