Grzegorz Cielniak, Tom Duckett and Achim J. Lilienthal
Improved Data Association and Occlusion Handling for Vision-Based People Tracking by Mobile Robots
Proc. IEEE Int. Conf. On Intelligent Robots and Systems (IROS), 2007, pp. 3436-3441
Abstract: This paper presents an approach for tracking multiple persons using a combination of colour and thermal vision sensors on a mobile robot. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is then incorporated into the tracker.
Download:
Paper: [PDF (0.7MB)]
Digest: [PDF (0.1MB)]
Bibtex:
@INPROCEEDINGS{Cielniak_etal:IROS:2007,
  AUTHOR = {Cielniak, Grzegorz and Duckett, Tom and Lilienthal, Achim J.},
  TITLE = {Improved Data Association and Occlusion Handling for Vision-Based People Tracking by Mobile Robots},
  BOOKTITLE = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  YEAR = {2007},
  MONTH = {October 29 -- November 2},
  ADRESS = {San Diego, USA},
  PAGES = {3436--3441}
}