Abstract
Image mosaicking is about constructing an image of a large field of view called mosaic from adjacent images, typically two, of the same scene. The problem is particularly difficult if the camera motion is arbitrary and the imaged scene is not planar and is in close range of the camera. In this paper, a novel mosaicking scheme applicable to polyhedral scene in the above scenario is described. The scheme requires only a few initial correspondences over the input images to work. A particular essence of the scheme is that it could handle surfaces that are visible in only one of the input images, and include them into the mosaic. In mosaic construction one has to line up, in the mosaic, surface boundaries that are corresponding but warped from the respective input images. A simple solution to that is also described, which requires only a minimum number of correspondences over the involved surfaces to have the task achieved seamlessly. Experimental results on real images show that the proposed mosaicking scheme is effective.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chung, R.: Object Locating using a single Model View. In: Proc. of IEEE International Symposium on Computer Vision, Florida, November 1995, pp. 545–550 (1995)
Chung, R., Wong, H.S.: Polyhedral Object Localization by referencing to a Single Model View. To appear in International Journal of Computer Vision
Faugeras, O.: Stratification of three-dimensional vision: projective, affine, and metric representations. Journal of the Optical Society of America: A 12(3), 465–484 (1995)
Mann, S., Picard, R.: Virtual bellows: Constructing high quality stills from video. In: First IEEE International Conference on Image Processing, Austin, Texas, November 1994, vol. I, pp. 363–367 (1994)
Nevatia, R., Babu, K.R.: Linear feature extraction and description. Computer Graphics and image processing 13, 257–269 (1980)
Semple, J.G., Kneebone, G.T.: Algebraic Projective Geometry. Oxford University Press, London (1952)
Szeliski, R.: Video mosaics for virtual environments. IEEE Computer Graphics and Applications 16(2), 22–30 (1996)
Zhang, Z., Deriche, R., Faugeras, O., Luong, Q.-T.: A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry. Artificial Intelligence Journal 78, 87–119 (1995)
Zoghlami, I., Faugeras, O., Deriche, R.: Using Geometry Corners to Build a 2D Mosaic from a set of Images. In: Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, June 1997, pp. 420–425 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
He, Y., Chung, R. (2003). Polyhedral Scene: Mosaic Construction from 2 Images Taken under the General Case. In: Petkov, N., Westenberg, M.A. (eds) Computer Analysis of Images and Patterns. CAIP 2003. Lecture Notes in Computer Science, vol 2756. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45179-2_80
Download citation
DOI: https://doi.org/10.1007/978-3-540-45179-2_80
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40730-0
Online ISBN: 978-3-540-45179-2
eBook Packages: Springer Book Archive