A global-to-local framework for infrared and visible image sequence registration

Michael Ying Yang, Yu Qiang, Bodo Rosenhahn

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Based on the development of image registration, sequence registration can be done by computing the transformations between consecutive frames. To take into account the accumulated error, global registration method is usually employed as a global error minimizing approach. However, in real surveillance applications, the visible sequence and infrared sequence may be taken at different times, or from different viewpoints, and may have different dynamic contents. Therefore, global registration is only an approximate estimation for two sequences, resulting in inferior local contents. In this paper we present a novel integrated global-to-local framework that addresses the problems of dynamic infrared and visible image sequence registration. We propose to maximize the sum of the mutual information of two sequences for the global homography estimation. Then, frame-to-frame registration is performed to estimate the per-frame local homography. Finally, a smoothing strategy is adopted to smooth the local homographies in the temporal domain to enforce temporal consistency. We evaluate our proposed framework by comparing it to the state-of-the art sequence registration algorithm. Our method achieves improved performance on the public benchmark dataset.

Original languageEnglish
Title of host publicationIEEE Winter Conference on Applications of Computer Vision, WACV 2015
PublisherIEEE
Pages381-388
Number of pages8
ISBN (Electronic)9781479966820
DOIs
Publication statusPublished - 19 Feb 2015
Externally publishedYes
EventIEEE Winter Conference on Applications of Computer Vision, WACV 2015 - Waikoloa Beach, United States
Duration: 5 Jan 20159 Jan 2015
http://wacv15.wacv.net/

Publication series

NameProceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision, WACV 2015
Abbreviated titleWACV 2015
CountryUnited States
CityWaikoloa Beach
Period5/01/159/01/15
Internet address

Fingerprint

Infrared radiation
Image registration

Cite this

Yang, M. Y., Qiang, Y., & Rosenhahn, B. (2015). A global-to-local framework for infrared and visible image sequence registration. In IEEE Winter Conference on Applications of Computer Vision, WACV 2015 (pp. 381-388). [7045911] (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015). IEEE. https://doi.org/10.1109/WACV.2015.57
Yang, Michael Ying ; Qiang, Yu ; Rosenhahn, Bodo. / A global-to-local framework for infrared and visible image sequence registration. IEEE Winter Conference on Applications of Computer Vision, WACV 2015. IEEE, 2015. pp. 381-388 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015).
@inproceedings{da6e2cdb677b421a88b31596aaa21f76,
title = "A global-to-local framework for infrared and visible image sequence registration",
abstract = "Based on the development of image registration, sequence registration can be done by computing the transformations between consecutive frames. To take into account the accumulated error, global registration method is usually employed as a global error minimizing approach. However, in real surveillance applications, the visible sequence and infrared sequence may be taken at different times, or from different viewpoints, and may have different dynamic contents. Therefore, global registration is only an approximate estimation for two sequences, resulting in inferior local contents. In this paper we present a novel integrated global-to-local framework that addresses the problems of dynamic infrared and visible image sequence registration. We propose to maximize the sum of the mutual information of two sequences for the global homography estimation. Then, frame-to-frame registration is performed to estimate the per-frame local homography. Finally, a smoothing strategy is adopted to smooth the local homographies in the temporal domain to enforce temporal consistency. We evaluate our proposed framework by comparing it to the state-of-the art sequence registration algorithm. Our method achieves improved performance on the public benchmark dataset.",
author = "Yang, {Michael Ying} and Yu Qiang and Bodo Rosenhahn",
year = "2015",
month = "2",
day = "19",
doi = "10.1109/WACV.2015.57",
language = "English",
series = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",
publisher = "IEEE",
pages = "381--388",
booktitle = "IEEE Winter Conference on Applications of Computer Vision, WACV 2015",
address = "United States",

}

Yang, MY, Qiang, Y & Rosenhahn, B 2015, A global-to-local framework for infrared and visible image sequence registration. in IEEE Winter Conference on Applications of Computer Vision, WACV 2015., 7045911, Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, IEEE, pp. 381-388, IEEE Winter Conference on Applications of Computer Vision, WACV 2015, Waikoloa Beach, United States, 5/01/15. https://doi.org/10.1109/WACV.2015.57

A global-to-local framework for infrared and visible image sequence registration. / Yang, Michael Ying; Qiang, Yu; Rosenhahn, Bodo.

IEEE Winter Conference on Applications of Computer Vision, WACV 2015. IEEE, 2015. p. 381-388 7045911 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - A global-to-local framework for infrared and visible image sequence registration

AU - Yang, Michael Ying

AU - Qiang, Yu

AU - Rosenhahn, Bodo

PY - 2015/2/19

Y1 - 2015/2/19

N2 - Based on the development of image registration, sequence registration can be done by computing the transformations between consecutive frames. To take into account the accumulated error, global registration method is usually employed as a global error minimizing approach. However, in real surveillance applications, the visible sequence and infrared sequence may be taken at different times, or from different viewpoints, and may have different dynamic contents. Therefore, global registration is only an approximate estimation for two sequences, resulting in inferior local contents. In this paper we present a novel integrated global-to-local framework that addresses the problems of dynamic infrared and visible image sequence registration. We propose to maximize the sum of the mutual information of two sequences for the global homography estimation. Then, frame-to-frame registration is performed to estimate the per-frame local homography. Finally, a smoothing strategy is adopted to smooth the local homographies in the temporal domain to enforce temporal consistency. We evaluate our proposed framework by comparing it to the state-of-the art sequence registration algorithm. Our method achieves improved performance on the public benchmark dataset.

AB - Based on the development of image registration, sequence registration can be done by computing the transformations between consecutive frames. To take into account the accumulated error, global registration method is usually employed as a global error minimizing approach. However, in real surveillance applications, the visible sequence and infrared sequence may be taken at different times, or from different viewpoints, and may have different dynamic contents. Therefore, global registration is only an approximate estimation for two sequences, resulting in inferior local contents. In this paper we present a novel integrated global-to-local framework that addresses the problems of dynamic infrared and visible image sequence registration. We propose to maximize the sum of the mutual information of two sequences for the global homography estimation. Then, frame-to-frame registration is performed to estimate the per-frame local homography. Finally, a smoothing strategy is adopted to smooth the local homographies in the temporal domain to enforce temporal consistency. We evaluate our proposed framework by comparing it to the state-of-the art sequence registration algorithm. Our method achieves improved performance on the public benchmark dataset.

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1109/WACV.2015.57

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2015/chap/yang_glo.pdf

U2 - 10.1109/WACV.2015.57

DO - 10.1109/WACV.2015.57

M3 - Conference contribution

T3 - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

SP - 381

EP - 388

BT - IEEE Winter Conference on Applications of Computer Vision, WACV 2015

PB - IEEE

ER -

Yang MY, Qiang Y, Rosenhahn B. A global-to-local framework for infrared and visible image sequence registration. In IEEE Winter Conference on Applications of Computer Vision, WACV 2015. IEEE. 2015. p. 381-388. 7045911. (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015). https://doi.org/10.1109/WACV.2015.57