A Real Time Video Stabilization Algorithm
Jitter or unintentional motion during image capture, poses a critical problem for any image processing application. Video stabilization is a technique used to correct images against unintentional camera motion. We propose a simple and fast video stabilization algorithm that can be used for real time pre-processing of images, which is especially useful in automotive vision applications. Corner and edge based features have been used for the proposed stabilization method. An affine model is used to estimate the motion parameters using these features. A scheme to validate the features and a variant of iterative least squares algorithm to eliminate the outliers is also proposed. The motion parameters obtained are smoothed using a moving average filter, which eliminates the higher frequency jitters obtained due to unintentional motion. The algorithm can be used to correct translational and rotational distortions arising in the video due to jitter.
KeywordsVideo Stabilization Corner detection Affine Transform Moving average filter Dolly motion
Unable to display preview. Download preview PDF.
- 1.Vella, F., Castorina, A., Mancuso, M., Messina, G.: Digital image stabilization by adaptive block motion vector filtering. IEEE Trans. on Consumer Electronics 48(3) (August 2002)Google Scholar
- 6.Litvin, A., Konrad, J., Karl, W.C.: Probabilistic video stabilization using Kalman filtering and mosaicking. In: Proc. of SPIE Electronic Imaging, vol. 5022, pp. 663–674 (2003)Google Scholar
- 8.Harris, C., Stephens, M.: A combined corner and edge detection. In: Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 287–293 (May 2002)Google Scholar
- 9.Tico, M., Vehvilainen, M.: Robust Method of Videos Stabilization. In: EUSIPCO (September 2007)Google Scholar
- 10.Chang, H.C., Lai, S.H., Lu, K.R.: A robust and efficient video stabilization algorithm. In: ICME 2004: International Conference on Multimedia and Expo., vol. 1, pp. 29–32, 7, 30, 40, 49, 64. IEEE, Los Alamitos (2004)Google Scholar