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.