基于YOLO-CDBW模型的列车接触网异物检测研究

摘要/Abstract

参考文献

相关文章 15

Metrics

doi:10.16088/j.issn.1001-6600.2024040102

摘要： 接触网是为列车行驶提供电力的输电线路,附着在接触网的塑料袋等异物会对列车运行造成安全隐患。针对目前人工检查效率低下、劳动成本高等问题,本文提出一种基于YOLOv7改进的接触网异物检测模型YOLO-CDBW。首先,在特征提取阶段构建一种使用残差瓶颈结构和深度分离卷积层的特征提取模块,避免因网络深度增加造成的小目标特征丢失问题,并降低网络运算量;其次,颈部改用BiFPN结构,捕捉多尺度信息,改善细节特征丢失问题,同时嵌入BiFormer注意力机制,重新分配融合后特征图的权重,提高网络对异物的关注度;最后,使用WIoU损失函数优化模型,通过动态聚焦机制,将注意力聚集在普通质量锚框上,提高预测精准度。经实验,YOLO-CDBW模型平均精度均值mAP_0.5达到87.1%,检测速度FPS达到66.5 frame/s,较YOLOv7模型分别提高5.0和10.8个百分点,满足接触网异物检测需求。

关键词: 接触网, 异物检测, YOLO, 目标检测, 损失函数, 注意力机制

Abstract: The catenary is a transmission line that provides power for the train, and foreign objects such as plastic bags attached to the catenary will cause potential safety hazards to the train operation. In order to solve the problems of low efficiency and high labor cost of manual inspection, a YOLO-CDBW model for catenary foreign body detection based on YOLOv7 is proposed. Firstly, in the feature extraction stage, a feature extraction module using residual bottleneck structure and depth separation convolutional layer is constructed to avoid the problem of small target feature loss caused by the increase of network depth and reduce the amount of network computation. Finally, the WIoU loss function is used to optimize the model and focus on the ordinary mass anchor frame through the dynamic focusing mechanism to improve the prediction accuracy. Experimental results show that, the average mAP_0.5 of the YOLO-CDBW model reaches 87.1% and the detection speed FPS reaches 66.5 frame/s, which are 5.0 and 10.8 percentage points higher than those of the YOLOv7 model, respectively, meeting the needs of catenary foreign body detection.

Key words: contact line, foreign substance examination, YOLO, object detection, loss function, attention mechanisms

中图分类号: U226.8;TP391.41

郭翔羽, 石天怡, 陈燕楠, 南新元, 蔡鑫. 基于YOLO-CDBW模型的列车接触网异物检测研究[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 56-69.

GUO Xiangyu, SHI Tianyi, CHEN Yannan, NAN Xinyuan, CAI Xin. Research on Foreign Object Detection in Railway Overhead Contact System Based on YOLO-CDBW Model[J]. Journal of Guangxi Normal University(Natural Science Edition), 2025, 43(2): 56-69.

