检索结果-内蒙古大学图书馆

Deep Learning-Based Algorithm for road defect detection

SENSORS 2025年第5期25卷 1287-1287页

作者： Li, Shaoxiang Zhang, Dexiang Anhui Univ Sch Elect Engn & Automat Hefei 230601 Peoples R China

With the increasing demand for road defect detection, existing deep learning methods have made significant progress in terms of accuracy and speed. However, challenges remain, such as insufficient detection precision for detection precision for road defect recognition and issues of missed or false detections in complex backgrounds. These issues reduce detection reliability and hinder real-world deployment. To address these challenges, this paper proposes an improved YOLOv8-based model, RepGD-YOLOV8W. First, it replaces the C2f module in the GD mechanism with the improved C2f module based on RepViTBlock to construct the Rep-GD module. This improvement not only maintains high detection accuracy but also significantly enhances computational efficiency. Subsequently, the Rep-GD module was used to replace the traditional neck part of the model, thereby improving multi-scale feature fusion, particularly for detecting small targets (e.g., cracks) and large targets (e.g., potholes) in complex backgrounds. Additionally, the introduction of the Wise-IoU loss function further optimized the bounding box regression task, enhancing the model's stability and generalization. Experimental results demonstrate that the improved REPGD-YOLOV8W model achieved a 2.4% increase in mAP50 on the RDD2022 dataset. Compared with other mainstream methods, this model exhibits greater robustness and flexibility in handling road defects of various scales.

关键词： road defect detection YOLOv8 GD mechanism RepViTBlock Wise-IoU loss function

来源：评论

学校读者我要写书评

暂无评论

Research on road defect detection Algorithm Based on LD-YOLOv8 1

引用

17th International Conference on Intelligent Robotics and Applications

作者： Zhao, Enlong Xi An Jiao Tong Univ Xian 710049 Peoples R China

ISBN: (数字)9789819607921

ISBN: (纸本)9789819607914;9789819607921

To enhance the performance of road defect detection methods, YOLOv8s is used as the benchmark model in this study, with improvements made to the model structure. Firstly, to better detect small object defects, the backbone network of YOLOv8s was modified by replacing the original Conv modules with SPD-Conv, and a new C2f-SPD module was constructed. Additionally, to better utilize the information in feature maps, the original model's feature fusion module was improved by substituting the nearest neighbor interpolation up-sampling module with a DySample up-sampling module. To better leverage the global context information of images and enhance the model's generalizability, the LSKA attention mechanism was introduced, creating a new SPPF-LSKA module. To adapt well to complex detection scenarios and environmental backgrounds, DyHead was used to improve the original model's detection head. The modified model significantly outperformed other models in the task of road surface defect detection. The improved LD-YOLOv8 model achieved a 1.8% increase in accuracy, a 0.9% increase in recall rate, and a 2.4% increase in mAP50.

关键词： road defect detection SPD-Conv Large Seqarable Kernel Attention Dynamic Head

来源：评论

学校读者我要写书评

暂无评论

A road defect detection Algorithm Based on Improved YOLOv8 5th

A Road Defect Detection Algorithm Based on Improved YOLOv8

引用

5th International Conference on Neural Computing for Advanced Applications (NCAA)

作者： Niu, Yiqing Cao, Jianrong Wang, Yuanchang Shandong Jianzhu Univ Sch Informat & Elect Engn Jinan 250101 Peoples R China

