Video stabilization method based on SURF for enhancing accuracy and reliability

摘要

In the present invention, when a first error occurs in the first mismatch determination step (S70) and the first mismatch restoration step (S80), the position of the corresponding feature point using the transformation matrix H estimated by the transformation matrix estimator While generating restoration information including (x, y) and the position (x', y') of the second frame, the second mismatch determination step (S90) and the second mismatch restoration step (S100) are performed in the second When an error occurs, it is configured to generate a new tracker corresponding to the corresponding key point, and the generated restoration information and the new tracker are configured to be utilized in the Kalman filter update step (S110) and the image mapping step (S120), so whether the key point is mismatched The accuracy of image stabilization can be improved by accurately determining and restoring It is configured to update the weight of the Kalman filter so that the restoration information generated by step S80 and the new tracker generated by the second mismatch restoration step S100 are reflected, thereby maximizing the accuracy and reliability of feature point tracking. It relates to an image stabilization method based on SURF feature point tracking.