ABSTRACT
This paper presents a Laser Intensity Vehicle Classification System (LIVCS) based upon imagery obtained from range sensors (called LIVCS). Current systems that utilize loop detectors, video cameras, and range sensors have deficiencies. The loop detectors have high failure rates due to pavement failures and poor maintenance. Video based systems and range sensors do not perform well in deteriorated atmospheric conditions (such as rain and fog). The developed generations of image based range sensors offer the promise of sensors that are less sensitive to deteriorated environmental conditions. LIVCS system extracts features of laser intensity images, produced by laser sensory units. These features are used to train a random neural network (RNN). The LIVCS system recalls its trained RNN for classification of vehicles. This technique outperforms loop detectors, video cameras, and range data techniques in deteriorated environmental conditions.
- Avery, R. P., Thomas, C. P., Wang, Y., and Rutherford, G. S., Development of a Length-Based Vehicle Classification System Using Uncelebrated Video Cameras, annual meeting of Transportation Research Board, Washington, D.C., 2004.Google Scholar
- Gupte, S., Masoud, O., Martin, R. F. K., and Papanikolopoulos, N. P., IEEE Transactions on Intelligent Transportation Systems, Vol. 3, No. 1, March 2002. Google ScholarDigital Library
- Al-Deek, H. M., Radwan A. E., Mohammed, A. A., and Klodzinski, J. G., evaluating the improvements in traffic operations at a real-life toll plaza with electronic toll collection, ITS J., Vol. 3, No. 3, 1996.Google Scholar
- Collard, A. and Alves, J., Video system breaks through the barriers of transponder-based tolling, ITS International, January/February 1997.Google Scholar
- Abdel-Aty, M. and Pande, A., Classification of Real-Time Traffic Speed Patterns to Predict Crashes on Freeways, annual meeting of Transportation Research Board, Washington, D.C., 2004.Google Scholar
- Chang, S. K. and Chang, H., Benefit-cost analysis on application of AVI technologies to toll services, Proceedings, Pacific Rim Transtech Conference, Seattle, Washington, July 1993.Google Scholar
- Barnard, S. T. and Thompson, W. B., Disparity Analysis of images, Technical Report 79-1, Computer Science Department, University of Minnesota at Minneapolis, January 1979.Google Scholar
- Marr, D. and Poggio, M., A computational theory of human vision, In Proc. Royal Soc., Lond., Vol. B, 1979.Google Scholar
- Gelenbe, E., Random neural networks with negative and positive signals and product form solution, Neural Comput., Gelenbe Vol. 1, No. 4, pp. 502--510, 1989.Google Scholar
- Gelenbe, E., and Hussain, K. F., Learning in the Multiple Class Random Neural Network, IEEE Transactions on Neural Networks, Vol. 13, No. 6, November 2002. Google ScholarDigital Library
- Ackley, D. H, Hinton, G. H., and Sejnowski, T. J., A learning algorithm for Boltzman machines, Cognitive Sci., Vol. 9, pp. 147--169, 1985.Google ScholarCross Ref
- Behrens, H., Gawronska, D., Hollatz, J. and Schurmann, B., Recurrent and feedforward backpropagation: Performance studies, in Artificial Neural Networks, T. Kohonen et al., Eds. Amsterdam, The Netherlands: North-Holland, 1991, vol. 11, pp. 1511--1514.Google ScholarCross Ref
- Pineda, F. J., Generalization of backpropagation to recurrent and higher order neural networks, in Neural Inform. Processing Syst., D. Z. Anderson, Ed. Woodbury, NY: Amer. Inst. Phys., 1987, p. 602.Google Scholar
- Hai, F., Hussain, K. F., Gelenbe, E., and Guha, R., Video Compression with Wavelets and Random Neural Network Approximations, SPIE Electronic Imaging Conf., San Jose (CA), January 20-26. 2001.Google Scholar
- Bakircoglu, H., and Gelenbe, E., Random neural network recognition of shaped objects in strong clutter, SPIE, Vol. 3307, pp. 22--28, 1998.Google Scholar
- Atalay, V. and Gelenbe, E., Parallel algorithm for color texture generation using the random neural network model, Int. J. Pattern Recognition Artificial Intell., Vol. 6, No. 2--3, pp. 437--446, 1992.Google Scholar
- Gelenbe, E., and Hussain, K. F., Learning and generating color textures with recurrent multiple class random neural networks, SPIE Electronic Imaging Conference, San Jose (CA), January 20-26, 2001.Google ScholarCross Ref
- Hussain, K. F. and Kaptan, V., Modeling and Simulation with Augmented Reality, International Journal on Operations Research, Vol. 38 No. 2, P. 89--104, 2004.Google Scholar
- Gelenbe, E., Hussain, K. F., and Kaptan, V., Simulating autonomous agents in augmented reality, Article in Press, Journal of Systems and Software, available online February 2004. Google ScholarDigital Library
- Gelenbe, E., Neural Networks Advances and Applications II, Amsterdam, Netherlands Elsevier, 1992. Google ScholarDigital Library
- Ghanwani, A., Neural and delay based heuristics for the Steiner problem in networks, European J. Operations Res., Vol. 108, pp. 241--265, 1998.Google ScholarCross Ref
- Kandel, E. C., and Schwartz, J. H., Principles of Neural Science, Amsterdam, Netherlands Elsevier, 1985.Google Scholar
- Abdelbaki, A. H., and Gelenbe, E., Analog hardware implementation of the Random Neural Network model, in Proc. Int. Joint Conf. Neural Networks, July 2000. Google ScholarDigital Library
- Abdelbaki, H. E., Hussain, K. F., and Gelenbe, E., A Laser Intensity Image Based Automatic Vehicle Classification System, IEEE Intelligent Transportation Systems Conference proceedings, Oaklad (CA), August 25-29, 2001.Google ScholarCross Ref
- Canny, J. F, Finding edges and lines in images, Master's thesis, MIT, 1983.Google Scholar
Index Terms
- Laser intensity vehicle classification system based on random neural network
Recommendations
Vehicle Detection and Neural Network Application for Vehicle Classification
CICN '11: Proceedings of the 2011 International Conference on Computational Intelligence and Communication NetworksIn recent years, video processing have been widely used in traffic management. Vehicle detection and vehicle classification using neural network (NN), can be achieved by video monitoring systems. In most vehicle detection methods in the literature, only ...
Vehicle inductive signatures recognition using a Madaline neural network
In this paper, we report results obtained with a Madaline neural network trained to classify inductive signatures of two vehicles classes: trucks with one rear axle and trucks with double rear axle. In order to train the Madaline, the inductive ...
A deep neural network approach with hyper-parameter optimization for vehicle type classification using 3-D magnetic sensor
AbstractThe identification of vehicle types plays a critical role in Intelligent Transportation Systems. In this study, battery-operated, easy-to-install, low-cost 3-D magnetic traffic sensors have been developed for vehicle type ...
Highlights- A low-cost, easy-to-install, battery-operated 3-D magnetic sensor is developed.
Comments