Author : Miss.Namrata Vijay Chavan 1
Date of Publication :23rd August 2017
Abstract: Now days, traffic sign detection attracted large number of researchers interest due to its important in efficient intelligent transportation systems (ITSs). Traffic sign detection helps to minimize the road accidents and hence to minimize the loss. The efficient traffic sign detection is vital research problem since from last decade. In ITSs, there is more work conducted already on name plate detection and recognition, however there only few concrete research studies presented to solve the problem of traffic sign detection and recognition. For applications like road surveying, autonomous vehicles are mainly demanding the system of road side sign detection and recognition. The current methods for road side sign detection having issues of efficiency and accuracy due to different factors affecting on road sign detection such as shadow, non-uniform sizes of signs, illumination conditions, blurring, occlusion, and sign deterioration etc. In this work, we proposed novel method for road sign detection and recognition based on saliency regions detection. Saliency regions detection helps to locate the road sign efficiently and hence traffic sign detection properly. In this paper, author introduced the efficient segmentation method and graph based ranking approach for the accurate detection salient regions. Additionally we applied the RGB image smoothing algorithm to improve the detection accuracy. The performance results claims that proposed approach outperforming the previous method.
Reference :
-
[1] S. Maldonado-Bascon, S. Lafuente-Arroyo, P. Gil-Jimenez, H. Gomez-Moreno, and F. opezFerreras, “Road-sign detection and recognition based on support vector machines,” EEE Trans. Intell. Transp. Syst., vol. 8, no. 2, pp. 264–278, Jun. 2007.
[2] P. Paclik, J. Novovicova, and R. Duin, “Building road-sign classifiers using a trainable similarity measure,” IEEE Trans. Intell. Transp. Syst., vol. 7, no. 3, pp. 309–321, Sep. 2006.
[3] S. M. A. Bhuiyan, M. N. Islam, and M. S. Alam, “Distortion-invariant multiple target detection using class-associative joint transform correlation,” Opt. Eng., vol. 44, no. 9, p. 097 201, Sep. 1–10, 2005.
[4] J. Miura, T. Kanda, and Y. Shirai, “An active vision system for on-line traffic sign recognition,” IEICE Trans. Inf. Syst., vol. 11, pp. 1784–1792, 2002.
[5] C. Bahlmann, Y. Zhu, R. Visvanathan, M. Pellkofer, and T. Koehler, “A system for traffic sign detection, tracking, and recognition using color, shape, and motion information,” in Proc. IEEE Conf. Intell. Veh. Symp. Jun. 2005, pp. 255–260.
[6] J. Matas, “Robust wide-baseline stereo from maximally stable extremal regions,” Image Vis. Comput., vol. 22, no. 10, pp. 761–767, Sep. 2004.
[7] Dept. Transp., London, U.K., Traffic Signs Image Database, 2011.
[8] Xue Yuan, Member, IEEE, Jiaqi Guo, Xiaoli Hao, and Houjin Chen, “Traffic Sign Detection via Graph-Based Ranking and Segmentation Algorithms", IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS, 2015.
[9] Jack Greenhalgh and Majid Mirmehdi, "Recognizing Text-Based Traffic Signs", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2014.
[10] Andreas Møgelmose, Dongran Liu, and Mohan Manubhai Trivedi, "Detection of U.S. Traffic Signs", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015
[11] Chunsheng Liu, Faliang Chang, and Zhenxue Chen, "Rapid Multiclass Traffic Sign Detection in High-Resolution Images", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 15, NO. 6, DECEMBER 2014