Jiawei Ren, Xiuhua Jiang, Xiaoyu Ma, Li Xu, Xiaoqiang Guo
{"title":"基于HEVC编码码流的超高清视频无参考质量评估","authors":"Jiawei Ren, Xiuhua Jiang, Xiaoyu Ma, Li Xu, Xiaoqiang Guo","doi":"10.1109/ICSAI.2017.8248490","DOIUrl":null,"url":null,"abstract":"The paper presents a No-Reference quality assessment algorithm for UHD videos based on HEVC encoded. The algorithm directly extracts the specific video characteristics from the HEVC bitstream, and establishes the mathematical model between the video characteristics and the final video quality through linear regression, so as to realize the objective evaluation of the video quality. The algorithm extracts three video features: the quantization parameters of the measurement compression damage, the number of CTU of different sizes (8×8 & 32×32) and the numbers of the SAO blocks. The experimental results show that the objective evaluation results obtained based on these three parameters have good correlation with the results of subjective experiment results. In addition, because the algorithm only needs to rely on the stream and the coding parameters can be reliable and rapid evaluated, can be widely used in the real-time terminal occasions.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"No-reference quality assessment for UHD videos based on HEVC encoded bitstream\",\"authors\":\"Jiawei Ren, Xiuhua Jiang, Xiaoyu Ma, Li Xu, Xiaoqiang Guo\",\"doi\":\"10.1109/ICSAI.2017.8248490\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper presents a No-Reference quality assessment algorithm for UHD videos based on HEVC encoded. The algorithm directly extracts the specific video characteristics from the HEVC bitstream, and establishes the mathematical model between the video characteristics and the final video quality through linear regression, so as to realize the objective evaluation of the video quality. The algorithm extracts three video features: the quantization parameters of the measurement compression damage, the number of CTU of different sizes (8×8 & 32×32) and the numbers of the SAO blocks. The experimental results show that the objective evaluation results obtained based on these three parameters have good correlation with the results of subjective experiment results. In addition, because the algorithm only needs to rely on the stream and the coding parameters can be reliable and rapid evaluated, can be widely used in the real-time terminal occasions.\",\"PeriodicalId\":285726,\"journal\":{\"name\":\"2017 4th International Conference on Systems and Informatics (ICSAI)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 4th International Conference on Systems and Informatics (ICSAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSAI.2017.8248490\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 4th International Conference on Systems and Informatics (ICSAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSAI.2017.8248490","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
No-reference quality assessment for UHD videos based on HEVC encoded bitstream
The paper presents a No-Reference quality assessment algorithm for UHD videos based on HEVC encoded. The algorithm directly extracts the specific video characteristics from the HEVC bitstream, and establishes the mathematical model between the video characteristics and the final video quality through linear regression, so as to realize the objective evaluation of the video quality. The algorithm extracts three video features: the quantization parameters of the measurement compression damage, the number of CTU of different sizes (8×8 & 32×32) and the numbers of the SAO blocks. The experimental results show that the objective evaluation results obtained based on these three parameters have good correlation with the results of subjective experiment results. In addition, because the algorithm only needs to rely on the stream and the coding parameters can be reliable and rapid evaluated, can be widely used in the real-time terminal occasions.