Image registration and mosaicing of noisy acoustic camera images

Kio Kim; Nathan Intrator; Nicola Neretti

Image registration and mosaicing of noisy acoustic camera images

Kio Kim, Nathan Intrator, Nicola Neretti

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

Abstract

We introduce an algorithm for image registration and mosaicing on underwater sonar image sequences characterized by a high noise level, inhomogeneous illumination and low frame rate. For a planar surface viewed through a pinhole camera undergoing translational and rotational motion, registration can be obtained via a projective transformation. For an acoustic camera, we show that, under the same conditions, an affine transformation is a good approximation. We propose a novel image fusion, which maximizes the signal-to-noise ratio of the mosaic image. The full procedure includes illumination correction, feature based transformation estimation, and image fusion for mosaicing.

Original language	English
Title of host publication	11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004
Pages	527-530
Number of pages	4
State	Published - 2004
Externally published	Yes
Event	11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004 - Tel Aviv, Israel Duration: 13 Dec 2004 → 15 Dec 2004

Publication series

Name	11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004

Conference

Conference	11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004
Country/Territory	Israel
City	Tel Aviv
Period	13/12/04 → 15/12/04

Cite this

@inproceedings{f20376c6a6b74e6086506c5164171216,

title = "Image registration and mosaicing of noisy acoustic camera images",

abstract = "We introduce an algorithm for image registration and mosaicing on underwater sonar image sequences characterized by a high noise level, inhomogeneous illumination and low frame rate. For a planar surface viewed through a pinhole camera undergoing translational and rotational motion, registration can be obtained via a projective transformation. For an acoustic camera, we show that, under the same conditions, an affine transformation is a good approximation. We propose a novel image fusion, which maximizes the signal-to-noise ratio of the mosaic image. The full procedure includes illumination correction, feature based transformation estimation, and image fusion for mosaicing.",

author = "Kio Kim and Nathan Intrator and Nicola Neretti",

note = "Funding Information: This work was partly supported by ONR grant N00014-02-C-0296. We thank E. O. Belcher for providing full details about the data. Leon N Cooper and other members of IBNS have provided valuable comments.; null ; Conference date: 13-12-2004 Through 15-12-2004",

year = "2004",

language = "אנגלית",

isbn = "0780387155",

series = "11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004",

pages = "527--530",

booktitle = "11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004",

}

Kim, K, Intrator, N & Neretti, N 2004, Image registration and mosaicing of noisy acoustic camera images. in 11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004., WB1.1, 11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004, pp. 527-530, 11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004, Tel Aviv, Israel, 13/12/04.

Image registration and mosaicing of noisy acoustic camera images. / Kim, Kio; Intrator, Nathan; Neretti, Nicola.

11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004. 2004. p. 527-530 WB1.1 (11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004).

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

TY - GEN

T1 - Image registration and mosaicing of noisy acoustic camera images

AU - Kim, Kio

AU - Intrator, Nathan

AU - Neretti, Nicola

N1 - Funding Information: This work was partly supported by ONR grant N00014-02-C-0296. We thank E. O. Belcher for providing full details about the data. Leon N Cooper and other members of IBNS have provided valuable comments.

PY - 2004

Y1 - 2004

N2 - We introduce an algorithm for image registration and mosaicing on underwater sonar image sequences characterized by a high noise level, inhomogeneous illumination and low frame rate. For a planar surface viewed through a pinhole camera undergoing translational and rotational motion, registration can be obtained via a projective transformation. For an acoustic camera, we show that, under the same conditions, an affine transformation is a good approximation. We propose a novel image fusion, which maximizes the signal-to-noise ratio of the mosaic image. The full procedure includes illumination correction, feature based transformation estimation, and image fusion for mosaicing.

AB - We introduce an algorithm for image registration and mosaicing on underwater sonar image sequences characterized by a high noise level, inhomogeneous illumination and low frame rate. For a planar surface viewed through a pinhole camera undergoing translational and rotational motion, registration can be obtained via a projective transformation. For an acoustic camera, we show that, under the same conditions, an affine transformation is a good approximation. We propose a novel image fusion, which maximizes the signal-to-noise ratio of the mosaic image. The full procedure includes illumination correction, feature based transformation estimation, and image fusion for mosaicing.

UR - http://www.scopus.com/inward/record.url?scp=27644491101&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:27644491101

SN - 0780387155

T3 - 11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004

SP - 527

EP - 530

BT - 11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004

Y2 - 13 December 2004 through 15 December 2004

ER -

Image registration and mosaicing of noisy acoustic camera images

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this