Implementation of Video Stabilization Algorithm for Surveillance System

Aerial video surveillance plays an important role in gathering the information for the public as well as military applications. Now-a-days cameras used for capturing video are of high quality, but because of the unintentional movement of cameras, the video gets unstabilized. The main aim of the video stabilization is to remove the unintentional motion and shakiness in the videos and preserve the desired motion. In this approach, speeded up robust features (SURF) and scale-invariant feature transform (SIFT) methods are used to detect and match the feature points of interest. The outliers and noise are removed using RANSAC, while affine transform is used to estimate the motion of the interest points. Finally, the video gets stabilized by compensating the global motion points obtained by the affine transform. These approaches for video stabilization show promising results in terms of Inter Transformation Fidelity (ITF) values for SURF and SIFT algorithms.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Harry Shum,et al.  Full-frame video stabilization with motion inpainting , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Michael Bosse,et al.  Non-metric image-based rendering for video stabilization , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Cecilio Angulo,et al.  Real-time video stabilization without phantom movements for micro aerial vehicles , 2014, EURASIP J. Image Video Process..

[6]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[7]  Wenbin Chen,et al.  Video Stabilization Using Scale-Invariant Features , 2007, 2007 11th International Conference Information Visualization (IV '07).

[8]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[9]  Li-Chen Fu,et al.  Multilayered Image Processing for Multiscale Harris Corner Detection in Digital Realization , 2010, IEEE Transactions on Industrial Electronics.

[10]  Michael Teutsch,et al.  Detection, Segmentation, and Tracking of Moving Objects in UAV Videos , 2012, 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance.

[11]  Huizhong Chen,et al.  Efficient Video Stabilization with Dual-Tree Complex Wavelet Transform , 2010 .