A method for image registration combined by edge region and cross correlation

Liang Chen; Meng Zhe Zhou; He Chen

doi:10.15918/j.tbit1001-0645.2016.03.018

A method for image registration combined by edge region and cross correlation

Liang Chen, Meng Zhe Zhou^*, He Chen

^*此作品的通讯作者

信息与电子学院

Beijing Institute of Technology

科研成果: 期刊稿件 › 文章 › 同行评审

3 引用（Scopus）

摘要

A new algorithm aimed at infrared and visible image registration based on cross-correlation coefficient and Canny edge region was presented: regarded the improved Cross-correlation coefficient as the similarity function, extracted the edge region and its nearby area, removed other regions with low correlation, used the particle swarm optimization(PSO) to seek. It shows that this algorithm can overcome the shortcomings which infrared and visible images are poor correlated and avoid the bad matching between multi-sensor images. Multi-sensor image registration could be achieved and small error is guaranteed.

源语言	英语
页（从-至）	320-325
页数	6
期刊	Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
卷	36
期	3
DOI	https://doi.org/10.15918/j.tbit1001-0645.2016.03.018
出版状态	已出版 - 1 3月 2016

访问文件

10.15918/j.tbit1001-0645.2016.03.018

其它文件与链接

链接到 Scopus 的出版物

引用此

Chen, L., Zhou, M. Z., & Chen, H. (2016). A method for image registration combined by edge region and cross correlation. Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 36(3), 320-325. https://doi.org/10.15918/j.tbit1001-0645.2016.03.018

@article{8bc93cfc838c459fa746edb524766779,

title = "A method for image registration combined by edge region and cross correlation",

abstract = "A new algorithm aimed at infrared and visible image registration based on cross-correlation coefficient and Canny edge region was presented: regarded the improved Cross-correlation coefficient as the similarity function, extracted the edge region and its nearby area, removed other regions with low correlation, used the particle swarm optimization(PSO) to seek. It shows that this algorithm can overcome the shortcomings which infrared and visible images are poor correlated and avoid the bad matching between multi-sensor images. Multi-sensor image registration could be achieved and small error is guaranteed.",

keywords = "Cross-correlation coefficient, Edge extraction, Edge region, Image registration, Similarity function",

author = "Liang Chen and Zhou, {Meng Zhe} and He Chen",

year = "2016",

month = mar,

day = "1",

doi = "10.15918/j.tbit1001-0645.2016.03.018",

language = "English",

volume = "36",

pages = "320--325",

journal = "Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology",

issn = "1001-0645",

publisher = "Beijing Institute of Technology",

number = "3",

}

TY - JOUR

T1 - A method for image registration combined by edge region and cross correlation

AU - Chen, Liang

AU - Zhou, Meng Zhe

AU - Chen, He

PY - 2016/3/1

Y1 - 2016/3/1

N2 - A new algorithm aimed at infrared and visible image registration based on cross-correlation coefficient and Canny edge region was presented: regarded the improved Cross-correlation coefficient as the similarity function, extracted the edge region and its nearby area, removed other regions with low correlation, used the particle swarm optimization(PSO) to seek. It shows that this algorithm can overcome the shortcomings which infrared and visible images are poor correlated and avoid the bad matching between multi-sensor images. Multi-sensor image registration could be achieved and small error is guaranteed.

AB - A new algorithm aimed at infrared and visible image registration based on cross-correlation coefficient and Canny edge region was presented: regarded the improved Cross-correlation coefficient as the similarity function, extracted the edge region and its nearby area, removed other regions with low correlation, used the particle swarm optimization(PSO) to seek. It shows that this algorithm can overcome the shortcomings which infrared and visible images are poor correlated and avoid the bad matching between multi-sensor images. Multi-sensor image registration could be achieved and small error is guaranteed.

KW - Cross-correlation coefficient

KW - Edge extraction

KW - Edge region

KW - Image registration

KW - Similarity function

UR - http://www.scopus.com/inward/record.url?scp=84964757020&partnerID=8YFLogxK

U2 - 10.15918/j.tbit1001-0645.2016.03.018

DO - 10.15918/j.tbit1001-0645.2016.03.018

M3 - Article

AN - SCOPUS:84964757020

SN - 1001-0645

VL - 36

SP - 320

EP - 325

JO - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

JF - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

IS - 3

ER -

A method for image registration combined by edge region and cross correlation

摘要

访问文件

其它文件与链接

指纹

引用此