基于中高位视频监控的图像及视频质量增强算法  

Image and video quality enhancement based on medium and high⁃altitude video surveillance

作　　者：向涛 葛宁[1] 宋奇蔚 XIANG Tao;GE Ning;SONG Qiwei(Department of Electronic Engineering,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《南京信息工程大学学报》2025年第1期22-30,共9页Journal of Nanjing University of Information Science & Technology

基　　金：国家重点研发计划“变革性技术关键科学问题”重点专项(2018YFA0701601)。

摘　　要：针对现有图像视频恢复增强方法存在的问题,本文提出一种基于语义特征提取的神经网络模型图像及视频质量增强算法.首先提出一种基于语义特征的图像恢复增强框架,然后建立退化模型和重建模型的联合优化.在公开数据集上对所提模型进行验证,并与现有算法进行对比,结果表明:所提方法相比新型超分辨率算法PULSE(Photo Upsampling via Latent Space Exploration,潜空间搜索照片升采样)能够实现RankIQA(Rank Image Quality Assessment,图像质量评价排名)得分50%的提升,并且和原始高清图像、视频质量得分接近;在用户评价方面,有81%的重建结果被认为优于对比算法,表明所提算法具有更高的重构图像和视频质量.To address the issues inherent in existing image and video restoration and enhancement techniques,this paper proposes a neural network model approach rooted in semantic feature extraction.Firstly,an image restoration and enhancement framework centered on semantic feature is introduced,followed by the joint optimization of degradation and reconstruction models.The proposed model is validated on a publicly accessible dataset and compared with existing algorithms.The results indicate that the proposed approach achieves a 50% improvement in RankIQA(Rank Image Quality Assessment)scores compared to the state⁃of⁃the⁃art super⁃resolution algorithm PULSE(Photo Upsampling via Latent Space Exploration).Furthermore,the quality scores of the enhanced images and videos are comparable to those of the original HD ones.In terms of user evaluation,81%of the reconstructed results are consid⁃ered to be superior to those produced by the comparison algorithms,demonstrating that the proposed approach offers higher quality in reconstructed images and videos.

关 键 词：视频增强 图像重建 感知质量 语义特征 语义理解 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]