Yumi Eom, Sang-il Park, Sunggeun Yoo, J. Choi, Sukhee Cho
{"title":"An analysis of scene change detection in HEVC bitstream","authors":"Yumi Eom, Sang-il Park, Sunggeun Yoo, J. Choi, Sukhee Cho","doi":"10.1109/ICOSC.2015.7050854","DOIUrl":null,"url":null,"abstract":"An improved method of scene change detection (SCD) is required for content-based video analysis, indexing, searching and editing. Many researchers have suggested various SCD techniques in recent years. However, it is difficult to detect a scene change in the video context with a variety of camera movements and shot transitions. Moreover, data volume becomes an issue in the influx of ultra-high definition (UHD) video with the resolution of 4K (3820×2160) or larger formats. The traditional SCD approach takes too much time to run with UHD video. In this paper four different SCD methods are suggested for UHD video which is coded with advanced codec programs. Then, the analysis of traditional SCD methods is presented. And these experimental SCD techniques for UHD video bit streams are tested with the different structures of advanced video codecs. Finally, the experiments are conducted to evaluate the performances of the techniques.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOSC.2015.7050854","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
An improved method of scene change detection (SCD) is required for content-based video analysis, indexing, searching and editing. Many researchers have suggested various SCD techniques in recent years. However, it is difficult to detect a scene change in the video context with a variety of camera movements and shot transitions. Moreover, data volume becomes an issue in the influx of ultra-high definition (UHD) video with the resolution of 4K (3820×2160) or larger formats. The traditional SCD approach takes too much time to run with UHD video. In this paper four different SCD methods are suggested for UHD video which is coded with advanced codec programs. Then, the analysis of traditional SCD methods is presented. And these experimental SCD techniques for UHD video bit streams are tested with the different structures of advanced video codecs. Finally, the experiments are conducted to evaluate the performances of the techniques.