{"title":"防止午夜潜行的离床检测系统的研制","authors":"Y. Takahashi, Yuhki Kitazono, Shota Nakashima","doi":"10.1109/SNPD.2014.6888740","DOIUrl":null,"url":null,"abstract":"In this study, we developed Leaving-bed Detection System to Prevent Midnight Prowl and checked the operation of the system constructed. First, installed the camera on the ceiling, get depth information in the field of view, and also get background's depth information. The detection of human get up was performed by taking the difference between the depth and the current depth of the background. Converted into numeric depth information a distance from the camera to be retrieved as a string, and obtains the height of the object from the difference between them. Take a threshold value than the height that was acquired to detect anything more than a certain height, and also in after removing those narrow areas coordinates from the coordinates, and performs the tracking to obtain the center coordinates of the target. However, in view of the error occurring in the case of detecting a plurality of persons, human tracking is performed after the extraction of the target person by labeling process. We went from the center point when the track is interrupted the entry and exit detection.","PeriodicalId":272932,"journal":{"name":"15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","volume":"53 11","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development of Leaving-bed Detection System to Prevent Midnight Prowl\",\"authors\":\"Y. Takahashi, Yuhki Kitazono, Shota Nakashima\",\"doi\":\"10.1109/SNPD.2014.6888740\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this study, we developed Leaving-bed Detection System to Prevent Midnight Prowl and checked the operation of the system constructed. First, installed the camera on the ceiling, get depth information in the field of view, and also get background's depth information. The detection of human get up was performed by taking the difference between the depth and the current depth of the background. Converted into numeric depth information a distance from the camera to be retrieved as a string, and obtains the height of the object from the difference between them. Take a threshold value than the height that was acquired to detect anything more than a certain height, and also in after removing those narrow areas coordinates from the coordinates, and performs the tracking to obtain the center coordinates of the target. However, in view of the error occurring in the case of detecting a plurality of persons, human tracking is performed after the extraction of the target person by labeling process. We went from the center point when the track is interrupted the entry and exit detection.\",\"PeriodicalId\":272932,\"journal\":{\"name\":\"15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)\",\"volume\":\"53 11\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SNPD.2014.6888740\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SNPD.2014.6888740","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Development of Leaving-bed Detection System to Prevent Midnight Prowl
In this study, we developed Leaving-bed Detection System to Prevent Midnight Prowl and checked the operation of the system constructed. First, installed the camera on the ceiling, get depth information in the field of view, and also get background's depth information. The detection of human get up was performed by taking the difference between the depth and the current depth of the background. Converted into numeric depth information a distance from the camera to be retrieved as a string, and obtains the height of the object from the difference between them. Take a threshold value than the height that was acquired to detect anything more than a certain height, and also in after removing those narrow areas coordinates from the coordinates, and performs the tracking to obtain the center coordinates of the target. However, in view of the error occurring in the case of detecting a plurality of persons, human tracking is performed after the extraction of the target person by labeling process. We went from the center point when the track is interrupted the entry and exit detection.