Abstract
In the context of intelligent vehicles, we perform a comparative study on recursive Bayesian filters for pedestrian path prediction at short time horizons (< 2s). We consider Extended Kalman Filters (EKF) based on single dynamical models and Interacting Multiple Models (IMM) combining several such basic models (constant velocity/acceleration/turn). These are applied to four typical pedestrian motion types (crossing, stopping, bending in, starting). Position measurements are provided by an external state-of-the-art stereo vision-based pedestrian detector. We investigate the accuracy of position estimation and path prediction, and the benefit of the IMMs vs. the simpler single dynamical models. Special care is given to the proper sensor modeling and parameter optimization. The dataset and evaluation framework are made public to facilitate benchmarking.
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
Barth, A., Franke, U.: Estimating the driving state of oncoming vehicles from a moving platform using stereo vision. IEEE Trans. ITS 10(4), 560–571 (2009)
Bertozzi, M., et al.: Pedestrian localization and tracking system with Kalman filtering. In: IEEE Intell. Veh., pp. 584–589 (2004)
Binelli, E., et al.: A modular tracking system for far infrared pedestrian recognition. In: IEEE Intell. Veh., pp. 759–764 (2005)
Blackman, S., Popoli, R.: Design and Analysis of Modern Tracking Systems. Artech House Norwood, MA (1999)
Burlet, J., et al.: Pedestrian tracking in car parks: An adaptive Interacting Multiple Models based filtering method. In: Proc. of the IEEE ITSC, pp. 462–467 (2006)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR, vol. 1, pp. 886–893. IEEE (2005)
Dollár, P., et al.: Pedestrian detection: An evaluation of the state of the art. IEEE PAMI 34(4), 743–761 (2012)
Enzweiler, M., Gavrila, D.: Monocular pedestrian detection: Survey and experiments. IEEE PAMI 31(12), 2179–2195 (2009)
Fardi, B., Scheunert, U., Wanielik, G.: Shape and motion-based pedestrian detection in IR images: a multisensor approach. In: IEEE Intell. Veh., pp. 18–23 (2005)
Hirschmüller, H.: Stereo processing by semiglobal matching and mutual information. IEEE PAMI 30(2), 328–341 (2008)
Keller, C.G., Hermes, C., Gavrila, D.M.: Will the pedestrian cross? Probabilistic path prediction based on learned motion features. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 386–395. Springer, Heidelberg (2011)
Köhler, S., et al.: Early detection of the pedestrians intention to cross the street. In: Proc. of the IEEE ITSC, pp. 1759–1764 (2012)
Li, X.R., Jilkov, V.P.: Survey of maneuvering target tracking. Part V. Multiple-model methods. IEEE Trans. Aerosp. Electron. Syst. 41(4), 1255–1321 (2005)
Li, X.R., Jilkov, V.: Survey of maneuvering target tracking. Part I. Dynamic models. IEEE Trans. Aerosp. Electron. Syst. 39(4), 1333–1364 (2003)
Meuter, M., et al.: Unscented Kalman filter for pedestrian tracking from a moving host. In: IEEE Intell. Veh., pp. 37–42 (2008)
Rabe, C.: Detection of Moving Objects by Spatio-Temporal Motion Analysis. Ph.D. thesis, University of Kiel, Kiel, Germany (2011)
Särkkä, S., Hartikainen, J., Solin, A.: EKF/UKF toolbox for Matlab v1.3 (2011), http://becs.aalto.fi/en/research/bayes/ekfukf/
Scheunert, U., et al.: Multi sensor based tracking of pedestrians: a survey of suitable movement models. In: IEEE Intell. Veh., pp. 774–778 (2004)
Tao, J., Klette, R.: Tracking of 2d or 3d irregular movement by a family of Unscented Kalman filters. JICCE 10(3), 307–314 (2012)
Welch, G., Bishop, G.: An introduction to the Kalman filter. In: Proc. of the ACM SIGGRAPH. ACM Press, Addison-Wesley, Los Angeles, CA (2001)
Westhofen, D., et al.: Transponder- and camera-based advanced driver assistance system. In: IEEE Intell. Veh., pp. 293–298 (2012)
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
Schneider, N., Gavrila, D.M. (2013). Pedestrian Path Prediction with Recursive Bayesian Filters: A Comparative Study. In: Weickert, J., Hein, M., Schiele, B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40602-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-40602-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40601-0
Online ISBN: 978-3-642-40602-7
eBook Packages: Computer ScienceComputer Science (R0)