RESEARCH AND RESTORATION TECHNOLOGY OF VIDEO MOTION TARGET DETECTION BASED ON KERNEL METHOD

Publications

Share / Export Citation / Email / Print / Text size:

International Journal on Smart Sensing and Intelligent Systems

Professor Subhas Chandra Mukhopadhyay

Exeley Inc. (New York)

Subject: Computational Science & Engineering , Engineering, Electrical & Electronic

GET ALERTS

eISSN: 1178-5608

DESCRIPTION

0
Reader(s)
0
Visit(s)
0
Comment(s)
0
Share(s)

VOLUME 7 , ISSUE 4 (December 2014) > List of articles

RESEARCH AND RESTORATION TECHNOLOGY OF VIDEO MOTION TARGET DETECTION BASED ON KERNEL METHOD

Pan Feng * / Wang Xiaojun / Wang Weihong

Keywords : Moving object, kernel method, active, pattern recognition, image features.

Citation Information : International Journal on Smart Sensing and Intelligent Systems. Volume 7, Issue 4, Pages 1,516-1,534, DOI: https://doi.org/10.21307/ijssis-2017-718

License : (CC BY-NC-ND 4.0)

Received Date : 15-August-2014 / Accepted: 21-October-2014 / Published Online: 01-December-2014

ARTICLE

ABSTRACT

In recent years, due to the video surveillance applications more and more widely, people are
not satisfied with the goal of monitoring, and the video monitoring technology of intelligent video
moving object detection and tracking technology has received extensive attention. The research work in
this paper is in the field, the moving target detection spatiotemporal correlation and difference contour
tracking algorithm based on a fixed background. The algorithm in the background under the condition
of fixed to pay a smaller time complexity, the target detection and tracking has a good effect, so it has
higher application value. In this paper, the prospect of caused motion detection of occlusion
background foreground correlation problem, put forward the video moving object detection method
based on kernel independent component analysis, canonical correlation to minimize the component in
the high dimensional feature space in order to separate the foreground nuclear background.
Independent component analysis assumes that the foreground and background independent, avoid the
correlation problem. The two objective functions based on Kernel Independent Component Analysis:
analysis of kernel independent component analysis based on kernel canonical component (KCCA) and
kernel independent component analysis (KGV) based on the generalized variance. KCCA is the
application of canonical correlation analysis in the kernel method, discuss is the first canonical
correlation separation component of high dimensional map, and KGV are typical correlation between
the components in the high dimensional space of the whole spectrum. Both KCCA and KGV improved
the accuracy of motion detection

