Next Article in Journal
Quantitative Analysis of Phase Response Enhancement in Distributed Acoustic Sensing Systems Using Helical Fiber Winding Technology
Previous Article in Journal
High-Sensitivity Solidly Mounted Resonator Load Sensor Based on AlN/AlScN Heterostructure
Previous Article in Special Issue
A Novel PTS Technique with Side Information Blind Detector Based on Minimized Error Accumulation for PAPR Reduction in Coded Underwater Acoustic OFDM Systems
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 25
Issue 23
10.3390/s25237284
sensors-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
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.
Article

Coral-YOLO: An Intelligent Optical Vision Sensing Framework for High-Fidelity Marine Habitat Monitoring and Forecasting

by
Jun Tao
1,
Hongjun Tian
1,*,
Shuai Huang
2,
Yuhan Ye
1,
Yang Xiong
1,
Shijie Huang
1,
Jingbo Qin
1,
Yijie Yin
1,
Jiesen Zhang
3,
Ying Tang
3 and
Jiani Wu
3
1
Engineering College, Shanghai Ocean University, Shanghai 201306, China
2
College of Energy and Mechanical Engineering, Shanghai Electric Power University, Shanghai 201306, China
3
College of Marine Science and Ecological Environment, Shanghai Ocean University, Shanghai 201306, China
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(23), 7284; https://doi.org/10.3390/s25237284 (registering DOI)
Submission received: 27 October 2025 / Revised: 20 November 2025 / Accepted: 25 November 2025 / Published: 29 November 2025
(This article belongs to the Special Issue Underwater Vision Sensing System: 2nd Edition)
Versions Notes

Abstract

Coral reefs are facing a catastrophic decline due to climate-induced bleaching, threatening critical marine biodiversity. Automated, large-scale monitoring is essential; however, modern object detectors are hindered by two fundamental limitations in complex underwater scenes: a spatial reasoning deficit in their decoupled heads, which inhibits robust multi-scale feature integration, and a feature robustness deficit, which renders deterministic networks vulnerable to stochastic visual variations. To address these limitations, we propose Coral-YOLO, a novel framework for detection and forecasting. We introduce the Holistic Attention Block Head (HAB-Head), which enables deep cross-scale reasoning through explicit feature interaction, and MCAttention, a randomized training mechanism that enables the network to learn scale-invariant features with inherent robustness. Evaluated on our newly curated, multi-year CR-Mix dataset, Coral-YOLO achieves a state-of-the-art 50.3% AP (average precision at IoU threshold 0.5:0.95, following COCO metrics), representing a +1.8 percentage point improvement over the YOLOv12-m baseline, with particularly pronounced gains on small objects (+2.6 percentage points in APS). Crucially, its integrated temporal forecasting module achieves 82.7% accuracy in predicting future coral health, substantially outperforming conventional methods. Coral-YOLO sets a new performance benchmark and enables proactive reef conservation. It provides a powerful tool to identify at-risk corals long before severe bleaching becomes visually apparent.
Keywords: object detection; coral reef monitoring; deep learning; underwater vision; spatio-temporal forecasting; YOLO; attention mechanisms; intelligent monitoring; stochastic learning object detection; coral reef monitoring; deep learning; underwater vision; spatio-temporal forecasting; YOLO; attention mechanisms; intelligent monitoring; stochastic learning

Share and Cite

MDPI and ACS Style

Tao, J.; Tian, H.; Huang, S.; Ye, Y.; Xiong, Y.; Huang, S.; Qin, J.; Yin, Y.; Zhang, J.; Tang, Y.; et al. Coral-YOLO: An Intelligent Optical Vision Sensing Framework for High-Fidelity Marine Habitat Monitoring and Forecasting. Sensors 2025, 25, 7284. https://doi.org/10.3390/s25237284

AMA Style

Tao J, Tian H, Huang S, Ye Y, Xiong Y, Huang S, Qin J, Yin Y, Zhang J, Tang Y, et al. Coral-YOLO: An Intelligent Optical Vision Sensing Framework for High-Fidelity Marine Habitat Monitoring and Forecasting. Sensors. 2025; 25(23):7284. https://doi.org/10.3390/s25237284

Chicago/Turabian Style

Tao, Jun, Hongjun Tian, Shuai Huang, Yuhan Ye, Yang Xiong, Shijie Huang, Jingbo Qin, Yijie Yin, Jiesen Zhang, Ying Tang, and et al. 2025. "Coral-YOLO: An Intelligent Optical Vision Sensing Framework for High-Fidelity Marine Habitat Monitoring and Forecasting" Sensors 25, no. 23: 7284. https://doi.org/10.3390/s25237284

APA Style

Tao, J., Tian, H., Huang, S., Ye, Y., Xiong, Y., Huang, S., Qin, J., Yin, Y., Zhang, J., Tang, Y., & Wu, J. (2025). Coral-YOLO: An Intelligent Optical Vision Sensing Framework for High-Fidelity Marine Habitat Monitoring and Forecasting. Sensors, 25(23), 7284. https://doi.org/10.3390/s25237284

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