Next Article in Journal
Stress Evaluation of a Maritime A-Frame Using Limited Strain Measurements from a Real Deep-Sea Mining Campaign
Previous Article in Journal
XAI Helps in Storm Surge Forecasts: A Case Study for the Southeastern Chinese Coasts
Previous Article in Special Issue
Dual-CycleGANs with Dynamic Guidance for Robust Underwater Image Restoration
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Review

Comparative Analysis of Traditional and Deep Learning Approaches for Underwater Remote Sensing Image Enhancement: A Quantitative Study

1
Ship and Maritime College, Guangdong Ocean University, Zhanjiang 524005, China
2
School of Electronics and Information Engineering, Guangdong Ocean University, Zhanjiang 524088, China
3
College of Business, Taizhou Institute of Sci.&Tech., NJUST, Taizhou 225300, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
J. Mar. Sci. Eng. 2025, 13(5), 899; https://doi.org/10.3390/jmse13050899 (registering DOI)
Submission received: 4 April 2025 / Revised: 25 April 2025 / Accepted: 26 April 2025 / Published: 30 April 2025
(This article belongs to the Special Issue Application of Deep Learning in Underwater Image Processing)

Abstract

Underwater remote sensing image enhancement is complicated by low illumination, color bias, and blurriness, affecting deep-sea monitoring and marine resource development. This study compares a multi-scale fusion-enhanced physical model and deep learning algorithms to optimize intelligent processing. The physical model, based on the Jaffe–McGlamery model, integrates multi-scale histogram equalization, wavelength compensation, and Laplacian sharpening, using cluster analysis to target enhancements. It performs well in shallow, stable waters (turbidity < 20 NTU, depth < 10 m, PSNR = 12.2) but struggles in complex environments (turbidity > 30 NTU). Deep learning models, including water-net, UWCNN, UWCycleGAN, and U-shape Transformer, excel in dynamic conditions, achieving UIQM = 0.24, though requiring GPU support for real-time use. Evaluated on the UIEB dataset (890 images), the physical model suits specific scenarios, while deep learning adapts better to variable underwater settings. These findings offer a theoretical and technical basis for underwater image enhancement and support sustainable marine resource use.
Keywords: underwater remote sensing; deep learning algorithms; multi-scale fusion-enhanced physical model; underwater image enhancement underwater remote sensing; deep learning algorithms; multi-scale fusion-enhanced physical model; underwater image enhancement

Share and Cite

MDPI and ACS Style

Ma, Y.; Cheng, Y.; Zhang, D. Comparative Analysis of Traditional and Deep Learning Approaches for Underwater Remote Sensing Image Enhancement: A Quantitative Study. J. Mar. Sci. Eng. 2025, 13, 899. https://doi.org/10.3390/jmse13050899

AMA Style

Ma Y, Cheng Y, Zhang D. Comparative Analysis of Traditional and Deep Learning Approaches for Underwater Remote Sensing Image Enhancement: A Quantitative Study. Journal of Marine Science and Engineering. 2025; 13(5):899. https://doi.org/10.3390/jmse13050899

Chicago/Turabian Style

Ma, Yunsheng, Yanan Cheng, and Dapeng Zhang. 2025. "Comparative Analysis of Traditional and Deep Learning Approaches for Underwater Remote Sensing Image Enhancement: A Quantitative Study" Journal of Marine Science and Engineering 13, no. 5: 899. https://doi.org/10.3390/jmse13050899

APA Style

Ma, Y., Cheng, Y., & Zhang, D. (2025). Comparative Analysis of Traditional and Deep Learning Approaches for Underwater Remote Sensing Image Enhancement: A Quantitative Study. Journal of Marine Science and Engineering, 13(5), 899. https://doi.org/10.3390/jmse13050899

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop