
浏览全部资源
扫码关注微信
内蒙古科技大学 自动化与电气工程学院, 内蒙古 包头 014010
向天明,男,硕士研究生,2023年于吉林化工大学获得学士学位,主要从事深度学习、目标检测方面的研究。E-mail:1377950574@qq.com
燕芳,女,教授,博士、2016年于北京科技大学获得博士学位,主要研究方向为无损检测及智能仪器仪表开发。E-mail:0472yanfang@163.com
收稿:2026-06-30,
修回:2026-07-13,
纸质出版:2026-08-05
移动端阅览
向天明, 燕芳, 李嘉辉, 等. SimCLR-YOLO:面向低标注依赖的公路病害检测算法[J]. 液晶与显示, 2026,41(8):1158-1174.
XIANG Tianming, YAN Fang, LI Jiahui, et al. SimCLR-YOLO: a road disease detection algorithm for low annotation dependence[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(8): 1158-1174.
向天明, 燕芳, 李嘉辉, 等. SimCLR-YOLO:面向低标注依赖的公路病害检测算法[J]. 液晶与显示, 2026,41(8):1158-1174. DOI: 10.3724/CJLCD.2026-0119. CSTR: 32172.14.CJLCD.2026-0119.
XIANG Tianming, YAN Fang, LI Jiahui, et al. SimCLR-YOLO: a road disease detection algorithm for low annotation dependence[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(8): 1158-1174. DOI: 10.3724/CJLCD.2026-0119. CSTR: 32172.14.CJLCD.2026-0119.
针对公路病害检测中样本稀缺、弱纹理漏检率高及复杂背景干扰等难题,提出融合无监督预训练SimCLR与YOLOv8n的公路病害检测算法SimCLR-YOLO。首先,将SimCLR骨干替换为YOLOv8n的CSPDarknet,实现结构对齐与特征无缝迁移,解决网络结构不匹配导致的特征丢失问题。其次,将掩码重构融入对比学习,驱使编码器聚焦裂缝与坑槽的纹理轮廓,弥补对比学习对弱纹理特征的欠拟合缺陷。最后,嵌入CBAM注意力模块,引导模型在预训练阶段抑制路面纹理、阴影等背景噪声,增强关键区域的特征响应。在RDD2022公开数据集上的实验表明,SimCLR-YOLO算法的mAP@0.5达到89.4%,较基线模型提升1.7%,mAP@0.5:0.95提升1.1%,F1-score提升1.8%。不同标注比例下的验证结果显示,引入预训练权重在各梯度下均优于从头训练,在50%标注比例下,SimCLR-YOLO算法的mAP@0.5仍可达87%,接近全量标注下的基线模型,显著降低了对标注数据的依赖。此外,改进仅在预训练生效,推理参数(3.01M)无额外开销,为样本匮乏条件下的公路病害实时检测提供了有效技术方案。
To address the challenges in road disease detection, such as sample scarcity, high miss rates for weakly textured targets, and complex background interference, a road disease detection algorithm named SimCLR-YOLO is proposed to integrate unsupervised pre-training SimCLR with YOLOv8n. Firstly, the SimCLR backbone is replaced with YOLOv8n’s CSPDarknet to achieve structural alignment and seamless feature transfer, resolving the feature loss issue caused by network structure mismatch. Secondly, masked reconstruction is incorporated into contrastive learning, forcing the encoder to focus on the texture contours of cracks and potholes, thereby compensating for the under-fitting of contrastive learning to weakly textured features. Finally, a CBAM attention module is embedded to guide the model in suppressing background noise such as road texture and shadows during the pre-training phase, while enhancing feature responses in critical regions. Experimental results on the public RDD2022 dataset show that the SimCLR-YOLO algorithm achieves an mAP@0.5 of 89.4%, which is 1.7% higher than the baseline model, with a 1.1% improvement in mAP@0.5:0.95 and a 1.8% increase in F1-score. Validation under different annotation ratios demonstrates that the scheme incorporating pre-trained weights outperforms training from scratch across all data gradients. At a 50% annotation ratio, the SimCLR-YOLO algorithm still achieves an mAP@0.5 of 87%, approaching the baseline model under full annotation, significantly reducing the dependence on annotated data. Moreover, the improvements are only effective during pre-training, with no additional overhead in inference parameters (3.01M), providing an effective technical solution for real-time road disease detection under sample-scarce conditions.
