Vehicle recognition finds wide-spread applications in analyzing traffic data, collecting electronic tolls and identifying unauthorized vehicles on roads, etc. Diverse methods have been developed for vehicle recognition and these methods give good results in controlled environment. However, variations of illumination, vehicle geometry and occlusion are frequent phenomena in real-world scenarios. Neural network proves effective in handling such variations. In this paper, we have investigated the effectiveness of single-layer neural network, multi-layer neural network and convolutional neural network (CNN) and deep CNN for vehicle detection using a standard Madrid dataset.

Vehicle recognition, Neural network, Convolutional neural network, Deep network

[1] Z. Chen, N. Pears, M. Freeman, and J. Austin, “Road vehicle classification using Support Vector Machines,” IEEE International Conference on Intelligent Computing and Intelligent Systems, vol. 4, pp. 214–218, 2009.
[2] N. S. Tadayuki Okada, “Development of preceding vehicle recognition algorithm for lead vehicle of autonomous platooning system based on multi sensor fusion and digital map," SICE Annual Conference, Tokyo, Japan, September 13-18, 2011.
[3] G. Z. Sun and R. Miller, “On-road vehicle detection using Gabor filters and support vector machines,” IEEE 14th International Conference on Digital Signal Processing, Santorini, Greece, 1-3 July 2002.
[4] Z. Xiao, B. Dai, T. Wu, L. Xiao, T. Chen, "Dense Scene Flow Based Coarse-to-Fine Rigid Moving Object Detection for Autonomous Vehicle, "IEEE Access, vol. 5, pp. 23492-23501, 2017.
[5] A. Petrovskaya and S. Thrun, "Model based vehicle detection and tracking for autonomous urban driving," Autonomous Robot, vol. 26, pp. 123-139, 2009.
[6] X. Zhang, N. Zheng, Y. He, F. Wang, "Vehicle detection using an extended hidden random field model," 14th IEEE International Conference on Intelligent Transportation Systems (ITSC), pp. 1555-1559, Washington DC, USA, 5-7 October 2011.
[7] F. M. Kazemi, "Vehicle recognition using curvelet transform and SVM, "IEEE 4th International Conference on Information Technology, pp. 516-521, Las Vegas, NV, USA, 2-4 April 2007.
[8] F. M. Kazemi, "Vehicle recognition based on Fourier, wavelet and curvelet transforms - a comparative study," IEEE Fourth International Conference on Information Technology, Las Vegas, NV, USA, 2-4 April 2007.
[9] W. Wang, "Research on Sobel operator for vehicle recognition," 1st IITA International Joint Conference on Artificial Intelligence, Hainan Island, China, 25-26 April 2009.
[10] Y. Freund, R. E. Schapire, "Large margin classification using the perceptron algorithm,” Machine Learning. 37 (3): 277–296, 1999.
[11] D. Gwala, V. Shrivastava and P. S. Parihar , “Secure Images for Copyright by Watermarking in Transform Sphere using Bidirectional Neural Network”, International Journal of Scientific Research in Computer Science and Engineering, Vol.1 , Issue.5 , pp.21-25, Sep-2013 (ISSN: 2320-7639).
[12] D. He, C. Lang, S. Feng, X. Du, and C. Zhang, "Vehicle detection and classification based on convolutional neural network," 7th International Conference on Internet Multimedia Computing and Service, Hunan, China, August 19-21, 2015.
[13] N. S. Lele, “Image Classification Using Convolutional Neural Network”, International Journal of Scientific Research in Computer Sciences and Engineering, Vol. 6, Issue 3 , pp.22-26, Jun-2018 (ISSN: 2320-7639).
[14] Alex Krizhevsky, I. Sutskever, G.E. Hinton, "ImageNet classification with deep convolutional neural networks," Twenty-sixth Annual Conference on Neural Information Processing Systems (NIPS), pp. 1097-1105, Nevada, USA, 2012.
[15] "Vehicle image database," Polytechnic University of Madrid, [Online]. Available: http://www.gti.ssr.upm.es/data/Vehicle_database.html