Fast optical flow field calculation method based on error-distributed multilayer grid

Abstract

The invention belongs to the field of machine vision, and discloses a fast optical flow field calculation method based on an error-distributed multilayer grid. The method comprises the following steps: step one, inputting an image, and constructing a linear equation, that is Ax is equal to f; step two, establishing a multilayer image pyramid; step three, performing prior optimization, and eliminating high-frequency components; step four, performing residual error transmission, and eliminating low-frequency components; step five, repeating steps three and four until residual errors are transmitted to the thickest layer; step six, solving equation sets on thick girds; step seven, performing error passing back from the thickest layer; step eight, performing error correction on thin grids; step nine, performing subsequent optimization iteration, and improving stability of solutions; and step ten, repeating steps seven, eight and nine until the residual errors are transmitted to the thinnest layer. The method provided by the invention is an effective method for accelerating optimization solution of equations, can quick converge high-frequency errors, and can remarkably improve computing speed of a visual optical flow field; and compared with a variational method, the convergence rate of the method can be improved above 3.5 times.

Description

technical field [0001] The invention belongs to the field of machine vision and relates to a fast optical flow field calculation method based on error distributed multi-layer grids. Background technique [0002] In the theory of visual motion analysis, when there is relative motion between the camera and the scene object, the motion of the image brightness pattern observed is called optical flow. Since the optical flow vector field between the sequence video images expresses the changes of the images, it can quantitatively describe the matching relationship between the same-named image points between frames and give the offset of the image plane, so it provides the observer with information about the target. Movement and structure information. [0003] The variational method is the mainstream method for solving optical flow. Its guiding idea is to construct an energy functional in the sense of gradient smoothing and data fidelity, focusing on obtaining a dense optical flow...

AI Technical Summary

Problems solved by technology

[0020] It can be seen that the function β not only contains constant coefficients, but also contains nonlinear Laplacian ope

Images