Time reference real-time calibration method and system for image collection platform

Abstract

The invention discloses a time reference real-time calibration method and system for an image collection platform, and the method is used in a mobile terminal. The method comprises the following steps: S1, obtaining a current image frame and N former image frames; S2, extracting first feature points in the current image frame so as to form a first feature point set, and extracting second feature points in a reference image frame so as to form a second feature point set; S3, carrying out the matching filtering of the first feature points in the first feature point set and the second feature points in the second feature point set, so as to obtain a first feature point pair set; S4, obtaining the mean overall displacement of the current image frame according to the first feature point pair set; S5, extracting gyroscopic data of a gyro sensor of the current image frame, and obtaining the posture overall displacement of the current image frame according to the gyroscopic data; S6, obtaining the time difference between a time stamp of a camera and a time stamp of the gyro sensor according to the Kalman filtering method, calibrating the time difference, and executing step S1.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and system for real-time calibration of a time reference based on a mobile terminal image acquisition platform. Background technique [0002] With the rapid development of electronic technology, people use mobile terminals, drones and other mobile platforms for video collection applications more and more. However, because the video captured by mobile terminals or drones is prone to jitter and has poor visual effects, it usually cannot be used normally, and the captured video needs to be stabilized. The image stabilization methods of different video image acquisition platforms according to the principles mainly include three categories: mechanical image stabilization, optical image stabilization and electronic image stabilization. [0003] Mechanical image stabilization uses a shock-absorbing platform or a mechanical gimbal to passively offset various jitters. Its advanta...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problem that the existing digital image acquisition system of the mobile platform cannot overcome the problem of time offset and attitude difference, an image acquisition platform that aims to realize the time difference between the time stamp of the camera and the time stamp of the gyro sensor can be obtained in real time Time base real-time calibration method and system

Images