{"title":"Human detection based on explicit skin colour space thresholding and minor motion detection","authors":"Divya Joshi, A. Purwar, M. S. Dasgupta","doi":"10.1109/INDICON.2014.7030518","DOIUrl":null,"url":null,"abstract":"In this paper, a novel approach for human presence detection from digital image is presented. This approach is based on combined clue from skin colour and minor motion detection. For skin colour detection, explicit thresholding of CbCr colour channels is used and for minor motion detection morphological differences of multiple consecutive images has been used. MATLAB® is used for processing. Relatively small part of exposed human body in the frame of an image is sufficient for detection. The approach is computationally efficient, potentially real time and robust. The combined technique gives improved performance compared to each individual technique. Location of the object (human) within the frame is also simultaneously identified.","PeriodicalId":409794,"journal":{"name":"2014 Annual IEEE India Conference (INDICON)","volume":"122 2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Annual IEEE India Conference (INDICON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INDICON.2014.7030518","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
In this paper, a novel approach for human presence detection from digital image is presented. This approach is based on combined clue from skin colour and minor motion detection. For skin colour detection, explicit thresholding of CbCr colour channels is used and for minor motion detection morphological differences of multiple consecutive images has been used. MATLAB® is used for processing. Relatively small part of exposed human body in the frame of an image is sufficient for detection. The approach is computationally efficient, potentially real time and robust. The combined technique gives improved performance compared to each individual technique. Location of the object (human) within the frame is also simultaneously identified.