Adaptive Alpha-Trimmed Correlation based underwater image stitching

Rahul Rajendran, Shishir P. Rao, Karen Panetta, Sos S. Agaian

Research output: ResearchConference contribution

Abstract

Image stitching (Mosaicing) is a technique of combining multiple underwater images to generate a composite image with a much larger field of view. With its advancement in various imaging applications, underwater image stitching, in particular presents its own challenges. Underwater images suffer from clouding effects and grayed out colors as a result of absorption and scattering of light. Such complexities hinder the image stitching process causing misalignments and non-uniform illumination. The paper presents a system that combines multiple underwater images to generate a fused image, overcoming the impediments of a visible seamline. The presented method is based on a novel stitching technique called Alpha-Trimmed Correlation. The system is designed to adapt to the difficulties encountered in underwater image stitching. The performance of the stitching algorithm is tested against its ground truth, both subjectively and quantitatively. The quantitative analysis is performed using non-reference underwater quality measures such as UICM, logAMEE, and CTSUIQM.

LanguageEnglish (US)
Title of host publication2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509063567
DOIs
StatePublished - Jun 7 2017
Event2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017 - Waltham, United States
Duration: Apr 25 2017Apr 26 2017

Other

Other2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017
CountryUnited States
CityWaltham
Period4/25/174/26/17

Fingerprint

Lighting
Scattering
Color
Imaging techniques
Composite materials
Chemical analysis
performance

Keywords

  • Color correction
  • Enhancement
  • Feature detectors
  • Image blending
  • Quality measures
  • Underwater image stitching

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Safety Research

Cite this

Rajendran, R., Rao, S. P., Panetta, K., & Agaian, S. S. (2017). Adaptive Alpha-Trimmed Correlation based underwater image stitching. In 2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017 [7943513] Institute of Electrical and Electronics Engineers Inc.. DOI: 10.1109/THS.2017.7943513

Adaptive Alpha-Trimmed Correlation based underwater image stitching. / Rajendran, Rahul; Rao, Shishir P.; Panetta, Karen; Agaian, Sos S.

2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 7943513.

Research output: ResearchConference contribution

Rajendran, R, Rao, SP, Panetta, K & Agaian, SS 2017, Adaptive Alpha-Trimmed Correlation based underwater image stitching. in 2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017., 7943513, Institute of Electrical and Electronics Engineers Inc., 2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017, Waltham, United States, 4/25/17. DOI: 10.1109/THS.2017.7943513
Rajendran R, Rao SP, Panetta K, Agaian SS. Adaptive Alpha-Trimmed Correlation based underwater image stitching. In 2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017. Institute of Electrical and Electronics Engineers Inc.2017. 7943513. Available from, DOI: 10.1109/THS.2017.7943513
Rajendran, Rahul ; Rao, Shishir P. ; Panetta, Karen ; Agaian, Sos S./ Adaptive Alpha-Trimmed Correlation based underwater image stitching. 2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inbook{fb72d6184dac49f1a9ae1481cbb26cdc,
title = "Adaptive Alpha-Trimmed Correlation based underwater image stitching",
abstract = "Image stitching (Mosaicing) is a technique of combining multiple underwater images to generate a composite image with a much larger field of view. With its advancement in various imaging applications, underwater image stitching, in particular presents its own challenges. Underwater images suffer from clouding effects and grayed out colors as a result of absorption and scattering of light. Such complexities hinder the image stitching process causing misalignments and non-uniform illumination. The paper presents a system that combines multiple underwater images to generate a fused image, overcoming the impediments of a visible seamline. The presented method is based on a novel stitching technique called Alpha-Trimmed Correlation. The system is designed to adapt to the difficulties encountered in underwater image stitching. The performance of the stitching algorithm is tested against its ground truth, both subjectively and quantitatively. The quantitative analysis is performed using non-reference underwater quality measures such as UICM, logAMEE, and CTSUIQM.",
keywords = "Color correction, Enhancement, Feature detectors, Image blending, Quality measures, Underwater image stitching",
author = "Rahul Rajendran and Rao, {Shishir P.} and Karen Panetta and Agaian, {Sos S.}",
year = "2017",
month = "6",
doi = "10.1109/THS.2017.7943513",
booktitle = "2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - CHAP

T1 - Adaptive Alpha-Trimmed Correlation based underwater image stitching

AU - Rajendran,Rahul

AU - Rao,Shishir P.

AU - Panetta,Karen

AU - Agaian,Sos S.

PY - 2017/6/7

Y1 - 2017/6/7

N2 - Image stitching (Mosaicing) is a technique of combining multiple underwater images to generate a composite image with a much larger field of view. With its advancement in various imaging applications, underwater image stitching, in particular presents its own challenges. Underwater images suffer from clouding effects and grayed out colors as a result of absorption and scattering of light. Such complexities hinder the image stitching process causing misalignments and non-uniform illumination. The paper presents a system that combines multiple underwater images to generate a fused image, overcoming the impediments of a visible seamline. The presented method is based on a novel stitching technique called Alpha-Trimmed Correlation. The system is designed to adapt to the difficulties encountered in underwater image stitching. The performance of the stitching algorithm is tested against its ground truth, both subjectively and quantitatively. The quantitative analysis is performed using non-reference underwater quality measures such as UICM, logAMEE, and CTSUIQM.

AB - Image stitching (Mosaicing) is a technique of combining multiple underwater images to generate a composite image with a much larger field of view. With its advancement in various imaging applications, underwater image stitching, in particular presents its own challenges. Underwater images suffer from clouding effects and grayed out colors as a result of absorption and scattering of light. Such complexities hinder the image stitching process causing misalignments and non-uniform illumination. The paper presents a system that combines multiple underwater images to generate a fused image, overcoming the impediments of a visible seamline. The presented method is based on a novel stitching technique called Alpha-Trimmed Correlation. The system is designed to adapt to the difficulties encountered in underwater image stitching. The performance of the stitching algorithm is tested against its ground truth, both subjectively and quantitatively. The quantitative analysis is performed using non-reference underwater quality measures such as UICM, logAMEE, and CTSUIQM.

KW - Color correction

KW - Enhancement

KW - Feature detectors

KW - Image blending

KW - Quality measures

KW - Underwater image stitching

UR - http://www.scopus.com/inward/record.url?scp=85023192326&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023192326&partnerID=8YFLogxK

U2 - 10.1109/THS.2017.7943513

DO - 10.1109/THS.2017.7943513

M3 - Conference contribution

BT - 2017 IEEE International Symposium on Technologies for Homeland Security, HST 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -