.png){kind=icon}
返回
Detecting underwater salient objects via self-supervised depth priors and task-driven optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.130873.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Underwater salient object detection (USOD) is important for marine exploration, ecological monitoring, and autonomous underwater vehicle navigation. However, the performance of existing methods remains limited by underwater optical distortions, color casts, and the absence of reliable depth sensing. To address these challenges, we propose the Underwater Depth-Fused Saliency Network (UDF-Net), a framework that couples self-supervised monocular depth estimation with attention-based multimodal fusion. To overcome the limitations of RGB-only USOD, UDF-Net utilizes a CNN-based encoder-decoder architecture combined with a lightweight multi-view transformer to effectively estimate depth from a single underwater RGB image. Given the lack of ground-truth depth underwater, we derive a physics-based self-supervisory signal by generating pseudo-depth via a generalized dark-channel prior. An attention-aware fusion module then enables fine-grained interaction between the RGB and depth modalities, while a task-driven joint optimization strategy trains saliency detection and depth estimation end-to-end to enforce semantic consistency and robustness. Extensive experiments on various USOD datasets demonstrate that UDF-Net significantly surpasses state-of-the-art models in accuracy and robustness.
Keyword:
Underwater salient object detection
Depth estimation
Self-supervision
Multimodal learning
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
.png){kind=icon}
Integrating QDWD with pattern distinctness and local contrast for underwater saliency detection
PREAI
分享收藏
An integrated underwater structural multi-defects automatic identification and quantification framework for hydraulic tunnel via machine vision and deep learning基于机器视觉和深度学习的水工隧洞水下结构多缺陷自动识别与量化集成框架
PREAI
分享收藏Multi-scale attention-edge interactive refinement network for salient object detection多尺度注意力-边缘交互式精炼网络用于显著目标检测
PREAI
分享收藏
查看更多内容