[1] 朱天乐,潘祉鸥,袁天笑,等.高铁牵引供电系统运行的电能质量评估[J].自动化应用,2021(11):104-110.DOI: 10.19769/j.zdhy.2021.11.026.
[2] 高天姿.基于深度卷积神经网络的接触网异物与缺陷检测算法研究[D].南昌:华东交通大学,2022.DOI: 10.27147/d.cnki.ghdju.2022.000326.
[3] 段旺旺,唐鹏,金炜东,等.基于关键区域HOG特征的铁路接触网鸟巢检测[J].中国铁路,2015(8):73-77.DOI: 10.3969/j.issn.1001-683X.2015.08.018.
[4] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C] // 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). Los Alamitos, CA: IEEE Computer Society, 2005: 886-893. DOI: 10.1109/CVPR.2005.177.
[5] 祝振敏,谢亮凯.基于相对位置不变性的接触网鸟巢识别检测[J].铁道科学与工程学报,2018,15(4):1043-1049.DOI: 10.3969/j.issn.1672-7029.2018.04.030.
[6] 张沐杰.面向高铁接触网的异物检测研究与实现[D].西安:西安电子科技大学,2017.DOI: 10.7666/d.D01386279.
[7] 顾䶮楠.铁路接触网异物检测图像处理技术研究[D].兰州:兰州交通大学,2022.DOI: 10.27205/d.cnki.gltec.2022.000485.
[8] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08)[2024-05-06]. https://arxiv.org/abs/1804.02767. DOI: 10.48550/arXiv.1804.02767.
[9] 吕嘉宜.基于视觉的高速铁路接触网异物检测[D].杭州:浙江大学,2021.DOI: 10.27461/d.cnki.gzjdx.2021.001267.
[10] KOLEKAR A, DALAL V. Barcode detection and classification using SSD (Single Shot Multibox Detector) deep learning algorithm[C] // Proceedings of the 3rd International Conference on Advances in Science & Technology (ICAST) 2020. Rochester, NY: Social Science Electronic Publishing, 2020: 1-4.
[11] 蒋欣兰,贾文博.高铁接触网异物侵入的机器视觉检测方法[J].计算机工程与应用,2019,55(22):250-257.DOI: 10.3778/j.issn.1002-8331.1908-0268.
[12] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2020: 10778-10787. DOI: 10.1109/CVPR42600.2020.01079.
[13] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2023: 7464-7475. DOI: 10.1109/CVPR52729.2023.00721.
[14] 潘海鹏,王云涛,马淼.基于注意力机制与多尺度融合学习的车辆重识别方法[J].浙江理工大学学报(自然科学版),2021,45(5):657-665.DOI: 10.3969/j.issn.1673-3851(n).2021.05.011.
[15] NASCIMENTO M G D, PRISACARIU V, FAWCETT R. DSConv: efficient convolution operator[C] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Los Alamitos, CA: IEEE Computer Society, 2020: 5147-5156. DOI: 10.1109/ICCV.2019.00525.
[16] 郝帅,杨磊,马旭,等.基于注意力机制与跨尺度特征融合的YOLOv5输电线路故障检测[J].中国电机工程学报,2023,43(6):2319-2330.DOI: 10.13334/j.0258-8013.pcsee.212607.
[17] 李秋华,李吉成,沈振康.基于多尺度特征融合的红外图像小目标检测[J].系统工程与电子技术,2005,27(9): 1557-1560.DOI: 10.3321/j.issn:1001-506X.2005.09.018.
[18] 辛世澳,葛海波,袁昊,等.改进YOLOv7的轻量化水下目标检测算法[J].计算机工程与应用,2024,60(3):88-99.DOI: 10.3778/j.issn.1002-8331.2308-0333.
[19] 周中,闫龙宾,张俊杰,等.基于自注意力机制与卷积神经网络的隧道衬砌裂缝智能检测[J].铁道学报,2024,46(9):182-192.DOI: 10.3969/j.issn.1001-8360.2024.09.021.
[20] 张林鍹,巴音塔娜,曾庆松.基于StyleGAN2-ADA和改进YOLO v7的葡萄叶片早期病害检测方法[J].农业机械学报,2024,55(1):241-252.DOI: 10.6041/j.issn.1000-1298.2024.01.023.
[21] 李安达,吴瑞明,李旭东.改进YOLOv7的小目标检测算法研究[J].计算机工程与应用,2024,60(1):122-134.DOI: 10.3778/j.issn.1002-8331.2307-0004.
[22] 代啟亮,熊凌,陈琳国,等.改进YOLOv5的PDC钻头复合片缺损识别[J].电子测量与仪器学报,2023,37(8):164-172.DOI: 10.13382/j.jemi.B2306476.
[23] 俞泉泉.面向光学遥感图像目标的检测与识别算法的研究与实现[D].成都:电子科技大学,2021.DOI: 10.27005/d.cnki.gdzku.2021.003795.
[24] CHENG G, HAN J W, ZHOU P C, et al. Multi-class geospatial object detection and geographic image classification based on collection of part detectors[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98: 119-132. DOI: 10.1016/j.isprsjprs.2014.10.002.
[25] CHENG G, HAN J W. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117: 11-28. DOI: 10.1016/j.isprsjprs.2016.03.014.
[26] CHENG G, ZHOU P C, HAN J W. Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12): 7405-7415. DOI: 10.1109/TGRS.2016.2601622.
[27] ELAOUA A, NADOUR M, CHERROUN L, et al. Real-time people counting system using YOLOv8 object detection[C] // 2023 2nd International Conference on Electronics, Energy and Measurement (IC2EM). Los Alamitos, CA: IEEE Computer Society, 2023: 1-5. DOI: 10.1109/IC2EM59347.2023.10419684.

