Human motion estimation based on low dimensional space incremental learning. (English) Zbl 1394.68398
Summary: This paper proposes a novel algorithm called low dimensional space incremental learning (LDSIL) to estimate the human motion in 3D from the silhouettes of human motion multiview images. The proposed algorithm takes the advantage of stochastic extremum memory adaptive searching (SEMAS) and incremental probabilistic dimension reduction model (IPDRM) to collect new high dimensional data samples. The high dimensional data samples can be selected to update the mapping from low dimensional space to high dimensional space, so that incremental learning can be achieved to estimate human motion from small amount of samples. Compared with three traditional algorithms, the proposed algorithm can make human motion estimation achieve a good performance in disambiguating silhouettes, overcoming the transient occlusion, and reducing estimation error.
References:
| [1] | Liu, Y.; Gall, J.; Stoll, C.; Dai, Q.; Seidel, H.-P.; Theobalt, C., Markerless motion capture of multiple characters using multiview image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 11, 2720-2735, (2013) · doi:10.1109/TPAMI.2013.47 |
| [2] | Yeguas-Bolivar, E.; Muñoz-Salinas, R.; Medina-Carnicer, R.; Carmona-Poyato, A., Comparing evolutionary algorithms and particle filters for Markerless Human Motion Capture, Applied Soft Computing Journal, 17, 153-166, (2014) · doi:10.1016/j.asoc.2014.01.007 |
| [3] | Güdükbay, U.; Demir, İ.; Dedeoğlu, Y., Motion capture and human pose reconstruction from a single-view video sequence, Digital Signal Processing, 23, 5, 1441-1450, (2013) · doi:10.1016/j.dsp.2013.06.008 |
| [4] | Sigal, L.; Balan, A. O.; Black, M. J., Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion, International Journal of Computer Vision, 87, 1-2, 4-27, (2010) · doi:10.1007/s11263-009-0273-6 |
| [5] | Deutscher, J.; Reid, I., Articulated body motion capture by stochastic search, International Journal of Computer Vision, 61, 2, 185-205, (2005) · doi:10.1023/b:visi.0000043757.18370.9c |
| [6] | Li, Y.; Sun, Z.-X.; Chen, S.-L.; Li, Q., 3D human pose analysis from monocular video by simulated annealed particle swarm optimization, Acta Automatica Sinica, 38, 5, 732-741, (2012) · doi:10.3724/sp.j.1004.2012.00732 |
| [7] | Sato, T., Particle relaxation method of Monte Carlo filter for structure system identification, Journal of Civil Structural Health Monitoring, 3, 4, 325-334, (2013) · doi:10.1007/s13349-013-0050-7 |
| [8] | Waechter, C. A. L.; Pustka, D.; Klinker, G. J., Real-time monocular people tracking by sequential Monte-Carlo filtering, Proceedings of the 6th International Conference on Computer Vision (CV ’13)/Computer Graphics Collaboration Techniques and Applications (CGCTA ’13) · doi:10.1145/2466715.2466728 |
| [9] | To, G.; Mahfouz, M. R., Quaternionic attitude estimation for robotic and human motion tracking using sequential monte carlo methods with von mises-fisher and nonuniform densities simulations, IEEE Transactions on Biomedical Engineering, 60, 11, 3046-3059, (2013) · doi:10.1109/TBME.2013.2262636 |
| [10] | Wang, J. M.; Fleet, D. J.; Hertzmann, A., Gaussian process dynamical models for human motion, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 2, 283-298, (2008) · doi:10.1109/TPAMI.2007.1167 |
| [11] | Wong, Y. W.; Seng, K. P.; Ang, L.-M., Radial basis function neural network with incremental learning for face recognition, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 41, 4, 940-949, (2011) · doi:10.1109/tsmcb.2010.2101591 |
| [12] | Sun, N.; Guo, Y.-F., An improved incremental learning approach based on SVM model for network data stream, Advances in Computer Science and Information Engineering. Advances in Computer Science and Information Engineering, Advances in Intelligent and Soft Computing, 277-282, (2012), Berlin, Germany: Springer, Berlin, Germany · doi:10.1007/978-3-642-30126-1_45 |
| [13] | Chen, S.; Cowan, C. F. N.; Grant, P. M., Orthogonal least squares learning algorithm for radial basis function networks, IEEE Transactions on Neural Networks, 2, 2, 302-309, (1991) · doi:10.1109/72.80341 |
| [14] | Zhang, Z.; Ke, T.; Deng, N.; Tan, J., Biased p-norm support vector machine for PU learning, Neurocomputing, 136, 265-261, (2014) · doi:10.1016/j.neucom.2014.01.007 |
| [15] | Dong, F.; Chen, Z.; Wang, J., A new level set method for inhomogeneous image segmentation, Image and Vision Computing, 31, 10, 809-822, (2013) · doi:10.1016/j.imavis.2013.08.003 |
| [16] | Kasaiezadeh, A.; Khajepour, A., Multi-agent stochastic level set method in image segmentation, Computer Vision and Image Understanding, 117, 9, 1147-1162, (2013) · doi:10.1016/j.cviu.2013.04.008 |
| [17] | He, B.; Wang, G.-J.; Zhang, C., Iterative transductive learning for automatic image segmentation and matting with RGB-D data, Journal of Visual Communication and Image Representation, 25, 5, 1031-1043, (2014) · doi:10.1016/j.jvcir.2014.03.002 |
| [18] | Andrei, N., Scaled conjugate gradient algorithms for unconstrained optimization, Computational Optimization and Applications, 38, 3, 401-416, (2007) · Zbl 1168.90608 · doi:10.1007/s10589-007-9055-7 |
| [19] | Nabney, I. T., Algorithms for Pattern Recognition, (2001), Berlin, Germany: Springer, Berlin, Germany |
| [20] | Zhang, X.-D., Matrix Analysis and Applications, (2013), Beijng, China: Tsinghua University press, Beijng, China |
| [21] | Bugallo, M. F.; Djuric, P. M., Gaussian particle filtering in high-dimensional systems, Proceedings of the IEEE Workshop on Statistical Signal Processing (SSP ’14) · doi:10.1109/ssp.2014.6884592 |
| [22] | Ruslan, F. A.; Adnan, R.; Samad, A. M.; Zain, Z. M., Parameters effect in Sampling Importance Resampling (SIR) particle filter prediction and tracking of flood water level performance, Proceedings of the 12th International Conference on Control, Automation and Systems (ICCAS ’12) |
| [23] | Sigal, L.; Balan, A. O.; Black, M. J., Humaneva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion, (2006), Providence, RI, USA: The Report of Brown University, Providence, RI, USA |
| [24] | Sandau, M.; Koblaucha, H.; Moeslundc, T. B.; Aanæs, H.; Alkjær, T.; Simonsen, E. B., Markerless motion capture can provide reliable 3D gait kinematics in the sagittal and frontal plane, Medical Engineering and Physics, 39, 9, 1168-1175, (2014) · doi:10.1016/j.medengphy.2014.07.007 |
| [25] | Luo, W.; Yamasaki, T.; Aizawa, K., Cooperative estimation of human motion and surfaces using multiview videos, Computer Vision and Image Understanding, 117, 11, 1560-1574, (2013) · doi:10.1016/j.cviu.2013.07.006 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
