基于三分量色差法和Ostu法的交通标志检测
|
摘要
交通标志检测是交通标志识别的难点。在复杂的交通环境下,采用传统颜色空间的固定阈值分割进行交通标志检测的方法鲁棒性差,难以准确有效地检测出交通标志。提出了一种基于三分量色差法和Ostu法的交通标志检测方法。首先,通过计算图像R、G、B分量的差值来得到红、蓝、黄三种颜色分量,然后利用Ostu法分别对它们进行阈值分割,得到交通标志的检测结果。实验结果表明,该算法的检测准确率和实时性满足实际要求。
One difficulty in traffic sign recognition is traffic sign detection. Algorithm based on traditional color space and one threshold segmentation is not robust or efficient enough in complex traffic environment. We propose a new method based on three color-components and Ostu. First, we can get three color-components of the image. Then, we can obtain detection result using Ostu method. Experimental results show that the proposed algorithm has good accuracy and efficiency.
One difficulty in traffic sign recognition is traffic sign detection. Algorithm based on traditional color space and one threshold segmentation is not robust or efficient enough in complex traffic environment. We propose a new method based on three color-components and Ostu. First, we can get three color-components of the image. Then, we can obtain detection result using Ostu method. Experimental results show that the proposed algorithm has good accuracy and efficiency.
引文
[1]朱双东,陆晓峰.道路交通标志识别的研究现状及展望[J].计算机工程与科学,2006,28(12):50-52.
[2]JIANG G,CHOI T.Robust detection of landmarks in color image based on fuzzy set theory[C].ICSP.Beijing:IEEE Signal Processing Society,1998:968-971.
[3]HOOSE N.Computer image processing in traffic engineering[M].New York:John Wiley&sons Inc.,1991.
[4]SOETEDIO A,YAMADA K.An efficient algorithm for traffic sign detection[J].Journal of Advanced Computational Intelligence and Intelligent Informatic,2006,10(3):409-417.
[5]黄志勇,孙光民,李芳.基于RGB视觉模型的交通标志分割[J].微电子学与计算机,2004,21(10):147-148.
[6]朱双东,张懿,陆晓峰.三角形交通标志的智能检测方法[J].中国图象图形学报,2006,11(8):1127-1131.
[7]ISHIZUKA Y,HIRAI Y.Segmentation of road sign symbols using opponent-color filters[C].Proceedings of 11th World Congress on ITS,Nagoya,Aichi Japan,2004:18-22.
[8]GRAM.Traffic sign UAH dataset(2007-03-16)[2014-07-20].http://agamenon.tsc.uah.es/Investigacion/gram/traffic_signs.html.
[2]JIANG G,CHOI T.Robust detection of landmarks in color image based on fuzzy set theory[C].ICSP.Beijing:IEEE Signal Processing Society,1998:968-971.
[3]HOOSE N.Computer image processing in traffic engineering[M].New York:John Wiley&sons Inc.,1991.
[4]SOETEDIO A,YAMADA K.An efficient algorithm for traffic sign detection[J].Journal of Advanced Computational Intelligence and Intelligent Informatic,2006,10(3):409-417.
[5]黄志勇,孙光民,李芳.基于RGB视觉模型的交通标志分割[J].微电子学与计算机,2004,21(10):147-148.
[6]朱双东,张懿,陆晓峰.三角形交通标志的智能检测方法[J].中国图象图形学报,2006,11(8):1127-1131.
[7]ISHIZUKA Y,HIRAI Y.Segmentation of road sign symbols using opponent-color filters[C].Proceedings of 11th World Congress on ITS,Nagoya,Aichi Japan,2004:18-22.
[8]GRAM.Traffic sign UAH dataset(2007-03-16)[2014-07-20].http://agamenon.tsc.uah.es/Investigacion/gram/traffic_signs.html.