Xinhao Zhou, Lin Zhao, Zhaodong Liu, Liping Fu, Guangyuan Pan
{"title":"用于多场景路面气象条件监测的自适应机器学习框架","authors":"Xinhao Zhou, Lin Zhao, Zhaodong Liu, Liping Fu, Guangyuan Pan","doi":"10.1139/cjce-2023-0405","DOIUrl":null,"url":null,"abstract":"Timely road surface condition (RSC) monitoring and maintenance significantly influences road safety. The current RSC relies on fixed road surveillance cameras and in-vehicle cameras. However, the fixed camera demands higher precision, while the in-vehicle camera requires higher timeliness. To address these challenges, this paper introduces an adaptive machine learning framework for simultaneous road surface detection on both device types. Initially, a convolutional neural network -based differentiation module identifies image sources. Subsequently, an adaptive algorithm switching mechanism leads to the development of two algorithms improved upon the real-time object detection algorithms. At last, extensive experiments with datasets collected from Ontario, Canada and Iowa U.S. validate the framework. Results show satisfactory classification accuracy, detection precision, and speed. Notably, the Mean Average Precision, namely mean of the average Precision for all categories(mAP)reaches 91.9% for fixed cameras and 90.6% for in-vehicle cameras, outperforming existing road surface snow detection models.","PeriodicalId":9414,"journal":{"name":"Canadian Journal of Civil Engineering","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Adaptive Machine Learning Framework for Multi-Scenes Road Surface Weather Condition Monitoring\",\"authors\":\"Xinhao Zhou, Lin Zhao, Zhaodong Liu, Liping Fu, Guangyuan Pan\",\"doi\":\"10.1139/cjce-2023-0405\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Timely road surface condition (RSC) monitoring and maintenance significantly influences road safety. The current RSC relies on fixed road surveillance cameras and in-vehicle cameras. However, the fixed camera demands higher precision, while the in-vehicle camera requires higher timeliness. To address these challenges, this paper introduces an adaptive machine learning framework for simultaneous road surface detection on both device types. Initially, a convolutional neural network -based differentiation module identifies image sources. Subsequently, an adaptive algorithm switching mechanism leads to the development of two algorithms improved upon the real-time object detection algorithms. At last, extensive experiments with datasets collected from Ontario, Canada and Iowa U.S. validate the framework. Results show satisfactory classification accuracy, detection precision, and speed. Notably, the Mean Average Precision, namely mean of the average Precision for all categories(mAP)reaches 91.9% for fixed cameras and 90.6% for in-vehicle cameras, outperforming existing road surface snow detection models.\",\"PeriodicalId\":9414,\"journal\":{\"name\":\"Canadian Journal of Civil Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2024-02-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Canadian Journal of Civil Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1139/cjce-2023-0405\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Canadian Journal of Civil Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1139/cjce-2023-0405","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
An Adaptive Machine Learning Framework for Multi-Scenes Road Surface Weather Condition Monitoring
Timely road surface condition (RSC) monitoring and maintenance significantly influences road safety. The current RSC relies on fixed road surveillance cameras and in-vehicle cameras. However, the fixed camera demands higher precision, while the in-vehicle camera requires higher timeliness. To address these challenges, this paper introduces an adaptive machine learning framework for simultaneous road surface detection on both device types. Initially, a convolutional neural network -based differentiation module identifies image sources. Subsequently, an adaptive algorithm switching mechanism leads to the development of two algorithms improved upon the real-time object detection algorithms. At last, extensive experiments with datasets collected from Ontario, Canada and Iowa U.S. validate the framework. Results show satisfactory classification accuracy, detection precision, and speed. Notably, the Mean Average Precision, namely mean of the average Precision for all categories(mAP)reaches 91.9% for fixed cameras and 90.6% for in-vehicle cameras, outperforming existing road surface snow detection models.
期刊介绍:
The Canadian Journal of Civil Engineering is the official journal of the Canadian Society for Civil Engineering. It contains articles on environmental engineering, hydrotechnical engineering, structural engineering, construction engineering, engineering mechanics, engineering materials, and history of civil engineering. Contributors include recognized researchers and practitioners in industry, government, and academia. New developments in engineering design and construction are also featured.