Shape Based People Detection for Visual Surveillance Systems

  • M. Leo
  • P. Spagnolo
  • G. Attolico
  • A. Distante
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2688)


People detection in outdoor environments is one of the most important problems in the context of video surveillance. In this work we propose an example-based learning technique to detect people in dynamic scenes. A classification based on people shape and not on image content has been applied. First, motion information and background subtraction have been used for highlighting objects of interest, then geometric and statistical information have been extracted from horizontal and vertical projections of detected objects to represent people shape. Finally, a supervised three layer neural network has been used to properly classify objects. Experiments have been performed on real image sequences acquired in a parking area. The results have shown that the proposed method is robust, reliable, fast and it can be easily adapted for the detection of any other moving object in the scene.


Binary Image Video Surveillance Vertical Projection Horizontal Projection Layer Neural Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    R. Cutler, L. Davis: Robust real-time periodic motion detection analysis and applications, IEEE Trans. Pattern Anal. and Mach. Intell. 22 8 (2000), pp. 781–796CrossRefGoogle Scholar
  2. [2]
    A. J. Lipton: Local application of optical flow to analyse rigid versus non rigid motion. In the website
  3. [3]
    R.T. Collins et al: A system for video surveillance and monitoring: VSAM, final report, CMU-RI-TR-00-12, technical Report, Carnegie Mellon University, 2000Google Scholar
  4. [4]
    A.J. Lipton, H. Fujiyoshi, R.S. Patil: Moving target classification and tracking from real time video, Proceedings of the IEEE-WACV, 1998, pp. 8–14Google Scholar
  5. [5]
    Y. Kuno, T. Watanable, Y. Shimosakoda, S. Nakagawa: Automated detection of human for visual surveillance system, Proceedings of ICPR, 1996, pp. 865–869Google Scholar
  6. [6]
    M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio “Pedestrian Detection using wavelet templates” In CVPR97, pp. 193–199, 1997Google Scholar
  7. [7]
    C. Papageorgiou and T. Poggio, A trainable System for Object Detection, International. Journal of Computer Vision,vol.38, no.1, pp. 15–33 (2000)zbMATHCrossRefGoogle Scholar
  8. [8]
    M. Leo, G. Attolico, A. Branca, A. Distante: Object classification with multiresolution wavelet decomposition, in Proc. of SPIE Aerosense 2002, conference on Wavelet Applications, 1—5 April, 2002, Orlando, Florida, USAGoogle Scholar
  9. [9]
    I. Haritaoglu, D. Harwood, L. Davis: W4: real time surveillance of people and their activities, IEEE Trans. Pattern Anal. and Mach. Intell. 22 8 (2000), pp. 809–830CrossRefGoogle Scholar
  10. [10]
    P. Spagnolo, A. Branca, G. Attolico, A. Distante: Fast Background Modeling and Shadow Removing for Outdoor Surveillance, in Proc. of IASTED VIIP 2002, 9–12 September, 2002, Malaga, SpainGoogle Scholar
  11. [11]
    A. Mohan, C. Papageorgiou, T. Poggio: Example-based Object Detection in Images by Components, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.23, No.4, April 2001Google Scholar
  12. [12]
    L. Zhao, C. Thorpe: Stereo and Neural Network based Pedestrian Detection, IEEE Transaction on Intelligent Transportation Systems, Vol.1, N. 3, September 2000Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • M. Leo
    • 1
  • P. Spagnolo
    • 1
  • G. Attolico
    • 1
  • A. Distante
    • 1
  1. 1.Istituto di Studi sui Sistemi Intelligenti per l’Automazione - C.N.R.BariITALY

Personalised recommendations