Multi-object tracking driven event detection for evaluation

ABSTRACT

This paper describes a monocular object tracker, able to detect and track multiple object classes in non-controlled environments. Our tracking framework uses Bayesian per-pixel classification to segment an image into foreground and background objects, based on observations of object appearances and motions in real-time. Furthermore, semantically high level events are automatically extracted from the tracking data for performance evaluation. The reliability of the event detection is demonstrated by applying it to state-of-the-art methods and comparing the results to human annotated ground truth data for multiple public datasets.

REFERENCES

• 1: P. Duizer and D. Hansen. Multi-view video surveillance of outdoor traffic (master thesis). In Digital Project Library, Aalborg University, Denmark, August 2007.
• 2: J. González, F. X. Roca, and J. J. Villanueva. Hermes: A research project on human sequence evaluation. In Computational Vision and Medical Image Processing (VipIMAGE'2007), October 2007.
• 3: http://www.ee.ethz.ch/bleibe/data/datasets.html. Central pedestrian crossing: Dataset.
• 4: M. Isard and J. MacCormick. Bramble: A bayesian multiple-blob tracker. In ICCV, pages 34--41, Los Alamitos, CA, USA, 2001. IEEE Computer Society.
• 5: Oswald Lanz, Approximate Bayesian Multibody Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.28 n.9, p.1436-1449, September 2006 [doi>10.1109/TPAMI.2006.177]
• 6: B. Leibe, K. Schindler, and L. Van Gool. Coupled detection and trajectory estimation for multi-object tracking. In International Conference on Computer Vision (ICCV'07), October 2007.
• 7: Thomas B. Moeslund , Adrian Hilton , Volker Krüger, A survey of advances in vision-based human motion capture and analysis, Computer Vision and Image Understanding, v.104 n.2, p.90-126, November 2006 [doi>10.1016/j.cviu.2006.08.002]
• 8: Daniel Roth , Petr Doubek , Luc Van Gool, Bayesian Pixel Classification for Human Tracking, Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2, p.78-83, January 05-07, 2005 [doi>10.1109/ACVMOT.2005.34]
• 9: D. Roth, E. Koller-Meier, D. Rowe, T. Moeslund, and L. Van Gool. Event-based tracking evaluation metric. In IEEE Workshop on Motion and Video Computing (WMVC), January 2008.
• 10: D. Rowe, I. Reid, J. González, and J. Villanueva. Unconstrained Multiple-people Tracking. In 28th DAGM, Berlin, Germany, pages 505--514. Springer LNCS, 2006.
• 11: C. Stauffer and W. Grimson. Adaptive background mixture models for real-time tracking. In CVPR, pages 246--252, 1999.
• 12: Bo Wu , Ram Nevatia, Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection, Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.951-958, June 17-22, 2006 [doi>10.1109/CVPR.2006.312]
• 13: Tao Zhao , Manoj Aggarwal , Rakesh Kumar , Harpreet Sawhney, Real-Time Wide Area Multi-Camera Stereo Tracking, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1, p.976-983, June 20-26, 2005 [doi>10.1109/CVPR.2005.296]
• 14: T. Zhao and R. Nevatia. Bayesian human segmentation in crowded situations. In CVPR, pages 459--466, 2003.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.m Miscellaneous

General Terms:
Algorithms, Experimentation

Keywords:
event detection, performance evaluation, real-time, tracking