Automatic pedestrian recognition using real-time motion analysis

  • Patrick Vannoorenberghe
  • Cina Motamed
  • Jean-Marc Blosseville
  • Jack-Gérard Postaire
Poster Session D: Biomedical Applications, Detection, Control & Surveillance, Inspection, Optical Character Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)


This paper presents a real-time vision system for automatic pedestrian recognition using image sequences analysis. We first introduce a robust motion detector based on a specific background structural model. The motion detection process exploits the structural difference between the model and features extracted from the current scene. The pedestrian recognition process analyses the signal provided by the motion detector in order to separate pedestrians from other moving objects (vehicles, buses, ...). The detection signal processing consists in the extraction of several kinematics and pattern features of each classes of objects. The percentage of good pedestrian discrimination, tested with real traffic image sequences under several illumination conditions, is about 85%.


Motion Detection Vehicle Detection Pedestrian Detection Surveillance Area Urban Scene 
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. [Nag83]
    Nagel H.H.: Overview on image sequence analysis. Proc. Image Sequence Processing and Dynamic Scene Analysis, pp 2-39, 1983.Google Scholar
  2. [Hor81]
    Horn B.K.P. and Schunk: Determining Optical Flow. Artificial Intelligence, Vol. 17, 1981.Google Scholar
  3. [Jai84]
    Jain R.: Difference and accumulative difference pictures in dynamic scene analysis. Image and Vision Computer, 1984.Google Scholar
  4. [Osc82]
    Oscarsson E.: TV-Camera detecting pedestrians for traffic light control. Proceedings of IMEKO 1982, pp 275–282, 1982.Google Scholar
  5. [Dep94]
    Deparis J.P. and Duvieubourg L.: Intrusion Detection by active linear cameras. Advanced Applications in Transportation Technologies, Capri, 1994.Google Scholar
  6. [Mec94]
    Mecocci A., Bartolini F. and Cappellini V.: Image sequence analysis for counting in real time people getting in and out of a bus. Signal Processing 35, pp 105–116, 1994.CrossRefGoogle Scholar
  7. [Gla95]
    Glachet R., Bouzar S. and Lenoir F.: Estimation des flux de voyageurs dans les couloirs du métro par traitement dimages. R.T.S. N 46, Mars 1995.Google Scholar
  8. [Rou94]
    Rourke A. and Bell M.G.H.: An image-processing system for pedestrian data-collection. Proceedings of the 7th International Conference on Road Traffic Monitoring and Control, London, April 1994, pp 123–126.Google Scholar
  9. [Vel94]
    Velastin S.A., Yin J.H., Davies A.C., Vicencio-silva M.A., Allsop R.E. and Penn A.: Automated measurement of crowd density and motion using image processing. Road Traffic Monitoring and Control, 26-28 April 1994, Conference publication No. 391, * IEE, 1994.Google Scholar
  10. [Rea95]
    Reading I.A.D., Wan C.L. and Dickinson K.W.: Developments in pedestrian detection. Traffic Engineering + Control, pp 538-542, 1995.Google Scholar
  11. [Van95]
    Vannoorenberghe P., Motamed C., Blosseville J.-M. and Postaire J.-G.: Detection of intrusion using a background structural model. Computers ind. Engng, Vol. 29, No. 1-4, pp 675–679, 1995.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Patrick Vannoorenberghe
    • 1
  • Cina Motamed
    • 1
  • Jean-Marc Blosseville
    • 2
  • Jack-Gérard Postaire
    • 3
  1. 1.Laboratoire d'Analyse des Systèmes du Littoral 195Rue du Pasteur Martin Luther KingCalais CEDEXFrance
  2. 2.Institut National de Recherche sur les Transports et leur Sécurité 2Arcueil CEDEXFrance
  3. 3.Centre d'Automatique de LilleEquipe Image et Décision Université des Sciences et Technologies de LilleVilleneuve d'Ascq CEDEXFrance

Personalised recommendations