全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

非凸加权核范数及其在运动目标检测中的应用

DOI: 10.11834/jig.20151107

Keywords: 运动目标检测,低秩矩阵分解,非凸加权核范数,区域连续性,矩阵恢复

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的近年来,低秩矩阵分解被越来越多的应用到运动目标检测中。但该类方法一般将矩阵秩函数松弛为矩阵核函数优化,导致背景恢复精度不高;并且没有考虑到前景目标的先验知识,即区域连续性。为此提出一种结合非凸加权核范数和前景目标区域连续性的目标检测算法。方法本文提出的运动目标检测模型以鲁棒主成分分析(RPCA)作为基础,在该基础上采用矩阵非凸核范数取代传统的核范数逼近矩阵低秩约束,并结合了前景目标区域连续性的先验知识。该方法恢复出的低秩矩阵即为背景图像矩阵,而稀疏大噪声矩阵则是前景目标位置矩阵。结果无论是在仿真数据集还是在真实数据集上,本文方法都能够取得比其他低秩类方法更好的效果。在不同数据集上,该方法相对于RPCA方法,前景目标检测性能提升25%左右,背景恢复误差降低0.5左右;而相对于DECOLOR方法,前景目标检测性能提升约2%左右,背景恢复误差降低0.2左右。结论矩阵秩函数的非凸松弛能够比凸松弛更准确的表征出低秩特征,从而在运动目标检测应用中更准确的恢复出背景。前景目标的区域连续性先验知识能够有效地过滤掉非目标大噪声产生的影响,使得较运动目标检测的精度得到大幅提高。因此,本文方法在动态纹理背景、光照渐变等较复杂场景中均能够较精确地检测出运动目标区域。但由于区域连续性的要求,本文方法对于小区域多目标的检测效果不甚理想。

