基于l^(1/2)-TV正则化RPCA的运动目标检测  

Moving Target Detection Based on l^(1/2)-TV Regularization RPCA

作　　者：赵俊豪 蒋峥[1,2] 刘斌[1,2] 张玲 ZHAO Jun-hao;JIANG Zheng;LIU Bin;ZHANG Ling(Institute of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan Hubei 430081,China;Engineering Research Center of Metallurgical Automation and Measurement Technology,Ministry of Education,Wuhan University of Science and Technology,Wuhan Hubei 430081,China;Institute of computer science and technology,Wuhan University of Science and Technology,Wuhan Hubei 430081,China)

机构地区：[1]武汉科技大学信息科学与工程学院,湖北武汉430081 [2]武汉科技大学冶金自动化与检测技术教育部工程研究中心,湖北武汉430081 [3]武汉科技大学计算机科学与技术学院,湖北武汉430081

出　　处：《计算机仿真》2024年第5期258-263,428,共7页Computer Simulation

基　　金：国家自然科学基金青年资助项目(61902286)。

摘　　要：针对复杂环境下背景干扰导致运动目标检测精度下降的问题,提出了一种基于l^(1/2)-TV正则化RPCA的运动目标检测方法。方法利用核范数来描述背景的低秩特性,采用l^(1/2)范数描述更稀疏的运动目标,以抑制运动目标中的背景干扰。同时结合TV正则化约束运动目标的空间连续性,使运动目标更加完整。利用Frobenius范数检测背景干扰。采用交替方向最小化策略扩展的增广拉格朗日乘子法求解所提出的约束最小化问题。实验结果表明,所提方法能有效去除背景干扰,提高运动目标的检测精度、改善视觉效果。Focusing on the issue that the accuracy of moving target detection decreases due to background interference in complex environment,a moving target detection method based on l^(1/2)-TV regularized RPCA is proposed.The method represents video sequences as three components,i.e.,a low-rank background,a moving target,and noise.The algorithm uses the kernel norm to describe the low rank characteristics of the background.The l^(1/2)norm is used to describe the more sparse moving target to suppress the background interference in the moving target.At the same time,TV regularization is combined to constrain the spatial continuity of the moving target to make the moving target more complete.Frobenius norm is used to detect background interference.The augmented Lagrangian multiplier method extended by the alternating direction minimization strategy is used to deal with the proposed constraint minimization problem.The experimental results show that the proposed method can effectively remove the background interference,improve the detection accuracy of moving targets and improve the visual effect.

关 键 词：运动目标检测 复杂环境 鲁棒主成分分析 全变分 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]