Gradient-based approach for fine registration of panorama images
- 44 Downloads
This paper studies the application of gradient-based motion detection techniques (i.e., optical flow methods) for registration of adjacent images taken using a hand-held camera for the purposes of building a panorama. A general 8-parameter model or a more compact 3-parameter model is commonly used for transformation estimation. However, both models are approximations to the real situation when viewpoint position is not absolutely fixed but includes a small translation, and thus distortion and blurring are sometimes present in the final registration results. This paper proposes a new 5-parameter model that shows better result and has less strict requirement on good choice of unknown initial parameters. An analysis of disparity recovery range and its enlargement using Gaussian filter is also given.
Keywordsimage registration motion estimation optical flow computer vision
- Brown M Z, Burscka D, Hager G D. Advances in computational stereo. InIEEE Trans. Pattern Analysis and Machine Intelligence, 2003, 25(8): 993–1008.Google Scholar
- Irani M, Anandan P, Hsu S. Mosaic based representations of video sequences and their applications. InFifth International Conference on Computer Vision (ICCV'95), Cambridge, Massachusetts, 1995, pp. 605–611.Google Scholar
- Bergen J R, Anandan P, Hanna K J, Hingorani R. Hierarchical model-based motion estimation. InProc. European Conference on Computer Vision, Santa Margarita Ligure, 1992, pp. 237–252.Google Scholar
- Szeliski R, Shum H-Y. Creating full view panoramic image mosaics and environment maps.Computer Graphics (SIGGRAPH'97), 1997, pp. 251–258.Google Scholar