摘要
针对低秩与稀疏方法一般将前景看作背景中存在的异常像素点,从而使得在复杂场景中前景检测精确度下降的问题,提出一种结合加权Schatten-p范数与3D全变分(3D-TV)的前景检测模型。该模型首先将观测数据三分为低秩背景、运动前景和动态干扰;然后利用3D全变分来约束运动前景,并加强对前景目标时空连续性的先验考虑,有效抑制了不连续动态背景异常点的随机扰动;最后利用加权Schatten-p范数约束视频背景的低秩性能,去除噪声干扰。实验结果表明,与鲁棒主成分分析(RPCA)、高阶RPCA(HoRPCA)和张量RPCA(TRPCA)等模型相比,所提模型的综合衡量指标F-measure值是最高的,查全率与查准率也处于最优或次优状态。由此可知,所提模型在动态背景、恶劣天气等复杂场景中能有效提高运动目标的提取精确度,且提取的前景目标视觉效果较好。
In view of the fact that the low rank and sparse methods generally regard the foreground as abnormal pixels in the background, which makes the foreground detection precision decrease in the complex scene, a new foreground detection method combining weighted Schatten-p norm with 3 D Total Variation(3 D-TV) was proposed. Firstly, the observed data were divided into low rank background, moving foreground and dynamic disturbance. Then 3 D total variation was used to constrain the moving foreground and strengthen the prior consideration of the spatio-temporal continuity of the foreground objects, effectively suppressing the random disturbance of the anomalous pixels in the discontinuous dynamic background. Finally, the low rank performance of video background was constrained by weighted Schatten-p norm to remove noise interference. The experimental results show that, compared with Robust Principal Component Analysis(RPCA), Higher-order RPCA(HoRPCA) and Tensor RPCA(TRPCA), the proposed model has the highest F-measure value, and the optimal or sub-optimal values of recall and precision. It can be concluded that the proposed model can better overcome the interference in complex scenes, such as dynamic background and severe weather, and its extraction accuracy as well as visual effect of moving objects is improved.
引文
[1]BOUWMANS T,ZAHZAH E H.Robust PCA via principal component pursuit:a review for a comparative evaluation in video surveillance[J].Computer Vision and Image Understanding,2014,122:22-34.
[2]ZHOU X,YANG C,ZHAO H,et al.Low-rank modeling and its applications in image analysis[J].ACM Computing Surveys,2014,47(2):1-33.
[3]REZAEI B,OSTADABBAS S.Background subtraction via fast robust matrix completion[C]//Proceeding of the 2017 IEEE International Conference on Computer Vision Workshop.Piscataway,NJ:IEEE,2017:1871-1879.
[4]XIE Y,GU S,LIU Y,et al.Weighted Schatten p-Norm minimization for image denoising and background subtraction[J].IEEETransactions on Image Processing,2016,25(10):4842-4 857.
[5]LU C,FENG J,CHEN Y,et al.Tensor robust principal component analysis with a new tensor nuclear norm[EB/OL].[2018-05-10].http://adsabs.harvard.edu/abs/2018ar Xiv180403728L.
[6]GOLDFARB D,QIN Z.Robust low-rank tensor recovery:models and algorithms[J].SIAM Journal on Matrix Analysis&Applications,2013,35(1):225-253.
[7]PANG Y,YE L,LI X,et al.Incremental learning with saliency map for moving object detection[J].IEEE Transactions on Circuits and Systems for Video Technology,2018,28(3):640-651.
[8]EBADI S E,IZQUIERDO E.Foreground segmentation with treestructured sparse RPCA[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(9):2273-2280.
[9]BHATTACHARYA S,VENKATSH K S,GUPTA S.Background estimation and motion saliency detection using total variation-based video decomposition[J].Signal,Image and Video Processing,2017,11(1):113-121.
[10]CAO X,YANG L,GUO X.Total variation regularized RPCA for irregularly moving object detection under dynamic background[J].IEEE Transactions on Cybernetics,2017,46(4):1014-1027.
[11]CHAN S H,KHOSHABEH R,GIBSON K B,et al.An augmented lagrangian method for total variation video restoration[J].IEEETransactions on Image Processing,2011,20(11):3097-3111.
[12]CAO W,WANG Y,SUN J,et al.Total variation regularized tensor RPCA for background subtraction from compressive measurements[J].IEEE Transactions on Image Processing,2016,25(9):4075-4090.
[13]BOYD S,PARIKH N,CHU E,et al.Distributed optimization and statistical learning via the alternating direction method of multipliers[J].Foundations and Trends in Machine Learning,2011,3(1):1-122.
[14]DENG W,YIN W.On the global and linear convergence of the generalized alternating direction method of multipliers[J].Journal of Scientific Computing,2016,66(3):889-916.
[15]ZUO W,MENG D,ZHANG L,et al.A generalized iterated shrinkage algorithm for non-convex sparse coding[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE,2013:217-224.
[16]WANG Y,JODOIN P M,PORIKLI F,et al.CDnet 2014:an expanded change detection benchmark dataset[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.Washington,DC:IEEE Computer Society,2014:387-394.
[17]常侃,张智勇,陈诚,等.采用低秩与加权稀疏分解的视频前景检测算法[J].电子学报,2017,45(9):2272-2280.(CHANG K,ZHANG Z Y,CHEN C,et al.Video foreground detection by low-rank and reweighted sparse decomposition[J].Acta Electronica Sinica,2017,45(9):2272-2280.)
[18]刘仲民,何胜皎,胡文瑾,等.基于背景减除法的视频序列运动目标检测[J].计算机应用,2017,37(6):1777-1781.(LIU Z M,HE S J,HU W J,et al.Moving object detection based on background subtraction for video sequence[J].Journal of Computer Applications,2017,37(6):1777-1781.)