An improved local similarity measure estimation for change detection in remote sensing images

Maha Shadaydeh, T. Szirányi

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

3 Citations (Scopus)

Abstract

Detecting changes in remote sensing images taken at different times is challenging when images' data come from different sensors. The performance of change detection algorithms based on radiometric values alone is not satisfactory and need the fusion of other features. Local similarity measures such as Mutual Information, Kullback-Leibler Divergence, and Cluster Reward Algorithm can be used for enhancing change detection. In the paper, we propose an improved local similarity measure using weighted local histogram. Each pixel contributes to the calculation of the histogram according to its weight only. The weight assigned to each pixel in the histogram estimation window follows an exponential function of its distance from the center of the window and the corresponding pixel value in an initial change map image which is derived from other micro-structure or radiometric information. The proposed improved similarity measure benefits from the good detection ability of small estimation window and the good estimation accuracy of large estimation window; hence it can replace the time-consuming multi-scale selection approaches for statistics based similarity measures in remote sensing. The efficiency of this useful improvement has been validated on change detection in remote sensing image series.

Original languageEnglish
Title of host publicationProceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages234-238
Number of pages5
ISBN (Print)9781479961887
DOIs
Publication statusPublished - Jan 27 2014
Event2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2014 - Yogyakarta, Indonesia
Duration: Nov 13 2014Nov 14 2014

Other

Other2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2014
CountryIndonesia
CityYogyakarta
Period11/13/1411/14/14

Fingerprint

Remote sensing
Pixels
Exponential functions
Fusion reactions
Statistics
Microstructure
Sensors

Keywords

  • change detection
  • multi-sensor images
  • remote sensing
  • similarity measure
  • weighted histogram

ASJC Scopus subject areas

  • Information Systems
  • Aerospace Engineering

Cite this

Shadaydeh, M., & Szirányi, T. (2014). An improved local similarity measure estimation for change detection in remote sensing images. In Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (pp. 234-238). [7024381] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARES.2014.7024381

An improved local similarity measure estimation for change detection in remote sensing images. / Shadaydeh, Maha; Szirányi, T.

Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology. Institute of Electrical and Electronics Engineers Inc., 2014. p. 234-238 7024381.

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

Shadaydeh, M & Szirányi, T 2014, An improved local similarity measure estimation for change detection in remote sensing images. in Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology., 7024381, Institute of Electrical and Electronics Engineers Inc., pp. 234-238, 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2014, Yogyakarta, Indonesia, 11/13/14. https://doi.org/10.1109/ICARES.2014.7024381
Shadaydeh M, Szirányi T. An improved local similarity measure estimation for change detection in remote sensing images. In Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology. Institute of Electrical and Electronics Engineers Inc. 2014. p. 234-238. 7024381 https://doi.org/10.1109/ICARES.2014.7024381
Shadaydeh, Maha ; Szirányi, T. / An improved local similarity measure estimation for change detection in remote sensing images. Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 234-238
@inproceedings{5e1602cc52b04ddcaa10127db9c7885a,
title = "An improved local similarity measure estimation for change detection in remote sensing images",
abstract = "Detecting changes in remote sensing images taken at different times is challenging when images' data come from different sensors. The performance of change detection algorithms based on radiometric values alone is not satisfactory and need the fusion of other features. Local similarity measures such as Mutual Information, Kullback-Leibler Divergence, and Cluster Reward Algorithm can be used for enhancing change detection. In the paper, we propose an improved local similarity measure using weighted local histogram. Each pixel contributes to the calculation of the histogram according to its weight only. The weight assigned to each pixel in the histogram estimation window follows an exponential function of its distance from the center of the window and the corresponding pixel value in an initial change map image which is derived from other micro-structure or radiometric information. The proposed improved similarity measure benefits from the good detection ability of small estimation window and the good estimation accuracy of large estimation window; hence it can replace the time-consuming multi-scale selection approaches for statistics based similarity measures in remote sensing. The efficiency of this useful improvement has been validated on change detection in remote sensing image series.",
keywords = "change detection, multi-sensor images, remote sensing, similarity measure, weighted histogram",
author = "Maha Shadaydeh and T. Szir{\'a}nyi",
year = "2014",
month = "1",
day = "27",
doi = "10.1109/ICARES.2014.7024381",
language = "English",
isbn = "9781479961887",
pages = "234--238",
booktitle = "Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - An improved local similarity measure estimation for change detection in remote sensing images

AU - Shadaydeh, Maha

AU - Szirányi, T.

PY - 2014/1/27

Y1 - 2014/1/27

N2 - Detecting changes in remote sensing images taken at different times is challenging when images' data come from different sensors. The performance of change detection algorithms based on radiometric values alone is not satisfactory and need the fusion of other features. Local similarity measures such as Mutual Information, Kullback-Leibler Divergence, and Cluster Reward Algorithm can be used for enhancing change detection. In the paper, we propose an improved local similarity measure using weighted local histogram. Each pixel contributes to the calculation of the histogram according to its weight only. The weight assigned to each pixel in the histogram estimation window follows an exponential function of its distance from the center of the window and the corresponding pixel value in an initial change map image which is derived from other micro-structure or radiometric information. The proposed improved similarity measure benefits from the good detection ability of small estimation window and the good estimation accuracy of large estimation window; hence it can replace the time-consuming multi-scale selection approaches for statistics based similarity measures in remote sensing. The efficiency of this useful improvement has been validated on change detection in remote sensing image series.

AB - Detecting changes in remote sensing images taken at different times is challenging when images' data come from different sensors. The performance of change detection algorithms based on radiometric values alone is not satisfactory and need the fusion of other features. Local similarity measures such as Mutual Information, Kullback-Leibler Divergence, and Cluster Reward Algorithm can be used for enhancing change detection. In the paper, we propose an improved local similarity measure using weighted local histogram. Each pixel contributes to the calculation of the histogram according to its weight only. The weight assigned to each pixel in the histogram estimation window follows an exponential function of its distance from the center of the window and the corresponding pixel value in an initial change map image which is derived from other micro-structure or radiometric information. The proposed improved similarity measure benefits from the good detection ability of small estimation window and the good estimation accuracy of large estimation window; hence it can replace the time-consuming multi-scale selection approaches for statistics based similarity measures in remote sensing. The efficiency of this useful improvement has been validated on change detection in remote sensing image series.

KW - change detection

KW - multi-sensor images

KW - remote sensing

KW - similarity measure

KW - weighted histogram

UR - http://www.scopus.com/inward/record.url?scp=84946689564&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946689564&partnerID=8YFLogxK

U2 - 10.1109/ICARES.2014.7024381

DO - 10.1109/ICARES.2014.7024381

M3 - Conference contribution

AN - SCOPUS:84946689564

SN - 9781479961887

SP - 234

EP - 238

BT - Proceeding - ICARES 2014: 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology

PB - Institute of Electrical and Electronics Engineers Inc.

ER -