监控视频子块快速聚类自适应速率压缩感知

北京邮电大学学报 ›› 2025, Vol. 48 ›› Issue (1): 59-65.

监控视频子块快速聚类自适应速率压缩感知

王健明^1,2,罗平²,杨青青²,彭艺²

1.昆明理工大学云南省计算机技术应用重点实验室; 2. 昆明理工大学信息工程与自动化学院

收稿日期:2023-11-18 修回日期:2024-01-11 出版日期:2025-02-26 发布日期:2025-02-25
通讯作者: 彭艺 E-mail:2331788991@ qq. com
基金资助:
云南省科技厅科技计划项目; 云南省计算机技术应用重点实验室开放基金项目

Fast Clustering Adaptive Rate Compressive Sensing for Surveillance Videos Subblocks

WANG Jianming^1,2, LUO Ping², YANG Qingqing², PENG Yi²

Received:2023-11-18 Revised:2024-01-11 Online:2025-02-26 Published:2025-02-25

摘要/Abstract

摘要： 视频监控系统具有显著的分布式特性，适当的分布式视频采样方法能够降低采样端复杂度。由于压缩感知也具有分布式特性，其在分布式视频采样方法中具有很大的应用潜力。为了推进压缩感知在分布式监控视频系统中的应用，对自适应速率压缩感知进行了研究。基于统计特征估计，根据压缩感知测量值估计出未知原始视频子块的均值和方差并对子块快速聚类，再估计各聚类中子块的稀疏度进而合理分配采样率，实现视频自适应速率压缩感知，在视频重建质量没有下降和不显著增加采样端复杂度的情况下降低了采样率消耗。仿真结果表明，所提方法能够合理分配采样率，且采样计算复杂度符合实际采样设备要求。

关键词: 监控视频, 压缩感知, 自适应速率采样, 统计特征估计, 子块聚类 , 稀疏表示

Abstract: The distributed characteristics of video surveillance systems are evident, and the complexity of the sampling side can be reduced by adopting an appropriate distributed video sampling scheme. Since compressive sensing also exhibits distributed characteristics, it is considered to have great application potential in distributed video sampling schemes. In order to facilitate the application of compressive sensing in distributed surveillance video systems, adaptive rate compressive sensing is investigated. Based on statistical characteristics estimation, the mean and variance of unknown original video subblocks are estimated from the measurements obtained through compressive sensing, and subblocks are rapidly clustered. The sparsity of subblocks in each cluster is then estimated, and the sampling rate is allocated accordingly. The video adaptive rate compressive sensing is implemented, and the consumption of sampling rate is reduced without causing degradation in video reconstruction quality or significantly increasing sampling complexity. Simulation results demonstrate that the proposed method effectively allocates the sampling rate, and the computational complexity of sampling meets the requirements of actual sampling equipment.

Key words: surveillance video, compressive sensing , adaptive rate sampling , statistical characteristics estimation , subblock clustering , sparse representation

中图分类号:

TN911.73

王健明罗平杨青青彭艺. 监控视频子块快速聚类自适应速率压缩感知[J]. 北京邮电大学学报, 2025, 48(1): 59-65.

WANG Jianming, LUO Ping, YANG Qingqing, PENG Yi. Fast Clustering Adaptive Rate Compressive Sensing for Surveillance Videos Subblocks[J]. Journal of Beijing University of Posts and Telecommunications, 2025, 48(1): 59-65.

[1]	刘峰杨柳赵磊. RIS 辅助通信系统中基于深度压缩感知的信道估计[J]. 北京邮电大学学报, 2024, 47(1): 38-44.
[2]	李民政曹宇青颜娟娟陆健. 多智能反射面辅助毫米波级联信道估计方法[J]. 北京邮电大学学报, 2023, 46(4): 15-20.
[3]	汤永利, 赵明洁, 李丽香. 压缩感知安全理论研究[J]. 北京邮电大学学报, 2020, 43(3): 125-130.
[4]	董春曦, 沈志博, 刘松杨. 基于压缩感知的雷达信号分选方法[J]. 北京邮电大学学报, 2016, 39(2): 82-87.
[5]	郭文彬, 李春波, 雷迪, 王文博. 基于联合稀疏模型的OFDM压缩感知信道估计[J]. 北京邮电大学学报, 2014, 37(3): 1-6.
[6]	刘勇, 魏东红, 毛京丽. 基于优化内积模型的压缩感知快速重构算法[J]. 北京邮电大学学报, 2013, 36(1): 19-22.
[7]	徐文波, 田耘, 齐彦松. 单比特协作压缩频谱感知[J]. 北京邮电大学学报, 2012, 35(5): 85-89.
[8]	孟庆微黄建国韩晶王刚马闯. 水声单载波分块传输中基于压缩感知的稀疏信道估计方法[J]. 北京邮电大学学报, 2012, 35(5): 14-17.
[9]	何宜宝毕笃彦马时平岳耀帅. 梯度投影法求解压缩感知信号重构问题[J]. 北京邮电大学学报, 2012, 35(4): 112-115.
[10]	田鹏武康荣宗于宏毅. 基于斜投影算子的压缩域滤波法[J]. 北京邮电大学学报, 2012, 35(3): 108-111.
[11]	石磊,周正,唐亮,孙璇，张静. 认知无线电网络中压缩协作频谱感知[J]. 北京邮电大学学报, 2011, 34(5): 76-79.
[12]	唐亮,周正,石磊,姚海鹏，张静. 基于LEACH和压缩感知的无线传感器网络目标探测[J]. 北京邮电大学学报, 2011, 34(3): 8-11.