MFL-YOLO：一种用于损坏交通标志的目标检测模型
MFL-YOLO: An Object Detection Model for Damaged Traffic Signs
AI总结：
针对损坏交通标志难以检测的问题，提出基于YOLOv5s的MFL-YOLO模型，通过设计跨层级损失函数和引入GSConv与VoVGSCSP模块，在不增加复杂度的前提下有效提升了检测精度与泛化能力。
摘要：
交通标志是保障交通安全与顺畅的重要设施，但可能因多种原因受损，从而造成极大的安全隐患。因此，研究一种检测损坏交通标志的方法具有重要意义。目前针对损坏交通标志的现有目标检测技术仍然缺失。由于损坏的交通标志在外观上与正常的标志更为相似，使用传统的目标检测方法难以捕捉损坏交通标志的详细局部损坏特征。在本文中，我们提出了一种基于 YOLOv5s 的改进目标检测方法，即 MFL-YOLO（Mutual Feature Levels Loss enhanced YOLO，互特征层级损失增强 YOLO）。我们设计了一个简单的跨层级损失函数，使模型的每个层级都有其自身的作用，这有利于模型能够学习更多样化的特征并提高细粒度。该方法可作为即插即用模块应用，在提高准确率的同时，不会增加结构复杂性或计算复杂性。我们还在 YOLOv5s 的颈部将传统卷积和 CSP 替换为 GSConv 和 VoVGSCSP，以降低规模和计算复杂度。与 YOLOv5s 相比，我们的 MFL-YOLO 在 F1 分数和 mAP 上分别提升了 4.3 和 5.1，同时 FLOPs 降低了 8.9%。Grad-CAM 热力图可视化表明，我们的模型能够更好地关注损坏交通标志的局部细节。此外，我们还在 CCTSDB2021 和 TT100K 上进行了实验，以进一步验证我们模型的泛化能力。
英文摘要：
Traffic signs are important facilities to ensure traffic safety and smooth flow, but may be damaged due to many reasons, which poses a great safety hazard. Therefore, it is important to study a method to detect damaged traffic signs. Existing object detection techniques for damaged traffic signs are still absent. Since damaged traffic signs are closer in appearance to normal ones, it is difficult to capture the detailed local damage features of damaged traffic signs using traditional object detection methods. In this paper, we propose an improved object detection method based on YOLOv5s, namely MFL-YOLO (Mutual Feature Levels Loss enhanced YOLO). We designed a simple cross-level loss function so that each level of the model has its own role, which is beneficial for the model to be able to learn more diverse features and improve the fine granularity. The method can be applied as a plug-and-play module and it does not increase the structural complexity or the computational complexity while improving the accuracy. We also replaced the traditional convolution and CSP with the GSConv and VoVGSCSP in the neck of YOLOv5s to reduce the scale and computational complexity. Compared with YOLOv5s, our MFL-YOLO improves 4.3 and 5.1 in F1 scores and mAP, while reducing the FLOPs by 8.9%. The Grad-CAM heat map visualization shows that our model can better focus on the local details of the damaged traffic signs. In addition, we also conducted experiments on CCTSDB2021 and TT100K to further validate the generalization of our model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
