{"title":"Bus Epidemic Monitoring System Based on K210","authors":"Xuewei Zhang, Fuwen Su, Zhe Wang, Fei Gao","doi":"10.1109/ISTTCA53489.2021.9654757","DOIUrl":null,"url":null,"abstract":"Out of the normalization of the epidemic, urban bus epidemic management system is a safety monitoring system that focuses on the detection of large-scale public health safety in public transport, which is assembled in both vehicle and cloud. Compared with the previous mainstream stand-alone epidemic surveillance system, three kinds of detection including mask, face and temperature can be done in the vehicle before the face information is uploaded to the cloud to be processed and extracted for digital facial features, which can be reserved with the trip record and health identification of designated individuals, providing an effective deep search that can quickly screen the persons who have a risk of contact with the designated individuals and give feedback to the car. The cloud platform is linked with the command center, indicating that the vehicle terminal will give an alarm as soon as a risk person gets on board while the cloud will also send details to the command center. This system adopts the architecture of edge computing and cloud collaboration, innovatively proposing the edge cloud monitoring structure, which has high precision and speed under normal flow and meets the demand of massive detection in public transport during the epidemic. The vehicle terminal centralizes the computation on edge extended, allowing for faster response of web service even with numerous functions without compromising the epidemic surveillance. In addition, a large amount of redundant computing power saved by edge computing can assist the secondary treatment and judgment of recognition results, and a data visualization platform can be built for comprehensive management.","PeriodicalId":383266,"journal":{"name":"2021 4th International Symposium on Traffic Transportation and Civil Architecture (ISTTCA)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 4th International Symposium on Traffic Transportation and Civil Architecture (ISTTCA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISTTCA53489.2021.9654757","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Out of the normalization of the epidemic, urban bus epidemic management system is a safety monitoring system that focuses on the detection of large-scale public health safety in public transport, which is assembled in both vehicle and cloud. Compared with the previous mainstream stand-alone epidemic surveillance system, three kinds of detection including mask, face and temperature can be done in the vehicle before the face information is uploaded to the cloud to be processed and extracted for digital facial features, which can be reserved with the trip record and health identification of designated individuals, providing an effective deep search that can quickly screen the persons who have a risk of contact with the designated individuals and give feedback to the car. The cloud platform is linked with the command center, indicating that the vehicle terminal will give an alarm as soon as a risk person gets on board while the cloud will also send details to the command center. This system adopts the architecture of edge computing and cloud collaboration, innovatively proposing the edge cloud monitoring structure, which has high precision and speed under normal flow and meets the demand of massive detection in public transport during the epidemic. The vehicle terminal centralizes the computation on edge extended, allowing for faster response of web service even with numerous functions without compromising the epidemic surveillance. In addition, a large amount of redundant computing power saved by edge computing can assist the secondary treatment and judgment of recognition results, and a data visualization platform can be built for comprehensive management.