YOLO-CBNet: A robust attention-enhanced detection framework for underwater fish recognition in aquaculture environments
- 1Innov’COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Technopark Elghazala, Raoued, Ariana, Tunisia
- 2Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
Abstract
The accurate identification of fish species remains a pivotal challenge in aquaculture, as it directly influences population management, health monitoring, and overall production efficiency. Yet, underwater environments often present difficult conditions such as reduced visibility, suspended particles, and uneven lighting that significantly limit the performance of traditional recognition approaches. In this study, we introduce YOLO-CBNet, an enhanced architecture designed to overcome these constraints and provide more dependable monitoring in real-world aquaculture systems. The method adopts a two-stage strategy. First, a Contrast Limited Adaptive Histogram Equalization (CLAHE) module is employed to counter low contrast, turbidity, and color distortion, restoring essential visual information. Second, the YOLOv11 framework is refined through the integration of the Convolutional Block Attention Module (CBAM) and a Bidirectional Feature Pyramid Network (BiFPN), a combination intended to improve multiscale feature fusion and reinforce the detection of small or partially occluded fish. Experimental results indicate that YOLO-CBNet delivers a clear performance boost, the precision score reaches 0.951, surpassing the baseline YOLOv11 model, which achieved 0.911 under the same conditions. These improvements highlight YOLO-CBNet’s potential as a reliable solution for underwater detection and recognition tasks within modern aquaculture environments.
Related
- Cross-level attention and lightweight feature extraction for improved tomato ripeness detection in complex greenhouse environments
- DAF-EfficientNetV2: distribution-aware feature enhancement for plant leaf disease recognition in complex environments
- VAD-EmotionNet: a spatial-spectral attention network for EEG emotion recognition in the 3D affective space
- Discovery and promotion of unknown sounds into operational detection targets for underwater passive acoustic monitoring under false alarm constraints
- Species-specific loop-mediated isothermal amplification (LAMP) assays for the detection of three blood flukes affecting bluefin tuna aquaculture
BibTeX
@article{hamzaoui2026yolocbnet,
title = {{YOLO-CBNet: A robust attention-enhanced detection framework for underwater fish recognition in aquaculture environments}},
author = {Mahdi Hamzaoui and Leila Bousbia and Mohamed Ould-Elhassen Aoueileyine and Imen Filali and Ridha Bouallegue},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0341525},
url = {https://doi.org/10.1371/journal.pone.0341525},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - YOLO-CBNet: A robust attention-enhanced detection framework for underwater fish recognition in aquaculture environments
AU - Mahdi Hamzaoui
AU - Leila Bousbia
AU - Mohamed Ould-Elhassen Aoueileyine
AU - Imen Filali
AU - Ridha Bouallegue
PY - 2026
DA - 2026/09/15
JO - PLOS One
DO - 10.1371/journal.pone.0341525
UR - https://doi.org/10.1371/journal.pone.0341525
AB - The accurate identification of fish species remains a pivotal challenge in aquaculture, as it directly influences population management, health monitoring, and overall production efficiency. Yet, underwater environments often present difficult conditions such as reduced visibility, suspended particles, and uneven lighting that significantly limit the performance of traditional recognition approaches. In this study, we introduce YOLO-CBNet, an enhanced architecture designed to overcome these constraints and provide more dependable monitoring in real-world aquaculture systems. The method adopts a two-stage strategy. First, a Contrast Limited Adaptive Histogram Equalization (CLAHE) module is employed to counter low contrast, turbidity, and color distortion, restoring essential visual information. Second, the YOLOv11 framework is refined through the integration of the Convolutional Block Attention Module (CBAM) and a Bidirectional Feature Pyramid Network (BiFPN), a combination intended to improve multiscale feature fusion and reinforce the detection of small or partially occluded fish. Experimental results indicate that YOLO-CBNet delivers a clear performance boost, the precision score reaches 0.951, surpassing the baseline YOLOv11 model, which achieved 0.911 under the same conditions. These improvements highlight YOLO-CBNet’s potential as a reliable solution for underwater detection and recognition tasks within modern aquaculture environments.
SN - 1932-6203
ER -