Video foreground detection of tensor low-rank representation and spatial-temporal sparsity decomposition

Zhong-shan SUI; Jun-shan LI; Jiao ZHANG; Shao-yun FAN; Sheng-yong SUN

doi:10.3788/OPE.20172402.0529

您当前的位置：

首页 >

文章列表页 >

Video foreground detection of tensor low-rank representation and spatial-temporal sparsity decomposition

Information Sciences | 更新时间：2020-07-07

- Video foreground detection of tensor low-rank representation and spatial-temporal sparsity decomposition
- Optics and Precision Engineering Vol. 25, Issue 2, Pages: 529-536(2017)
- 作者机构：
  
  1.火箭军工程大学信息工程系, 陕西西安 710025
  2.96518部队, 湖南怀化 418000
  3.南京炮兵学院战役战术教研室, 江苏南京 211132
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20172402.0529
  CLC： TP391.4
- Received：21 July 2016，
  
  Accepted：12 October 2016，
  
  Published：25 February 2017
- 稿件说明：
移动端阅览
Zhong-shan SUI, Jun-shan LI, Jiao ZHANG, et al. Video foreground detection of tensor low-rank representation and spatial-temporal sparsity decomposition[J]. Optics and precision engineering, 2017, 25(2): 529-536.
DOI：

Zhong-shan SUI, Jun-shan LI, Jiao ZHANG, et al. Video foreground detection of tensor low-rank representation and spatial-temporal sparsity decomposition[J]. Optics and precision engineering, 2017, 25(2): 529-536. DOI： 10.3788/OPE.20172402.0529.

摘要

针对视频中前景检测的问题，提出了一种基于张量低秩表示（Tensor Low-Rank Representation，TLRR）和时空稀疏分解的检测方法。由于视频序列中的前景除具有稀疏性外，本身还具有空间上的连续性以及时间上的持续性，本文提出采用时空稀疏范数对前景特性进行深入发掘。利用张量低秩表示方法将原始视频用张量形式进行分解，充分利用了原始数据的行信息和列信息，且将原始的背景、前景二分解泛化为背景、前景和噪声的三分解，使用非精确增广拉格朗日乘子（Inexact Augmented Lagrange Multiplier，IALM）方法进行最优化求解，并对算法进行了分析。设计实验对本文新方法的有效性进行了验证和比较，并对影响算法效果的重要参数ρ进行了进一步研究实验。实验结果表明：该方法能够有效检测出视频中的运动前景，其准确性相对已有方法有一定提高。

Abstract

A detection method based on Tensor Low-Rank Representation (TLRR) and spatial-temporal sparsity decomposition was proposed to detect foreground targets in video sequences. Since foreground in video sequence has sparsity inherently besides spatially continuous and temporally continuous

this paper put forward spatial-temporal sparsity-inducing norm to perform deep research on property of foreground. Original video was decomposed in tensor representation formed by tensor low-rank representation method

line information and column information of original data were fully used

and two-stage decomposition of original background and foreground was generalized to three-stage decomposition of background

foreground and noises. Optimization solution was performed with Inexact Augmented Lagrange Multiplier (IALM) method.Verification and comparison experiment was established

and further research experiment was performed to research how ρ affecting performance of algorithm. Experimental results show that the method can detect moving foreground in video effectively and improve accuracy when compared with existing methods.

关键词

Keywords

references

STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins:IEEE, 1999:246-252.

ELGAMMAL A, HARWOOD D, DAVIS L. Non-parametric model for background subtraction[C]. Proc. Eur. Conf. Comput. Vis. Springer, 2000:751-767.

YASER S, MUBARAK S. Bayesian modeling of dynamic scenes for object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(11):1778-1792.

HEIKKILA M, PIETIKAINEN M. A texture-based method for modeling the background and detecting moving objects[J]. IEEE Trans on Pattern Anal. and Machine Intelligence, 2006, 28(4):657-662.

KIM K, CHJIDABHONGSE T H, HARWOOD D, et al.. Real-time foreground-background segmentation using codebook model[J]. Real-Time Imaging, 2005, 11(3):172-185.

BOUWMANS T, ZAHZAH E H. Robust PCA via principal component pursuit:A review for a comparative evaluation in video surveillance[J]. Comput. Vis. Image Underst., 2014, 122:22-34.

BAO B K, LIU G C, XU C S, et al.. Inductive robust principal component analysis[J]. IEEE Trans on Image Processing, 2012, 21(8):3794-3800.

LIU G C, LIN Z C, YAN S C, et al.. Robust recovery of subspace structures by low-rank representation[J].IEEE Trans. Pattern Analysis and Machine Intelligence, 2013, 35(1):171-184.

LIU G C, YAN S C. Latent low-rank representation for subspace segmentation and feature extraction[C]. Proceedings of the International Conference on Computer Vision (ICCV), 2011:1615-1622.

ZHANG Z, YAN S C, ZHAO M B, et al.. Robust bilinear matrix recovery by tensor low-rank representation[C]. 2014 International Joint Conference on Neural Networks (IJCNN), 2014:2945-2951.

LIU X, ZHAO G Y. Background Subtraction Based on Low-rank and Structured Sparse Decomposition IEEE Trans on Image Processing DRAFT, 2015.

何玉杰, 李敏, 张金利, 等.基于低秩三分解的红外图像杂波抑制[J].光学精密工程. 2015, 23(7):2070-2078.

HE Y J, LI M, ZHANG J L, et al.. Clutter suppression of infrared image based on three-component low-rank matrix decomposition[J].Opt. Precision Eng., 2015, 23(7):2070-2078.(in Chinese)

YAO J W, LIU X, QI CH. Foreground detection using low rank and structured sparsity[C]. 2014 IEEE International Conference on Multimedia and Expo (ICME), 2014.

穆治亚, 魏仲慧, 何昕, 等.采用稀疏表示的红外图像自适应杂波抑制[J].光学精密工程, 2013, 21(7):1850-1857.

MU ZH Y, WEI ZH H, HE X, et al.. Adaptive clutter suppression of infrared images by using low-rank representation[J]. Opt. Precision Eng., 2013, 21(7):1850-1857.(in Chinese)

ZHANG Z, ZHAO M B, CHOW T W. Binary-and multi-class group sparse canonical correlation analysis for feature extraction and classification[J]. IEEE Trans. Knowledge and Data Engineering, 2013, 25(10):2192-2205.

赵九龙, 马瑜, 李爽, 等.三维医学图像的混合噪声去除方法[J].液晶与显示, 2015, 30(2):340-346.

ZHAO J L, MA Y, LI SH, et al.. Mixed noise removing method for three-dimensional medical images[J]. Chinese Journal of Liquid and Displays, 2015, 30(2):340-346. (in Chinese)

杨亚威, 李俊山, 张士杰, 等.基于生物视觉标准模型特征的无参考型图像质量评价方法[J].液晶与显示, 2014, 29(6):1016-1023.

YANG Y W, LI J SH, ZHANG SH J, et al.. Non-reference image quality assessment approach based on standard model features of biological vision[J]. Chinese Journal of Liquid and Displays, 2014, 29(6):1016-1023. (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Foreground detection based on modified ViBe in dynamic background

Related Author

CHEN Xing-ming

LIAO Juan

LI Bo

CHEN Qi-mei

Related Institution

College of Electronic Science and Engineering, Nanjing University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