提升海洋机器人在模糊图像中检测垃圾的能力
A Marine Debris Detection Framework for Ocean Robots via Self-Attention Enhancement and Feature Interaction Optimization
- 用双分支自注意力模块增强特征表达
- 在真实海况下实现84.9%的mAP50性能
- 适合部署于资源受限的海洋探测机器人
海洋垃圾检测对生态保护至关重要，但低质量图像中的模糊、复杂背景和小目标常导致性能下降。为此，我们提出基于YOLO的增强框架YOLO-MD。设计了双分支卷积增强自注意力（DB-CASA）模块，强化空间-通道交互，提升退化图像的特征表示能力；引入轻量级移位操作，增强多尺度物体的细粒度特征提取，同时保持参数效率；提出SFG-Loss，通过动态样本重加权缓解类别不平衡与优化不稳定性。在UODM数据集上的实验表明，YOLO-MD达到0.875精确率、0.822 F1分数和0.849 mAP50，优于当前最先进方法。该方法的真实机器人边缘部署实验也验证了其有效性。
原文摘要 · Abstract (English)
Marine debris detection for ocean robot is crucial for ecological protection, yet performance is often degraded by low-quality images with blur, complex backgrounds, and small targets. To address these challenges, we propose YOLO-MD, an enhanced YOLO-based detection framework. A Dual-Branch Convolutional Enhanced Self-Attention (DB-CASA) module is designed to strengthen spatial-channel interactions, improving feature representation in degraded images. Additionally, a lightweight shift-based operation is introduced to enhance fine-grained feature extraction for objects of varying scales while maintaining parameter efficiency. We further propose SFG-Loss to mitigate class imbalance and optimization instability via dynamic sample reweighting. Experiments on the UODM dataset demonstrate that YOLO-MD achieves 0.875 precision, 0.822 F1-score, and 0.849 mAP50, outperforming the latest state-of-the-art methods. The effectiveness of this method has also been verified through real-world robotic edge deployment experiments.
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。