基于改进RT-DETR模型的雨天环境车辆目标检测研究
1. 四川师范大学, 物理与电子工程学院, 四川成都 610101
2. 四川师范大学, 计算机科学学院, 四川成都 610101
| 摘 要： | 针对雨天环境下车辆检测易受能见度降低、雨滴遮挡及对比度不足等因素影响而导致检测精度下降的问题，本文提出一种基于改进RT-DETR-R18模型的雨天车辆检测方法（R-RTDETR）。采用Conv与C2f-wConv组合网络替换原主干网络，通过加权卷积实现特征自适应调节，以增强关键区域信息表达；在编码器，引入全局-局部空间注意力模块（Global-Local Spatial Attention, GLSA）以实现全局语义与局部细节的高效融合；在解码器，引入P2浅层特征分支，优化多尺度融合路径，强化车辆感知能力。实验结果表明，R-RTDETR在测试集上的mAP较基线RT-DETR-R18提升1.52%，召回率提升1.25%；在ACDC雨天数据集上的mAP@0.5提升2.33%，在保证计算效率的同时提高了雨天车辆检测的稳定性与鲁棒性，验证了其在智能交通场景中的应用潜力。 |
| 关 键 词： | 目标检测; RT-DETR; 雨天车辆检测; 注意力机制; 深度学习 |
| DOI： | 10.57237/j.cst.2026.02.001 |
View:
Downloads:
收稿日期: 2026-02-11
接受日期: 2026-03-04
在线出版日期: 2026-03-24
Research on Vehicle Target Detection in Rainy Environment Based on Improved RT-DETR Model
1. College of Physics and Electronic Engineering, Sichuan Normal University, Chengdu 610101, China
2. College of Computer Science, Sichuan Normal University, Chengdu 610101, China
| Abstract: | To address the issue of decreased vehicle detection accuracy in rainy conditions due to reduced visibility, raindrop obstruction, and insufficient contrast, this paper proposes a rain-based vehicle detection method (R-RTDETR) based on an improved RT-DETR-R18 model. The original backbone network is replaced with a combined Conv and C2f-wConv network, and weighted convolutions are used to adaptively adjust features, enhancing the representation of key region information. In the encoder, a Global-Local Spatial Attention (GLSA) module is introduced to achieve efficient fusion of global semantics and local details. In the decoder, a P2 shallow feature branch is introduced to optimize the multi-scale fusion path and strengthen vehicle perception capabilities. Experimental results show that R-RTDETR improves mAP by 1.52% and recall by 1.25% on the test set compared to the baseline RT-DETR-R18; on the ACDC rainy dataset, mAP@0.5 is improved by 2.33%, demonstrating improved stability and robustness of rain-based vehicle detection while maintaining computational efficiency, validating its application potential in intelligent transportation scenarios. |
| Keywords: | Object Detection; RT-DETR; Vehicle Detection in Rainy Weather; Attention Mechanism; Deep Learning |
参考文献
| [1] | SONG Y F, LU Y F. A review of unmanned visual target detection in adverse weather [J]. Electronics, 2025, 14(13): 2582. |
| [2] | PENNELLY C, REUTER G W, TJANDRA S. Effects of weather on traffic collisions in Edmonton, Canada [J]. Atmosphere-Ocean, 2018, 56(5): 362-371. |
| [3] | LI X, GENG S. Improved traffic sign detection algorithm for YOLOv5s [C] // International Conference on Computer Engineering and Application. Piscataway: IEEE, 2023: 696-699. |
| [4] | REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. |
| [5] | REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788. |
| [6] | LYU Z W, JIN H F, ZHEN T, et al. Small object recognition algorithm of grain pests based on SSD feature fusion [J]. IEEE Access, 2021, 9: 43202-43213. |
| [7] | CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C] // Computer Vision–ECCV 2020: 16th European Conference, Proceedings, Part I. Cham: Springer International Publishing, 2020: 213-229. |
| [8] | ZHAO Y A, LÜ W Y, XU S L, et al. DETRs beat YOLOs on real-time object detection [C] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 16965-16974. |
| [9] | 胡待方, 仝秋红, 柴国庆, 等. 雨天车辆检测的两阶段渐进式图像去雨算法 [J]. 激光与光电子学进展, 2023, 60(22): 2215001. |
| [10] | 陈婷, 姚大春, 高涛, 等. 基于PReNet和YOLOv4融合的雨天交通目标检测网络 [J]. 交通运输工程学报, 2022, 22(3): 225-237. |
| [11] | OGINO Y, SHOJI Y, TOIZUMI T, et al. ERUP-YOLO: enhancing object detection robustness for adverse weather condition by unified image-adaptive processing [EB/OL]. arXiv, 2024. |
| [12] | JING Z Y, LI S, ZHANG Q W, et al. YOLOv8-STE: enhancing object detection performance under adverse weather conditions with deep learning [J]. Electronics, 2024, 13(24): 5049-5063. |
| [13] | TABASSUM N, EL-SHARKAWY M. Vehicle detection in adverse weather: a multi-head attention approach with multimodal fusion [J]. Journal of Low Power Electronics and Applications, 2024, 14(2): 23. |
| [14] | GHARATAPPEH S, SEKEH S, DHIMAN V, et al. Weather-aware object detection transformer for domain adaptation [EB/OL]. arXiv, 2025. |
| [15] | SALSCHEIDER N O. Featurenms: non-maximum suppression by learning feature embeddings [C] // Proceedings of the 2020 25th International Conference on Pattern Recognition. Piscataway: IEEE, 2021: 7848-7854. |
| [16] | CAMMARASANA S, PATANÈ G. Optimal density functions for weighted convolution in learning models [EB/OL]. arXiv, 2025. |
| [17] | TANG F L, XU Z X, HUANG Q M, et al. DuAT: dual-aggregation transformer network for medical image segmentation [C] // Pattern Recognition and Computer Vision: 6th Chinese Conference, PRCV 2023, Proceedings, Part III. Cham: Springer, 2023: 343-356. |
| [18] | ZHOU Y, WEI Y. UAV-DETR: an enhanced RT-DETR architecture for efficient small object detection in UAV imagery [J]. Sensors, 2025, 25(15): 4582. |
| [19] | HUANG J, LI T. Small object detection by DETR via information augmentation and adaptive feature fusion [C] // Proceedings of the 2024 ACM International Conference on Multimedia Retrieval. New York: ACM, 2024: 39-44. |
| [20] | YU F, CHEN H, WANG X, et al. BDD100K: a diverse driving dataset for heterogeneous multitask learning [EB/OL]. arXiv, 2020. |
| [21] | KENK M A, HASSABALLAH M. DAWN: vehicle detection in adverse weather nature dataset [EB/OL]. arXiv, 2020. |
| [22] | SAKARIDIS C, DAI D, VAN GOOL L. ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding [C] // Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 10765-10775. |
