Abstract
This paper addresses the automatic analysis and segmentation of real-life traffic images aimed at providing the necessary and sufficient information for automatic car driving. The paper focuses on the basic task of segmenting the lane boundaries. As the general objective is to build a very robust segmentation module, able to cope with any kind of road and motorway and for any kind of surroundings and background, either rural or urban, we face a complex problem of texture analysis and classification which we have approached by applying the frequency histogram of connected elements (FHCE). To assure an efficient design of the segmentation module, a thorough experimentation with numerous traffic images has been undertaken. In particular, the optimum design of the crucial parameters of the FHCE (namely, the structurant morphological element, the connectivity level and the scanning window) has been carried out with special care. Experimental results are finally presented and discussed.
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.
Similar content being viewed by others
References
Vlacic, L., Parent, M., Harashima, F.: Intelligent Vehicle Technologies. Butterworth Heinemann, Oxford (2001)
Handmann, U., Kalinke, T., Tzomakes, C., Werner, M., Seelen, W.V.: An image processing system for driver assistance. Image and Vision Computing 18, 367–376 (2000)
Bertozzi, M., Broggi, A., Cellario, M., Fascioli, A., Lombardi, P., Porta, M.: Artificial Vision in Road Vehicles. Proceedings of the IEEE 90(7), 1258–1271 (2002)
Ran, B., Liu, H.X.: Development of A Vision-Based Real Time Lane Detection and Tracking System for Intelligent Vehicles (1999)
Gonzalez, J.P., Özgüner, Ü.: Lane Detection Using Histogram-Based Segmentation and Decision Tree. In: Proc. of the IEEE Intelligent Transportation Systems, pp. 346–351 (2000)
Charbonnier, P., Nicolle, P., Guillard, Y., Charrier, J.: Road boundaries detection using color saturation. In: Proc. 9th Eur. Signal Processing Conf. (1998)
Goldbeck, J., Graeder, D., Huertgen, B., Ernst, S., Wilms, F.: Lane following combining vision and DGPS. In: Proc. IEEE IV, pp. 445–450 (1998)
Kim, K.T., Oh, S.Y., Kim, S.W., Jeong, H., Lee, C.N., Kim, B.S., Kim, C.S.: An autonomous land vehicle PRV II: Progress and performance enhancement. In: Proc. IEEE IV, pp. 264–269 (1995)
Goldbeck, J., Huertgen, B.: Lane detection and tracking by video sensors. In: Proc. IEEE Intelligent Transportation Systems, pp. 74–79 (1999)
Schneiderman, H., Nashman, M.: A discriminating feature tracker for vision-based autonomous driving. IEEE Trans. Robotics and Automation 10(6), 769–775 (1994)
Konishi, S., Yuille, A.L.: Statistical cues for domain specific image segmentation with performance analysis. In: Proc. CVPR 2000, pp. 1125–1132 (2000)
Patricio, M.A., Maravall, D.: Wood Texture Analysis by Combining the Connected Elements Histogram and Artificial Neural Networks. In: Mira, J., Prieto, A.G. (eds.) IWANN 2001. LNCS, vol. 2085, pp. 160–167. Springer, Heidelberg (2001)
Maravall, D., Patricio, M.A.: Image Segmentation and Pattern Recognition: A Novel Concept, the Histogram of Connected Elements. In: Chen, D., Cheng, X. (eds.) Pattern Recognition and String Matching. Kluwer Academic Publishers, Dordrecht (2002)
Soille, P.: Morphological Image Analysis. Springer, Berlin (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Patricio, M.Á., Maravall, D. (2003). Segmentation of Traffic Images for Automatic Car Driving. In: Moreno-Díaz, R., Pichler, F. (eds) Computer Aided Systems Theory - EUROCAST 2003. EUROCAST 2003. Lecture Notes in Computer Science, vol 2809. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45210-2_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-45210-2_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20221-9
Online ISBN: 978-3-540-45210-2
eBook Packages: Springer Book Archive