Classifying and Counting Vehicles in Traffic Control Applications
This paper presents a machine learning system to handle traffic control applications. The input of the system is a set of image sequences coming from a fixed camera. The system can be divided into two main subsystems: the first one, based on Artificial Neural Networks classifies the typology of vehicles moving within a limited image area for each frame of the sequence; the second one, based on Genetic Algorithms, takes as input the frame-by-frame classifications and reconstructs the global traffic scenario by counting the number of vehicles of each typology. This task is particularly hard when the frame rate is low. The results obtained by our system are reliable even for very low frame rate (i.e. four frames per second). Our system is currently used by a company for real-time traffic control.
KeywordsGenetic Algorithm Hide Markov Model Image Sequence Feed Forward Neural Network Probabilistic Neural Network
Unable to display preview. Download preview PDF.
- 1.Papanikolopoulos, N., Wahlstrom, E., Masoud, O.: Monitoring driver activities, Report no. CTS 04-05. Intelligent Transportation Systems Institute. Internal Report (2004), http://www.its.umn.edu/research/complete.html
- 2.Eikvil, L., Huseby, R.B.: Traffic surveillance in real-time using hidden markov models. In: Scandinavian Conference on Image Analysis, SCIA 2001 (2001), http://citeseer.ist.psu.edu/eikvil01traffic.html
- 3.Giuliano, G., Heidemann, J., Hu, M., Silva, F., Wang, X.: Rapidly deployable sensors for vehicle counting and classification. Internal report of the I-LENSE: ISI Laboratory for Embedded Networked Sensor Experimentation (2004)Google Scholar
- 6.Holland, J.H.: Adaptation in Natural and Artificial Systems. The University of Michigan Press, Ann Arbor (1975)Google Scholar
- 7.Hourdakis, J., Morris, T., Michalopoulos, P., Wood, K.: Advanced portable wireless measurement and observation station, Report no. CTS 05-07. Intelligent Transportation Systems Institute. Internal Report (2005), http://www.its.umn.edu/research/complete.html
- 8.Kwigizile, V., Selekwa, M.F., Mussa, R.: Highway vehicle classification by probabilistic neural networks. In: Barr, V., Markov, Z. (eds.) Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, Miami Beach, Florida, USA. AAAI Press, Menlo Park (2004)Google Scholar
- 9.ALVARADO Manufacturing. Computerized vehicle counting system, Internal report (2005)Google Scholar
- 11.Oja, E.: Principal component analysis. In: Arbib, M.A. (ed.) Handbook of Brain Theory and Neural Networks, pp. 753–756. MIT Press, Cambridge (1995)Google Scholar
- 12.Ricerche, C.M.: Reti neurali per la classificazione di immagini e il riconoscimento di veicoli, Status Report Progetto Comerson. Internal Report (2005)Google Scholar
- 13.Vanneschi, L., Archetti, F.: Resolving temporal sequences for traffic control applications with genetic algorithms. In: Talbi, E.-G., Liardet, P., Collet, P., Lutton, E., Schoenauer, M. (eds.) EA 2005. LNCS, vol. 3871. Springer, Heidelberg (2006)Google Scholar