[1]	苏春海, 夏海英. 抗噪声双约束网络的面部表情识别[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 70-82.
[2]	刘玉娜, 马双宝. 基于改进YOLOv8n的轻量化织物疵点检测算法[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 83-94.
[3]	戴林华, 黎远松, 石睿, 何忠良, 李雷. HSED-YOLO:一种轻量化的带钢表面缺陷检测模型[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 95-106.
[4]	余快, 宋宝贵, 邵攀, 余翱. 基于层级尺度交互的U-Net遥感影像建筑物提取方法[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 121-132.
[5]	卢家辉, 陈庆锋, 王文广, 余谦, 何乃旭, 韩宗钊. 基于多尺度注意力的器官图像分割方法[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 138-148.
[6]	于雪松, 徐宝. 加权p、q对称损失函数下Burr分布参数的Bayes估计[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 186-193.
[7]	涂智荣, 凌海英, 李帼, 陆声链, 钱婷婷, 陈明. 基于改进YOLOv7-Tiny的轻量化百香果检测方法[J]. 广西师范大学学报（自然科学版）, 2024, 42(5): 79-90.
[8]	杜帅文, 靳婷. 基于用户行为特征的深度混合推荐算法[J]. 广西师范大学学报（自然科学版）, 2024, 42(5): 91-100.
[9]	田晟, 胡啸. 基于Transformer模型的车辆轨迹预测[J]. 广西师范大学学报（自然科学版）, 2024, 42(3): 47-58.
[10]	吕辉, 吕卫峰. 基于改进YOLOv5的眼底出血点检测算法[J]. 广西师范大学学报（自然科学版）, 2024, 42(3): 99-107.
[11]	王天雨, 袁嘉伟, 齐芮, 李洋. 多类型知识增强的微博立场检测模型[J]. 广西师范大学学报（自然科学版）, 2024, 42(1): 79-90.
[12]	肖宇庭, 吕晓琪, 谷宇, 刘传强. 基于拆分残差网络的糖尿病视网膜病变分类[J]. 广西师范大学学报（自然科学版）, 2024, 42(1): 91-101.
[13]	曾亮, 胡谦, 杨腾飞, 谭微微. 基于L-ConvNeXt网络的变电站人员安全操作检测方法[J]. 广西师范大学学报（自然科学版）, 2024, 42(1): 102-110.
[14]	席凌飞, 伊力哈木·亚尔买买提, 刘雅洁. 基于改进YOLOv5的铝型材表面缺陷检测方法[J]. 广西师范大学学报（自然科学版）, 2024, 42(1): 111-119.
[15]	赵伟, 田帅, 张强, 王耀申, 王思博, 宋江. 基于改进YOLOv5的平贝母检测模型[J]. 广西师范大学学报（自然科学版）, 2023, 41(6): 22-32.

Just accepted

Online first

Just accepted

Online first

Viewed

Full text

Abstract

Just accepted	Online first	Issue

0	0	5

From	Others	local

Times	4	1
Rate	80%	20%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed