Dynamically Visual Learning for People Identification with Sparsely Distributed Cameras

  • Hidenori Tanaka
  • Itaru Kitahara
  • Hideo Saito
  • Hiroshi Murase
  • Kiyoshi Kogure
  • Norihiro Hagita
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)


We propose a dynamic visual learning method that aims to identify people by using sparsely distributed multiple surveillance cameras. In the proposed method, virtual viewpoint images are synthesized by interpolating the sparsely distributed images with a simple 3D shape model of the human head, so that virtual densely distributed multiple images can be obtained. The multiple images generate an initial eigenspace in the initial learning step. In the following additional learning step, other distributed cameras capture additional images that update the eigenspace to improve the recognition performance. The discernment capability for personal identification of the proposed method is demonstrated experimentally.


Input Image Spline Function Multiple Image Multiple Camera Surveillance Camera 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Jain, A.K., Pankanti, S., Prabhakar, S., Hong, L., Ross, A.: Biometrics: A Grand Challenge. In: Proc. of IC PR, vol. 2, pp. 935–942 (2004)Google Scholar
  2. 2.
    Pentland, A.: Looking at People: Sensing for Ubiquitous and Wearable Computing. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(1), 107–118 (2000)CrossRefGoogle Scholar
  3. 3.
    Lao, S., Kozuru, T., Okamoto, T., Yamashita, T., Tabata, N., Kawade, M.: A fast 360-degree rotation invariant face detection system. In: ICCV (2003)Google Scholar
  4. 4.
  5. 5.
    Murase, H., Nayar, S.K.: Parametric Eigenspace Representation for Visual Learning and Recognition. In: Workshop on Geometric Method in Computer Vision, SPIE, pp. 378–391 (1993)Google Scholar
  6. 6.
    Murase, H., Nayar, S.K.: Illumination Planning for Object Recognition Using Parametric Eigenspaces. IEEE Trans. on Pattern Analysis and Machine Intelligence 16(12), 1219–1227 (1995)CrossRefGoogle Scholar
  7. 7.
    Kanade, T., Narayanan, P.J., Rander, P.W.: Virtualized reality: concepts and early results. In: Proc. of IEEE Workshop on Representation of Visual Scenes, pp. 69–76 (1995)Google Scholar
  8. 8.
  9. 9.
    Laurentini, A.: The Visual Hull Concept for Silhouette-Based Image Understanding. IEEE Trans. on Pattern Analysis and Machines Intelligence 16(2), 150–162 (1994)CrossRefGoogle Scholar
  10. 10.
    Koyama, T., Kitahara, I., Ohta, Y.: Live Mixed-Reality 3D Video in Soccer Stadium. In: Proc. of ISMAR, pp. 178–187 (2003)Google Scholar
  11. 11.
    Kitahara, I., Kogure, K., Hagita, N.: Stealth Vision for Protecting Privacy. In: Proc. of ICPR, vol. 4, pp. 404–407 (2004)Google Scholar
  12. 12.
    Kitahara, I., Saito, H., Akimichi, S., Ono, T., Ohta, Y., Kanade, T.: Large-scale Virtualized Reality. In: CVPR, Technical Sketches (2001)Google Scholar
  13. 13.
    Everitt, C.: Projective Texture Mapping. White paper, NVidia Corporation (2001)Google Scholar
  14. 14.
    Nelder, J.A., Mead, R.: A Simplex Method for Function Minimization. Computer Journal 7, 308–313 (1965)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Hidenori Tanaka
    • 1
    • 2
  • Itaru Kitahara
    • 1
  • Hideo Saito
    • 2
  • Hiroshi Murase
    • 3
  • Kiyoshi Kogure
    • 1
  • Norihiro Hagita
    • 1
  1. 1.Intelligent Robotics and Communication LaboratoriesATRKyotoJapan
  2. 2.Graduate School of Science and TechnologyKeio UniversityYokohamaJapan
  3. 3.Graduate School of Information ScienceNagoya UniversityNagoyaJapan

Personalised recommendations