唐湘松 , 杨炜 , 李相衡 , 等 . 基于改进EfficientNetV2网络的路面类型及状态检测方法 [J]. 汽车工程学报 , 2026 , 16 ( 2 ): 294 - 304 .
TANG X S , YANG W , LI X H , et al . Road-surface type and condition detection based on an improved EfficientNetV2 [J]. Chinese Journal of Automotive Engineering , 2026 , 16 ( 2 ): 294 - 304 . (in Chinese)
马荣贵 , 黄训燕 , 董世浩 . 基于改进YOLOv8的实时坑槽检测算法 [J]. 计算机工程 , 2025 , 51 ( 11 ): 226 - 234 .
MA R G , HUANG X Y , DONG S H . Real-time pothole detection algorithm based on improved YOLOv8 [J]. Computer Engineering , 2025 , 51 ( 11 ): 226 - 234 . (in Chinese)
朱世松 , 高虹 , 芦碧波 , 等 . 基于改进YOLOv8n的城市道路病害检测算法 [J]. 液晶与显示 , 2025 , 40 ( 9 ): 1356 - 1368 . doi: 10.37188/cjlcd.2025-0101 http://dx.doi.org/10.37188/cjlcd.2025-0101
ZHU S S , GAO H , LU B B , et al . Urban road defect detection algorithm based on improved YOLOv8n [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 9 ): 1356 - 1368 . (in Chinese) . doi: 10.37188/cjlcd.2025-0101 http://dx.doi.org/10.37188/cjlcd.2025-0101
周建新 , 张媛 , 贾梓涵 , 等 . 改进YOLOv8的路面缺陷检测算法 [J]. 电子测量技术 , 2024 , 47 ( 19 ): 146 - 154 .
ZHOU J X , ZHANG Y , JIA Z H , et al . The pavement defect detection algorithm of YOLOv8 was improved [J]. Electronic Measurement Technology , 2024 , 47 ( 19 ): 146 - 154 . (in Chinese)
魏陈浩 , 杨睿 , 刘振丙 , 等 . 具有双层路由注意力的YOLOv8道路场景目标检测方法 [J]. 图学学报 , 2023 , 44 ( 6 ): 1104 - 1111 .
WEI C H , YANG R , LIU Z B , et al . YOLOv8 with Bi-level routing attention for road scene object detection [J]. Journal of Graphics , 2023 , 44 ( 6 ): 1104 - 1111 . (in Chinese)
张子轶 , 马丽 , 吕帅 , 等 . 基于RT-DETR的轻量化车辆目标检测算法 [J]. 液晶与显示 , 2026 , 41 ( 3 ): 373 - 387 .
ZHANG Z Y , MA L , LÜ S , et al . Lightweight vehicle object detection algorithm based on RT-DETR [J]. Chinese Journal of Liquid Crystals and Displays , 2026 , 41 ( 3 ): 373 - 387 . (in Chinese)
张旭中 , 李波 , 贝绍轶 , 等 . 改进YOLOv8的道路凹陷检测算法 [J]. 重庆理工大学学报(自然科学) , 2024 , 38 ( 10 ): 79 - 87 .
ZHANG X Z , LI B , BEI S Y , et al . Improved road depression detection algorithm for YOLOv8 [J]. Journal of Chongqing University of Technology (Natural Science) , 2024 , 38 ( 10 ): 79 - 87 . (in Chinese)
YIN L , XIA G , WANG Q , et al . Infrared monitoring and identification of lubricating oil pipe on a gas turbine based on faster RCNN [C]// Proceedings of SPIE 12617 , . Hefei : SPIE , 2023 : 126173I . doi: 10.1117/12.2665999 http://dx.doi.org/10.1117/12.2665999
VEERABHADRASWAMY K M , BANSOD P J , PATEL W , et al . Analysis of CT-images for COVID-19 using blockchain networks for mask RCNN and capsule [J]. Journal of Environmental Protection and Ecology , 2024 , 25 ( 5 ): 1717 - 1727 .
SYETIAWAN A , SUSETYO D B , LUMBAN-GAOL Y , et al . Deep learning-based palm tree detection in unmanned aerial vehicle imagery with Mask R-CNN [J]. TELKOMNIKA , 2025 , 23 ( 1 ): 156 - 165 . doi: 10.12928/telkomnika.v23i1.26244 http://dx.doi.org/10.12928/telkomnika.v23i1.26244
WANG D , XUE Y K , LIU Y , et al . On the understanding and modeling of non-negligible subthreshold-state degradation (SSD) in sub-20-nm DRAM technology [J]. IEEE Electron Device Letters , 2024 , 45 ( 9 ): 1582 - 1585 . doi: 10.1109/led.2024.3425860 http://dx.doi.org/10.1109/led.2024.3425860
岳永恒 , 雷文朋 . 基于改进的CycleGAN和YOLOv8联合雾天道路环境感知算法 [J]. 华南理工大学学报(自然科学版) , 2025 , 53 ( 2 ): 48 - 57 .
