Side scan sonar image super resolution via region-selective sparse coding

Jaihyun Park, Bonhwa Ku, Youngsaeng Jin, Hanseok Ko

Research output: Contribution to journalArticle

Abstract

Side scan sonar using low frequency can quickly search a wide range, but the images acquired are of low quality. The image super resolution (SR) method can mitigate this problem. The SR method typically uses sparse coding, but accurately estimating sparse coefficients incurs substantial computational costs. To reduce processing time, we propose a region-selective sparse coding based SR system that emphasizes object regions. In particular, the region that contains interesting objects is detected for side scan sonar based underwater images so that the subsequent sparse coding based SR process can be selectively applied. Effectiveness of the proposed method is verified by the reduced processing time required for image reconstruction yet preserving the same level of visual quality as conventional methods.

Original languageEnglish
Pages (from-to)210-213
Number of pages4
JournalIEICE Transactions on Information and Systems
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Sonar
Processing
Image reconstruction
Costs

Keywords

  • Object detection
  • Side scan sonar
  • Sparse coding
  • Super resolution

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Side scan sonar image super resolution via region-selective sparse coding. / Park, Jaihyun; Ku, Bonhwa; Jin, Youngsaeng; Ko, Hanseok.

In: IEICE Transactions on Information and Systems, No. 1, 01.01.2019, p. 210-213.

Research output: Contribution to journalArticle

@article{340ff0d8c2ca4c3fb0c593084a52379f,
title = "Side scan sonar image super resolution via region-selective sparse coding",
abstract = "Side scan sonar using low frequency can quickly search a wide range, but the images acquired are of low quality. The image super resolution (SR) method can mitigate this problem. The SR method typically uses sparse coding, but accurately estimating sparse coefficients incurs substantial computational costs. To reduce processing time, we propose a region-selective sparse coding based SR system that emphasizes object regions. In particular, the region that contains interesting objects is detected for side scan sonar based underwater images so that the subsequent sparse coding based SR process can be selectively applied. Effectiveness of the proposed method is verified by the reduced processing time required for image reconstruction yet preserving the same level of visual quality as conventional methods.",
keywords = "Object detection, Side scan sonar, Sparse coding, Super resolution",
author = "Jaihyun Park and Bonhwa Ku and Youngsaeng Jin and Hanseok Ko",
year = "2019",
month = "1",
day = "1",
doi = "10.1587/transinf.2018EDL8170",
language = "English",
pages = "210--213",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "1",

}

TY - JOUR

T1 - Side scan sonar image super resolution via region-selective sparse coding

AU - Park, Jaihyun

AU - Ku, Bonhwa

AU - Jin, Youngsaeng

AU - Ko, Hanseok

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Side scan sonar using low frequency can quickly search a wide range, but the images acquired are of low quality. The image super resolution (SR) method can mitigate this problem. The SR method typically uses sparse coding, but accurately estimating sparse coefficients incurs substantial computational costs. To reduce processing time, we propose a region-selective sparse coding based SR system that emphasizes object regions. In particular, the region that contains interesting objects is detected for side scan sonar based underwater images so that the subsequent sparse coding based SR process can be selectively applied. Effectiveness of the proposed method is verified by the reduced processing time required for image reconstruction yet preserving the same level of visual quality as conventional methods.

AB - Side scan sonar using low frequency can quickly search a wide range, but the images acquired are of low quality. The image super resolution (SR) method can mitigate this problem. The SR method typically uses sparse coding, but accurately estimating sparse coefficients incurs substantial computational costs. To reduce processing time, we propose a region-selective sparse coding based SR system that emphasizes object regions. In particular, the region that contains interesting objects is detected for side scan sonar based underwater images so that the subsequent sparse coding based SR process can be selectively applied. Effectiveness of the proposed method is verified by the reduced processing time required for image reconstruction yet preserving the same level of visual quality as conventional methods.

KW - Object detection

KW - Side scan sonar

KW - Sparse coding

KW - Super resolution

UR - http://www.scopus.com/inward/record.url?scp=85060080097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060080097&partnerID=8YFLogxK

U2 - 10.1587/transinf.2018EDL8170

DO - 10.1587/transinf.2018EDL8170

M3 - Article

AN - SCOPUS:85060080097

SP - 210

EP - 213

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 1

ER -