Automatic Digital Image Stabilization

This paper presents an automatic digital image stabilization system that is able to handle large image displacements. The system has been implemented in a parallel pipeline image processing hardware (Datacube Max Video 200) connected to a SUN SPARCstation 20/612 via a VME bus adaptor. Our technique is based on a two-dimensional feature-based multi-resolution motion estimation algorithm, that tracks a small set of features to estimate the motion of the camera. Stabilization is achieved by combining all motion from a reference frame and subtracting this motion from the current frame. Preliminary experimental results using video sequences taken from a camera rigidly mounted on a vehicle moving on rough terrain demonstrate the robustness of the system when processing 15 frames per second.

[1]  Qi Tian,et al.  Algorithms for subpixel registration , 1986 .

[2]  Thierry Viéville,et al.  Computation of ego-motion and structure from visual and inertial sensors using the vertical cue , 1993, 1993 (4th) International Conference on Computer Vision.

[3]  Rama Chellappa,et al.  A computational vision approach to image registration , 1993, IEEE Trans. Image Process..

[4]  Michal Irani,et al.  Recovery of ego-motion using image stabilization , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Kristin J. Dana,et al.  Real-time scene stabilization and mosaic construction , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[6]  Larry S. Davis,et al.  RSTA on the Move , 1994 .

[7]  Oh-Jin Kwon,et al.  Motion compensated subband coding of video acquired from a moving platform , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[8]  Larry S. Davis,et al.  Detection of independently moving objects in passive video , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[9]  R. Chellappa,et al.  Electronic image stabilization using multiple visual cues , 1995, Proceedings., International Conference on Image Processing.