YUE Y H , LEI W P . Foggy road environment perception algorithm based on an improved CycleGAN and YOLOv8 [J]. Journal of South China University of Technology (Natural Science Edition) , 2025 , 53 ( 2 ): 48 - 57 . (in Chinese)
刘彦磊 , 李孟喆 , 王宣宣 . 轻量型YOLOv5s车载红外图像目标检测 [J]. 中国光学(中英文) , 2023 , 16 ( 5 ): 1045 - 1055 . doi: 10.37188/co.2022-0254 http://dx.doi.org/10.37188/co.2022-0254
LIU Y L , LI M Z , WANG X X . Lightweight YOLOv5s vehicle infrared image target detection [J]. Chinese Optics , 2023 , 16 ( 5 ): 1045 - 1055 . (in Chinese) . doi: 10.37188/co.2022-0254 http://dx.doi.org/10.37188/co.2022-0254
罗磊 , 谢竹逵 . 基于改进YOLOv8的交通标志检测算法 [J]. 机电工程技术 , 2024 , 53 ( 3 ): 205 - 210 .
LUO L , XIE Z K . Traffic sign detection algorithm based on improved YOLOv8 [J]. Mechanical & Electrical Engineering Technology , 2024 , 53 ( 3 ): 205 - 210 . (in Chinese)
路成龙 , 庆光蔚 , 孙勇 , 等 . 一种轻量级道路缺陷检测算法 [J]. 汽车工程学报 , 2026 , 16 ( 3 ): 395 - 405 .
LU C L , QING G W , SUN Y , et al . A lightweight algorithm for road defect detection [J]. Chinese Journal of Automotive Engineering , 2026 , 16 ( 3 ): 395 - 405 . (in Chinese)
GANGA B , LATA B T , VENUGOPAL K R . Object detection and crowd analysis using deep learning techniques: comprehensive review and future directions [J]. Neurocomputing , 2024 , 597 : 127932 . doi: 10.1016/j.neucom.2024.127932 http://dx.doi.org/10.1016/j.neucom.2024.127932
叶发茂 , 张立 , 袁燎 , 等 . DB-YOLO:特征增强融合的双骨干YOLOv8道路缺陷检测模型 [J]. 计算机工程与应用 , 2024 , 60 ( 24 ): 260 - 269 . doi: 10.3778/j.issn.1002-8331.2404-0019 http://dx.doi.org/10.3778/j.issn.1002-8331.2404-0019
YE F M , ZHANG L , YUAN L , et al . DB-YOLO: dual backbone YOLOv8 model with feature enhancement fusion for road defect detection [J]. Computer Engineering and Applications , 2024 , 60 ( 24 ): 260 - 269 . (in Chinese) . doi: 10.3778/j.issn.1002-8331.2404-0019 http://dx.doi.org/10.3778/j.issn.1002-8331.2404-0019
CHEN T , KORNBLITH S , NOROUZI M , et al . A simple framework for contrastive learning of visual representations [C]// Proceedings of the 37th International Conference on Machine Learning . Online : PMLR , 2020 : 1597 - 1607 .
WOO S , PARK J , LEE J Y , et al . CBAM: convolutional block attention module [C]// Proceedings of the 15th European Conference on Computer Vision (ECCV) . Munich : Springer , 2018 : 3 - 19 . doi: 10.1007/978-3-030-01234-2_1 http://dx.doi.org/10.1007/978-3-030-01234-2_1
HE K M , CHEN X L , XIE S N , et al . Masked autoencoders are scalable vision learners [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans : IEEE , 2022 : 15979 - 15988 . doi: 10.1109/cvpr52688.2022.01553 http://dx.doi.org/10.1109/cvpr52688.2022.01553
ARYA D , MAEDA H , GHOSH S K , et al . RDD2022: a multi-national image dataset for automatic road damage detection [J]. Geoscience Data Journal , 2024 , 11 ( 4 ): 846 - 862 .
0
浏览量
53
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621