{"title":"基于互信息差分序列的镜头边界检测","authors":"Dingyuan Xia, Xuefei Deng, Qingning Zeng","doi":"10.1109/ICIG.2007.169","DOIUrl":null,"url":null,"abstract":"Aimed at the characteristics and localizations of mutual information used in shot boundary detection, a new shot boundary detection method based on difference sequences of mutual information is presented. The measure used for detecting the shot boundary is not the mutual information itself involved in the frames of video sequences, but the absolute value difference between the frames, thereby the disadvantage influences resulted from the zoom of camera or movement of object are effectively eliminated. Moreover, the two-order mutual information is introduced into the shot boundary detection to make up for the scarcity of spatial information and fully utilize the relativity of gray-level between the adjacent pixels, and the detection effect is further improved. Experimental results validate the validity of the new method.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":"{\"title\":\"Shot Boundary Detection Based on Difference Sequences of Mutual Information\",\"authors\":\"Dingyuan Xia, Xuefei Deng, Qingning Zeng\",\"doi\":\"10.1109/ICIG.2007.169\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Aimed at the characteristics and localizations of mutual information used in shot boundary detection, a new shot boundary detection method based on difference sequences of mutual information is presented. The measure used for detecting the shot boundary is not the mutual information itself involved in the frames of video sequences, but the absolute value difference between the frames, thereby the disadvantage influences resulted from the zoom of camera or movement of object are effectively eliminated. Moreover, the two-order mutual information is introduced into the shot boundary detection to make up for the scarcity of spatial information and fully utilize the relativity of gray-level between the adjacent pixels, and the detection effect is further improved. Experimental results validate the validity of the new method.\",\"PeriodicalId\":367106,\"journal\":{\"name\":\"Fourth International Conference on Image and Graphics (ICIG 2007)\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-08-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"16\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fourth International Conference on Image and Graphics (ICIG 2007)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIG.2007.169\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fourth International Conference on Image and Graphics (ICIG 2007)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIG.2007.169","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Shot Boundary Detection Based on Difference Sequences of Mutual Information
Aimed at the characteristics and localizations of mutual information used in shot boundary detection, a new shot boundary detection method based on difference sequences of mutual information is presented. The measure used for detecting the shot boundary is not the mutual information itself involved in the frames of video sequences, but the absolute value difference between the frames, thereby the disadvantage influences resulted from the zoom of camera or movement of object are effectively eliminated. Moreover, the two-order mutual information is introduced into the shot boundary detection to make up for the scarcity of spatial information and fully utilize the relativity of gray-level between the adjacent pixels, and the detection effect is further improved. Experimental results validate the validity of the new method.