CoChat

Underwater Optical-Sonar Image Fusion Systems

Open access

The DOI matches its Crossref record; 27 of the 30 references it cites were found in a registry or an index; 5 of the 17 sources its claims cite were checked for support.

Abstract

Unmanned underwater operations using remotely operated vehicles or unmanned surface vehicles are increasing in recent times, and this guarantees human safety and work efficiency. Optical cameras and multi-beam sonars are generally used as imaging sensors in underwater environments. However, the obtained underwater images are difficult to understand intuitively, owing to noise and distortion. In this study, we developed an optical and sonar image fusion system that integrates the color and distance information from two different images. The enhanced optical and sonar images were fused using calibrated transformation matrices, and the underwater image quality measure (UIQM) and underwater color image quality evaluation (UCIQE) were used as metrics to evaluate the performance of the proposed system. Compared with the original underwater image, image fusion increased the mean UIQM and UCIQE by 94% and 27%, respectively. The contrast-to-noise ratio was increased six times after applying the median filter and gamma correction. The fused image in sonar image coordinates showed qualitatively good spatial agreement and the average IoU was 75% between the optical and sonar pixels in the fused images. The optical-sonar fusion system will help to visualize and understand well underwater situations with color and distance information for unmanned works.

Overview

CoChat Summary

## TL;DR

The paper develops an underwater optical-sonar fusion system that simultaneously enhances optical and multi-beam sonar images and then merges RGB color with distance information using geometric calibration. On 28 calibration image pairs, fusion improved mean UIQM by 94%, mean UCIQE by 27%, and achieved an average IoU of 75% between optical and sonar pixels in the fused images.

## Key findings

  • On 28 calibration image pairs, image fusion increased mean UIQM from 0.56 ± 0.13 to 1.1 ± 0.17, a 94% increase.
  • Mean UCIQE increased from 19.96 ± 1.15 to 25.53 ± 2.35, a 27% increase.
  • For sonar enhancement, contrast-to-noise ratio increased from 0.33 ± 0.05 to 2.03 ± 0.12 after median filtering and gamma correction, described as a sixfold increase.
  • Spatial alignment of fused optical-sonar images was quantified by IoU; average IoU was 75%, with 69% at 5 m and 81% at 6 m.

## Methods

  • Built an underwater optical-sonar fusion system with two underwater cameras, a multi-beam sonar, LED lights, a communication case, and a movable bracket with servo motor control.
  • Used an RGB phantom in a water tank to collect 28 simultaneous optical and sonar calibration image pairs at multiple distances, depths, and orientations.
  • Enhanced optical images with white balancing, CLAHE, and unsharp masking; enhanced sonar images with a median filter and gamma correction; then estimated transformation matrices from paired corner points to fuse the modalities.

## Limitations

  • The paper does not report a formal limitation section; this is not stated in the paper.
  • Evidence from the text suggests the evaluation was limited to an RGB phantom in a controlled water-tank setup, so generalization to natural underwater scenes is not established; this is inferred from the text.
  • Evidence from the text suggests the calibration and fusion results were based on a small number of calibration pairs (28), so robustness beyond the tested conditions is not established; this is inferred from the text.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/s22218445

