Skip to main navigation Skip to search Skip to main content

Logical Stitching: A Panoramic Image Stitching Method Based on Color Calibration Box

  • Weihua Ye
  • , Kaiwen Yu
  • , Yang Yu
  • , Jia Li*
  • *Corresponding author for this work
  • Beihang University

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

Abstract

In this paper, we present a novel method to stitch two fisheye images into a panoramic image by using a color calibration box. The color calibration box is a new calibration tool with five planes for double fisheyes camera to calibrate. With the color calibration box, we obtain parameters used in our method to map the fisheye images back to the same logical sphere and stitch them according to the imaging model of the two fisheye cameras aligned back-to-back. Experimental results show that our method can not only produce 360-degree panoramic scenes but also eliminate the brightness difference from the two fisheye cameras. Moreover, our approach achieves comparable stitching performance with Gear360 camera in stitching details, and outperforms it in handling stitching colors.

Original languageEnglish
Title of host publication2018 14th IEEE International Conference on Signal Processing Proceedings, ICSP 2018
EditorsYuan Baozong, Ruan Qiuqi, Zhao Yao, An Gaoyun
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1139-1143
Number of pages5
ISBN (Electronic)9781538646724
DOIs
StatePublished - 2 Feb 2019
Event14th IEEE International Conference on Signal Processing, ICSP 2018 - Beijing, China
Duration: 12 Aug 201816 Aug 2018

Publication series

NameInternational Conference on Signal Processing Proceedings, ICSP
Volume2018-August

Conference

Conference14th IEEE International Conference on Signal Processing, ICSP 2018
Country/TerritoryChina
CityBeijing
Period12/08/1816/08/18

Keywords

  • Calibration
  • Fisheye
  • Panoramic
  • Stitching

Fingerprint

Dive into the research topics of 'Logical Stitching: A Panoramic Image Stitching Method Based on Color Calibration Box'. Together they form a unique fingerprint.

Cite this