Segmenting Images of Occluded Humans Using a Probabilistic Neural Network

  • Yongtae Do
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4113)


When processing an image of multiple occluded humans, segmenting them is a prerequisite for higher-level tasks such as tracking and activity analysis. Although a human observer can easily segment target humans partly occluded among themselves in an image, automatic segmentation in computer vision is difficult. In this paper, the use of a probabilistic neural network is proposed to learn various outline shape patterns of a foreground image blob of occluded humans, and then to segment the blob into its constituents. The segmentation is here regarded as a two-class pattern recognition problem; segmentable positions constitute a class and other positions constitute the other. The technique proposed is useful particularly for low-resolution images where existing image analysis techniques are difficult to be applied.


Probabilistic Neural Network Bayesian Classifier Pattern Recognition Problem Foreground Image Summation Layer 
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.
    Collins, R.T., Lipton, A.J., Fujiyoshi, H., Kanade, T.: Algorithms for Cooperative Multisensor Surveillance. Proc. IEEE 89, 1456–1477 (2001)CrossRefGoogle Scholar
  2. 2.
    Collins, R.T., Lipton, A.J., Kanade, T.: Introduction to the Special Section on Video Surveillance. IEEE Trans. Pattern Analysis and Machine Intelligence 22, 745–746 (2000)CrossRefGoogle Scholar
  3. 3.
    Zhao, T., Nevatia, R., Fengjun, L.: Segmentation and Tracking of Multiple Humans in Complex Situations. In: Proc. Computer Vision and Pattern Recognition, vol. II, pp. 194–201 (2001)Google Scholar
  4. 4.
    Lipton, A.J., Fujiyoshi, H., Patil, R.S.: Moving Target Classification and Tracking from Real-Time Video. In: Proc. IEEE Workshop on Application of Computer Vision, pp. 8–14 (1998)Google Scholar
  5. 5.
    Grimson, W.E.L., Stauffer, C., Romano, R., Lee, L.: Using Adaptive Tracking to Classify and Monitor Activities in a Site. In: Proc. IEEE Computer Vision and Pattern Recognition, pp. 22–29 (1998)Google Scholar
  6. 6.
    Sindhu, A.J., Morris, T.: A Region Based Approach to Tracking People before, during, and after Occlusions. In: Proc. IASTED Int. Conf. Visualization, Imaging, and Image Processing (2004)Google Scholar
  7. 7.
    Heikkila, J., Silven, O.: A Real-Time System for Monitoring Cyclists and Pedestrians. In: Proc. IEEE Workshop on Visual Surveillance, pp. 74–81 (1999)Google Scholar
  8. 8.
    Specht, D.F.: Probabilistic Neural Networks for Classification, Mapping, or Associate Memory. In: Proc. IEEE Int. Conf. Neural Networks, vol. 1, pp. 525–532 (1988)Google Scholar
  9. 9.
    Anderson, C., Burt, P., van der Wal, G.: Change Detection and Tracking Using Pyramid Transformation Techniques. In: Proc. SPIE, vol. 579, pp. 72–78 (1985)Google Scholar
  10. 10.
    Barron, J., Fleet, D., Beauchemin, S.: Performance of Optical Flow Techniques. Int. Journal of Computer Vision 12, 42–77 (1994)CrossRefGoogle Scholar
  11. 11.
    Becanovic, V., Hosseiny, R., Indiveri, G.: Object Tracking Using Multiple Neuromorphic Vision Sensors. In: Proc. RoboCup, pp. 426–433 (2004)Google Scholar
  12. 12.
    Parzen, E.: On Estimation of a Probability Density Function and Mode. Annals of Mathematical Statistics 33, 1065–1076 (1962)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Goh, A.T.C.: Probabilistic Neural Network for Evaluating Seismic Liquefaction Potential. Canadian Geotechnical Journal 39, 219–232 (2002)CrossRefGoogle Scholar
  14. 14.
    Specht, D.F.: Probabilistic Neural Networks. Neural Networks 3, 109–118 (1990)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yongtae Do
    • 1
  1. 1.School of Electronic EngineeringDaegu UniversityGyeongsan-CitySouth Korea

Personalised recommendations