{"title":"Elderly Care System for Classification and Recognition of Sitting Posture","authors":"S. Bhatlawande, Ishan Girgaonkar","doi":"10.1109/CONIT55038.2022.9848298","DOIUrl":null,"url":null,"abstract":"Technological advancements in medical field have caused increase in life expectancy of humankind. Recent societal changes and other conditions cause most of the elder population to live alone. Health and safety of such elders have become a burning issue nowadays. Growth in Computer vision and sensor technology has presented a prominent solution for this problem. In this paper, a study on elderly monitoring system is presented with a proposed posture monitoring model. Proposed model takes video frames as input. Model works on the concept of Bag of Visual Words (BoVW). Model uses Oriented FAST and rotated BRIEF (ORB) to obtain features from input images. Subsequently, K means method is deployed for feature reduction. Reduced dimension vectors are used to classify various posture of person in frame. In this study provides major emphasis on posture recognition of sitting, standing and transitional postures. this non-intrusive, efficient monitoring system is tested on various datasets which have yielded good results.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 2nd International Conference on Intelligent Technologies (CONIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CONIT55038.2022.9848298","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
Technological advancements in medical field have caused increase in life expectancy of humankind. Recent societal changes and other conditions cause most of the elder population to live alone. Health and safety of such elders have become a burning issue nowadays. Growth in Computer vision and sensor technology has presented a prominent solution for this problem. In this paper, a study on elderly monitoring system is presented with a proposed posture monitoring model. Proposed model takes video frames as input. Model works on the concept of Bag of Visual Words (BoVW). Model uses Oriented FAST and rotated BRIEF (ORB) to obtain features from input images. Subsequently, K means method is deployed for feature reduction. Reduced dimension vectors are used to classify various posture of person in frame. In this study provides major emphasis on posture recognition of sitting, standing and transitional postures. this non-intrusive, efficient monitoring system is tested on various datasets which have yielded good results.