Video sequence registering method based on combination of motion information and background information

Abstract

The invention discloses a video sequence registering method based on combination of motion information and background information. The method mainly solves the problem that in the prior art, video sequences in different view points cannot be accurately registered. The method includes the steps that (1) separation of background images and motion targets is carried out on two input video sequences; (2) feature point matching pairs of the background images are obtained, and basis matrixes between the background images are calculated; (3) four sets of matching point pairs corresponding to four spatial points not on the same plane in a three-dimensional space are selected from the background images; (4) intersection points of projection lines, in another video sequence, of points in motion tracks and bipolar lines are obtained; (5) motion track points are matched and a point pair set corresponding to candidate time is obtained; (6) a time line is fitted and time transformation parameters are recovered. The time relation between video sequences can be accurately recovered, registering accuracy is improved and the method can be used for registering video sequences with static backgrounds.

Description

technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a video sequence registration method, the object of which is to calibrate video sequences shot from different angles of view or at different times, which can be applied to video sequence registration of static backgrounds. Background technique [0002] Video sequence registration is an important field of image processing. It calculates the spatio-temporal transformation parameters between similar videos of the same scene from different perspectives or at different times obtained by multiple sensors, and then synchronizes these videos in time and in space. geometric calibration. In general, feature-based methods can be used, especially methods characterized by moving object trajectories for video sequence registration. These motion-trajectory-based video sequence registration methods mainly consider the shape of the motion trajectory itself or the polarity b...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that because this method only considers the information of the trajectory itself and uses the local features in the neighborhood of the trajectory point to describe the trajectory point, when there are multiple moving objects in the scene and the trajectory is similar, or when the trajectory When there are a large number of trajectory segments with similar local characteristics, the obtained trajectory descriptors are not very distinguishable. In these cases, the registration results of the video sequences obtained by this method have large errors or even cannot complete the registration.

Images