Video stabilization based on modified invariant feature

Abstract

To accurately estimate the motion parameters, especially for rotation, scale and transition, a new invariant feature descriptor is proposed based on simplified polar sampling. The Gaussian weighed regions in original version are replaced by the uniform weighted regions. Fast calculation of gradient-orientation histogram by means of integral map is adopted to improve the efficiency. Then a new method is proposed based on linear fitting of motion path and it can estimate the current frame position by local fitting parameters. The frame rate of stabilized output can reach 30 f/s, which gains notable improvement compared with the general invariant feature methods such as SIFT and SURF.

Keywords

Feature Point / Motion Estimation / Current Frame / Polar Arrangement / Motion Curve

References

[1] LoweD.. International Journal of Computer Vision, 2004, 60: 91

[2] MatsushitaY., OfekE., GeW., TangX., ShumH.-Y.. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28: 1150

[3] S. Winder and M. Brown, IEEE Conference on Computer Vision and Pattern Recognition, 2007, 1.

[4] Andrew Litvin, Janusz Konrad and William C. Karl, SPIE Conference on Electronic Imaging, Santa Clara, 2003, 663.

[5] H. Bay, T. Tuytelaars and L. Van Gool, 9th European Conference on Computer Vision, 2006.