ISBN: (纸本)9789819770069;9789819770076

road defect detection is considered a prerequisite for maintaining road quality and a necessary measure to ensure driving safety. In addressing the challenges posed by existing methods' inefficiency, inaccuracy, and high cost, an improved road defect detection algorithm grounded in the YOLOv8 framework is proposed, denoted as YOLOv8n-CSW. First, we integrate the CBAM attention mechanism into the backbone network's C2f module, now termed the C2fCBAM module, to enhance feature extraction capabilities and suppress irrelevant information interference. Then the lightweight convolutional method GSConv and cross-level partial network module, VoV-GSCSP, can be flexibly integrated as a sleek and efficient slim-neck to seamlessly displace the initial neck network, thus optimizing the overall architecture and performance, ensuring accuracy while reducing computational complexity. Moreover, substituting the loss function with Wise-IoU enables focusing on the anchor frame of common quality and improving overall detector performance. The experimental results conclusively present that on the RDD2022 dataset, the mAP50 of the enhanced algorithm achieves 56.9%, surpassing the original algorithm accuracy by 1.7%. The computational volume is reduced to 7.3G, representing a 9.8% decrease. Additionally, the algorithm achieves an impressive frame detection rate of 83 frames per second (FPS) enabling accurate detection of road defects in real-time.

关键词： road defect detection YOLOv8 attention mechanism slim-neck WIoU

来源：评论

学校读者我要写书评

暂无评论

Lightweight road defect detection Algorithm Based on Improved YOLOv10

引用

ENGINEERING LETTERS 2025年第5期33卷 1193-1202页

作者： Zhang, Kaihui Wu, Yanze Li, Nan Guo, Xiaoyu Cheng, Ran Zhu, Lijun Shenyang Univ Chem Technol Sch Comp Sci & Technol Shenyang 110142 Peoples R China

road defect detection is an important task for road repair. Aiming at the problems of current road defect detection algorithms, such as large occupied space, low precision and complicated calculation, this paper introduces a lightweight algorithm for detecting road defects, improved by YOLOv10n. Firstly, In the backbone, we propose to replace C2f module with DERC2f module. The DERC2f module uses residual connection and Efficient Local Attention mechanism (ELA)to retain more original input information and accurately obtain the location information of defect features,enhance the feature extraction ability of the model. Secondly, the depthwise separable convolution is introduced, and the size of the convolution kernel is re-optimized, which lightens the detection head part and improves the detection efficiency of the model. Finally, SIoU and Slide Loss were introduced to replace the loss functions, which accelerated the convergence of the model, assigned higher weights to difficult samples, and further improved the accuracy. The experimental results show that in the dataset RDD2022, compared with the YOLOv10n model, the improved model has a 2.5% increase in mAP50, a 30% and 37.8% reduction in Params and FLOPs, respectively, which realize the lightweight of the model and the accurate detection of road defects.

关键词： road defect detection YOLOv10n lightweight attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Advancing smart transportation: A review of computer vision and photogrammetry in learning-based dimensional road pavement defect detection

引用

COMPUTER SCIENCE REVIEW 2025年 56卷

作者： Tafida, Adamu Alaloul, Wesam Salah Zawawi, Noor Amila Bt Wan Musarat, Muhammad Ali Sani, Adamu Abubakar Univ Teknol PETRONAS Dept Civil & Environm Engn Bandar Seri Iskandar 32610 Perak Malaysia Univ Teknol PETRONAS Inst Autonomous Syst Offshore Engn Ctr Bandar Seri Iskandar 32610 Perak Malaysia Abubakar Tafawa Balewa Univ Dept Quant Surveying Bauchi Nigeria Abubakar Tafawa Balewa Univ Dept Bldg Bauchi Nigeria

road infrastructure networks are crucial in facilitating smart mobility, as indicated by the emergence of innovative transportation concepts that offer improved efficiency and environmental sustainability. This study seeks to review the literature regarding road pavement condition assessment performance improvement tools which utilize various computer vision and photogrammetry tools aided by machine learning algorithms towards mitigating challenges encountered and promoting smart transportation trends. A comprehensive search of available literature was conducted, and relevant studies were analyzed to identify computer vision and photogrammetry tools used, learning-based algorithms deployed and contribution to the improvement of road infrastructure to aid smart transportation. The review considered emerging challenges of the techniques, identified research gaps and explored the potentials of the techniques as it relates to aiding wider acceptance of the implementation of autonomous vehicles and smart transportation The study found gaps in knowledge relating to the computer vision (CV) and photogrammetry tools standardization of evaluation parameters, the applicability of the models for real-time assessment and implications regarding the adoption of autonomous vehicles and smart transportation which were not sufficiently considered in the previous cited literature. Future research areas were highlighted and its implication regarding the promotion of smart transportation.

