Abstract
This paper addresses the diagnosis of interactions between pairs of pedestrians in outdoor scenes, using a generative model for the trajectories. It is assumed that pedestrians’ motions are driven by a set of velocity fields, learned from the video signal. This model is extended to account for the interaction among pedestrians, using attractive/repulsive velocity components. An inference algorithm is provided to estimate the attraction/repulsion velocity from the pedestrian trajectory and characterize pedestrians’ interaction. Since we consider multiple motion models switched according to space-varying probabilities, inference is performed by combining a data association filter with a HMM-like forward algorithm. The proposed algorithm is denoted I-PDAF and is tested with synthetic data and pedestrians trajectories.
This work was supported by FCT in the framework of contract PTDC/EEA-CRO/098550/2008, PEst-OE/EEI/LA0009/2011 and PEst-OE/EEI/LA0021/2011.
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
Duong, T., Bui, H., Phung, D., Venkatesh, S.: Activity recognition and abnormality detection with the switching hidden semi-markov model. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 838–845 (2005)
Li, B., Ayazoglu, M., Mao, T., Camps, O., Sznaier, M.: Activity recognition using dynamic subspace angles. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3193–3200 (2011)
Nascimento, J., Marques, J., Lemos, J.: Modeling and classifying human activities from trajectories using a class of space-varying parametric motion fields. IEEE Transactions on Image Processing 22, 2066–2080 (2013)
Oliver, N., Rosario, B., Pentland, A.: A bayesian computer vision system for modeling human interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 831–843 (2000)
Nascimento, J., Figueiredo, M., Marques, J.: Activity recognition using a mixture of vector fields. IEEE Transactions on Image Processing 22, 1712–1725 (2013)
Bar-Shalom, Y., Daum, F., Huang, J.: The probabilistic data association filter. IEEE Control Systems 29, 82–100 (2009)
Nascimento, J., Marques, J.: Robust shape tracking in the presence of cluttered background. IEEE Transactions on Multimedia 6, 852–861 (2004)
Kalman, R.E.: A new approach to linear filtering and prediction problems. Transactions of the ASME–Journal of Basic Engineering 82 Series D, 35–45 (1960)
Portêlo, A., Ribeiro, R., Figueiredo, M., Lemos, J.M., Marques, J.S.: A velocity field approach to the detection of pedestrian interactions. In: 2013 21st Mediterranean Conference on Control and Automation, MED 2013 (2013)
Rabiner, L.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77, 257–286 (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ribeiro, R.A., Marques, J.S., Lemos, J.M. (2013). A Multiple Velocity Fields Approach to the Detection of Pedestrians Interactions Using HMM and Data Association Filters. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2013. Lecture Notes in Computer Science, vol 8033. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41914-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-41914-0_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41913-3
Online ISBN: 978-3-642-41914-0
eBook Packages: Computer ScienceComputer Science (R0)