|本期目录/Table of Contents|

[1]李 娟,王 富*,王维锋,等.基于数据融合的疲劳驾驶检测算法[J].武汉工程大学学报,2016,38(05):505-510.[doi:10. 3969/j. issn. 1674?2869. 2016. 05. 018]
 LI Juan,WANG Fu*,WANG Weifeng,et al.Detection Algorithm of Fatigue Driving Based on Data Fusion[J].Journal of Wuhan Institute of Technology,2016,38(05):505-510.[doi:10. 3969/j. issn. 1674?2869. 2016. 05. 018]
点击复制

基于数据融合的疲劳驾驶检测算法(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
38
期数:
2016年05期
页码:
505-510
栏目:
出版日期:
2016-11-02

文章信息/Info

Title:
Detection Algorithm of Fatigue Driving Based on Data Fusion
作者:
李 娟1王 富1*王维锋2汪恩军1杨 阳1
1. 武汉工程大学资源与土木工程学院,湖北 武汉 430074;2. 江苏省交通规划设计院智能交通设计研究中心,江苏 南京 210014
Author(s):
LI Juan1 WANG Fu*1 WANG Weifeng2 WANG Enjun1 YANG Yang1
1. School of Resources and Civil Engineering, Wuhan Institue of Technology, Wuhan 430074 China;2. Intelligent Tansportation Design Research Center of Jiangsu Province Traffic Planning and Design Institute, Co. LTD, Nanjing 210014, China
关键词:
驾驶行为疲劳识别车道偏离P80支持向量机数据融合
Keywords:
driving behavior fatigue detection lane departure P80 supporting vector machine data fusion
分类号:
TP305
DOI:
10. 3969/j. issn. 1674?2869. 2016. 05. 018
文献标志码:
A
摘要:
为减少交通事故,采用基于数据融合的疲劳检测技术以提高疲劳检测精度. 通过驾驶行为与车辆跟踪技术研究现状分析,选择眼睑遮住瞳孔的面积超过80%的P80和眨眼次数指标作为眼部特征参数、车辆越线指标作为驾驶行为特征参数. 将两个特征参数分为3类,分别为:清醒状态、轻微疲劳状态、疲劳状态;最后通过支持向量机算法建立基于数据融合的疲劳检测模型. 实验结果分别为灵敏度为86.45%,检测准确率为85.79%,特异度为84.63%,较单一数据源的疲劳检测方式精准,建立的融合模型提高了疲劳检测的准确性.
Abstract:
To reduce traffic accidents, we adopted fatigue detection technology based on data fusion to improve the accuracy of fatigue detection. By analyzing the driving behavior and vehicle tracking technology, P80 (the eyelids cover the pupillary area of more than 80%) and blink frequency were selected as the eye characteristic parameters, and the vehicle cross line was selected as the driving behavior characteristic parameters. The two characteristic parameters were divided into three categories, the waking state, mild fatigue and fatigue; finally, the fatigue detection model based on data fusion was established by supporting vector machine. Experimental results show that the sensitivity is 86.45%, the detection accuracy is 85.79%, and the specificity is 84.63%, which is more accurate compared with the fatigue detection method based on single data source. It is concluded that the established fusion model can improve the accuracy of fatigue detection.

参考文献/References:

[1] 沈永增,胡立芳,冯继妙. 多源信息融合在驾驶疲劳检测中的应用[J],计算机应用与软件, 2012. 29(2):271-274,297. SHEN Y Z, HU L F, FENG J M. Multi-source information fusion application to driving fatigue detection[J]. Computer applications and software,2012,29(2):271-274,297. [2] YANG G, LIN Y, BHATTACHARYA P. A driver fatigue recognition model using fusion of multiple features[M]. Hawei: IEEE, 2005. [3] GUO S Y, YING Z L, PRABIR BHATTACHARYA. A driver fatigue recognition model based on information fusion and dynamic Bayesian network[J]. Information sciences, 2010, 180 (10):1942-1954. [4] 王连震,裴玉龙. 基于贝叶斯网络的驾驶疲劳程度识别模型[J]. 交通工程, 2014,12(3):66-74. WANG L Z, PEI Y L. Driving fatigue recognition model based on bayesian network[J]. Traffic engineering,2014,12(3):66-74. [5] 张晖. 基于驾驶行为的疲劳程度识别研究[D]. 武汉:武汉理工大学,2009. [6] 杨述斌,金璐,章振保. 疲劳驾驶检测中的快速人眼定位方法[J]. 武汉工程大学学报,2013,35(6) :67-72.YANG S B, JIN L, ZHANG Z B. The method of quick eye location for fatigue test[J]. Journal of Wuhan university of engineering, 2013,35(6):67-72. [7] 袁翔,黄博学,夏晶晶. 疲劳驾驶检测方法研究现状[J]. 公路与汽运,2007,18(3):51-54. YUAN X, HUANG B X, XIA J J. Fatigue test method of research status[J]. Roads and trucks, 2007,18(3):51-54. [8] 牛清宁. 基于信息融合的疲劳驾驶检测方法研究[D]. 长春:吉林大学,2014. [9] 邵佳. 基于眼部特征的疲劳驾驶实时检测算法研究[D]. 长沙:湖南大学,2013. [10] 王景丹. 疲劳驾驶自主检测的研究与实现[D]. 成都:电子科技大学,2013. [11] 王雷. 一种基于双曲线模型的车道线跟踪检测算法设计与实现[D]. 长春:吉林大学,2014. [12] 秦洪懋,刘志强,汪澎. 基于多通道信息融合的疲劳驾驶行为分析研究[J]. 中国安全科学学报, 2011,21(2):115-120. QING H M, LIU Z Q,WANG P. Research on drowsy driving behavior based on mult-i channel information fusion[J]. Chinese journal of safety science,2011,21(2):115-120. [13] 刘佳兴. 基于多参数融合的疲劳驾驶监测及预警系统[D]. 兰州:兰州大学,2013. [14] 肖献强,王其东,赵永. 基于信息融合的驾驶行为识别技术的研究[J]. 汽车工程,2012,34(3):223-226. XIAO X Q,WANG Q D, ZHAO Y. A research on the technique of driving behavior identification based on information fusion[J]. Automotive engineering,2012,34(3):222-226. [15] 刘莉. 基于眼部信息的疲劳驾驶检测方法研究[D]. 长沙:湖南大学,2011.

相似文献/References:

备注/Memo

备注/Memo:
-
更新日期/Last Update: 2016-10-31