Abstract:
Mosaicing and super resolution are two ways to combine information from multiple frames in video sequences. Mosaicing displays the information of multiple frames in a single panoramic image. Super-resolution uses regions which appear in multiple frames to improve resolution and reduce noise. Combining both methods enables to represent all the static information in the sequence in a compact and visual way. This work presents new algorithms for mosaicing, super resolution, and their combination. In the rst part, a solution is proposed for mosaicing video sequences taken from a translating camera. Based on some general assumptions on the geometrical structure of the scene, the algorithm handles the parallax which is the result of depth di erences, and creates a mosaic image which is tailored to the scene. We call this method Generalized Manifold Mosaicing. Only few of the existing mosaicing algorithms can handle these depth di erences, and it is shown that the proposed algorithm outperforms them. The proposed algorithm can also solve the case of a camera rotating along an arbitrary constant axis. When trying to combine mosaicing and super resolution there is a problem: The alignment
Citations
|
461
|
Hierarchical modelbased motion estimation
– Bergen, Anandan, et al.
- 1992
|
|
199
|
Video mosaics for virtual environments
– Szeliski
- 1996
|
|
190
|
Catadioptric omnidirectional camera
– Nayar
- 1997
|
|
178
|
Iterative Methods for Linear and Nonlinear Equations
– Kelley
- 1995
|
|
142
|
Improving Resolution by Image Registration
– Irani, Peleg
- 1991
|
|
122
|
Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images
– Elad, Feuer
- 1997
|
|
122
|
Extraction of highresolution frames from video sequences
– Schultz, Stevenson
- 1996
|
|
104
|
Mosaic based representation of video sequences and their applications
– Irani, Anandan, et al.
- 1995
|
|
104
|
Virtual bellows: Constructing high-quality images from video
– Mann, Picard
- 1994
|
|
95
|
Motion analysis for image enhancement: resolution, occlusion and transparency
– Irani, Peleg
- 1993
|
|
82
|
Panoramic mosaics by manifold projection
– Peleg, Herman
- 1997
|
|
71
|
Tekalp, “Superresolution Video Reconstruction with Arbitrary Sampling Lattices and Nonzero Aperture Time
– Patti, Sezan, et al.
- 1997
|
|
64
|
Panoramic representation for route recognition by a mobile robot
– Zheng, Tsuji
- 1992
|
|
59
|
Stereo panorama with a single camera
– Peleg, Ben-Ezra
- 1999
|
|
54
|
Improved resolution from sub-pixel shifted pictures
– Ur, Gross
- 1992
|
|
39
|
Truncated sampling expansions
– Papoulis
- 1967
|
|
39
|
High resolution image recovery from image-plane arrays, using convex projections
– Stark, Oskoui
- 1989
|
|
33
|
Image sequence enhancement using sub-pixel displacements
– Keren, Peleg, et al.
- 1988
|
|
21
|
Universal Mosaicing Using Pipe Projection
– Peleg, Rousso
- 1998
|
|
16
|
Reconstruction of high resolution 3d visual information using sub-pixel camera displacements
– Berthod, Shekarforoush, et al.
- 1994
|
|
16
|
Data-driven multichannel superresolution with application to video sequences
– Shekarforoush, Chellappa
- 1999
|
|
11
|
Mosaicing with generalized strips
– Rousso, Peleg, et al.
- 1997
|
|
11
|
Applying superresolution to panoramic mosaics
– Zomet, Peleg
- 1998
|
|
5
|
Super-resolution reconstruction of continuous image sequence
– Elad, Feuer
- 1996
|
|
3
|
Recursive reconstraction of high-resolution image from noisy undersampled frames
– Kim, Bose, et al.
- 1990
|
|
2
|
Generation of high-resolution stereo panoramic images by omnidirectional imaging sensor using hexagonal pyramidal mirrors
– Yokoya, Iwasa, et al.
- 1998
|
|
1
|
The periodic step gradient descent algorithm - general analysis and application to the super-resolution reconstuction problem
– Elad, Feuer, et al.
- 1998
|
