A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images

Abhijit Kallapur; Murat Tahtali; Ian Petersen

doi:10.1109/CCA.2010.5611098

A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images

Abhijit Kallapur^*, Murat Tahtali, Ian Petersen

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

This paper presents the application of a robust extended Kalman filter (REKF) for an image processing problem in order to mitigate the effects of noise introduced during registration of geometrically warped anisoplanatic images. Emphasis is laid upon maintaining accuracy at the pixel-level. The perceived wander (random motion) of image intensities at the pixel level is modeled as a second-order oscillator, with a time-varying uncertain natural frequency. A robust extended Kalman filter (REKF) is used to estimate the state of the uncertain system and restore the pixel wander from a set of synthetically generated noisy measurements of registration shiftmaps. Also, a comparison of REKF and standard EKF estimation methods is presented.

Original language	English
Title of host publication	2010 IEEE International Conference on Control Applications, CCA 2010
Pages	280-285
Number of pages	6
DOIs	https://doi.org/10.1109/CCA.2010.5611098
Publication status	Published - 2010
Externally published	Yes
Event	2010 IEEE International Conference on Control Applications, CCA 2010 - Yokohama, Japan Duration: 8 Sept 2010 → 10 Sept 2010

Publication series

Name	Proceedings of the IEEE International Conference on Control Applications

Conference

Conference	2010 IEEE International Conference on Control Applications, CCA 2010
Country/Territory	Japan
City	Yokohama
Period	8/09/10 → 10/09/10

Access to Document

10.1109/CCA.2010.5611098

Cite this

Kallapur, A., Tahtali, M., & Petersen, I. (2010). A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images. In 2010 IEEE International Conference on Control Applications, CCA 2010 (pp. 280-285). Article 5611098 (Proceedings of the IEEE International Conference on Control Applications). https://doi.org/10.1109/CCA.2010.5611098

@inproceedings{923dea0546934c3a9cdabbcb93b32924,

title = "A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images",

abstract = "This paper presents the application of a robust extended Kalman filter (REKF) for an image processing problem in order to mitigate the effects of noise introduced during registration of geometrically warped anisoplanatic images. Emphasis is laid upon maintaining accuracy at the pixel-level. The perceived wander (random motion) of image intensities at the pixel level is modeled as a second-order oscillator, with a time-varying uncertain natural frequency. A robust extended Kalman filter (REKF) is used to estimate the state of the uncertain system and restore the pixel wander from a set of synthetically generated noisy measurements of registration shiftmaps. Also, a comparison of REKF and standard EKF estimation methods is presented.",

author = "Abhijit Kallapur and Murat Tahtali and Ian Petersen",

year = "2010",

doi = "10.1109/CCA.2010.5611098",

language = "English",

isbn = "9781424453627",

series = "Proceedings of the IEEE International Conference on Control Applications",

pages = "280--285",

booktitle = "2010 IEEE International Conference on Control Applications, CCA 2010",

note = "2010 IEEE International Conference on Control Applications, CCA 2010 ; Conference date: 08-09-2010 Through 10-09-2010",

}

Kallapur, A, Tahtali, M & Petersen, I 2010, A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images. in 2010 IEEE International Conference on Control Applications, CCA 2010., 5611098, Proceedings of the IEEE International Conference on Control Applications, pp. 280-285, 2010 IEEE International Conference on Control Applications, CCA 2010, Yokohama, Japan, 8/09/10. https://doi.org/10.1109/CCA.2010.5611098

A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images. / Kallapur, Abhijit; Tahtali, Murat; Petersen, Ian.
2010 IEEE International Conference on Control Applications, CCA 2010. 2010. p. 280-285 5611098 (Proceedings of the IEEE International Conference on Control Applications).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images

AU - Kallapur, Abhijit

AU - Tahtali, Murat

AU - Petersen, Ian

PY - 2010

Y1 - 2010

N2 - This paper presents the application of a robust extended Kalman filter (REKF) for an image processing problem in order to mitigate the effects of noise introduced during registration of geometrically warped anisoplanatic images. Emphasis is laid upon maintaining accuracy at the pixel-level. The perceived wander (random motion) of image intensities at the pixel level is modeled as a second-order oscillator, with a time-varying uncertain natural frequency. A robust extended Kalman filter (REKF) is used to estimate the state of the uncertain system and restore the pixel wander from a set of synthetically generated noisy measurements of registration shiftmaps. Also, a comparison of REKF and standard EKF estimation methods is presented.

AB - This paper presents the application of a robust extended Kalman filter (REKF) for an image processing problem in order to mitigate the effects of noise introduced during registration of geometrically warped anisoplanatic images. Emphasis is laid upon maintaining accuracy at the pixel-level. The perceived wander (random motion) of image intensities at the pixel level is modeled as a second-order oscillator, with a time-varying uncertain natural frequency. A robust extended Kalman filter (REKF) is used to estimate the state of the uncertain system and restore the pixel wander from a set of synthetically generated noisy measurements of registration shiftmaps. Also, a comparison of REKF and standard EKF estimation methods is presented.

UR - http://www.scopus.com/inward/record.url?scp=78649410417&partnerID=8YFLogxK

U2 - 10.1109/CCA.2010.5611098

DO - 10.1109/CCA.2010.5611098

M3 - Conference contribution

SN - 9781424453627

T3 - Proceedings of the IEEE International Conference on Control Applications

SP - 280

EP - 285

BT - 2010 IEEE International Conference on Control Applications, CCA 2010

T2 - 2010 IEEE International Conference on Control Applications, CCA 2010

Y2 - 8 September 2010 through 10 September 2010

ER -

A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this