OpenStreetMap中使用MaskCNN和航空图像的自动路面分类。

IF 2.4 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS
Frontiers in Big Data Pub Date : 2025-08-13 eCollection Date: 2025-01-01 DOI:10.3389/fdata.2025.1657320
R Parvathi, V Pattabiraman, Nancy Saxena, Aakarsh Mishra, Utkarsh Mishra, Ansh Pandey
{"title":"OpenStreetMap中使用MaskCNN和航空图像的自动路面分类。","authors":"R Parvathi, V Pattabiraman, Nancy Saxena, Aakarsh Mishra, Utkarsh Mishra, Ansh Pandey","doi":"10.3389/fdata.2025.1657320","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>OpenStreetMap (OSM) road surface data is critical for navigation, infrastructure monitoring, and urban planning but is often incomplete or inconsistent. This study addresses the need for automated validation and classification of road surfaces by leveraging high-resolution aerial imagery and deep learning techniques.</p><p><strong>Methods: </strong>We propose a MaskCNN-based deep learning model enhanced with attention mechanisms and a hierarchical loss function to classify road surfaces into four types: asphalt, concrete, gravel, and dirt. The model uses NAIP (National Agriculture Imagery Program) aerial imagery aligned with OSM labels. Preprocessing includes georeferencing, data augmentation, label cleaning, and class balancing. The architecture comprises a ResNet-50 encoder with squeeze-and-excitation blocks and a U-Net-style decoder with spatial attention. Evaluation metrics include accuracy, mIoU, precision, recall, and F1-score.</p><p><strong>Results: </strong>The proposed model achieved an overall accuracy of 92.3% and a mean Intersection over Union (mIoU) of 83.7%, outperforming baseline models such as SVM (81.2% accuracy), Random Forest (83.7%), and standard U-Net (89.6%). Class-wise performance showed high precision and recall even for challenging surface types like gravel and dirt. Comparative evaluations against state-of-the-art models (COANet, SA-UNet, MMFFNet) also confirmed superior performance.</p><p><strong>Discussion: </strong>The results demonstrate that combining NAIP imagery with attention-guided CNN architectures and hierarchical loss functions significantly improves road surface classification. The model is robust across varied terrains and visual conditions and shows potential for real-world applications such as OSM data enhancement, infrastructure analysis, and autonomous navigation. Limitations include label noise in OSM and class imbalance, which can be addressed through future work involving semi-supervised learning and multimodal data integration.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"8 ","pages":"1657320"},"PeriodicalIF":2.4000,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382388/pdf/","citationCount":"0","resultStr":"{\"title\":\"Automated road surface classification in OpenStreetMap using MaskCNN and aerial imagery.\",\"authors\":\"R Parvathi, V Pattabiraman, Nancy Saxena, Aakarsh Mishra, Utkarsh Mishra, Ansh Pandey\",\"doi\":\"10.3389/fdata.2025.1657320\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>OpenStreetMap (OSM) road surface data is critical for navigation, infrastructure monitoring, and urban planning but is often incomplete or inconsistent. This study addresses the need for automated validation and classification of road surfaces by leveraging high-resolution aerial imagery and deep learning techniques.</p><p><strong>Methods: </strong>We propose a MaskCNN-based deep learning model enhanced with attention mechanisms and a hierarchical loss function to classify road surfaces into four types: asphalt, concrete, gravel, and dirt. The model uses NAIP (National Agriculture Imagery Program) aerial imagery aligned with OSM labels. Preprocessing includes georeferencing, data augmentation, label cleaning, and class balancing. The architecture comprises a ResNet-50 encoder with squeeze-and-excitation blocks and a U-Net-style decoder with spatial attention. Evaluation metrics include accuracy, mIoU, precision, recall, and F1-score.</p><p><strong>Results: </strong>The proposed model achieved an overall accuracy of 92.3% and a mean Intersection over Union (mIoU) of 83.7%, outperforming baseline models such as SVM (81.2% accuracy), Random Forest (83.7%), and standard U-Net (89.6%). Class-wise performance showed high precision and recall even for challenging surface types like gravel and dirt. Comparative evaluations against state-of-the-art models (COANet, SA-UNet, MMFFNet) also confirmed superior performance.</p><p><strong>Discussion: </strong>The results demonstrate that combining NAIP imagery with attention-guided CNN architectures and hierarchical loss functions significantly improves road surface classification. The model is robust across varied terrains and visual conditions and shows potential for real-world applications such as OSM data enhancement, infrastructure analysis, and autonomous navigation. Limitations include label noise in OSM and class imbalance, which can be addressed through future work involving semi-supervised learning and multimodal data integration.</p>\",\"PeriodicalId\":52859,\"journal\":{\"name\":\"Frontiers in Big Data\",\"volume\":\"8 \",\"pages\":\"1657320\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-08-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382388/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Big Data\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/fdata.2025.1657320\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Big Data","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fdata.2025.1657320","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

