{"title":"基于优势区域跟踪的镜头检测","authors":"Tianming Liu, F. Qi","doi":"10.1109/ICOSP.2002.1181132","DOIUrl":null,"url":null,"abstract":"The paper presents a novel video shot detection method based on dominant region tracking. The basic idea is that a shot boundary decision is made when tracked dominant regions are lost and/or new dominant regions occur. The tracking is based on region mapping between consecutive frames and performed on the MPEG DC sequence, which greatly accelerates the process. The dominant regions are obtained using a fast static image segmentation method. As a whole, the shot detection algorithm is effective and very fast.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"197 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Shot detection based on dominant region tracking\",\"authors\":\"Tianming Liu, F. Qi\",\"doi\":\"10.1109/ICOSP.2002.1181132\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper presents a novel video shot detection method based on dominant region tracking. The basic idea is that a shot boundary decision is made when tracked dominant regions are lost and/or new dominant regions occur. The tracking is based on region mapping between consecutive frames and performed on the MPEG DC sequence, which greatly accelerates the process. The dominant regions are obtained using a fast static image segmentation method. As a whole, the shot detection algorithm is effective and very fast.\",\"PeriodicalId\":159807,\"journal\":{\"name\":\"6th International Conference on Signal Processing, 2002.\",\"volume\":\"197 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2002-08-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"6th International Conference on Signal Processing, 2002.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICOSP.2002.1181132\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"6th International Conference on Signal Processing, 2002.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOSP.2002.1181132","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The paper presents a novel video shot detection method based on dominant region tracking. The basic idea is that a shot boundary decision is made when tracked dominant regions are lost and/or new dominant regions occur. The tracking is based on region mapping between consecutive frames and performed on the MPEG DC sequence, which greatly accelerates the process. The dominant regions are obtained using a fast static image segmentation method. As a whole, the shot detection algorithm is effective and very fast.