Abstract
A vehicle classification is essential for effective transportation system, parking optimization and law enforcement. Proposed methods of vehicle image classification, obtained from videos of road traffic, have known limitations, such as dependence on detection methods, hard image normalization and low accuracy. This paper presents a classification method for vehicle images using NN with conditional adaptive distance. Its aims are to improve the classification accuracy, evaluate the conditional adaptive-NN rule and to discuss the feasibility of the features based on the edge. Results are compared with NN, adaptive-NN and SVM. The experimental platform is built on Matlab R2009a.
This is a preview of subscription content, log in via an institution to check access.
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
Kafai, M., Bhanu, B.: Dynamic Baysiane Networks for Vehicle Classification in Video. IEEE Transaction on Industrial Informatics 8(1), 100–109 (2012)
Wang, W., Shang, Y., Guo, J., Qian, Z.: Real-Time Vehicle Classification Based on Eigenface. International Conference on Consumer Electronics, Communications and Networks, pp. 4292-4295, Lai (2011)
Sanchez, A., Suarez, P., Conci, A., Nunes, E.O.: Video-based Distance Traffic Analysis: Application to Vehicle Tracking and Counting. Computer Science and Engineering, Scientific Image Processing 13(3), 38–45 (2012)
Mithun, N.C., Rashid, N.U., Rahman, S.M.M.: Detection and Classification Using Multiple Time-spatial Image. IEEE Transaction on Intelligent Transportation System 13(3), 1215–1225 (2012)
Brazilian ministry of transport (June 2013), http://www.transportes.gov.br/conteudo/53887/
Ha, D.M., Lee, J.M., Kim, Y.D.: Neural-edge-based Vehicle Detection and Traffic Parameter Extraction. Image and Vision Computing 22(11), 899–907 (2004)
Ranga, H.T.P., Kiran, M.R., Shekar, R.S., Kumar, S.K.N.: Vehicle Detection and Classification Based on Morphological Technique. In: International Conference on Signal and Image Processing (ICSIP), pp. 45–48 (2010)
Matos, F.M.S., Souza, R.M.C.R.: An Image Vehicle Classification Method Based on Edge and PCA Applied to Blocks. In: IEEE International Conference on Systems, Man, and Cybernetics, pp. 1688–1693 (2012)
Wang, N., Neskovic, P., Cooper, L.N.: Improving Nearest Neighbor with a Simple Adaptive Distance Measure. Pattern Recognition Letters 28, 207–213 (2007)
Chen, Z., Ellis, T., Velastin, S.A.: Vehicle Detection, Tracking and Classification in Urban Traffic. In: IEEE International Conference on Intelligent Transportation System, pp. 951–956 (2012)
de Matos, F.M.S., de Souza, R.M.C.R.: Vehicle Image Classification Based on Edge: Features and Distances Comparison. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds.) ICONIP 2012, Part IV. LNCS, vol. 7666, pp. 691–698. Springer, Heidelberg (2012)
Matos, F.M.S., Souza, R.M.C.: Vehicle Image Classification Method Using Edge Dimensions, SVM and Prototype. In: International Conference on Artificial Intelligence, ICAI (2013)
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
de S. Matos, F.M., de Souza, R.M.C.R. (2013). Hierarchical Classification of Vehicle Images Using NN with Conditional Adaptive Distance. In: Lee, M., Hirose, A., Hou, ZG., Kil, R.M. (eds) Neural Information Processing. ICONIP 2013. Lecture Notes in Computer Science, vol 8227. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42042-9_92
Download citation
DOI: https://doi.org/10.1007/978-3-642-42042-9_92
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42041-2
Online ISBN: 978-3-642-42042-9
eBook Packages: Computer ScienceComputer Science (R0)