Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation
It addresses underwater object detection for autonomous navigation and marine exploration, offering an incremental improvement through a hybrid method.
This study tackled the problem of underwater object detection by integrating physics-informed augmentation techniques with the YOLOv12 architecture, achieving state-of-the-art performance with 98.30% mAP at 142 FPS on the Brackish dataset and improvements such as 18.9% better occlusion robustness and 22.4% higher small-object recall.
Underwater object detection is crucial for autonomous navigation, environmental monitoring, and marine exploration, but it is severely hampered by light attenuation, turbidity, and occlusion. Current methods balance accuracy and computational efficiency, but they have trouble deploying in real-time under low visibility conditions. Through the integration of physics-informed augmentation techniques with the YOLOv12 architecture, this study advances underwater detection. With Residual ELAN blocks to preserve structural features in turbid waters and Area Attention to maintain large receptive fields for occluded objects while reducing computational complexity. Underwater optical properties are addressed by domain-specific augmentations such as turbulence adaptive blurring, biologically grounded occlusion simulation, and spectral HSV transformations for color distortion. Extensive tests on four difficult datasets show state-of-the-art performance, with Brackish data registering 98.30% mAP at 142 FPS. YOLOv12 improves occlusion robustness by 18.9%, small-object recall by 22.4%, and detection precision by up to 7.94% compared to previous models. The crucial role of augmentation strategy is validated by ablation studies. This work offers a precise and effective solution for conservation and underwater robotics applications.