关键词： Smart transportation road infrastructure Computer vision and photogrammetry Machine learning algorithm road defect detection

来源：评论

学校读者我要写书评

暂无评论

road defect detection from on-board cameras with scarce and cross-domain data

引用

AUTOMATION IN CONSTRUCTION 2022年 144卷

作者： Zhou, Wei Zhan, Yunfei Zhang, Hancheng Zhao, Lei Wang, Chen Southeast Univ Sch Transportat Southeast Univ Rd Nanjing 211189 Jiangsu Peoples R China Purple Mt Labs Mozhou East Rd Nanjing 210008 Jiangsu Peoples R China

Deep learning methods have attained promising performance on road defect detection from on-board cameras. However, they oftentimes rely heavily on well-annotated datasets with sufficient samples, limiting the practical applications when only few labeled samples are available. To fill this gap, this paper proposes a framework based on Faster Region-Convolutional Neural Network (Faster R-CNN) for road defect detection with scarce and cross-domain data. First, a defect weighting branch is developed to enable Faster R-CNN to quickly learn to detect road defects with few annotated data, then a data augmentation method is proposed to enlarge the abundance of annotated data and alleviate the cross-domain issue. Experimental results demonstrate that the proposed framework has attained better performance compared to a state-of-the-art few-shot detector, in terms of an improved mean average precision of 1.83% when only limited samples (i.e., 30 images per category) are provided for training. In the future, the proposed framework could also be extended to other detection tasks with limited data (e.g., construction vehicle detection), allowing humans to reduce their efforts and time required for arduous data collection and annotation.

关键词： road defect detection Computer vision Few-shot object detection Data augmentation method

来源：评论

学校读者我要写书评

暂无评论

Platform for road defect detection Based on Edge Computing Devices 11

Platform for Road Defect Detection Based on Edge Computing D...

引用

11th IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) - Empower of Innovative Consumer Technology

作者： Lin, Jia-Yan Lin, Feng-Cheng Feng Chia Univ Dept Informat Engn & Comp Sci Taichung Taiwan

ISBN: (纸本)9798350386851;9798350386844

The importance of road defect detection is evident in maintaining and improving transportation infrastructure, enhancing traffic safety, and reducing vehicle damage and accident risks. However, current detection methods often rely on manual inspection and the recording of defect locations. Leveraging advancements in edge computing and artificial intelligence, we have designed a road defect detection device for in-car use. The device incorporates road defect recognition and the Global Positioning System (GPS), allowing users to view detection results on a web platform map. This innovation significantly improves the efficiency of current road inspection methods. In this research, we utilize the Nvidia Jetson Xavier NX as the edge computing device and employ an object detection model (evaluations by YOLOv7 and YOLOv8 under CIoU loss and SIoU loss functions) for road defect detection on this device.

关键词： road defect detection Edge computing Artificial intelligence Transportation infrastructure

来源：评论

学校读者我要写书评

暂无评论

YOLO-RDD: A road defect detection algorithm based on YOLO 27

YOLO-RDD: A road defect detection algorithm based on YOLO

引用

27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

作者： Pei, Jiabin Wu, Xiaoming Liu, Xiangzhi Qilu Univ Technol Shandong Acad Sci Shandong Comp Sci CtrMinist Educ Natl Supercomp Ctr JinanKey Lab Comp Power Netwo Jinan Peoples R China Shandong Fundamental Res Ctr Comp Sci Shandong Prov Key Lab Comp Networks Jinan Peoples R China

