Optical flow estimation method based on multiple dimensioned corresponding structuring learning

Abstract

The invention discloses an optical flow estimation method based on multiple dimensioned corresponding structuring learning; under given successive video frames, the method can parse the motion conditions of the first frame relative to the second frame; the method specifically comprises the following steps: obtaining a successive frame image data set used for training optical flow estimation, and defining an algorithm object; carrying out structuring modeling for correspondences between two successive frame images in different dimensions; joint encoding the corresponding relations in different dimensions; building an optical flow estimation prediction model; using the prediction model to estimate the successive video frame optical flow values. The optical flow estimation method is applied to the optical flow motion analysis in true videos, and can provide better effect and robustness under various complex conditions.

Description

Technical field [0001] The present invention belongs to the field of computer vision, and particularly relates to an optical flow estimation method based on multi-scale corresponding structured learning. Background technique [0002] As a low-level vision technology, optical flow estimation is often used as auxiliary information for some high-level vision tasks, such as video abnormal event detection, video action recognition, etc. Optical flow considers the correlation between frames by providing motion information between video frames Inside. The goal of optical flow estimation is to predict the motion displacement of each pixel in the first frame given two consecutive video frames. The key factors of optical flow estimation include robust representation of pixels or image regions, modeling of correspondence between pixels, and computational effectiveness. Traditional methods generally regard the task of optical flow estimation as a sparse or dense pixel matching problem. Alt...

AI Technical Summary

Problems solved by technology

However, for the former, it is often difficult to determine an appropriate search range, especially for large-displacement motion; for the latter, once the prediction error is made on a coarse scale, it is likely to cause this error to propagate backwards and make the prediction wrong result

Images