An improved mutual information similarity measure for registration of multi-modal remote sensing images

Maha Shadaydeh, T. Szirányi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Registration of multi-modal remote sensing images is an essential and challenging task in different remote sensing applications such as image fusion and multi-temporal change detection. Mutual Information (MI) has shown to be successful similarity measure for multi-modal image registration applications, however it has some drawbacks. 1. MI surface is highly non-convex with many local maxima. 2. Spatial information is completely lost in the calculation of the joint intensity probability distribution. In this paper, we present an improved MI similarity measure based on a new concept in integrating other image features as well as spatial information in the estimation of the joint intensity histogram which is used as an estimate of the joint probability distribution. The proposed method is based on the idea that each pixel in the reference image is assigned a weight, then each bin in the joint histogram is calculated as the summations of the weights of the pixels corresponding to that bin. The weight given to each pixel in the reference image is an exponential function of the corresponding pixel values in a distance image and a normalized gradient image such that higher weights are given to points close to one or more selected key points as well as points with high normalized gradient values. The proposed method is in essence a kind of calculating similarity measure using irregular sampling where sampling frequency is higher in areas close to key-points or areas with higher gradients. We have compared the proposed method with the conventional MI and Normalized MI methods for registration of pairs of multi-temporal multi-modal remote sensing images. We observed that the proposed method produces considerably better registration function containing fewer erroneous maxima and leading to higher success rate.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSPIE
Volume9643
ISBN (Print)9781628418538
DOIs
Publication statusPublished - 2015
EventImage and Signal Processing for Remote Sensing XXI - Toulouse, France
Duration: Sep 21 2015Sep 23 2015

Other

OtherImage and Signal Processing for Remote Sensing XXI
CountryFrance
CityToulouse
Period9/21/159/23/15

Fingerprint

Information Measure
Remote Sensing Image
Mutual Information
Similarity Measure
Registration
remote sensing
Remote sensing
Pixels
Pixel
Bins
Probability distributions
Spatial Information
Gradient
Histogram
Sampling
pixels
Probability Distribution
Irregular Sampling
Image fusion
Exponential functions

Keywords

  • joint intensity histogram
  • Multi-modal Image Registration
  • mutual information

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Shadaydeh, M., & Szirányi, T. (2015). An improved mutual information similarity measure for registration of multi-modal remote sensing images. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 9643). [96430F] SPIE. https://doi.org/10.1117/12.2194319

An improved mutual information similarity measure for registration of multi-modal remote sensing images. / Shadaydeh, Maha; Szirányi, T.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9643 SPIE, 2015. 96430F.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shadaydeh, M & Szirányi, T 2015, An improved mutual information similarity measure for registration of multi-modal remote sensing images. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 9643, 96430F, SPIE, Image and Signal Processing for Remote Sensing XXI, Toulouse, France, 9/21/15. https://doi.org/10.1117/12.2194319
Shadaydeh M, Szirányi T. An improved mutual information similarity measure for registration of multi-modal remote sensing images. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9643. SPIE. 2015. 96430F https://doi.org/10.1117/12.2194319
Shadaydeh, Maha ; Szirányi, T. / An improved mutual information similarity measure for registration of multi-modal remote sensing images. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9643 SPIE, 2015.
@inproceedings{2be1dbb7e837439486738751c931009b,
title = "An improved mutual information similarity measure for registration of multi-modal remote sensing images",
abstract = "Registration of multi-modal remote sensing images is an essential and challenging task in different remote sensing applications such as image fusion and multi-temporal change detection. Mutual Information (MI) has shown to be successful similarity measure for multi-modal image registration applications, however it has some drawbacks. 1. MI surface is highly non-convex with many local maxima. 2. Spatial information is completely lost in the calculation of the joint intensity probability distribution. In this paper, we present an improved MI similarity measure based on a new concept in integrating other image features as well as spatial information in the estimation of the joint intensity histogram which is used as an estimate of the joint probability distribution. The proposed method is based on the idea that each pixel in the reference image is assigned a weight, then each bin in the joint histogram is calculated as the summations of the weights of the pixels corresponding to that bin. The weight given to each pixel in the reference image is an exponential function of the corresponding pixel values in a distance image and a normalized gradient image such that higher weights are given to points close to one or more selected key points as well as points with high normalized gradient values. The proposed method is in essence a kind of calculating similarity measure using irregular sampling where sampling frequency is higher in areas close to key-points or areas with higher gradients. We have compared the proposed method with the conventional MI and Normalized MI methods for registration of pairs of multi-temporal multi-modal remote sensing images. We observed that the proposed method produces considerably better registration function containing fewer erroneous maxima and leading to higher success rate.",
keywords = "joint intensity histogram, Multi-modal Image Registration, mutual information",
author = "Maha Shadaydeh and T. Szir{\'a}nyi",
year = "2015",
doi = "10.1117/12.2194319",
language = "English",
isbn = "9781628418538",
volume = "9643",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",

