Browse > Article

A FUZZY NEURAL NETWORK-BASED DECISION OF ROAD IMAGE QUALITY FOR THE EXTRACTION OF LANE-RELATED INFORMATION  

YI U. K. (Department of Digital Animation, Busan Kyungsang College)
LEE J. W. (Department of Industrial Engineering, Automotive Research Center, Chonnam National University)
BAEK K. R. (Department of Electronics Engineering, Research Institute of Computer Information and Communication, Pusan National University)
Publication Information
International Journal of Automotive Technology / v.6, no.1, 2005 , pp. 53-63 More about this Journal
Abstract
We propose a fuzzy neural network (FNN) theory capable of deciding the quality of a road image prior to extracting lane-related information. The accuracy of lane-related information obtained by image processing depends on the quality of the raw images, which can be classified as good or bad according to how visible the lane marks on the images are. Enhancing the accuracy of the information by an image-processing algorithm is limited due to noise corruption which makes image processing difficult. The FNN, on the other hand, decides whether road images are good or bad with respect to the degree of noise corruption. A cumulative distribution function (CDF), a function of edge histogram, is utilized to extract input parameters from the FNN according to the fact that the shape of the CDF is deeply correlated to the road image quality. A suitability analysis shows that this deep correlation exists between the parameters and the image quality. The input pattern vector of the FNN consists of nine parameters in which eight parameters are from the CDF and one is from the intensity distribution of raw images. Experimental results showed that the proposed FNN system was quite successful. We carried out simulations with real images taken in various lighting and weather conditions, and obtained successful decision-making about $99\%$ of the time.
Keywords
Fuzzy-neural network; Cumulative distribution function; Suitability analysis; Image quality; Image processing;
Citations & Related Records

Times Cited By Web Of Science : 5  (Related Records In Web of Science)
Times Cited By SCOPUS : 5
연도 인용수 순위
1 Lin, C. T. and Lee, C. S. G. (1996). Neural Fuzzy Systems. Prentice Hall. New Jersey
2 Ozawa, S. (1999). Image processing for intelligent transport systems. IEICE Trans. Information and Systems E82-D, 3, 629-636
3 Takahashi, A. Ninomiya, Y. Ohta, M. and Tange, K. (1999). A robust lane detection using real-time voting processor. Proc. IEEE/IEE1/1SAI Int. Conf on Intelligent Transportation Systems, 577-580
4 Lee, J. W, Yi, U. K. and Baek, K. R. (2001). A cumulative distribution function of edge direction for road-lane detection. IEICE Trans. Information and Systems E84-D, 9,1206-1216
5 Aoki, M. (1998). Image processing in ITS. Proc. IEEE Intelligent Vehicles '98, Germany, 1-4
6 Gonzalez, R. G. and Woods, R. E. (1992). Digital Image Processing. Addison-Wesley. Reading. Massachusetts
7 Bertozzi, M. Broggi, A. and Fascioli, A. (2000). Visionbased intelligent vehicles: State of the art and perspectives. Robotics and Autonomous Systems 32, 1-16   DOI   ScienceOn
8 Lee, J. W (2002). A machine vision system for lanedeparture detection. CVIU 86, 1, 52-78   DOI   ScienceOn
9 Horikawa, S. Furuhashi, T. and Uchikawa, Y. (1992). On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm. IEEE Trans. Neural Networks 3, 5, 801-806   DOI   ScienceOn
10 Kreucher, C. and Lakshmanan, S. (1999). A frequency domain approach to lane detection on roadway images. Proc. 1999 Int. Conl on Image Processing 2,31-35
11 Lee, J. W. Kim, K. S. Jeong, S. S. and Jeon, Y. W (2000). Lane departure warning system: Its logic and on-board equipment (20005331). Proc. lSAE, Japan, 9-11
12 Maki, Y. and Laparo, K. A. (1997). A neural-network approach to fault detection and diagnosis in industrial process. IEEE Trans. on Control Systems 5, 6, 529-54l   DOI   ScienceOn
13 Duda, R. O. and Hart, P. E. (1973). Pattern Classification and Scene Analysis. Jone Wiley & Sons. New York