Advertisement

People Detection Using Multiple Sensors on a Mobile Robot

  • Zoran Zivkovic
  • Ben Kröse
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 8)

This chapter considers the important problem of dealing with multiple sensors. An approach for combining information from multiple sensors for people detection on a mobile robot is described. A person will be represented by a constellation of body parts. Person body parts are detected and the parts are constrained to be at certain positions with respect to each other. Similar part based representations are widely used in the computer vision area for describing objects in images. A probabilistic model is presented here to combine part detections from multiple sensors typical for mobile robots. For detecting the body parts specific detectors can be constructed in many ways. In this chapter the Ada-Boost [7] is used as a general ”out of box” approach for building the part detectors.

The chapter starts with the related work which is presented in Section 3.2. Next, in Section 3.3 people detection using 2D laser range scanner is considered. Persons legs can be detected in the scans. A probabilistic part-based representation is presented that takes into account the spatial arrangement of the detected legs. The method is inspired by the latest results on the ”part-based representations” from the computer vision area and the work of Weber, Perona and colleagues [21, 5]. The approach takes into account that the leg detector might produce false detections or fail to detect legs, for example because of partial occlusion. Section 3.4 describes a straightforward way to extend the presented probabilistic model to properly combine body parts detected using other sensors that might be present on the robot, a pan-tilt camera and an omnidirectional camera in our case, see Figure 3.1. Evaluation of the proposed model and some practical issues are discussed in Section 3.5. Finally, the conclusions are given in Section 3.6.

Keywords

Mobile Robot False Detection Multiple Sensor Part Detector Human Body Part 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Breazeal, C.: Designing sociable robots. MIT Press, Cambridge (2002)Google Scholar
  2. 2.
    Burl, M., Leung, T., Perona, P.: Recognition of planar object classes. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (1996)Google Scholar
  3. 3.
    Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2005)Google Scholar
  4. 4.
    Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. Intl. Journal of Computer Vision 61(1), 55-79 (2005)CrossRefGoogle Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2003)Google Scholar
  6. 6.
    Ferryman, J., Crowley, J. (eds.): Proc. of the 9th IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance (2006)Google Scholar
  7. 7.
    Friedman, J.H., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Technical Report, Dept. of Statistics, Stanford University (1998)Google Scholar
  8. 8.
    Gavrila, D., Philomin, V.: Real-time object detection for smart vehicles. In Proc. of the Intl. Conf. on Computer Vision (1999)Google Scholar
  9. 9.
    Giebel, J., Gavrila, D., Schnrr, C.: A Bayesian framework for multi-cue 3D object tracking. In Proc. of the European Conf. on Computer Vision (2004)Google Scholar
  10. 10.
    Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2006)Google Scholar
  11. 11.
    Arras, K., Mozos, O., Burgard, W.: Using boosted features for detection of people in 2D range scans. In Proc. of the IEEE Intl. Conf. on Robotics and Automation (2007)Google Scholar
  12. 12.
    Kruppa, H., Castrillon-Santana, M., Schiele, B.: Fast and robust face finding via local context. In: Proc of the IEEE Intl. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (2003)Google Scholar
  13. 13.
    Schulz, D., Burgard, W., Fox, D., Cremers, A.: People tracking with a mobile robot using sample-based joint probabilistic data association filters. International Journal of Robotics Research 22(2), 99-116 (2003)Google Scholar
  14. 14.
    Seemann, E., Leibe, B., Mikolajczyk, K., Schiele, B.: An evaluation of local shape-based features for pedestrian detection. In Proc. of the British Machine Vision Conference (2005)Google Scholar
  15. 15.
    Munder, S., Gavrila, D.M.: An experimental study on pedestrian classification. IEEE Trans. on Pattern Analysis and Machine Intelligence 28(11), 1863-1868 (2006)CrossRefGoogle Scholar
  16. 16.
    Fong, T., Nourbakhsh, I., Dautenhahn, K.: A survey of socially interactive robots. Robots and Autonomous Systems 42, 143-166 (2003)MATHCrossRefGoogle Scholar
  17. 17.
    Treptow, A., Cielniak, G., Duckett, T.: Real-time people tracking for mobile robots using thermal vision. Robotics and Autonomous Systems 54(9), 729-739 (2006)CrossRefGoogle Scholar
  18. 18.
    Tuzel, O., Porikli, F., Meer, P.: Human detection via classification on riemannian manifolds. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2007)Google Scholar
  19. 19.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2001)Google Scholar
  20. 20.
    Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In Proc. of the Intl. Conf. on Computer Vision (2003)Google Scholar
  21. 21.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In Proc. of the European Conf. on Computer Vision (2000)Google Scholar
  22. 22.
    Wu, B., Nevatia, R.: Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In Proc. of the Intl. Conf. on Computer Vision (2005)Google Scholar
  23. 23.
    Zajdel, W., Zivkovic, Z., Kr öse, B.: Keeping track of humans: have I seen this person before? In Proc. of the IEEE Intl. Conf. on Robotics and Automation (2005)Google Scholar
  24. 24.
    Zivkovic, Z., Kr öse, B.: Part based people detection using 2D range data and images. In Proc. of the IEEE/RSJ Intl. Conf. Robots and Autonomous Systems (IROS) (2007)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Zoran Zivkovic
    • 1
  • Ben Kröse
    • 1
  1. 1.ISLA LabUniversity of AmsterdamNetherlands

Personalised recommendations