Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views

Objects intruding high-speed railway clearance do great threat to running trains. In order to improve accuracy of railway intrusion detection, an automatic multimodal registration and fusion algorithm for infrared and visible images with different field of views is presented. The ratio of the neares...

Full description

Bibliographic Details
Main Authors: Baoqing Guo, Xingfang Zhou, Yingzi Lin, Liqiang Zhu, Zujun Yu
Format: Article
Language:English
Published: Hindawi-Wiley 2018-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2018/7836169
id doaj-f9e3d570fc8245cfbb935c2f34b5dba0
record_format Article
spelling doaj-f9e3d570fc8245cfbb935c2f34b5dba02020-11-24T21:50:58ZengHindawi-WileyJournal of Advanced Transportation0197-67292042-31952018-01-01201810.1155/2018/78361697836169Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of ViewsBaoqing Guo0Xingfang Zhou1Yingzi Lin2Liqiang Zhu3Zujun Yu4School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, ChinaKey Laboratory of Vehicle Advanced Manufacturing, Measuring and Control Technology (Beijing Jiaotong University), Ministry of Education, Beijing 100044, ChinaDepartment of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115, USASchool of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, ChinaObjects intruding high-speed railway clearance do great threat to running trains. In order to improve accuracy of railway intrusion detection, an automatic multimodal registration and fusion algorithm for infrared and visible images with different field of views is presented. The ratio of the nearest to next nearest distance, geometric, similar triangle, and RANSAC constraints are used to refine the matching SURF feature points successively. Correct matching points are accumulated with multiframe to overcome the insufficient matching points in single image pair. After being registered, an improved Contourlet transform fusion algorithm combined with total variation and local region energy is proposed. Inverse Contourlet transform to low frequency subband coefficient fused with total variation model and high frequency subband coefficients fused with local region energy is used to reconstruct the fused image. The comparison to other 4 popular fusion methods shows that our algorithm has the best comprehensive performance for multimodal railway image fusion.http://dx.doi.org/10.1155/2018/7836169
collection DOAJ
language English
format Article
sources DOAJ
author Baoqing Guo
Xingfang Zhou
Yingzi Lin
Liqiang Zhu
Zujun Yu
spellingShingle Baoqing Guo
Xingfang Zhou
Yingzi Lin
Liqiang Zhu
Zujun Yu
Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views
Journal of Advanced Transportation
author_facet Baoqing Guo
Xingfang Zhou
Yingzi Lin
Liqiang Zhu
Zujun Yu
author_sort Baoqing Guo
title Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views
title_short Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views
title_full Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views
title_fullStr Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views
title_full_unstemmed Novel Registration and Fusion Algorithm for Multimodal Railway Images with Different Field of Views
title_sort novel registration and fusion algorithm for multimodal railway images with different field of views
publisher Hindawi-Wiley
series Journal of Advanced Transportation
issn 0197-6729
2042-3195
publishDate 2018-01-01
description Objects intruding high-speed railway clearance do great threat to running trains. In order to improve accuracy of railway intrusion detection, an automatic multimodal registration and fusion algorithm for infrared and visible images with different field of views is presented. The ratio of the nearest to next nearest distance, geometric, similar triangle, and RANSAC constraints are used to refine the matching SURF feature points successively. Correct matching points are accumulated with multiframe to overcome the insufficient matching points in single image pair. After being registered, an improved Contourlet transform fusion algorithm combined with total variation and local region energy is proposed. Inverse Contourlet transform to low frequency subband coefficient fused with total variation model and high frequency subband coefficients fused with local region energy is used to reconstruct the fused image. The comparison to other 4 popular fusion methods shows that our algorithm has the best comprehensive performance for multimodal railway image fusion.
url http://dx.doi.org/10.1155/2018/7836169
work_keys_str_mv AT baoqingguo novelregistrationandfusionalgorithmformultimodalrailwayimageswithdifferentfieldofviews
AT xingfangzhou novelregistrationandfusionalgorithmformultimodalrailwayimageswithdifferentfieldofviews
AT yingzilin novelregistrationandfusionalgorithmformultimodalrailwayimageswithdifferentfieldofviews
AT liqiangzhu novelregistrationandfusionalgorithmformultimodalrailwayimageswithdifferentfieldofviews
AT zujunyu novelregistrationandfusionalgorithmformultimodalrailwayimageswithdifferentfieldofviews
_version_ 1725881256697135104