}

TY - GEN

T1 - An improved mutual information similarity measure for registration of multi-modal remote sensing images

AU - Shadaydeh, Maha

AU - Szirányi, T.

PY - 2015

Y1 - 2015

N2 - Registration of multi-modal remote sensing images is an essential and challenging task in different remote sensing applications such as image fusion and multi-temporal change detection. Mutual Information (MI) has shown to be successful similarity measure for multi-modal image registration applications, however it has some drawbacks. 1. MI surface is highly non-convex with many local maxima. 2. Spatial information is completely lost in the calculation of the joint intensity probability distribution. In this paper, we present an improved MI similarity measure based on a new concept in integrating other image features as well as spatial information in the estimation of the joint intensity histogram which is used as an estimate of the joint probability distribution. The proposed method is based on the idea that each pixel in the reference image is assigned a weight, then each bin in the joint histogram is calculated as the summations of the weights of the pixels corresponding to that bin. The weight given to each pixel in the reference image is an exponential function of the corresponding pixel values in a distance image and a normalized gradient image such that higher weights are given to points close to one or more selected key points as well as points with high normalized gradient values. The proposed method is in essence a kind of calculating similarity measure using irregular sampling where sampling frequency is higher in areas close to key-points or areas with higher gradients. We have compared the proposed method with the conventional MI and Normalized MI methods for registration of pairs of multi-temporal multi-modal remote sensing images. We observed that the proposed method produces considerably better registration function containing fewer erroneous maxima and leading to higher success rate.

AB - Registration of multi-modal remote sensing images is an essential and challenging task in different remote sensing applications such as image fusion and multi-temporal change detection. Mutual Information (MI) has shown to be successful similarity measure for multi-modal image registration applications, however it has some drawbacks. 1. MI surface is highly non-convex with many local maxima. 2. Spatial information is completely lost in the calculation of the joint intensity probability distribution. In this paper, we present an improved MI similarity measure based on a new concept in integrating other image features as well as spatial information in the estimation of the joint intensity histogram which is used as an estimate of the joint probability distribution. The proposed method is based on the idea that each pixel in the reference image is assigned a weight, then each bin in the joint histogram is calculated as the summations of the weights of the pixels corresponding to that bin. The weight given to each pixel in the reference image is an exponential function of the corresponding pixel values in a distance image and a normalized gradient image such that higher weights are given to points close to one or more selected key points as well as points with high normalized gradient values. The proposed method is in essence a kind of calculating similarity measure using irregular sampling where sampling frequency is higher in areas close to key-points or areas with higher gradients. We have compared the proposed method with the conventional MI and Normalized MI methods for registration of pairs of multi-temporal multi-modal remote sensing images. We observed that the proposed method produces considerably better registration function containing fewer erroneous maxima and leading to higher success rate.

KW - joint intensity histogram

KW - Multi-modal Image Registration

KW - mutual information

UR - http://www.scopus.com/inward/record.url?scp=84961572635&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961572635&partnerID=8YFLogxK

U2 - 10.1117/12.2194319

DO - 10.1117/12.2194319

M3 - Conference contribution

AN - SCOPUS:84961572635

SN - 9781628418538

VL - 9643

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - SPIE

ER -