Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions

T Wan; G Tzagkarakis; P Tsakalides; CN Canagarajah; AM Achim

doi:10.1109/ICASSP.2008.4517858

Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions

T Wan, G Tzagkarakis, P Tsakalides, CN Canagarajah, AM Achim

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

15 Citations (Scopus)

497 Downloads (Pure)

Abstract

A novel context enhancement technique is presented to automatically combine images of the same scene captured at different times or seasons. A unique characteristic of the algorithm is its ability to extract and maintain the meaningful information in the enhanced image while recovering the surrounding scene information by fusing the background image. The input images are first decomposed into multiresolution representations using the Dual-Tree Complex Wavelet Transform (DT-CWT) with the subband coefficients modelled as Cauchy random variables. Then, the convolution of Cauchy distributions is applied as a probabilistic prior to model the fused coefficients, and the weights used to combine the source images are optimised via Maximum Likelihood (ML) estimation. Finally, the importance map is produced to construct the composite approximation image. Experiments show that this new model significantly improves the reliability of the feature selection and enhances fusion process.

Translated title of the contribution	Context enhancement through image fusion: a multiresolution approach based on convolution of Cauchy distributions
Original language	English
Title of host publication	IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1309 - 1312
Number of pages	4
ISBN (Print)	9781424414833, 1424414849
DOIs	https://doi.org/10.1109/ICASSP.2008.4517858
Publication status	Published - 2008
Event	2008 IEEE International Conference on Acoustics, Speech, and Signal Processing - Caesars Palace, Las Vegas, United States Duration: 30 Mar 2008 → 4 Apr 2008

Conference

Conference	2008 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP '08
Country/Territory	United States
City	Las Vegas
Period	30/03/08 → 4/04/08

Bibliographical note

Rose publication type: Conference contribution

Sponsorship: This work was supported by the Overseas Research Students Award
Scheme (ORSAS - Tao Wan), UK, and by the Greek General Secretariat for
Research and Technology under program EΠAN, Code 131-γ.

Terms of use: Copyright © 2008 IEEE. Reprinted from IEEE International Conference on Acoustics, Speech and Signal Processing, 2008 (ICASSP 2008).

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected].

By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Keywords

context enhancement
image fusion
surveillance
Cauchy distribution
wavelet decompostion

Access to Document

10.1109/ICASSP.2008.4517858

Wan IEEE ICASSP 2008Accepted author manuscript, 320 KB

http://hdl.handle.net/1983/1460

Handle.net

Persistent link

Cite this

Wan, T., Tzagkarakis, G., Tsakalides, P., Canagarajah, CN., & Achim, AM. (2008). Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions. In IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas (pp. 1309 - 1312). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2008.4517858

@inproceedings{6b4a2e057cde424d97004f5415fac6cf,

title = "Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions",

abstract = "A novel context enhancement technique is presented to automatically combine images of the same scene captured at different times or seasons. A unique characteristic of the algorithm is its ability to extract and maintain the meaningful information in the enhanced image while recovering the surrounding scene information by fusing the background image. The input images are first decomposed into multiresolution representations using the Dual-Tree Complex Wavelet Transform (DT-CWT) with the subband coefficients modelled as Cauchy random variables. Then, the convolution of Cauchy distributions is applied as a probabilistic prior to model the fused coefficients, and the weights used to combine the source images are optimised via Maximum Likelihood (ML) estimation. Finally, the importance map is produced to construct the composite approximation image. Experiments show that this new model significantly improves the reliability of the feature selection and enhances fusion process.",

keywords = "context enhancement, image fusion, surveillance, Cauchy distribution, wavelet decompostion",

author = "T Wan and G Tzagkarakis and P Tsakalides and CN Canagarajah and AM Achim",