Content not available PDF Share

FIGURES & TABLES

REFERENCES

[1] Richard O. Duda, Peter E. Hart, David G. stork. Pattern Classification [M].Beijing: China
Machine Press, 2014.
[2] A. J. Lipton, H. Fujiyoshi. Moving target classification and tracking from real-time video
[C]. The IEEE International Conference on Image Processing (JCIP), UK, 2009: 8-11.
[3] Cucchiara R., Grana C., Piccardi M., et al. Detecting moving objects, ghosts and shadows
in video streams [J]. IEEE Trans. On Pattern Analysis & Machine Intelligence, 2013, 25 (10):
1337-1342.
[4] C. Stauffer, W. E. I. Grimson. Learning Patterns of Activity Using Real-Time Tracking
[J]. IEEE Trans. PAMI, 2010, 22(8): 747-757.
[5] Krzysztof Kowalski. Linearization Transformation for Non-linear Dynamical Systems:
Hilbert Space Approach [J]. Physica A: Statistical Mechanics and its Applications, 1992, 180(1-
2): 156-170.
[6] Yong Xu, Jing-Yu Yang, Zhong Jin. A Novel Method For Fisher Discriminate Analysis
[J]. Pattern Recognition, 2004, 37(2):381-384.
[7] Theodore S. Rappaport etc. “Wireless Communications Principles and Practice.
Publishing House of Electronics Industry. Mar. 2003. Cortes Corinna and Vapnik Vladimir N..
Support Vector Networks [J]. Machines Learning, 2005, 20: 273-297.
[8] Mercer J. Functions of Positive and Negative Type and Their Connection with the Theory
of Integral Equations [J]. Philosophical Transactions of the Royal Society of London, 2009, A209:
415-446.
[9] N. Aronszajn. Theory of reproducing kernels [J]. Trans. Amer. Math. Soc., 2000, 68(3):
337-404.
[10] Aizerman M A, Braverman E M, Rozonoer L I. Theoretical foundation of potential
function method in pattern recognition learning [J]. Automation and Remote Control, 2004, 25:
821-837.
[11] H. Landau, H. O.. Prolate spheriodal wave functions, Fourier analysis and uncertainty-III:
The dimension of the space of essentially time and band-limited signal [J]. Bell Syst. Tech. 2002.
pp: 41.
[12] Krishnanand K N. Ghose D. A glowworm swarm optimization based multi-robot system
for signal source localization [M]. Design and Control of Intelligent Robotic Systems, 2009: 53-
74.
[13] C.Y. Lin, T.C. Wu, and F. Zhang. A Structured Multisignature Scheme from the Gap
Difffie-Hellman Group.Cryptology ePrint Archive, Report 2003/090, 2003.
[14] Steve Lu, Rafail Ostrovsky, Amit Sahai, Hovav Shacham, Brent Waters. Sequential
Aggregate Signatures and Multisignatures Without Random Oracles. In EUROCRYPT 2006,
LNCS 4004, Springer, Berlin, 2006, pp.465–485.
[15] B Waters. Effcient identity-based encryptionwithoutrandom oracles. In Proceedings of
Eurocrypt 2005, LNCS 3494 , Springer, Berlin, 2005, pp.14–27.
[16] Yong Xu, Chuan-Cai Liu, Chong-Yang Zhang. Determine the Kernel Parameter of KFDA
using a Minimum Search Algorithm[C]. Proceedings of Third International Conference on
Intelligent Computing, Qingdao, 2012:418-426.
[17] Tsuda K. Optimal hyperplane classifier based on entropy number bound[C]. Ninth
International Conference on Artificial Neural Network, 2009, 1: 419-424.
[18] Vapnik V N, Chapelle O. Bounds on error expectation for support vector machines [J].
Neural Computation, 2010, 12(9): 2013-2036.
[19] De-Gang Chen, Heng-You Wang. Generalized Mercer theorem and its application to
feature space related to indefinite kernels[C]. 2008 International Conference on Machine
Learning and Cybernetics, 2008, 2: 774-777.
[20] Ding-Xuan Zhou. Capacity of reproducing kernel spaces in learning theory [J]. IEEE
Transactions on Information Theory, 2003, 49(7): 1743-1752.
[21] Alain Rakotomamonjy, Francis R. Bach, Stephane Canu and Yves Grandvalet. Simple
MKL[J]. Journal of Machine Learning Research, 2012, 9: 2491-2521.
[22] M.Iwahara, S.C.Mukhopadhyay, S.Yamada and F.P.Dawson, "Development of Passive
Fault Current Limiter in Parallel Biasing Mode", IEEE Transactions on Magnetics, Vol. 35, No.
5, pp 3523-3525, September 1999.
[23] Yanmin LUO, Peizhong LIU and Minghong LIAO, AN ARTIFICIAL IMMUNE
NETWORK CLUSTERING ALGORITHM FOR MANGROVES REMOTE SENSING,
International Journal on Smart Sensing and Intelligent Systems, VOL. 7, NO. 1, pp. 116 – 134,
2014.
[24] G. Sen Gupta, S.C. Mukhopadhyay, Michael Sutherland and Serge Demidenko, Wireless
Sensor Network for Selective Activity Monitoring in a home for the Elderly, Proceedings of 2007
IEEE IMTC conference, Warsaw, Poland, (6 pages).
[25] Daode Zhang et al., RESEARCH ON CHIPS’ DEFECT EXTRACTION BASED ON
IMAGE-MATCHING, International Journal on Smart Sensing and Intelligent Systems, VOL. 7,
NO. 1, pp.321 – 336, 2014.
[26] G.Sengupta, T.A.Win, C.Messom, S.Demidenko and S.C.Mukhopadhyay, “Defect analysis
of grit-blasted or spray printed surface using vision sensing technique”, Proceedings of Image
and Vision Computing NZ, Nov. 26-28, 2003, Palmerston North, pp. 18-23.

EXTRA FILES

COMMENTS