An Efficient Large Displacement Optical Flow Estimation Method

Abstract

The invention discloses an effective estimation method for large displacement optical flows, comprising capturing two continuous images from a video and marking the frame images of the two as I1 and I2 in a time order; taking I1 and I2 as the lowest layers to establish image pyramids respectively (described in the specification); generating seed points in equal numbers on each layer of the image pyramids (described in the specification); initiating the matching of seed points at the top layer (described in the specification) for random values; matching the obtained seed points from the top layer to the lowest lower of the image pyramids successively and the matching result of seed points at each layer serves as an initial value for the next layer; and interpolating the matching result of seed points at the lowest layer through an edge sensitive interpolation algorithm; using the interpolating result as the initial value for optical flow estimation and optimizing it through a variation energy optimization model to finally achieve the estimation result of large displacement optical flows. According to the invention, a more effective and flexible result can be achieved. The number of seed points can be controlled for different application scenarios for optical flow results with varied efficiency and accuracy.

Description

technical field [0001] The invention belongs to the field of digital video processing, and in particular relates to a high-efficiency large-displacement optical flow estimation method. Background technique [0002] Optical flow estimation is an important basic module in the field of computer vision. Its research purpose is to calculate the motion information between two consecutive frames of video through modeling, specifically the corresponding matching pixels of each pixel in the first frame in the second frame. . After more than thirty years of development, there have been a lot of related researches on the optical flow estimation problem, but the robust optical flow estimation in real-world videos is still a challenging problem. [0003] Depending on the method used, optical flow estimation can be roughly divided into two types: one is based on the variational energy optimization model proposed by Horn and Schunck, and the other is based on the matching interpolation op...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide an efficient large-displacement optical flow estimation method, which aims to solve the main problem of the matching-based interpolation optimization model that the calculation of dense matching requires a considerable cost, and the accuracy of the matching result also directly affects the final optical flow The problem with estimating the effect

Images