基于连续性约束背景模型减除的运动目标检测

doi:10.11896/j.issn.1002-137X.2019.06.047

Abstract

Abstract: Moving target detection is one of the key technologies in the field of machine vision.Moving object detection is widely used in video moving object detection,remote sensing information processing and military reconnaissance,etc.Considering that the background similarity of adjacent video frames is high,and the shadow and noise are disconti-nuous,this paper proposed a low-rank decomposition background updating model with time continuity constraint,and applied it to the moving object detection of background subtraction.Firstly,low-rank components and sparse components are obtained by using low-rank decomposition.Then the background is constructed by updating the low-rank components based on time continuity constrained.Finally,moving object is obtained by background subtraction and adaptive threshold segmentation.Experimental results show that both the FM index and the ROC curve reflect that compared with the state-of-the-art background subtraction methods,this method can effectively overcome the influence of shadow and noise,reduce holes,extract moving objects more accurately,and has good robustness.

Key words: Background subtraction, Continuity constraint, Low rank decomposition, Moving object detection

CLC Number:

TN911.73

ZHU Xuan, WANG Lei, ZHANG Chao, MEI Dong-feng, XUE Jia-ping, CAO Qing-wen. Moving Object Detection Based on Continuous Constraint Background Model Deduction[J].Computer Science, 2019, 46(6): 311-315.

References

[1]ZHAO Y,SHI H,CHEN X,et al.An overview of object detection and tracking[C]∥IEEE International Conference on Information and Automation.2015:280-286.
[2]XUE L X,LUO Y L,WANG Z C.Detection algorithm of adaptive moving objects based on frame difference method[J].Application Research of Computers,2011,28(4):1551-274.
[3]GAO P,SUN X,WANG W.Moving object detection based on kirsch operator combined with Optical Flow[C]∥International Conference on Image Analysis and Signal Processing.2010:620-624.
[4]BARNICH O,DROOGENBROECK M V.ViBe:A Universal Background Subtraction Algorithm for Video Sequences[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2011,20(6):1709-1724.
[5]WENG M,HUANG G,DA X.A new interframe difference algorithm for moving target detection[C]∥International Congress on Image and Signal Processing.2010:A52-A53.
[6]HUANG S Q,LI G.A Review of Research on Moving Target Detection Technology in Intelligent Video Surveillance System[J].Information and Communications,2012,120(4):57-58.(in Chinese)
黄斯茜,李光.智能视频监控系统运动目标检测技术研究综述[J].信息通信,2012,120(4):57-58.
[7]LI Q L,HE J F.Vehicle Detection Based on Three-Frame Difference Method and Cross Entropy Threshold Method[J].Computer Engineering,2011,37(4):172-174.(in Chinese)
李秋林,何家峰.基于三帧差法和交叉熵阈值法的车辆检测[J].计算机工程,2011,37(4):172-174.
[8]ZUO F Y,GAO S F,HAN J Y.Moving Object Detection and Tracking Based on Weighted Accumulative Difference[J].Computer Engineering,2009,35(22):159-161.
[9]KROEGER T,TIMOFTE R,DAI D,et al.Fast Optical Flow Using Dense Inverse Search[M]∥Computer Vision-ECCV 2016.Springer International Publishing,2016:471-488.
[10]YANG H,QU S.Real-time vehicle detection and counting in complex traffic scenes using background subtraction model with low-rank decomposition[J].Iet Intelligent Transport Systems,2018,12(1):75-85.
[11]LI X.Research on Moving Target Detection Method in Intelligent Video Surveillance Images[J].Wireless Interconnect Technology,2013(8):158-158.(in Chinese)
李想.智能视频监控图像中运动目标检测方法的研究[J].无线互联科技,2013(8):158-158.
[12]ZHOU M,SONG Z J.Video background modeling based on sparse and low rank matrix decomposition[J].Application Research of Computers,2015,32(10):3175-3178.(in Chinese)
周密,宋占杰.基于稀疏与低秩矩阵分解的视频背景建模[J].计算机应用研究,2015,32(10):3175-3178.
[13]LIN Z,CHEN M,MA Y.The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices[J].arXiv:1009.5055.
[14]AYBAT N S,GOLDFARB D,MA S.Efficient algorithms for robust and stable principal component pursuit problems[J].Computational Optimization & Applications,2014,58(1):1-29.
[15]LIU G,YAN S.Active subspace:toward scalable low-rank learning[J].Neural Computation,2012,24(12):3371-3394.
[16]ZHOU T,TAO D.GoDec:Randomized Lowrank & Sparse Matrix Decomposition in Noisy Case[C]∥International Confe-rence on Machine Learning.DBLP,2011:33-40.
[17]YE X,YANG J,SUN X,et al.Foreground-Background Separation From Video Clips via Motion-Assisted Matrix Restoration[J].IEEE Transactions on Circuits & Systems for Video Technology,2015,25(11):1721-1734.
[18]WRIGHT J,GANESH A,RAO S,et al.Robust Principal Component Analysis:Exact Recovery of Corrupted Low-Rank Matrices[C]∥Neural Networks for Signal Processing X,2000.Proceedings of the 2000 IEEE Signal Processing Society Workshop.IEEE,2009:289-298.
[19]VIDAL R,MA Y,SASTRY S S.Robust Principal Component Analysis[J].Journal of the Acm,2016,58(3):1-37.
[20]LIU G,LIN Z,YU Y.Robust Subspace Segmentation by Low-Rank Representation[C]∥International Conference on Machine Learning.DBLP,2010:663-670.
[21]LI S S,AN J B,LI C G,et al.Sports Ship Detection Method Based on Background Difference and Visual Saliency[J].Internet of Things Technology,2018(1):17-20.
[22]GU S,XIE Q,MENG D,et al.Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision[J].Internatio-nal Journal of Computer Vision,2017,121(2):183-208.
[23]MEI D,ZHU X,WANG X,et al.Image super-resolution based on structural dissimilarity learning dictionary[C]∥International Conference on the Frontiers and Advances in Data Science.IEEE,2018:12-17.