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Two image coordinate systems, (a) Cartesian and (b) fan-shaped image coordinate systems of optical and multi-beam sonar sensors.
Figure 1 Two image coordinate systems, (a) Cartesian and (b) fan-shaped image coordinate systems of optical and multi-beam sonar sensors.CC BY · PubMed Central
Figure 2 Optical-sonar fusion system, (a) schematic design and (b) real hardware comprising two underwater cameras and one multi-beam sonar.
Figure 2 Optical-sonar fusion system, (a) schematic design and (b) real hardware comprising two underwater cameras and one multi-beam sonar.CC BY · PubMed Central
Figure 3 Schematic of the bracket equipped with a servo motor for tilting imaging sensors.
Figure 3 Schematic of the bracket equipped with a servo motor for tilting imaging sensors.CC BY · PubMed Central
Figure 4 Software to control the display and acquisition of optical and sonar images, light operation, and enhancing and fusing both images.
Figure 4 Software to control the display and acquisition of optical and sonar images, light operation, and enhancing and fusing both images.CC BY · PubMed Central
Figure 5 Calibration phantom, (a) schematic and (b) real RGB phantom for geometric calibration of underwater optical-sonar fusion system.
Figure 5 Calibration phantom, (a) schematic and (b) real RGB phantom for geometric calibration of underwater optical-sonar fusion system.CC BY · PubMed Central
Figure 6 Experimental setup of the RGB phantom and optical-sonar fusion system for acquisition of calibration data.
Figure 6 Experimental setup of the RGB phantom and optical-sonar fusion system for acquisition of calibration data.CC BY · PubMed Central
Figure 7 World coordinates (Wx,Wy,Wz), optical, and sonar image coordinates (Xn,Yn;n=1,2,3).
Figure 7 World coordinates (Wx,Wy,Wz), optical, and sonar image coordinates (Xn,Yn;n=1,2,3).CC BY · PubMed Central
Figure 8 Corner detection numbering, (a) thirty-six optical and (b) eight sonar corner image points for estimating coordinate transformation matrices.
Figure 8 Corner detection numbering, (a) thirty-six optical and (b) eight sonar corner image points for estimating coordinate transformation matrices.CC BY · PubMed Central
Figure 9 Single optical image enhancement, (a) original underwater optical image and (b) its enhanced image by image fusion.
Figure 9 Single optical image enhancement, (a) original underwater optical image and (b) its enhanced image by image fusion.CC BY · PubMed Central
Figure 10 Single sonar image enhancement, (a) original sonar image and (b) its enhanced image by median filter (5 × 5) and gamma correction (γ2 = 0.2).
Figure 10 Single sonar image enhancement, (a) original sonar image and (b) its enhanced image by median filter (5 × 5) and gamma correction (γ2 = 0.2).CC BY · PubMed Central
Figure 11 Enhanced and fused optical and sonar images taken at different distances of 5 and 6 m from the fusion system, (a) enhanced optical images (top and bottom rows are images measured from camera 1 and 2 at each distance, respectively), (b) enhanced sonar images, (c) overlayered optical color image on the sonar image.
Figure 11 Enhanced and fused optical and sonar images taken at different distances of 5 and 6 m from the fusion system, (a) enhanced optical images (top and bottom rows are images measured from camera 1 and 2 at each distance, respectively), (b) enhanced sonar images, (c) overlayered optical color image on the sonar image.CC BY · PubMed Central

Verification

Claims the paper makes

3 Valid · 1 Not valid · 5 Not checked · 24 Own results and interpretations

18 more claims

Create a free account to see all 33 claims and to verify the 1 reference still open.

See all claims — free account
  • Probably not a substantial claim. 6
  • It may state two separate claims as one. 6

Create a free account to see these claims.

Citations

Cites

Show all 27 references

Research works printed but not linked: 2

  1. Mobley C.D. Mobley C.D. Light and Water: Radiative Transfer in Natural Waters Academic Press Cambridge, MA, USA 1994
  2. Hartley R. Zisserman A. Multiple View Geometry in Computer Vision Cambridge University Press Cambridge, UK 2013

Cited by

See all 29

Metadata

Authors
Kim, H.-G., Seo, J., & Kim, S. M.
Affiliations
Korea Institute of Ocean Science and Technology (KR)
Corresponding author
Kim, Soo Mee
Venue
Sensors
Publisher
MDPI AG
Published
2022-11-03
Volume
22
Issue
21
Pages
8445
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4309089949
Cited by
29
References
30
Citations by year
2026: 17 · 2025: 5 · 2024: 4 · 2023: 2 · 2022: 1
FWCI
1.17
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Research Foundation of Korea (NRF-2021R1A2C2006682, 20210658, PEA0032)
  • Ministry of Oceans and Fisheries (NRF-2021R1A2C2006682, 20210658, PEA0032)
  • Korea Institute of Ocean Science and Technology (NRF-2021R1A2C2006682, 20210658, PEA0032)
Topics
  • Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
  • Physical Sciences › Engineering › Ocean Engineering › Underwater Vehicles and Communication Systems
Keywords
underwater imaging, multibeam echosounder, remotely operated vehicle, underwater image quality, image registration, median filter, gamma correction
MeSH terms
Humans, Noise, Sound, Optical Devices

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.