Human Activity Recognition by Class Label LLE

  • Juliana Valencia-Aguirre
  • Andrés M. Álvarez-Meza
  • Genaro Daza-Santacoloma
  • Carlos Daniel Acosta-Medina
  • Germa Castellanos-Domínguez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)


Human motion analysis has emerged as an important area of research for different fields and applications. However, analyzing image and video sequences to perform tasks such as action recognition, becomes a challenge due to the high dimensionality of this type of data, not mentioning the restrictions in the recording conditions (lighting, angle, distances, etc). In that sense, we propose a framework for human action recognition, which involves a preprocessing stage that decreases the influence of the record conditions in the analysis. Further, our proposal is based on a new supervised feature extraction technique that includes class label information in the mapping process, to enhance both the underlying data structure unfolding and the margin of separability among classes. Proposed methodology is tested on a benchmark dataset. Attained results show how our approach obtains a suitable performance using straightforward classifiers.


Motion recognition video processing dimensionality reduction 


  1. 1.
    Cao, D., Masoud, O.T., Boley, D., Papanikolopoulos, N.: Human motion recognition using support vector machines. Comput. Vis. Image Underst. 113, 1064–1075 (2009)CrossRefGoogle Scholar
  2. 2.
    Efros, A., Berg, A., Mori, G., Malik, J.: Recognizing action at a distance. In: Proceedings of Ninth IEEE International Conference on Computer Vision, vol. 2, pp. 726–733 (2003)Google Scholar
  3. 3.
    Mori, T., Shimosaka, M., Sato, T.: Svm-based human action recognition and its remarkable motion features discovery algorithm. In: ISER 2004. Springer Tracts in Advanced Robotics, vol. 21, pp. 15–25. Springer (2004)Google Scholar
  4. 4.
    Masoud, O., Papanikolopoulos, N.: A method for human action recognition. Image and Vision Computing 21, 729–743 (2003)CrossRefGoogle Scholar
  5. 5.
    Meng, H., Pears, N., Freeman, M., Bailey, C.: Motion history histograms for human action recognition. Embedded Computer Vision 139, 139–162 (2009)CrossRefGoogle Scholar
  6. 6.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local svm approach. In: ICPR, pp. 32–36 (2004)Google Scholar
  7. 7.
    Daza-Santacoloma, G., Castellanos-Dominguez, G., Principe, J.C.: Locally linear embedding based on correntropy measure for visualization and classification. Neurocomputing 80(0), 19–30 (2012)CrossRefGoogle Scholar
  8. 8.
    Saul, L.K., Roweis, S.T.: Think globally, fit locally: Unsupervised learning of low dimensional manifolds. Machine Learning Research 4, 119–155 (2003)MathSciNetGoogle Scholar
  9. 9.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15(6), 1373–1396 (2003)zbMATHCrossRefGoogle Scholar
  10. 10.
    Álvarez Meza, A., Valencia-Aguirre, J., Daza-Santacoloma, G., Castellanos-Domínguez, G.: Global and local choice of the number of nearest neighbors in locally linear embedding. Patter Recognition Letters 32(16), 2171–2177 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Juliana Valencia-Aguirre
    • 1
  • Andrés M. Álvarez-Meza
    • 1
  • Genaro Daza-Santacoloma
    • 1
  • Carlos Daniel Acosta-Medina
    • 1
    • 2
  • Germa Castellanos-Domínguez
    • 1
  1. 1.Signal Processing and Recognition GroupUniversidad Nacional de ColombiaManizalesColombia
  2. 2.Scientific Computing and Mathematical Modeling GroupUniversidad Nacional de ColombiaManizalesColombia

Personalised recommendations