References

[1]  Yilmaz A, Javed O, Shah M. Object tracking:a survey[J]. ACM Computing Surveys, 2006, 38(2):1-45.[DOI:10.1145/1177352.1177355]
[2]  Cremers D, Soatto S. Motion competition:a variational approach to piecewise parametric motion segmentation[J]. lnternational Journal of Computer Vision, 2005, 62(3):249-265.[DOI:10.1007/s11263-005-4882-4]
[3]  Amiaz T, Kirvati N. Piecewise-smooth dense optical flow via level sets[J]. International Journal of Computer Vision, 2006, 68(2):111-124.[DOI:10.1007/s11263-005-6206-0]
[4]  Beauchemin S S, Barron J L. The computation of optical flow[J]. ACM Computing Surveys (CSUR), 1995, 27(3):433-466.[DOI:10.1145/212094. 212141]
[5]  Nagel H H, Enkelmann W. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(5):565-593.[DOI:10.1109/TPAMI. 1986. 4767833]
[6]  Meoslund T B, Hilton A, Kruger V. A survey of advances in vision-based human motion capture and analysis[J]. Computer Vision and Image Understanding, 2006, 104(2):90-126.[DOI:10.1016/J.CVIU.2006.08.002]
[7]  Wren C R, Azarbayejani A, Darrell T, et al. Pfinder:real-time tracking of the human body[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):780-785.[DOI:10.1109/34.598236]
[8]  Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1999. Fort Collins, CO:IEEE, 1999, 2:246-252.[DOI:10.1109/CVPR.1999. 784637]
[9]  Mittal A, Paragios N. Motion-based background subtraction using adaptive kernel density estimation[C]//Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE, 2004, 2(2):II-302-II-309.[DOI:10.1109/CVPR. 2004. 1315179]
[10]  Rittscher J, Kato J, Joga S, et al. A Probabilistic Background Model For Tracking[M]//European Conference on Computer Vision. Springer Berlin Heidelberg:ECCV, 2000(1843):336-350.[DOI:10.1007/3-540-450530X_32]
[11]  Zhong J, Sclaroff S. Segmenting foreground objects from a dynamic textured background via a robust kalman filter[C]//Proceedings of Ninth IEEE International Conference on Computer Vision. Nice, France:IEEE, 2003:44-50.[DOI:10.1109/ICCV. 2003. 1238312]
[12]  Kim K, Chalidabhongse T H, Harwood D, et al. Real-time foreground-background segmentation using codebook model[J]. Real-Time Imaging, 2005, 11(3):172-85.[DOI:10.1016/J. RTI. 2004. 12. 004]
[13]  Wang L, Cheng H, Liu C, et al. A robust elastic net approach for feature learning[J]. Journal of Visual Communication and Image Representation, 2014, 25(2):313-321.
[14]  Candes E, Li X, Ma Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011, 58(3):11.[DOI:10.1145/1970392. 1970395]
[15]  Zhou X, Yang C. Moving object detection by detecting contiguous in the low-rank representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(3):597-610.[DOI:10.1109/TPAMI. 2012. 132]
[16]  Chen K, Dong H, Chan K. Reduced rank regression via adaptive nuclear norm penalization[J]. Biometrika, 2015,102(2):439-456.[DOI:10.1093/BIOMET/AST036]
[17]  Li S Z. Markov Random Field Modeling In Image Analysis[M]. London:Springer, 2009:1-21.
[18]  Candes E, Tao T. The power of convex relaxtion:near-optimal matrix completion[J]. IEEE Transactions on Information Theory, 2010, 56(5):2053-2080.[DOI:10.1109/TIT. 1020. 2044061]
[19]  Candes E, Wakin M, Boyd S. Enhancing sparsity by reweighted l1 minimization[J]. Journal of Fourier Analysis and Applications,2008, 14(5-6):877-905.[DOI:10.1007/S00041-008-9045-X]
[20]  Lu C Y, Tang J H, Yan S C, et al. Generalized nonconvex nonsmooth low-rank minimization[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 2014. Columbus, Ohio:IEEE, 2014:4130-4137.[DOI:10.1109/CVPR.2014.526]
[21]  更多...
[22]  Lu C, Zhu C, Xu C, et al. Generalized singular value thresholding[C]//Proceedings of Twenty-Ninth AAAI Conference on Artificial Intelligence. Austin, Texas:AAAI. 2015:1805-1811.
[23]  Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transcation on Pattern Analysis and Machine Intelligence, 2004, 26(9):1124-1137.[DOI:10.1109/TPAMI.2004.60]
[24]  Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts[J]. IEEE Transcation on Pattern Analysis and Machine Intelligence, 2001, 23(11):1222-1239.[DOI:10.1109/34.969114]
[25]  Kolmogorov V, Zabih R. What energy functions can be minimized via graph cuts?[J]. IEEE Transcations Pattern Analysis and Machine Intelligence, 2004, 26(2):147-159.[DOI:10.1109/TPAMI.2004.1262177]
[26]  Davis J, Goadrich M. The relationship between Precision-Recall and ROC curves[C]//Proceedings of the 23rd International Conference on Machine Learning. Corvallis:ACM, 2006:233-240.[DOI:10.1145/1143844. 1143874]
[27]  Wang H, Suter D. A Novel Robust Statistical Method For Background Initialization And Visual Surveillance[M]//Computer Vision-ACCV 2006. Berlin Heidelberg:Springer, 2006:328-337.[DOI:10.1007/11612032_34]
[28]  Chan A, Vasconcelos N. Layered dynamic textures[J]. IEEE Transcation on Pattern Analysis and Machine Intelligence, 2009, 31(10):1862-1879.[DOI:10.1109/TPAMI.2009.110]
[29]  Li L, Huang W, Gu I, et al. Statistical modeling of complex backgrounds for foreground object detection[J]. IEEE Transcations on Image Processing, 2004, 13(11):1459-1472.[DOI:10.1109/TIP. 2004. 836169]
[30]  Ross D A, Lim J, Lin R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(1-3):125-141.[DOI:10.1007/S11263-007-0075-7]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133