{"title":"Motion Segmentation Based on 3D Histogram and Temporal Mode Selection","authors":"D. Mukherjee, Q. M. J. Wu","doi":"10.1109/ICMEW.2012.90","DOIUrl":null,"url":null,"abstract":"Motion segmentation has been a well explored research topic due to its vast application area. This work proposes a real-time motion segmentation method based on 3D histogram and temporal mode selection. The temporal distribution of a video sequence consists of the motion in the foreground and the relatively immobile background. A 3D histogram provides a short-term memory of the aforementioned distribution. The temporal mode selection process involves identifying the most frequent values in the distribution and construct the background thereafter. This work provides a detailed analysis of the proposed method along with an easy-to-implement algorithm. A number of experimental results and comparisons with some of the leading algorithms are provided to show that the proposed method can provide real-time, robust and highly accurate results.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE International Conference on Multimedia and Expo Workshops","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMEW.2012.90","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
Motion segmentation has been a well explored research topic due to its vast application area. This work proposes a real-time motion segmentation method based on 3D histogram and temporal mode selection. The temporal distribution of a video sequence consists of the motion in the foreground and the relatively immobile background. A 3D histogram provides a short-term memory of the aforementioned distribution. The temporal mode selection process involves identifying the most frequent values in the distribution and construct the background thereafter. This work provides a detailed analysis of the proposed method along with an easy-to-implement algorithm. A number of experimental results and comparisons with some of the leading algorithms are provided to show that the proposed method can provide real-time, robust and highly accurate results.