ISBN: (纸本)9798350349184;9798350349191

road maintenance is an indispensable part of the transportation system, ensuring road safety and maximizing road efficiency. The rapid and accurate acquisition of road surface information is crucial for effective road maintenance management. With the development of artificial intelligence, computer vision-based road defect detection methods are becoming popular. In this study, we propose a universal road defect detection model named YOLO-RDD, using You Only Look Once version 8 as the basic framework. Firstly, we introduce a new feature extraction and fusion approach to enhance the interaction between shallow and deep feature information, enabling multi-scale defect detection. Secondly, inspired by dynamic snake convolution, as cracks are the major road defects, we propose a new feature extraction module called DSC-C2f to adapt to the elongated and continuous morphology of cracks. Finally, we establish cross-layer connections between the backbone, neck, and prediction stages and integrate a coordinate attention module that considers inter-channel relationships and long-range positional dependencies. This allows the model to selectively focus on relevant parts of shallow and deep semantic information. We evaluate our model using the dataset provided by the crowdsensing-based road damage detection challenge (CRDDC2022) and further assess its performance on a publicly available crack and sealed crack dataset. The experiments demonstrated that our model achieved the best performance compared to the state-of-the-art (SOTA) models. Compared to the baseline model YOLOv8, our model achieved improvements of 1.2% in Precision, 1.9% in Recall, 1.9% in mAP@0.5, 0.8% in mAP@0.5:0.95, and 1.6% in F1-Score.

关键词： road defect detection YOLO attention mechanism crack detection

来源：评论

学校读者我要写书评

暂无评论

A Lightweight road defect detection Method Based on Multi-scale Hybrid Feature Fusion 13

A Lightweight Road Defect Detection Method Based on Multi-sc...

引用

13th International Conference on Graphics and Image Processing (ICGIP)

作者： Kuang, Jin Liu, Dong Lv, Hong Xu, Xinyue Zhang, Lingrong Xiangnan Univ Sch Comp & Artificial Intelligence Chenzhou 423300 Hunan Peoples R China

ISBN: (数字)9781510650435

ISBN: (纸本)9781510650435;9781510650428

Automatic road defect detection plays a significant role in road upkeep and transportation safety. However, existing approaches still have some shortcomings in detection accuracy, real-time, and hardware requirement. In this paper, we propose a novel anchor-free road defect detection method based on multi-scale hybrid feature fusion. First, we design a lightweight first-order detector to keep more semantic features. Then, we employ a depth separable convolutional layer to reduce the computational complexity. Finally, we propose a hybrid feature fusion framework to improve the feature description capability. Rigorous experimental evaluations on road benchmark data sets demonstrate that our method achieves the highest accuracy and outperforms the YOLO series models. Furthermore, our method has a short inference time of 32ms, which makes it an excellent model in real-time defect detection tasks.

关键词： road defect detection feature fusion deep learning deep separable convolution

来源：评论

学校读者我要写书评

暂无评论

Research on road defect detection based on improved YOLOv8 11

Research on road defect detection based on improved YOLOv8

引用

11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023

作者： Li, Guoxin Zhu, Dongbi College of Engineering Yanbian University Jilin China

ISBN: (纸本)9798350333664

Currently, the use of autonomous driving technology in China is generally limited by strict lane division and road conditions. In contrast to Tesla's vision-based autonomous driving technology, autonomous driving in China generally relies on radar signal reflection for positioning. As target detection algorithms continue to advance, it is a future trend to introduce computer vision methods into autonomous driving. This article proposes an improved YOLOv8 network model for research using relevant Chinese road datasets. By introducing a better backbone network, convnextv2, based on YOLOv8, it can effectively extract features from the data. Additionally, by introducing the novel WIOU computation function, it can better calculate the rectangular boxes. In this experiment, the improved YOLOv8-ATE achieved an average precision of mAPO.5 and mAPO.5:0.95, which were 18.1 % and 19% higher, respectively, compared to YOLOv8-base. The proposed YOLOv8-ATE model can effectively detect road defects and provide theoretical and technical support for future visual research in autonomous driving. © 2023 IEEE.

关键词： Attention mechanism Computer vision Object detection road defect detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：