Thang Nguyen Dang, T. Kim Le, Thai Phan Hong, V. B. Nguyen
{"title":"Fast and Accurate Fall Detection and Warning System Using Image Processing Technology","authors":"Thang Nguyen Dang, T. Kim Le, Thai Phan Hong, V. B. Nguyen","doi":"10.1109/atc52653.2021.9598204","DOIUrl":null,"url":null,"abstract":"Accidental falls can cause serious injuries, which can lead to serious medical problems, especially for construction and factory workers. This paper proposes a study on a fall detection system based on computer vision. This system is applied to help detect people falling in harsh working environment such as dust, loud noise, few people working. From the recorded video streams, the data is processed to recognize a person falling, lying motionless. Algorithms for tracking people are implemented on a compact, easy-to-install embedded system. Experimental results show that the system ensures safety and can provide emergency assistance to people who have fallen within the view of the camera.","PeriodicalId":196900,"journal":{"name":"2021 International Conference on Advanced Technologies for Communications (ATC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Advanced Technologies for Communications (ATC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/atc52653.2021.9598204","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
Accidental falls can cause serious injuries, which can lead to serious medical problems, especially for construction and factory workers. This paper proposes a study on a fall detection system based on computer vision. This system is applied to help detect people falling in harsh working environment such as dust, loud noise, few people working. From the recorded video streams, the data is processed to recognize a person falling, lying motionless. Algorithms for tracking people are implemented on a compact, easy-to-install embedded system. Experimental results show that the system ensures safety and can provide emergency assistance to people who have fallen within the view of the camera.