基于多颜色空间级联分类的交通标志图像颜色标准化

doi:10.19678/j.issn.1000-3428.0057802

摘要/Abstract

摘要： 在构建交通标志颜色矩阵的基础上，进行颜色标准化映射分析，确定交通标志颜色标准化的映射目标颜色集合。分析交通标志三角中心区域和环状区域RGB分量统计数据，提出一种基于区域RGB统计数据的图像粗分类方法，实现基于图像粗分类的参数设置和亮度增强，并基于矩形中心区域的亮度统计数据，提出一种图像逆光判定方法。在对图像进行预处理后，基于YIQ颜色空间和HSV颜色空间，级联基于Y值和S值二值化的黑白色分类器、基于H值可变区间划分的红绿蓝黄色分类器、基于YIQ空间的红棕色分类器和基于图像粗分类的黑白色补偿分类器，实现颜色标准化处理。利用中国交通标志检测数据集构建测试数据集进行实验，结果表明，该方法较好地实现了交通标志颜色标准化映射，具有较高的成功率。

关键词: 颜色标准化, 交通标志, 粗分类, 级联分类, 多颜色空间

Abstract: Based on a constructed traffic sign color matrix,the analysis of color standardization mappings is carried out,and the mapping target color set of traffic sign color standardization is determined.Then the statistical data of RGB componentsin triangle center area and the ring area of the traffic sign is analyzed,and on this basis,a coarse image classification method based on the statistical data of regional RGB is proposed to implement parameter setting and brightness enhancement.Also,based on the statistical data of brightness of the rectangular center area,this paper proposes a determination method of image backlight.After image preprocessing,based on YIQ color space and HSV color space,four classifiers are cascaded,which are black-white color classifier based on Y value and S value binarization,red-green-blue-yellow classifier based on the variable interval division of H value,red-brown classifier based on YIQ space and black-white color compensation classifier based on coarse image classification to implement color standardization.Finally,the test data set is constructed based on the Chinese traffic sign detection data set,and experimental results show that the proposed color standardization method can realize traffic sign color standardization mapping at a high success rate.

Key words: color standardization, traffic sign, coarse classification, cascade classification, multi-color space

中图分类号:

TP391.41

刘洋, 黄大荣, 刘洋, 钟蔚. 基于多颜色空间级联分类的交通标志图像颜色标准化[J]. 计算机工程, 2020, 46(9): 233-241.

LIU Yang, HUANG Darong, LIU Yang, ZHONG Wei. Color Standardization of Traffic Sign Images Based on Multi-Color Space Cascade Classification[J]. Computer Engineering, 2020, 46(9): 233-241.