Related Articles 15

[1]	XIN Yuan-xue, SHI Peng-fei, XUE Rui-yang. Moving Object Detection Based on Region Extraction and Improved LBP Features [J]. Computer Science, 2021, 48(7): 233-237.
[2]	ZHANG Wen-ya, XU Hua-zhong and LUO Jie. Moving Objects Detection under Complex Background Based on ViBe [J]. Computer Science, 2017, 44(9): 304-307.
[3]	WANG Rong-qi, ZHENG Lin and WANG Biao. Foreground Object Detection Based on Improved PBAS [J]. Computer Science, 2017, 44(5): 294-298.
[4]	GAO Hong-wei, WANG Hui-ke and LI Zhuo. Investigation of Improved FOD Detection Algorithm [J]. Computer Science, 2015, 42(Z6): 205-208.
[5]	ZHANG Xiao-jun, LIU Zhi-jing and CHEN Kun. Background Subtraction Based on Local Gradient Feature [J]. Computer Science, 2015, 42(8): 300-304.
[6]	YANG Guo-liang,ZHOU Dan and ZHANG Jin-hui. Moving Object Detection Algorithm Using SILTP Texture Information [J]. Computer Science, 2014, 41(4): 302-305.
[7]	HU Xiao-ran and SUN Han. Novel Moving Object Detection Method Based on ViBe [J]. Computer Science, 2014, 41(2): 149-152.
[8]	TIAN Hong-jin and ZHAN Yin-wei. Moving Object Detection Based on Adaptive Image Blocking and SSIM [J]. Computer Science, 2014, 41(2): 119-122.
[9]	SUN Jian-kun and YANG Ruo-yu. Smoke Detection in Video Based on Color Histogram and Wavelets [J]. Computer Science, 2014, 41(12): 251-254.
[10]	. Approach of Moving Object Detection Based on Image Blocks and Improved Particle Filter Algorithm [J]. Computer Science, 2012, 39(11): 261-263.
[11]	. Moving Objects Segmentation Method Combining DM and Background Reconstruction [J]. Computer Science, 2012, 39(10): 290-293.
[12]	LIN Qing,XU Zhu,WANG Shi-tong,ZHAN Yong-zhao. Moving Objects Detection of Adaptive Gaussian Mixture Models on HSV [J]. Computer Science, 2010, 37(10): 254-256.
[13]	. [J]. Computer Science, 2007, 34(2): 253-255.
[14]	GU Lei ,WU Hui-Zhong, XIAO Liang （School of Computer Science and Technology,Nanjing University of Science and Technology, Nanjing 210094）. [J]. Computer Science, 2007, 34(11): 167-169.
[15]	LIU Yang, LI Yu-Shan,Zhang Da-Pu (Institute of Electronic CAD, Xidian University, Xi'an 710071). [J]. Computer Science, 2005, 32(9): 211-214.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Moving Object Detection Based on Continuous Constraint Background Model Deduction

PDF (PC)

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 0