Invariant feature extraction for color image mosaic by graph card processing

Image mosaic can be widely used in remote measuring, scout in battlefield and Panasonic image demonstration. In this project, we find a general method for video (or sequence images) mosaic by techniques, such as extracting invariant features, gpu processing, multi-color feature selection, ransac algorithm for homograph matching. In order to match the image sequence automatically without influence of rotation, scale and contrast transform, local invariant feature descriptor have been extracted by graph card unit. The gpu mosaic algorithm performs very well that can be compare to slow CPU version of mosaic program with little cost time.

[1]  Jiri Matas,et al.  Matching with PROSAC - progressive sample consensus , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[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]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[4]  Thomas Wiegand,et al.  SIFT Implementation and Optimization for General-Purpose GPU , 2007 .

[5]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

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

[7]  Matthew A. Brown,et al.  Invariant Features from Interest Point Groups , 2002, BMVC.