Moving horizon estimation of pedestrian interactions using multiple velocity fields
- 226 Downloads
This paper describes a model, and algorithms based on it, for the analysis of pedestrian interactions in outdoor scenes. Pedestrian activities are described by their trajectories in the scene, and we wish to know if they were independently generated or if they are correlated. Two models are considered: (i) a model based on multiple velocity fields recently proposed in Nascimento et al. (IEEE Trans Image Process 22(5):1712–1725, 2013) and (ii) an interaction model based on the attraction/repulsion between pairs of pedestrians. Several combinations of these models are studied and evaluated. An estimation method based on a moving horizon optimization of a quadratic cost functional is proposed. Experimental results with synthetic data and real video data are presented to assess the performance of the algorithms.
KeywordsHuman activity recognition Trajectory analysis Probabilistic models
This work was supported by FCT in the framework of contract PTDC/EEA-CRO/098550/2008, PEst-OE/ EEI/LA0009/2013, and PEst-OE/EEI/LA0021/2013.
- 1.Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. (CSUR) Surv. Homepage Arch. 43(3) (2011)Google Scholar
- 5.Ntalampiras, S., Arsic, D., Hofmann, M., Andersson, M., Ganchev, T.: PROMETHEUS: Heterogeneous Sensor Database in Support of Human Behavioral Patterns in Unrestricted Environments. Signal, Image and Video Processing. Springer (2012) Google Scholar
- 6.Mahbub, U., Imtiaz, H., Ahad, A.R.: Action recognition based on statistical analysis from clustered flow vectors. Signal, Image and Video Processing. Springer (2013)Google Scholar
- 8.Nascimento, J., Marques, J., Figueiredo, M.A.T.: Classification of complex pedestrian activities from trajectories. IEEE International Conference Image Processing, pp. 3481–3484 (2010)Google Scholar
- 11.Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: IEEE International Conf. on Computer Vision and Pattern Recognition, pp. 935–942 (2009)Google Scholar
- 12.Zhang, Y., Qin, L., Yao, H., Huang, Q.: Abnormal crowd behavior detection based on social attribute-aware force model. In: IEEE Internatinal Conference Image Processing, pp. 2689–2692 (2012)Google Scholar
- 14.Okazaki, S.: A study of pedestrian movement in architectural space, part 1: pedestrian movement by the application on of magnetic models. Trans. A.I.J 283, 111–119 (1979)Google Scholar
- 15.Luber, M., Stork, J., Tipaldi, G., Arras, K.O.: People tracking with human motion predictions from social forces. In: IEEE Conference on ICRA, pp. 464–469 (2010)Google Scholar
- 16.Liu, X., Chua, C.: Multi-agent activity recognition using observation decomposed hidden markov models. Image Vis. Comput. 24, 166–175 (2006)Google Scholar