Optical flow estimation method and apparatus

Abstract

The embodiment of the invention provides an optical flow estimation method and apparatus. The method comprises: determining M first inliers of a first image and M second inliers of a second image, wherein the M first inliers and the M second inliers are corresponding one-to-one, the M first inliers are M pixels in the first image meeting preset conditions, the M second inliers are M pixels in the second image meeting preset conditions, and the first image employs the second image as a reference image; obtaining a first optical flow field of the first image according to the M first inliers and the M second inliers; determining a second optical flow field according to a second algorithm based on the first optical flow field, wherein the second algorithm makes the optical flow vector quantity in the second optical flow field greater than the optical flow vector quantity in the first optical flow field; and using the second optical flow field as the coupling item constraint of an energy equation to solve the energy equation and obtain an object optical flow field. The optical flow estimation method and apparatus can realize more accurate optical flow estimation under large displacement scenes.

Description

technical field [0001] The present invention relates to the field of computer vision, in particular to methods and devices for optical flow estimation, Background technique [0002] Optical flow estimation is one of the basic research topics of computer vision. Its purpose is to estimate the motion vector of each pixel in the image from the current frame to the next time frame, which can also be called optical flow vector. Optical flow estimation is widely used in video editing, target tracking, scene analysis, motion capture and recognition, etc. Although the existing optical flow estimation algorithm can obtain results close to real motion in a small displacement and controllable environment, but There are still some problems in the face of large displacements in practical engineering applications. For example, when dealing with large-displacement scenes in the prior art, the corresponding relationship between the sparse feature points of the two images, that is, the spar...

AI Technical Summary

Problems solved by technology

Optical flow estimation is widely used in video editing, target tracking, scene analysis, motion capture and recognition, etc. Although the existing optical flow estimation algorithm can obtain results close to real motion in a small displacement and controllable environment, but There are still some problems when facing large displacements in practical engineering applications

For example, when dealing with large-displacement scenes in the prior art, the corresponding relationship between the sparse feature points of the two images, that is, the sparse optical flow field, is usually obtained through the method of feature point detection and matching, and then the sparse optical flow field As a matching item constraint in the energy equation, the variational optical flow optimization is performed to obtain the optical flow field, and the accuracy of the optical flow field obtained in this way is usually relatively low

Images