AUTHORS: Kaibo Fan, Ping Wang
Download as PDF
ABSTRACT: In this work, we present a novel optimizing approach to the problem of human body location in video surveillance. The pixels of the object extracted by background subtraction technique are grouped into a point set. It can be covered by an optimal ellipsoid with the minimum enclosing volume. The task of constructing the minimum volume enclosing ellipsoid (MVEE) is implemented by convex optimization theory. We get the parameters of the minimum volume enclosing ellipsoid by solving the problem of the dual formation of the MVEE. Compared with the traditional geometrical moment based method and enclosing box, our approach gives a better result in terms of computing time and object locating affinity. The computing time of the proposed method is only 5.1% and 9.7% of the time used up by the geometrical moment based method and the enclosing box, respectively. The object locating affinity is 10.0% and 8.2% higher than that of the two compared methods.
KEYWORDS: video surveillance, fall detection, object location, minimum volume enclosing ellipsoids
REFERENCES:
[1] S. Boyd, and L. Vandenberghe, Convex optimization, Cambridge University Press, Cambridge, 2004.
[2] S. Silvey, Optimal design: an introduction to the theory for parameter estimation, Springer, New York, 2013.
[3] J. Music, M. Cecic, and M. Bonkovic, Testing inertial sensor performance as hands free human-computer interface, WSEAS T. Computers. 8(4), 2009, pp. 715724.
[4] J. Music, M. Cecic, and V. Zanchi, Real time body orientation estimation based on two layer stochastic filter architecture, Automatika. 51(3), 2010, pp. 264274.
[5] P. Kumar, and E. A. Yildirim, Computing minimum volume enclosing axis aligned ellipsoids, J. Optimiz. Theory App. 136(2), 2008, pp. 211228.
[6] G. Grosklos, and J. Theiler, Ellipsoids for anomaly detection in remote sensing imagery, Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI. 2015, pp. 351370.
[7] H. Lee, D. Moon, I. Kim, H. Jung, and D. Park, Anomaly intrusion detection based on hyper ellipsoid in the kernel feature space, KSII T. Internet Inf. 9(3), 2015, pp. 11731192.
[8] S. Ha, Probabilistic space time analysis of human mobility patterns, WSEAS T. Computers. 21(15), 2016, pp. 222238.
[9] L. Källberg, and T. Larsson, Improved pruning of large data sets for the minimum enclosing ball problem, Graph. Models. 76(6), 2014, pp. 609619.
[10] D. Martinez Rego, E. Castillo, O. Fontenla Romero, and A. Alonso Betanzos, A minimum volume covering approach with a set of ellipsoids, IEEE T. Pattern Anal. 35(12), 2013, pp. 39973009.
[11] S. D. Ahipasaoglu, Fast algorithms for the minimum volume estimator, J. Global Optim. 62(2), 2015, pp. 351370.
[12] T. Horprasert, D. Harwood, and L. S. Davis, A statistical approach for real time robust background subtraction and shadow detection, IEEE International Conference On Computer Vision. 1999, pp. 119.
[13] M. Grötschel, L. Lovász, and A. Schrijver, Geometric algorithms and combinatorial optimization, Springer, New York, 2012.
[14] M. Yu, A. Rhuma, S. Naqvi, L. Wang, and J. Chambers, A posture recognition based fall detection system for monitoring an elderly person in a smart home environment, IEEE T. Inf. Technol. B. 16(6), 2012, pp. 12741286.
[15] Y. Nesterov, and A. Nemirovskii, Interiorpoint polynomial algorithms in convex programming, SIAM, 1994.
[16] J. Grandon, and I. Derpich, A Heuristic for the multi knapsack problem, WSEAS T. Math.10(3), 2011, pp. 95104.
[17] F. Nater, T. Tommasi, H. Grabner, G. Van, and B. Caputo, Transferring activities: updating human behaviour analysis, IEEE International Conference on Computer Vision Workshops. 2011, pp. 17371744.
[18] B. Mirmahboub, S. Samavi, N. Karimi, and S. Shirani, Automatic monocular system for human fall detection based on variations in silhouette area, IEEE T. Bio. Med. Eng. 60(2), 2013, pp. 427436.
[19] M.Yu, A. Rhuma, S. M. Naqvi, L. Wang, and J. Chambers, A posture recognition based fall detection system for monitoring an elderly person in a smart home environment, IEEE T. Inf. Technol. B. 16(6), 2012, pp. 12741286.
[20] J. L. Chua, Y. C. Chang, and W. K. Lim, A simple vision based fall detection technique for indoor video surveillance, Signal Image Video P. 9(3), 2015, pp. 623633.