Feature match for underwater image via superpixel tracking

Shu Zhang; Junyu Dong; Hui Yu

doi:10.23919/IConAC.2017.8081988

Feature match for underwater image via superpixel tracking

Shu Zhang, Junyu Dong, Hui Yu

Ocean University of China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

268 Downloads (Pure)

Abstract

Feature matching is fundamental to many vision tasks. Due to the low visibility of images in underwater environments, traditional pixels-based matching methods suffer from miss-matching or error-matching. Recently, Superpixel based features have been applied to image feature analysis. However, most of existing methods dedicate to rectified stereo matching with images captured in the air. This paper presents a novel feature matching scheme aiming at underwater images. It targets the un-rectified image pair from the video sequence. The Superpixel matching process is fulfilled with multiclass labelling based on Markov Random Field (MRF). Experiments show that the proposed method produces competitive performance.

Original language	English
Title of host publication	2017 23rd International Conference on Automation and Computing (ICAC)
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	978-0701702601
ISBN (Print)	978-1509050406
DOIs	https://doi.org/10.23919/IConAC.2017.8081988
Publication status	Published - 26 Oct 2017
Event	2017 23rd International Conference on Automation and Computing - Huddersfield, United Kingdom Duration: 7 Sept 2017 → 8 Sept 2017

Conference

Conference	2017 23rd International Conference on Automation and Computing
Abbreviated title	ICAC
Country/Territory	United Kingdom
City	Huddersfield
Period	7/09/17 → 8/09/17

Keywords

component
feature matching
superpixel
underwater
RCUK
EPSRC
EP/N025849/1

Access to Document

10.23919/IConAC.2017.8081988

Superpixel matching2017
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 752 KB

Cite this

@inproceedings{4af02925b2d5430a803dd328cc52de3b,

title = "Feature match for underwater image via superpixel tracking",

abstract = "Feature matching is fundamental to many vision tasks. Due to the low visibility of images in underwater environments, traditional pixels-based matching methods suffer from miss-matching or error-matching. Recently, Superpixel based features have been applied to image feature analysis. However, most of existing methods dedicate to rectified stereo matching with images captured in the air. This paper presents a novel feature matching scheme aiming at underwater images. It targets the un-rectified image pair from the video sequence. The Superpixel matching process is fulfilled with multiclass labelling based on Markov Random Field (MRF). Experiments show that the proposed method produces competitive performance.",

keywords = "component, feature matching, superpixel, underwater, RCUK, EPSRC, EP/N025849/1",

author = "Shu Zhang and Junyu Dong and Hui Yu",

year = "2017",

month = oct,

day = "26",

doi = "10.23919/IConAC.2017.8081988",

language = "English",

isbn = "978-1509050406 ",

booktitle = "2017 23rd International Conference on Automation and Computing (ICAC)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2017 23rd International Conference on Automation and Computing, ICAC ; Conference date: 07-09-2017 Through 08-09-2017",

}

TY - GEN

T1 - Feature match for underwater image via superpixel tracking

AU - Zhang, Shu

AU - Dong, Junyu

AU - Yu, Hui

PY - 2017/10/26

Y1 - 2017/10/26

N2 - Feature matching is fundamental to many vision tasks. Due to the low visibility of images in underwater environments, traditional pixels-based matching methods suffer from miss-matching or error-matching. Recently, Superpixel based features have been applied to image feature analysis. However, most of existing methods dedicate to rectified stereo matching with images captured in the air. This paper presents a novel feature matching scheme aiming at underwater images. It targets the un-rectified image pair from the video sequence. The Superpixel matching process is fulfilled with multiclass labelling based on Markov Random Field (MRF). Experiments show that the proposed method produces competitive performance.

AB - Feature matching is fundamental to many vision tasks. Due to the low visibility of images in underwater environments, traditional pixels-based matching methods suffer from miss-matching or error-matching. Recently, Superpixel based features have been applied to image feature analysis. However, most of existing methods dedicate to rectified stereo matching with images captured in the air. This paper presents a novel feature matching scheme aiming at underwater images. It targets the un-rectified image pair from the video sequence. The Superpixel matching process is fulfilled with multiclass labelling based on Markov Random Field (MRF). Experiments show that the proposed method produces competitive performance.

KW - component

KW - feature matching

KW - superpixel

KW - underwater

KW - RCUK

KW - EPSRC

KW - EP/N025849/1

U2 - 10.23919/IConAC.2017.8081988

DO - 10.23919/IConAC.2017.8081988

M3 - Conference contribution

SN - 978-1509050406

BT - 2017 23rd International Conference on Automation and Computing (ICAC)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 23rd International Conference on Automation and Computing

Y2 - 7 September 2017 through 8 September 2017

ER -

Feature match for underwater image via superpixel tracking

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this