https://www.ecice06.com/CN/Y2020/V46/I9/233

图/表 23

20200915141641

20200915141644

20200915141647

20200915141650

20200915141653

20200915141656

20200915141659

20200915141702

20200915141706

20200915141709

20200915141712

20200915141715

20200915141719

20200915141722

20200915141727

20200915141730

20200915141733

20200915141737

20200915141741

20200915141745

20200915141749

20200915141752

20200915141756

参考文献

[1] FLEYEH H.Traffic sign recognition without color information[C]//Proceedings of 2015 Colour and Visual Computing Symposium.Washington D.C.,USA:IEEE Press,2015:1-6.
[2] FLEYEH H.Traffic sign detection and recognition[M]//ROBERT P L,RAJA B,MOHN T.Computer vision and imaging in intelligent transportation systems.Chichester,UK:John Wiley and Sons,2017:343-373.
[3] DE LA ESCALERA A,MORENO L E,SALICHS M A,et al.Road traffic sign detection and classification[J].IEEE Transactions on Industrial Electronics,1997,44(6):848-859.
[4] MALDONADO B S,LAFUENTE A S,GIL J P,et al.Road-sign detection and recognition based on support vector machines[J].IEEE Transactions on Intelligent Transportation Systems,2007,8(2):264-278.
[5] SOUANI C,FAIEDH H,FARHAT W,et al.Embedded real-time system for traffic sign recognition on ARM processor[J].International Journal of Applied Metaheuristic Computing,2020,11(2):77-98.
[6] ZHU Shuangdong,JIANG Tiantian,LIU Lanlan.Traffic sign recognition based on color standardization[J].Computer Applications and Software,2008,25(1):220-222.(in Chinese)朱双东,蒋甜甜,刘兰兰.基于颜色规格化的交通标志识别[J].计算机应用与软件,2008,25(1):220-222.
[7] ZHU Shuangdong,LIU Lanlan.Traffic sign detection based on color information and SVM network[J].Automatic Instruments,2009,30(3):69-72.(in Chinese)朱双东,刘兰兰.基于颜色信息与SVM网络的交通标志检测[J].自动化仪表,2009,30(3):69-72.
[8] ZHU Jun,HOU Zhenjie,CHEN Shuyue,et al.Traffic sign recognition based on depth feature reconstruction and weight assignment[J].Journal of Chinese Computer Systems,2019,40(9):1932-1939.(in Chinese)朱军,侯振杰,陈树越,等.深度特征重构与权重分配的交通标志识别算法[J].小型微型计算机系统,2019,40(9):1932-1939.
[9] LI He,HAO Xiaoli,QI Fei.Traffic sign detection based on color standardization and contour polygon[J].Railway Computer Application,2013,22(2):9-13.(in Chinese)李贺,郝晓莉,齐飞.基于颜色规格化和轮廓多边形的交通标志检测[J].铁路计算机应用,2013,22(2):9-13.
[10] MA Xing,MU Chunyang,WANG Yan,et al.Traffic sign detection and recognition using color standardization and Zernike moments[C]//Proceedings of the 28th Chinese Control and Decision Conference.Washington D.C.,USA:IEEE Press,2016:5195-5198.
[11] JAMES M,PHILIPP R,RONAK C,et al.Image segmenta-tion with implicit color standardization using cascaded EM:detection of myelodysplastic syndromes[C]//Proceedings of the 9th IEEE International Symposium on Biomedical Imaging.Washington D.C.,USA:IEEE Press,2012:740-743.
[12] YAGI Y.Color standardization and optimization in whole slide imaging[J].Diagnostic Pathology,2011,6(S1):15-20.
[13] PINKY A B,NORIAKI H,YUKAKO Y.Color standardiza-tion in whole slide imaging using a color calibration slide[J].Journal of Pathology Informatics,2014,5(1):32-35.
[14] BASAVANHALLY A,MADABHUSHI A.EM-based segmentation-driven color standardization of digitized histopathology[EB/OL].[2020-02-15].https://engineering.case.edu/centers/ccipd/sites/ccipd.case.edu/files/publications/Ajay-HistoStandardization.pdf.
[15] CREUSEN I M,HAZELHOFF L,DE WITH P H N.Color transformation for improved traffic sign detection[C]//Proceedings of the 19th IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2012:461-464.
[16] National Standardization Administration of China.Road traffic signs and markings Part II:road traffic signs:GB 5678.2-2009[S].Beijing:China Standards Press,2009.(in Chinese)中国国家标准化管理委员会.道路交通标志和标线第二部分:道路交通标志:GB 5678.2-2009[S].北京:中国标准出版社,2009.
[17] OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[18] HUANG Jin,YUAN Weiqi.Self-affine fitting based iris texture segmentation and coarse classification[J].Chinese Journal of Scientific Instrument,2015,36(4):758-767.(in Chinese)黄静,苑玮琦.自仿射拟合的虹膜纹理分割及粗分类[J].仪器仪表学报,2015,36(4):758-767.
[19] National Standardization Administration of China.Chinese color system:GB/T 15608-2006[S].Beijing:China Standards Press,2007.(in Chinese)中国国家标准化管理委员会.中国颜色体系:GB/T 15608-2006[S].北京:中国标准出版社,2007.
[20] QIU Zhaowen,ZHANG Tianwen.A new image color feature extraction method[J].Journal of Harbin Institute of Technology,2004,36(12):1699-1701.(in Chinese)邱兆文,张田文.一种新的图像颜色特征提取方法[J].哈尔滨工业大学学报,2004,36(12):1699-1701.
[21] ZHANG Jianming,JIN Xiaokang,SUN Juan,et al.Spatial and semantic convolutional features for robust visual object tracking[J].Multimedia Tools and Applications,2020,79(21/22):15095-15115.
[22] ZHANG Jianming,HUANG Manting,JIN Xiaokang,et al.A real-time Chinese traffic sign detection algorithm based on modified YOLOv2[J].Algorithms,2017,10(4):127-128.
[23] ZHANG Jianming,HUANG Qianqian,WU Honglin,et al.Effective traffic signs recognition via kernel PCA network[J].International Journal of Embedded Systems,2018,10(2):120-125.

选择文件类型/文献管理软件名称

选择包含的内容