Abstract
This paper presents a solution to the problem of tracking people within crowded scenes. The aim is to maintain individual object identity through a crowded scene which contains complex interactions and heavy occlusions of people. Our approach uses the strengths of two separate methods; a global object detector and a localised frame by frame tracker. A temporal relationship model of torso detections built during low activity period, is used to further disambiguate during periods of high activity. A single camera with no calibration and no environmental information is used. Results are compared to a standard tracking method and groundtruth. Two video sequences containing interactions, overlaps and occlusions between people are used to demonstrate our approach. The results show that our technique performs better that a standard tracking method and can cope with challenging occlusions and crowd interactions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multi-Camera People Tracking with a Probabilistic Occupancy Map. IEEE Transactions on Pattern Analysis and Machine Intelligence (to be published, 2007)
Khan, S., Javed, O., Shah, M.: Tracking in Uncalibrated Cameras with Overlapping Fields of View. In: 2nd IEEE Workshop on Performance Evaluation of Tracking and Surveillance, IEEE Computer Society Press, Los Alamitos (2001)
Isard, M., MacCormick, J.: Brammble: A Bayesian Multiple Blob Tracker. In: Proc. IEEE International Conference on Computer Vision and Pattern Reconition, vol. 2, pp. 34–41 (2001)
Bose, B., Wang, X., Grimson, E.: Detecting and Tracking Multiple Interacting Objects Without Class-Specifc Models. Technical report MIT-CSAIL-TR-2006-027 Massachusetts Institute of Technology (2006)
Okuma, K., Taleghani, A., DeFreitas, N., Little, J., Lowe, D.: A Boosted Particle Filter. In: Proc. European Conference on Computer Vision (2004)
Welch, G., Bishop, G.: An Introduction to the Kalman Kilter. Technical Report 95-041, University of North Carolina at Chapel Hill (1995)
Xu, M., Orwell, J., Jones, G.: Tracking Football Players with Multiple Cameras. In: IEEE International Conference on Image Processing, IEEE Computer Society Press, Los Alamitos (2004)
Boykov, Y., Huttenlocher, D.: Adaptive Bayesian Recognition in Tracking Rigid Objects. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 697–704. IEEE Computer Society Press, Los Alamitos (2000)
Giebel, J., Gavrilla, D., Schnorr, C.: A Bayesian Framework for Multi-cue 3d Object Tracking. In: Proc. European Conference on Computer Vision (2004)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-Based Object Tracking. IEEE Transactions Pattern Analysis and Machine Intelligence 25, 564–577 (2003)
Nillius, P., Sullivan, J., Carlsson, S.: Multi-Target Tracking - Linking Identities using Bayesian Netweork Inference. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2006)
Perez, P., Hue, C., Vermaak, J., Gannet, M.: Color-Based Probabilistic Tracking. In: Proc. European Conference on Computer Vision (2002)
Mikolajczyk, K., Leibe, B., Schiele, B.: Multiple Object Class Detection with a Generative Model. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2006)
CAVIAR: Context Aware Vision using Image-based Active Recognition, EC project/ist 2001 37540, http://homepages.inf.ed.ac.uk/rbf/CAVIAR/
PETS: Performance Evaluation of Tracking and Surveillance, http://www.cvgcs.rdg.ac.uk/slides/pets.html
Crowded groundtruthed video sequnces, http://personal.ee.surrey.ac.uk/Personal/a.gilbert
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gilbert, A., Bowden, R. (2007). Multi Person Tracking Within Crowded Scenes. In: Elgammal, A., Rosenhahn, B., Klette, R. (eds) Human Motion – Understanding, Modeling, Capture and Animation. HuMo 2007. Lecture Notes in Computer Science, vol 4814. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75703-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-75703-0_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75702-3
Online ISBN: 978-3-540-75703-0
eBook Packages: Computer ScienceComputer Science (R0)