Revisiting Underwater Image Enhancement for Object Detection: A Unified Quality–Detection Evaluation Framework
Journal of Imaging · 30.12.2025 · 12 (1) · 18
DOI: 10.3390/jimaging12010018 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 30.12.2025. Verfasst von Ali Awad und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Computing, College of Computing, Michigan Technological University, Houghton, MI 49931, USA. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United States Geological Survey (USGS), U.S National Science Foundation.
Abstract (Originalsprache)
Underwater images often suffer from severe color distortion, low contrast, and reduced visibility, motivating the widespread use of image enhancement as a preprocessing step for downstream computer vision tasks. However, recent studies have questioned whether enhancement actually improves object detection performance. In this work, we conduct a comprehensive and rigorous evaluation of nine state-of-the-art enhancement methods and their interactions with modern object detectors. We propose a unified evaluation framework that integrates (1) a distribution-level quality assessment using a composite quality index (Q-index), (2) a fine-grained per-image detection protocol based on COCO-style mAP, and (3) a mixed-set upper-bound analysis that quantifies the theoretical performance achievable through ideal selective enhancement. Our findings reveal that traditional image quality metrics do not reliably predict detection performance, and that dataset-level conclusions often overlook substantial image-level variability. Through per-image evaluation, we identify numerous cases in which enhancement significantly improves detection accuracy—primarily for low-quality inputs—while also demonstrating conditions under which enhancement degrades performance. The mixed-set analysis shows that selective enhancement can yield substantial gains over both original and fully enhanced datasets, establishing a new direction for designing enhancement models optimized for downstream vision tasks. This study provides the most comprehensive evidence to date that underwater image enhancement can be beneficial for object detection when evaluated at the appropriate granularity and guided by informed selection strategies. The data generated and code developed are publicly available.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Applied Computing, College of Computing, Michigan Technological University, Houghton, MI 49931, USA.
- Department of Computer Science and Engineering, Fairfield University, Fairfield, CT 06824, USA.
- Department of Computer Science, Michigan Technological University, Houghton, MI 49931, USA.
ORCID-Profile: Ali Awad, Ashraf Saleem, Sidike Paheding, Evan Lucas
Förderung
- United States Geological Survey (USGS)
- U.S National Science Foundation
Zitieren
APA
Awad, A., Saleem, A., Paheding, S., Lucas, E., Al-Ratrout, S., & Havens, T. C. (2025). Revisiting Underwater Image Enhancement for Object Detection: A Unified Quality–Detection Evaluation Framework. Journal of Imaging, 12(1), 18. https://doi.org/10.3390/jimaging12010018
Vancouver
Awad A, Saleem A, Paheding S, Lucas E, Al-Ratrout S, Havens TC. Revisiting Underwater Image Enhancement for Object Detection: A Unified Quality–Detection Evaluation Framework. Journal of Imaging. 2025;12(1):18. doi:10.3390/jimaging12010018
BibTeX
@article{Awad2025,
author = {Awad, Ali and Saleem, Ashraf and Paheding, Sidike and Lucas, Evan and Al-Ratrout, Serein and Havens, Timothy C},
title = {Revisiting Underwater Image Enhancement for Object Detection: A Unified Quality–Detection Evaluation Framework},
journal = {Journal of Imaging},
year = {2025},
volume = {12},
number = {1},
pages = {18},
doi = {10.3390/jimaging12010018}
}
EUVIMED