非均匀低光照环境下视频动态图像清晰化研究  

Research on Video Dynamic Image Clarity in Non-uniform Low Light Environment

作　　者：张爽 Zhang Shuang(Liaoning Police College,Dalian 116026,China)

机构地区：[1]辽宁警察学院,辽宁大连116026

出　　处：《兵工自动化》2025年第2期60-65,共6页Ordnance Industry Automation

基　　金：辽宁省科技厅项目(2020JH2/10300109);辽宁省科技厅应用基础研究计划项目(2023JH2/101300134);辽宁省公安大数据智能应用重点实验室项目(2022JH13/10200047)。

摘　　要：为提高非均匀低光照环境下视频动态图像的清晰化水平,提出一种非均匀低光照环境下视频动态图像清晰化研究方法。构建视频动态图像光照变化尺度分解模型,依据光照初始变换参数敏感性,融合匹配视频动态图像噪点特征参数并分解离群参数。采用高阶相似度特征匹配法建空间一致化噪点过滤模型,依过滤结果清晰化视频动态图像。实验结果表明:该方法处理后图像的信噪比达到了47.8dB,图像结构相似性均值为0.980,均方误差仅为0.086,图像清晰化处理时间为5.21 s,证明该方法实用且能有效提高图像清晰化能力。In order to improve the level of video image clarity in non-uniform low-light environment,a research method of video image clarity in non-uniform low-light environment is proposed.A video dynamic image illumination change scale decomposition model is construct,and according to that sensitivity of the illumination initial transformation parameter,the noise feature parameters of the matched video dynamic images are fuse and the outlier parameters are decomposed.A spatial uniform noise filtering model is established by using a high-order similarity feature matching method,and a video dynamic image is made clear according to a filtering result.The experimental results show that the signal to noise ratio(SNR)of the image processed by this method reaches 47.8 dB,the mean value of image structure similarity is 0.980,the mean square error is only 0.086,and the processing time of image clarity is 5.21 s,which proves that this method is practical and can effectively improve the ability of image clarity.

关 键 词：变光照环境 视频 动态图像 清晰化 噪点过滤 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]