Abstract
The estimation of the 3D trajectory, the class and the dimensions of a vehicle represents three relevant tasks for traffic monitoring. They are usually performed by separate sub-systems and only few existing algorithms cope with the three tasks at the same time. However, if these tasks are integrated, the trajectory estimation enforces the classification with temporal consistency, and at the same time, the estimation of the vehicle class and dimensions can be used to increase the trajectory estimate accuracy. In this work, we propose an algorithm to estimate the 3D trajectory, the class and the dimensions of vehicles simultaneously by means of a Backward-Simulation Particle Smoother whose state contains both continuous (vehicle pose and dimensions), and discrete (vehicle class) quantities. To integrate the class estimate in the Particle Smoother we model the class prediction as a Markov Chain. We performed experimental tests on both simulated and real datasets; they show that the pose and dimension estimation reaches centimeter-accuracy and the classification accuracy is higher than 95 %.
Similar content being viewed by others
Notes
PETS 2000: First IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.
References
Arulampalam, M., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. Signal Process. IEEE Trans. 50(2), 174–188 (2002). doi:10.1109/78.978374
Bar-Shalom, Y., Li, X.R., Kirubarajan, T.: Estimation with Applications to Tracking and Navigation: Theory Algorithms and Software. Wiley, New York (2001)
Buch, N., Orwell, J., Velastin, S.A.: 3d extended histogram of oriented gradients (3dhog) for classification of road users in urban scenes (2009)
Buch, N., Orwell, J., Velastin, S.A.: Urban road user detection and classification using 3d wire frame models. IET Comput. Vis. 4(2), 105–116 (2010)
Buch, N., Velastin, S., Orwell, J.: A review of computer vision techniques for the analysis of urban traffic. Intell. Transp. Syst. IEEE Trans. 12(3), 920–939 (2011). doi:10.1109/TITS.2011.2119372
Buch, N., Yin, F., Orwell, J., Makris, D., Velastin, S.: Urban vehicle tracking using a combined 3D model detector and classifier. In: Velásquez, J., Ríos, S., Howlett, R., Jain, L.: (eds.) Knowledge-Based and Intelligent Information and Engineering Systems, Lecture Notes in Computer Science, vol. 5711, pp. 169–176. Springer, Berlin (2009). doi:10.1007/978-3-642-04595-0_21
Godsill, S.J., Doucet, A., West, M.: Monte carlo smoothing for nonlinear time series. J. Am. Stat. Assoc. 99, 465 (2004)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, vol. 2. Cambridge University Press, Cambridge (2000)
Huber, P.J.: Robust Statistics. Springer, New York (2011)
Johansson, B., Wiklund, J., Forssén, P., Granlund, G.: Combining shadow detection and simulation for estimation of vehicle size and position. Pattern Recognit. Lett. 30(8), 751–759 (2009). doi:10.1016/j.patrec.2009.03.005
Koller, D., Daniilidis, K., Nagel, H.H.: Model-based object tracking in monocular image sequences of road traffic scenes. Int. J. Comput. Vis. 10, 257–281 (1993). doi:10.1007/BF01539538
Lai, A., Fung, G., Yung, N.: Vehicle type classification from visual-based dimension estimation. In: Proceedings of Intelligent Transportation Systems 2001, IEEE, pp. 201–206 (2001)
Lepetit, V., Fua, P.: Monocular model-based 3D tracking of rigid objects: a survey, vol. 1. In: Proceedings of Foundations and Trends in Computer Graphics and Vision, pp. 1–89 (2005)
Lou, J., Tan, T., Hu, W.: Visual vehicle tracking algorithm. Electron. Lett. 38(18), 1024–1025 (2002)
Lou, J., Tan, T., Hu, W., Yang, H., Maybank, S.: 3-D model-based vehicle tracking. Image Process. IEEE Trans. 14(10), 1561–1569 (2005)
Marslin, R., Sullivan, G.D., Baker, K.: Kalman filters in constrained model-based tracking. Proc. British Mach. Vis. Conf. 1991, 371–374 (1991)
