[1]史晓鹏,何为,韩力群.灰度直方图与LDA的路况分类[J].智能系统学报,2011,6(4):328-332.
SHI Xiaopeng,HE Wei,HAN Liqun.Research on traffic information classification based on a greyhistogram and linear discriminant analysis[J].CAAI Transactions on Intelligent Systems,2011,6(4):328-332.
点击复制
SHI Xiaopeng,HE Wei,HAN Liqun.Research on traffic information classification based on a greyhistogram and linear discriminant analysis[J].CAAI Transactions on Intelligent Systems,2011,6(4):328-332.
灰度直方图与LDA的路况分类
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
6
期数:
2011年第4期
页码:
328-332
栏目:
学术论文—机器感知与模式识别
出版日期:
2011-08-25
- Title:
- Research on traffic information classification based on a greyhistogram and linear discriminant analysis
- 文章编号:
- 1673-4785(2011)04-0328-05
- Keywords:
- traffic information classification; greyhistogram; LDA; KNN
- 分类号:
- TP391.4
- 文献标志码:
- A
- 摘要:
- 道路路况实时分类研究，是路况信息诱导系统的基础.通过对大量路况图像进行研究，提出使用路况图像中道路区域统计灰度直方图作为表征路况信息的特征向量，采用LDA（linear discriminat analysis）算法对高维特征向量进行降维，采用改进的K近邻分类器实现对道路路况实时分类，并给出实际分类结果.实验结果表明，采用上述方法进行路况分类，其结果与交通管理部门给出的结果一致率达91.7%，对路况实时分类具有较高的实用价值.
- Abstract:
- Research on realtime traffic information classification is the basis of traffic guidance systems. In this paper, a high dimension feature vector based on a greyhistogram sampling of a road region image was proposed. The classification algorithms of linear discriminant analysis (LDA) and an improved KNearest Neighborhood (KNN) were adopted to reduce the high dimension vector and classify real time traffic information. The experimental results show that the proposed traffic information classification method can supply the same traffic information as what comes from the Beijing Traffic Management Bureau; the rate of identical information is as high as 91.7%.
- 参考文献/References:
-
［1］钟石泉, 马寿峰, 贺国光. 交通诱导系统路网状态描述方法及仿真研究［J］ . 系统工程学报, 2009, 24(1): 2531.
ZHONG Shiquan, MA Shoufeng, HE Guoguang. Description and simulation of dynamic route guidance system road network［J］. Journal of System Engineering, 2009， 24(1): 2531.
［2］叶青. 道路交通参数检测系统设计［J］. 中南公路工程, 2005, 30(4): 110112.
?YE Qing. Design of traffic flow parameter detection system［J］. Central South Highway Engineering, 2005, 30(4): 110112.
［3］WANG Guolin, XIAO Deyun. Review on vehicle detection based on video for traffic surveillance［C］//Proceedings of the IEEE International Conference on Automation and Logistics. Qingdao, China: IEEE Press, 2008: 29612965.
［4］SHI Wei, WU Jian, ZHOU Shaolin，et al. Variable message sign and dynamic regional traffic guidance［J］. Intelligent Transportation System Magazine， 2009, 1(3): 1521.
［5］王燕清, 陈德运, 石朝侠. 基于单目视觉的非结构化道路检测与跟踪［J］. 哈尔滨工程大学学报, 2011, 32(3):334339.
?WANG Yanqing, CHEN Deyun, SHI Chaoxia. Unstructured road detection and tracking based on monocular vision［J］. Journal of Harbin Engineering University, 2011, 32(3): 334339.
［6］耿凯, 姚丹亚, 张毅. 一种基于灰度直方图的交通检测系统［J］. 计算机工程与应用, 2006, 4: 222225.
GENG Kai, YAO Danya, ZHANG Yi. A greyhistogram based traffic detection system［J］. Computer Engineering and Applications, 2006, 4: 222225.
［7］边肇祺, 张学工. 模式识别［M］. 2版，北京：清华大学出版社, 1999: 140142.
［8］李晓辉, 梨湘, 郭桂蓉. 基于LDA算法的一维距离像特征提取［J］. 国防科技大学学报, 2005, 27(6): 7276.
LI Xiaohui, LI Xiang, GUO Guirong. Feature extraction of HRRP based on LDA algorithm［J］. Journal of National university of Defense Technology, 2005, 27(6): 7276.
［9］LU Juwei, PLATANIOTIS K N, VENETSANOPOULOS A N. Face recognition using LDAbased algorithms［J］. IEEE Transactions on Neural Networks, 2003, 14(1): 195200.
?［10］BRESSAN M, VITRIA J. Nonparametric discriminant analysis and nearest neighbor classification［J］. Pattern Recognition Letters, 2003, 24(15): 27432749.
［11］LI Zhifeng, LIN Dahua, TANG Xiaoou. Nonparametric discriminant analysis for face recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(4): 755761.
［12］CEVIKALP H, NEAMTU M, WILKES M, et al. Discriminative common vectors for face recognition［J］. IEEE Transactions on Analysis and Machine Intelligence, 2005, 27(1): 413.
［13］WANG Jigang, NESKOVIC P, COOPER L N. Neighborhood size selection in the Knearestneighbor rule using statistical confidence［J］. Pattern Recognition, 2006, 39(3): 417423.
备注/Memo
收稿日期： 2010-08-02. 通信作者： 史晓鹏.E - mail:davidxp87@yahoo.com.cn. 作者简介：史晓鹏，男，1987年生，硕士研究生，主要研究方向为图像处理与模式识别；何为, 男，1953年生，硕士, 高级工程师, IEEE 会员，中国人工智能学会理事，中国人工智能学会智能产品与产业工作委员会秘书长，中国计量测试学会高级会员.主要研究方向为非电量检测技术、计算机测控技术、嵌入式技术应用.主持或参加国家科技攻关、省部级、横向等各类科研项目30余项，获国家发明专利3项，发表学术论文30余篇；韩力群,女,1953年生,教授,中国人工智能学会副理事长,主要研究方向为事智能信息处理与图像工程领域研究,主持各类科研课题30余项,出版著作10部;获国家发明专利3项,北京发明创新大赛银奖1项,发表学术论文120余篇.
更新日期/Last Update:
2011-09-30