| 图像端到端感知质量的快速估测方法 |
| |
| 引用本文： | 袁 飞,陈炜玲,张 籍,程 恩.图像端到端感知质量的快速估测方法[J].仪器仪表学报,2016,37(3):497-504. |
| |
| 作者姓名： | 袁 飞 陈炜玲 张 籍 程 恩 |
| |
| 作者单位： | 1. 厦门大学 信息科学与技术学院通信工程系 厦门361005；2. 厦门大学 水声通信与海洋信息技术教育部重点实验室 厦门361005,1. 厦门大学 信息科学与技术学院通信工程系 厦门361005；2. 厦门大学 水声通信与海洋信息技术教育部重点实验室 厦门361005,中国电子科技集团第二十六研究所 微声事业部重庆404100,1. 厦门大学 信息科学与技术学院通信工程系 厦门361005；2. 厦门大学 水声通信与海洋信息技术教育部重点实验室 厦门361005 |
| |
| 基金项目： | 国家自然科学基金面上(61571377，61471308)项目资助 |
| |
| 摘 要： | 本文介绍了一种新型的利用图像活动性(IAM)快速估计水下图像端到端体验质量的方法。首先引入结构相似度(SSIM)作为图像感知服务质量(PQo S)参数评价图像质量,将图像初始活动性(IAM)作为区分图像内容的本征参数;随后基于质量向量(QV)的概念,分别分析了非压缩图像的结构相似度,图像初实活动性与无条件丢失概率(SSIM-IAM.-ulp)之间的联合特性,以及压缩图像的结构相似性,压缩率与无条件丢失概率(SSIM-IAM.-ulp)之间的联合特性。最后,在上述联合特性的基础上提出了劣化图像SSIM的预测算法。测试实验证明,该类算法有较高的预测准确率,预测误差最低可达0.8%。
|
| 关 键 词： | 感知服务质量 曲线拟合 空域活动性 服务质量向量 |
Quick estimation of end to end PQoS of image |
| |
| Yuan Fei,Chen Weiling,Zhang Ji and Cheng En.Quick estimation of end to end PQoS of image[J].Chinese Journal of Scientific Instrument,2016,37(3):497-504. |
| |
| Authors: | Yuan Fei Chen Weiling Zhang Ji and Cheng En |
| |
| Affiliation: | 1. Department of Communication Engineering, School of Information Science and Technology, Xiamen University, Xiamen 361005,China; 2. Key Laboratory of Underwater Acoustic Communication and Marine Information Technology,Ministry of Education, Xiamen University, Xiamen 361005, China,1. Department of Communication Engineering, School of Information Science and Technology, Xiamen University, Xiamen 361005,China; 2. Key Laboratory of Underwater Acoustic Communication and Marine Information Technology,Ministry of Education, Xiamen University, Xiamen 361005, China,Microsonic Department, Institute No. 26, China Electronics Technology Group Corporation, Chongqing 404100, China and 1. Department of Communication Engineering, School of Information Science and Technology, Xiamen University, Xiamen 361005,China; 2. Key Laboratory of Underwater Acoustic Communication and Marine Information Technology,Ministry of Education, Xiamen University, Xiamen 361005, China |
| |
| Abstract: | This paper introduces a novel method for quick estimating the end to end Perceived Quality of Service (PQoS) of underwater image based on image activity measure (IAM). Structure Similarity (SSIM) is first introduced as the evaluation standard of image PQoS parameter to evaluate the quality of image, while the IAM of original image is utilized as an intrinsic parameter to discriminate the image contents. Then, based on the concept of quality vector (QV), the SSIM ulp IAM0 features for non compressed picture are analyzed, and the SSIM CR ulp features for compressed picture are analyzed as well. On this basis, the prediction algorithm based on SSIM for the degraded image is proposed. Test experiment result shows that this kind of prediction algorithm has high accuracy rate, and the lowest prediction error reaches to 0.8%. |
| |
| Keywords: | perceived quality of service (PQoS) curve fitting image activity measure (IAM) QoS vector |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《仪器仪表学报》浏览原始摘要信息 |
|
点击此处可从《仪器仪表学报》下载全文 |
|