note = "Rose publication type: Conference contribution Sponsorship: This work was supported by the Overseas Research Students Award Scheme (ORSAS - Tao Wan), UK, and by the Greek General Secretariat for Research and Technology under program EΠAN, Code 131-γ. Terms of use: Copyright {\textcopyright} 2008 IEEE. Reprinted from IEEE International Conference on Acoustics, Speech and Signal Processing, 2008 (ICASSP 2008). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. ; 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '08 ; Conference date: 30-03-2008 Through 04-04-2008",

year = "2008",

doi = "10.1109/ICASSP.2008.4517858",

language = "English",

isbn = "9781424414833",

pages = "1309 -- 1312",

booktitle = "IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Wan, T, Tzagkarakis, G, Tsakalides, P, Canagarajah, CN & Achim, AM 2008, Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions. in IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas. Institute of Electrical and Electronics Engineers (IEEE), pp. 1309 - 1312, 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing, Las Vegas, United States, 30/03/08. https://doi.org/10.1109/ICASSP.2008.4517858

Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions. / Wan, T; Tzagkarakis, G; Tsakalides, P et al.
IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas. Institute of Electrical and Electronics Engineers (IEEE), 2008. p. 1309 - 1312.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions

AU - Wan, T

AU - Tzagkarakis, G

AU - Tsakalides, P

AU - Canagarajah, CN

AU - Achim, AM

N1 - Rose publication type: Conference contribution Sponsorship: This work was supported by the Overseas Research Students Award Scheme (ORSAS - Tao Wan), UK, and by the Greek General Secretariat for Research and Technology under program EΠAN, Code 131-γ. Terms of use: Copyright © 2008 IEEE. Reprinted from IEEE International Conference on Acoustics, Speech and Signal Processing, 2008 (ICASSP 2008). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

PY - 2008

Y1 - 2008

N2 - A novel context enhancement technique is presented to automatically combine images of the same scene captured at different times or seasons. A unique characteristic of the algorithm is its ability to extract and maintain the meaningful information in the enhanced image while recovering the surrounding scene information by fusing the background image. The input images are first decomposed into multiresolution representations using the Dual-Tree Complex Wavelet Transform (DT-CWT) with the subband coefficients modelled as Cauchy random variables. Then, the convolution of Cauchy distributions is applied as a probabilistic prior to model the fused coefficients, and the weights used to combine the source images are optimised via Maximum Likelihood (ML) estimation. Finally, the importance map is produced to construct the composite approximation image. Experiments show that this new model significantly improves the reliability of the feature selection and enhances fusion process.

AB - A novel context enhancement technique is presented to automatically combine images of the same scene captured at different times or seasons. A unique characteristic of the algorithm is its ability to extract and maintain the meaningful information in the enhanced image while recovering the surrounding scene information by fusing the background image. The input images are first decomposed into multiresolution representations using the Dual-Tree Complex Wavelet Transform (DT-CWT) with the subband coefficients modelled as Cauchy random variables. Then, the convolution of Cauchy distributions is applied as a probabilistic prior to model the fused coefficients, and the weights used to combine the source images are optimised via Maximum Likelihood (ML) estimation. Finally, the importance map is produced to construct the composite approximation image. Experiments show that this new model significantly improves the reliability of the feature selection and enhances fusion process.

KW - context enhancement

KW - image fusion

KW - surveillance

KW - Cauchy distribution

KW - wavelet decompostion

U2 - 10.1109/ICASSP.2008.4517858

DO - 10.1109/ICASSP.2008.4517858

M3 - Conference Contribution (Conference Proceeding)

SN - 9781424414833

SN - 1424414849

SP - 1309

EP - 1312

BT - IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 30 March 2008 through 4 April 2008

ER -

Wan T, Tzagkarakis G, Tsakalides P, Canagarajah CN, Achim AM. Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions. In IEEE International Conference on Acoustic, Speech and Signal Processes (ICASSP 2008), Las Vegas. Institute of Electrical and Electronics Engineers (IEEE). 2008. p. 1309 - 1312 doi: 10.1109/ICASSP.2008.4517858

Context enhancement through image fusion: A multiresolution approach based on convolution of cauchy distributions

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this