Automatic Motion Segmentation via a Cumulative Kernel Representation and Spectral Clustering

  • O. R. Oña-RochaEmail author
  • O. T. Sánchez-Manosalvas
  • A. C. Umaquinga-Criollo
  • P. D. Rosero-Montalvo
  • L. E. Suárez-Zambrano
  • J. L. Rodríguez-Sotelo
  • D. H. Peluffo-Ordóñez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10585)


Dynamic or time-varying data analysis is of great interest in emerging and challenging research on automation and machine learning topics. In particular, motion segmentation is a key stage in the design of dynamic data analysis systems. Despite several studies have addressed this issue, there still does not exist a final solution highly compatible with subsequent clustering/classification tasks. In this work, we propose a motion segmentation compatible with kernel spectral clustering (KSC), here termed KSC-MS, which is based on multiple kernel learning and variable ranking approaches. Proposed KSC-MS is able to automatically segment movements within a dynamic framework while providing robustness to noisy environments.


Kernel spectral clustering Motion segmentation Time-varying data Variable ranking 


  1. 1.
    Lu, L., Zhang, X., Xu, X., Shang, D.: Video analysis using spatiotemporal descriptor and kernel extreme learning machine for lip reading. J. Electron. Imaging 24(5), 053023–053023 (2015)CrossRefGoogle Scholar
  2. 2.
    Yadav, S., Dubey, R., Ahmed, M.: An advanced motion detection algorithm with video quality analysis for video surveillance systems. Int. J. Adv. Res. Comput. Sci. 5(8) (2014)Google Scholar
  3. 3.
    Saripalle, S.K., Paiva, G.C., Cliett, T.C., Derakhshani, R.R., King, G.W., Lovelace, C.T.: Classification of body movements based on posturographic data. Hum. Mov. Sci. 33, 238–250 (2014)CrossRefGoogle Scholar
  4. 4.
    Shanmao, G., Yunlong, L., Lijun, L., Ni, Z.: Weighted principal component analysis applied to continuous stirred tank reactor system with time-varying. In: 2015 34th Chinese Control Conference (CCC), pp. 6377–6381. IEEE (2015)Google Scholar
  5. 5.
    Langone, R., Alzate, C., Suykens, J.A.: Kernel spectral clustering with memory effect. Physica A: Statistical Mechanics and Its Applications (2013)Google Scholar
  6. 6.
    Alzate, C., Suykens, J.A.: Multiway spectral clustering with out-of-sample extensions through weighted kernel PCA. IEEE Trans. Pattern Anal. Mach. Intell. 32(2), 335–347 (2010)CrossRefGoogle Scholar
  7. 7.
    Bucak, S.S., Jin, R., Jain, A.K.: Multiple kernel learning for visual object recognition: a review. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1354–1369 (2014)CrossRefGoogle Scholar
  8. 8.
    Peluffo, D., Garcia, S., Langone, R., Suykens, J., Castellanos, G.: Kernel spectral clustering for dynamic data using mulitple kernel learning. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1085–1090 (2013)Google Scholar
  9. 9.
    Peluffo-Ordóñez, D., García-Vega, S., Castellanos-Domínguez, C.G.: Kernel spectral clustering for motion tracking: a first approach. In: Ferrández Vicente, J.M., Álvarez Sánchez, J.R., de la Paz López, F., Toledo Moreo, F.J. (eds.) IWINAC 2013. LNCS, vol. 7930, pp. 264–273. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-38637-4_27 CrossRefGoogle Scholar
  10. 10.
    Suykens, J.A.K., Van Gestel, T., De Brabanter, J., De Moor, B., Vandewalle, J.: Least Squares Support Vector Machines. World Scientific, Singapore (2002)CrossRefzbMATHGoogle Scholar
  11. 11.
    Alzate, C., Suykens, J.A.K.: Multiway spectral clustering with out-of-sample extensions through weighted kernel PCA. IEEE Trans. Pattern Anal. Mach. Intell. 32(2), 335–347 (2010)CrossRefGoogle Scholar
  12. 12.
    Peluffo, D., Lee, J., Verleysen, M., Rodríguez-Sotelo, J., Castellanos-Domínguez, G.: Unsupervised relevance analysis for feature extraction and selection: A distance-based approach for feature relevance. In: International Conference on Pattern Recognition, Applications and Methods-ICPRAM (2014)Google Scholar
  13. 13.
    Molina-Giraldo, S., Álvarez-Meza, A.M., Peluffo-Ordoñez, D.H., Castellanos-Domínguez, G.: Image segmentation based on multi-kernel learning and feature relevance analysis. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds.) IBERAMIA 2012. LNCS, vol. 7637, pp. 501–510. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-34654-5_51 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • O. R. Oña-Rocha
    • 1
    • 2
    Email author
  • O. T. Sánchez-Manosalvas
    • 2
  • A. C. Umaquinga-Criollo
    • 1
  • P. D. Rosero-Montalvo
    • 1
    • 4
  • L. E. Suárez-Zambrano
    • 1
  • J. L. Rodríguez-Sotelo
    • 5
  • D. H. Peluffo-Ordóñez
    • 1
    • 3
    • 6
  1. 1.Universidad Técnica del NorteIbarraEcuador
  2. 2.Universidad de las Fuerzas Armadas - ESPESangolquíEcuador
  3. 3.Corporación Universitaria Autónoma de NariñoPastoColombia
  4. 4.Instituto Tecnológico Superior 17 de JulioYachayEcuador
  5. 5.Universidad Autónoma de ManizalesManizalesColombia
  6. 6.Universidad de NariñoPastoColombia

Personalised recommendations