用物理增强+YOLOv12提升水下目标检测，实时性与鲁棒性双突破。
Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation
- 融合物理增强与YOLOv12，引入残差ELAN块和区域注意力机制。
- 在咸淡水数据集上达98.30% mAP，推理速度142 FPS，精度提升7.94%。
- 特别适合水下机器人、生态监测等低可见度场景应用。
水下目标检测对自主导航、环境监测和海洋探索至关重要，但受光衰减、浑浊度和遮挡严重影响。现有方法在精度与效率间权衡，难以实现实时检测。本文结合物理感知增强与YOLOv12架构，通过残差ELAN块保留浑浊水域中的结构特征，利用区域注意力在保持大感受野的同时降低计算复杂度。针对水下光学特性，设计湍流自适应模糊、生物基础遮挡模拟及色域HSV变换以应对颜色失真。在四个挑战性数据集上测试，取得领先性能：咸淡水数据集达到98.30% mAP，推理速度142 FPS。相比前代模型，遮挡鲁棒性提升18.9%，小目标召回率提高22.4%，检测精度最高提升7.94%。消融实验验证了增强策略的关键作用。本工作为生态保护与水下机器人提供高效精准的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。