OpenStreetMap (OSM)的路面数据对导航、基础设施监测和城市规划至关重要,但往往不完整或不一致。本研究通过利用高分辨率航空图像和深度学习技术解决了路面自动验证和分类的需求。方法:我们提出了一个基于maskcnn的深度学习模型,增强了注意机制和分层损失函数,将路面分为四种类型:沥青、混凝土、砾石和污垢。该模型使用与OSM标签对齐的NAIP(国家农业图像计划)航空图像。预处理包括地理参考、数据增强、标签清理和类平衡。该架构包括一个具有压缩和激励块的ResNet-50编码器和一个具有空间注意力的u - net风格解码器。评估指标包括准确性、mIoU、精度、召回率和f1分数。结果:该模型总体准确率为92.3%,平均mIoU准确率为83.7%,优于SVM(准确率81.2%)、Random Forest(准确率83.7%)和标准U-Net(准确率89.6%)等基准模型。即使在砾石和污垢等具有挑战性的表面类型上,同级性能也具有很高的精度和召回率。与最先进的模型(COANet, SA-UNet, MMFFNet)的比较评估也证实了优越的性能。讨论:结果表明,将NAIP图像与注意力引导的CNN架构和分层损失函数相结合,显著提高了路面分类能力。该模型在各种地形和视觉条件下都具有鲁棒性,并显示出实际应用的潜力,例如OSM数据增强、基础设施分析和自主导航。局限性包括OSM中的标签噪声和类不平衡,这可以通过未来涉及半监督学习和多模态数据集成的工作来解决。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automated road surface classification in OpenStreetMap using MaskCNN and aerial imagery.

Introduction: OpenStreetMap (OSM) road surface data is critical for navigation, infrastructure monitoring, and urban planning but is often incomplete or inconsistent. This study addresses the need for automated validation and classification of road surfaces by leveraging high-resolution aerial imagery and deep learning techniques.

Methods: We propose a MaskCNN-based deep learning model enhanced with attention mechanisms and a hierarchical loss function to classify road surfaces into four types: asphalt, concrete, gravel, and dirt. The model uses NAIP (National Agriculture Imagery Program) aerial imagery aligned with OSM labels. Preprocessing includes georeferencing, data augmentation, label cleaning, and class balancing. The architecture comprises a ResNet-50 encoder with squeeze-and-excitation blocks and a U-Net-style decoder with spatial attention. Evaluation metrics include accuracy, mIoU, precision, recall, and F1-score.

Results: The proposed model achieved an overall accuracy of 92.3% and a mean Intersection over Union (mIoU) of 83.7%, outperforming baseline models such as SVM (81.2% accuracy), Random Forest (83.7%), and standard U-Net (89.6%). Class-wise performance showed high precision and recall even for challenging surface types like gravel and dirt. Comparative evaluations against state-of-the-art models (COANet, SA-UNet, MMFFNet) also confirmed superior performance.

Discussion: The results demonstrate that combining NAIP imagery with attention-guided CNN architectures and hierarchical loss functions significantly improves road surface classification. The model is robust across varied terrains and visual conditions and shows potential for real-world applications such as OSM data enhancement, infrastructure analysis, and autonomous navigation. Limitations include label noise in OSM and class imbalance, which can be addressed through future work involving semi-supervised learning and multimodal data integration.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.20
自引率
3.20%
发文量
122
审稿时长
13 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信