An Efficient Human Tracking System Using Local Binary Pattern And Cellular Non Linear Networks

  IJPTT-book-cover
 
International Journal of P2P Network Trends and Technology (IJPTT)          
 
© 2020 by IJPTT Journal
Volume-10 Issue-5
Year of Publication : 2020
Authors : K.karthiga,P.karpagavalli
DOI :  10.14445/22492615/IJPTT-V10I5P401

Citation

MLA Style:K.karthiga,P.karpagavalli "An Efficient Human Tracking System Using Local Binary Pattern And Cellular Non Linear Networks" International Journal of P2P Network Trends and Technology 10.5 (2020): 1-6.

APA Style:K.karthiga,P.karpagavalli(2019). An Efficient Human Tracking System Using Local Binary Pattern And Cellular Non Linear Networks. International Journal of P2P Network Trends and Technology, 10(5),1-6.

Abstract

The general objective of this cycle is to make a framework which pre-screens the action of the human in video groupings. The planned a semi automated plan fit for performing three enormous scope errands: distinguishing human, human following, and action acknowledgment. Video reconnaissance of human action normally expects individuals to be followed. It is imperative to security and wellbeing reason, the cameras quickly expanding on the planet lately. Subsequently strategy for utilizing the MCMC technique to choose the genuine scene limits, exceptionally exact scene segmentation gets conceivable. It should be noticed that when the earlier likelihood concerning the quantity of scenes in an objective video succession is given effectively, the MCMC strategy can give a more precise scene segmentation result. The deduction of the foundation with the foreground isn`t acceptable in segmentation.The computational complex of the foreground extraction is more. An executing a local binary pattern (LBP) based feature extraction framework with cellular nonlinear networks (CNNs). The LBP procedure depends on changing local binary features of a picture into miniature patterns that can be utilized to, for instance, moving item discovery and face acknowledgment and recognition. Because of fine segmentation the foreground and afterward the foundation will be extricated independently. The Classification/Recognition exactness will be more.

References

[1] Young-Gun Lee, Student Member, IEEE, Zheng Tang, Student Member, IEEE, Jenq-Neng Hwang, Fellow2018 “Online-Learning-Based Human Tracking Across Non-Overlapping Cameras,”vol.28,no:10,PP.2870-2883. [2] Y.-G. Lee, S.-C. Chen, J.-N. Hwang, and Y.-P. Hung, “An ensembleof invariant features for person re-identification,” IEEE Transactions onCircuits and Systems for Video Technology, vol. 27, no. 3, pp. 470–483,2017. [3] “Multiple target tracking by learning based hierarchical association of detection responses” C. Huang, Y. Li, and R. Nevatia, NOV 2015 PP.1890-1904. [4] D. Kuettel, M. Breitenstein, L. V anGool, and V. Ferrari, “What’s goingon? Discovering spatio-temporal dependencies in dynamic scenes,”in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015,pp. 1951–1958. [5] T. Lan, L. Sigal, and G. Mori, “Social roles in hierarchical models for human activity recognition,” in Proc. IEEE Conf. Comput. Vis. PatternRecognit. , Jun. 2014, pp. 1354–1361. [6] A. Milan, L. Leal-Taixe, I. Reid, S. Roth, and K. Schindler ‘‘A Benchmark for Multi-Object Tracking.,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 2953–2960. [7] W. Choi, K. Shahid, and S. Savarese, “Learning context for collec-tive activity recognition,” in Proc. IEEE Conf. Comput. Vis. PatternRecognit. , Jun. 2016, pp. 3273–3280. [8] M. Hoai, Z.-Z. Lan, and F. De la Torre, “Joint segmentation andclassification of human actions in video,” in Proc. IEEE Conf. Comput.Vis. Pattern Recognit. , Jun. 2011, pp. 3265–3272. [9] S. Ji, W. Xu, M. Yang, and K. Yu, “3D convolutional neural networksfor human action recognition,” IEEE Trans. Pattern Anal. Mach. Intell.,vol. 35, no. 1, pp. 221–231, Jan. 2012. [10] Y.-G. Jiang, C.-W. Ngo, and J. Yang, “Towards optimal bag-of-features for object categorization and semantic video retrieval,” in Proc. 6th ACMInt. Conf. Image Video Retr. , 2010, pp. 494–501. [11] U. Gaur, Y. Zhu, B. Song, and A. Roy-Chowdhury, “A ‘string offeature graphs’ model for recognition of complex activities in naturalvideos,” in Proc. IEEE Int. Conf. Comput. Vis., Nov. 2011,pp. 2595–2602. [12] K.-W. Chen, C.-C. Lai, Y.-P. Hung, and C.-S. Chen., ‘‘An adaptive learningmethod for target tracking across multiple cameras.,’’ in Proc. CVPR, Jun. 2013, pp. 1273–1280. [13] “Histograms of Oriented Gradients for Human Detection.,’’ INRIA Rhone-Alps, avenue de Europe, Montbonnot, France Navneet.Dala,Bill.Triggs IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 9, pp. 1806–1819, Sep. 2011. [14] Q. V. Le, W. Y. Zou, S. Y. Yeung, and A. Y. Ng, “Learning hierarchica subspace analysis,” in Proc. IEEE Conf. Comput. Vis. PatternRecognit. , Jun. 2011, pp. 3361–3368. [15] Y. Li and R. Nevatia, “Key object driven multi-category object recogni-tion, localization and tracking using spatio-temporal context,” in Proc.10th Eur. Conf. Comput. Vis. , 20013, pp. 409–422.

Keywords
Adaptive segmentation, multi-object tracking, visual surveillance, multiple camera tracking, NLPR MCT da- taset.