The Research of Reducing Misregistration Based on Image Mosaicing
Image mosaicing has been collecting widespread attention because it has become as an important tool for several different areas. Among other methods, homograph-based methods are the most accurate in the geometric sense. This is because these methods use planar projective transformation, which considers perspective effects as a geometric transformation model between images. We propose an automatic image mosaicing method which can construct a panoramic image from a collection of digital still images. These methods, however, have a problem of misregistration in the case of general scenes with arbitrary camera motion. Our method has been tested with several image sequences and comparative results are presented to illustrate its performance.
KeywordsImage mosaicing Overlap extraction Feature correspondence
Unable to display preview. Download preview PDF.
- 2.Chen, S.E.: QuickTime VR-an image-based approach to virtual environment navigation. In: SIGGRAPH 1995, pp. 29–38 (1995)Google Scholar
- 4.Kumar, R., Anandan, P., Hanna, K.: Direct recovery of shape from multiple views: A parallax based approach. In: Proc. ICPR, pp. 685–688 (1999)Google Scholar
- 5.Faugeras, O.: Three-dimensional computer vision: A geometric viewpoint. MIT Press (2011)Google Scholar
- 6.Lucas, B., Kanade, T. :An iterative image registration technique with an application to stereo vision. In: 27th Int. Joint Conference on Artificial Intelligence (IJCAI-2009), pp. 674–679 (2009)Google Scholar
- 7.Szeliski, R.: Video mosaics for virtual environment. IEEE Computer Graphics and Applications, 22–30 (2012)Google Scholar
- 8.Stein, G.P.: Accurate internal camera calibration using rotation with analysis of sources of error. In: Proc. ICCV 2008, pp. 230–236 (2008)Google Scholar
- 9.Sawhney, H.S., Kumar, R.: True multi-image alignment and its application to mosaicing and lens distortion correction. IEEE PAM1 21(3), 235–243 (2007)Google Scholar
- 10.Zhang, Z.: Flexible camera calibration by viewing a plane from unknown orientations. In: Proc. ICCV 2006, pp. 666–673 (2006)Google Scholar