Skip to main navigation Skip to search Skip to main content

Infrared and Visible Image Registration in Railway Scenarios via Analytical Vanishing Point Constraints

  • Jianhua Wang
  • , Jun Tian
  • , Ruiming Zheng
  • , Hao Sun
  • , Yunxu Sun*
  • , Wei Liu
  • *Corresponding author for this work
  • Ltd.
  • Harbin Institute of Technology Shenzhen

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

Abstract

To address the significant modal differences between infrared (IR) and visible (VIS) railway images, this paper introduces a registration method centered on an analytical vanishing point constraint. Within a coarse-to-fine framework, the method robustly estimates the vanishing point from rail lines to analytically derive translation parameters from scaling, which fundamentally simplifies the coarse registration. Subsequently, using the coarse result as an initial value, an iterative optimization solver refines a full 6-parameter affine model to achieve precise alignment. Experimental results on a self-collected dataset demonstrate that the proposed method effectively overcomes modal discrepancies and achieves accurate registration for railway scenarios.

Original languageEnglish
Title of host publication2025 23rd International Conference on Optical Communications and Networks, ICOCN 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331548759
DOIs
StatePublished - 2025
Externally publishedYes
Event23rd International Conference on Optical Communications and Networks, ICOCN 2025 - Zhangjiajie, China
Duration: 28 Jul 202531 Jul 2025

Publication series

Name2025 23rd International Conference on Optical Communications and Networks, ICOCN 2025

Conference

Conference23rd International Conference on Optical Communications and Networks, ICOCN 2025
Country/TerritoryChina
CityZhangjiajie
Period28/07/2531/07/25

Keywords

  • Coarse-to-fine
  • Image Registration
  • Infrared and Visible Images
  • Railway Scenarios
  • Vanishing Point

Fingerprint

Dive into the research topics of 'Infrared and Visible Image Registration in Railway Scenarios via Analytical Vanishing Point Constraints'. Together they form a unique fingerprint.

Cite this