Matteucci, M., Rizzi, D., Romanoni, A., Mussone, L.: 3d image processing of vehicular trajectories in roundabouts. In: Proceedings of World Conference on Transportation Research, pp. 1–11 (2013). http://www2.wctr2013rio.com/publications/1077/index.html
Messelodi, S., Modena, C., Zanin, M.: A computer vision system for the detection and classification of vehicles at urban road intersections. Pattern Anal. Appl. 8, 17–31 (2005). doi:10.1007/s10044-004-0239-9
Messelodi, S., Modena, C.M., Zanin, M.: A computer vision system for the detection and classification of vehicles at urban road intersections. Pattern Anal. Appl. 8(1–2), 17–31 (2005)
Migliore, D.A., Matteucci, M., Naccari, M.: A revaluation of frame difference in fast and robust motion detection. In: Proceedings of the 4th ACM International Workshop on Video Surveillance and Sensor Networks, ACM, pp. 215–218 (2006)
Mussone, L., Matteucci, M., Bassani, M., Rizzi, D.: An innovative method for the analysis of vehicle movements in roundabouts based on image processing. J. Adv. Transp. (2011)
Mussone, L., Matteucci, M., Bassani, M., Rizzi, D.: Traffic analysis in roundabout intersections by image processing. In: Proceedings of the 18th IFAC World Congress, vol. 18, pp. 14922–14927 (2011)
Neal, R.M.: Probabilistic inference using markov chain monte carlo methods (1993)
Pang, C., Lam, W., Yung, N.: A method for vehicle count in the presence of multiple-vehicle occlusions in traffic images. Intell. Transp. Syst. IEEE Trans. 8(3), 441–459 (2007)
Piccardi, M.: Background subtraction techniques: a review. In: Proceedings of Systems, Man and Cybernetics, 2004 IEEE International Conference vol. 4, pp. 3099–3104 (2004). doi:10.1109/ICSMC.2004.1400815
Romanoni, A.: Ricostruzione 3d delle traiettorie veicolari da immagini di una o più telecamere (2012). M.Sc. Thesis (in Italian)
Romanoni, A., Matteucci, M., Sorrenti, D.: Background subtraction by combining temporal and spatio-temporal histograms in the presence of camera movement. Mach. Vis. Appl. 25(6), 1573–1584 (2014). 10.1007/s00138-013-0587-9
Romanoni, A., Mussone, L., Rizzi, D., Matteucci, M.: A comparison of two monte carlo algorithms for 3d vehicle trajectory reconstruction in roundabouts. Pattern Recognit. Lett. 51(0), 79–85 (2015). doi:10.1016/j.patrec.2014.09.003
Salih, Y., Malik, A.S.: Comparison of stochastic filtering methods for 3D tracking. Pattern Recognit. 44(10–11), 2711–2737 (2011). (Comparison among filters)
Särkkä, S.: Bayesian Filtering and Smoothing, vol. 3. Cambridge University Press, Cambridge (2013)
Song, X., Nevatia, R.: Detection and tracking of moving vehicles in crowded scenes. In: Proceedings of Motion and Video Computing, 2007, IEEE Workshop on WMVC ’07, p. 4 (2007). doi:10.1109/WMVC.2007.13
Tan, T., Sullivan, G., Baker, K.: Model-based localisation and recognition of road vehicles. Int. J. Comput. Vis. 27, 5–25 (1998). doi:10.1023/A:1007924428535
Zhang, Z.: A flexible new technique for camera calibration. Pattern Anal. Mach. Intell. IEEE Trans. 22(11), 1330–1334 (2000)
Zhang, Z., Tan, T., Huang, K., Wang, Y.: Three-dimensional deformable-model-based localization and recognition of road vehicles. Image Process. IEEE Trans. 21(1), 1–13 (2012). doi:10.1109/TIP.2011.2160954
Acknowledgments
This work has been partially supported by the Italian Ministry of University and Research (MIUR) through the “SMELLER” project.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Romanoni, A., Sorrenti, D.G. & Matteucci, M. Backward-Simulation Particle Smoother with a hybrid state for 3D vehicle trajectory, class and dimension simultaneous estimation. Machine Vision and Applications 26, 369–385 (2015). https://doi.org/10.1007/s00138-015-0668-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-015-0668-z