基于EOG的安全辅助驾驶系统算法设计与实现

doi:10.11959/j.issn.1000-436x.2016111

摘要/Abstract

摘要：

为保证驾驶安全，提高车辆控制系统的智能化水平，实现“手不离盘”操作，设计并实现了一种基于眼电图(EOG)的安全辅助驾驶系统。该系统利用安装在驾驶员眼睛周围的生物电极采集其在观测抬头显示器(HUD, head up display)上提示符时所产生的扫视信号，生成多种车载设备控制命令；对原始多导联EOG信号进行端点检测后，使用了独立分量分析(ICA, independent component analysis)方法进行空域滤波后提取眼动信号特征参数，并结合支持向量机实现了上、左与右扫视动作的识别。实验室环境下对所提算法进行了测试，15位受试者在疲劳与非疲劳状态下的在线平均正确率达到了98.43%与96.0%。实验结果表明，基于 ICA 多类扫视信号识别算法的安全辅助驾驶系统在眼动信号分析中呈现出了良好的分类性能。

关键词: 眼电图, 扫视信号, 独立分量分析, 空域滤波, 支持向量机

Abstract:

In order to ensure driving safety, improve the intelligent level of the vehicle control system and realize“keeping hands on the wheel”, a safe driver assistant system (SDAS) based on EOG was proposed. The proposed sys-tem utilized saccade signals which come from bio-electrodes installed around driver's eyes, to generate some control commands when the driver observes different signs located on the head up display (HUD). Furthermore, independent component analysis (ICA) algorithm was used to extract spatial feature parameters of activity-detected EOG signals, and combined with support vector machine (SVM) method to recognize the type of saccade signals, such as up-rolling, left-rolling and right-rolling. Experiments have been carried out in lab environment, and the average correct ratio on 15 sub-jects is 98.43% and 96.0% corresponding to fatigue condition and non-fatigue condition respectively. Experiential results re-veal that the SDAS based on the multi-class saccade signals recognition algorithm presents an excellent classification per-formance.

Key words: EOG, saccade signal, independent component analysis, spatial filtering, support vector machine

吕钊,吴小培,张超,卫兵. 基于EOG的安全辅助驾驶系统算法设计与实现[J]. 通信学报, 2016, 37(7): 87-95.

Zhao LYU,Xiao-pei WU,Chao ZHANG,Bing WEI. Design and implementation algorithm of safe driver assistant system based on EOG[J]. Journal on Communications, 2016, 37(7): 87-95.

图/表 10

图1

图2

图3

图4

图5

图6

表1

图7

图8

表2

参考文献 17

[1]	BENGLER K , DIETMAYER K , FARBER B , et al. Three decades of driver assistance systems: review and future perspectives[J]. Intelligent Transportation Systems Magazine, IEEE, 2014,6(4):6-22.
[2]	MENCHER B , GOLLIN W , REITER F , et al. Overview of electrical and electronic systems in the vehicle[M]// Fundamentals of Automotive and Engine Technology.Springer Fachmedien Wiesbaden, 2014:158-160.
[3]	PLANING P . Innovation acceptance: the case of advanced driver-assistance systems[M]. Springer Science ＆ Business Media, 2014.
[4]	程时伟，孙志强．用于移动设备人机交互的眼动跟踪方法[J]．计算机辅助设计与图形学学报， 2014,26(8):1354-1361. CHENG S W , SUN Z Q . An approach to eye tracking for mobile de-vice based interaction[J]. Journal of Computer-Aided Design ＆ Computer Graphics, 2014,26(8):1354-1361.
[5]	LARA O D , LABRADOR M A . A survey on human activity recognition using wearable sensors[J]. Communications Surveys ＆ Tutorials, IEEE, 2013,15(3):1192-1209.
[6]	MAJARANTA P , BULLING A . Eye tracking and eye-based hu-man–computer interaction[M]. Advances in Physiological Computing.Springer London, 2014:39-65.
[7]	BEDELL H E , STEVENSON S B . Eye movement testing in clinical examination[J]. Vision Research, 2013,90(39):32-37.
[8]	LV Z , WU X , LI M , et al. A novel eye movement detection algorithm for EOG driven human computer interface[J]. Pattern Recognition Letters, 2010,31(9):1041-1047.
[9]	CLEMENT R A . Natural coordinates for specification of eye movements[J]. Vision Research, 1991,31(11):2029-2032.
[10]	AUNGSAKUN S , PHINYOMARK A , PHUKPATTARANONT P , et al. Robust eye movement recognition using EOG signal for hu-man-computer interface[M]// Software Engineering and Computer Systems.Springer Berlin Heidelberg, 2011:714-723.
[11]	SOLTANI S , MAHNAM A . Design of a novel wearable human computer interface based on electrooculograghy[C]// Electrical Engineering (ICEE), 2013 21st Iranian Conference.IEEE, c2013:1-5.
[12]	VIDAL M , BULLING A , GELLERSEN H . Analysing EOG signal features for the discrimination of eye movements with wearable devices[C]// The 1st International Workshop on Pervasive Eye Tracking＆ Mobile Eye-Based Interaction.ACM, c2011:15-20.
[13]	BULLING A , WEICHEL C , GELLERSEN H . Eyecontext: recognition of high-level contextual cues from human visual behaviour[C]// The SIGCHI Conference on Human Factors in Computing Systems.ACM, c2013:305-308.
[14]	FUKUNAGA K . Introduction to statistical pattern recognition[M]. Access Online via Elsevier, 1990.
[15]	RABINER L , JUANG B H . Fundamentals of speech recognition[C]// Pearson Education,First Indian Reprint, 1993.
[16]	吴小培，周蚌艳，张磊，等．运动想象脑-机接口中的ICA滤波器设计[J]．生物物理学报， 2014,7:006. WU X P , ZHOU B Y , ZHANG L , et al. ICA filter design in brain-computer interface of motor imagery[J]. Acta Biophysica Sinica, 2014,7:006.
[17]	LEE T W , GIROLAMI M , SEJNOWSKI T J . Independent component analysis using an extended-infomax algorithm for mixed sub-gaussian and super-gaussian sources[J]. Neural Computation, 1999,11(1):417-441.

受试者		类型/%		平均
受试者	左扫视	右扫视	上扫视	平均
1	97.78	97.83	97.82	97.81
2	99.01	98.24	98.11	98.45
3	98.32	97.59	98.27	98.06
4	98.88	98.64	99.03	98.85
5	98.26	99.12	98.87	98.75
6	98.76	99.05	99.19	99.00
7	97.15	97.69	98.13	97.66
8	98.92	99.23	98.83	98.99
9	98.81	98.67	98.56	98.68
10	98.42	98.13	98.5	98.35
11	99.01	98.64	98.02	98.56
12	97.38	98.29	98.88	98.19
13	99.12	98.57	98.02	98.57
14	97.56	97.81	98.09	97.82
15	98.23	99.03	98.74	98.67
平均	98.43	98.42	98.53	98.43

受试者		类型/%		平均
受试者	左扫视	右扫视	上扫视	平均
2	95.32	96.48	94.45	95.42
5	98.05	97.2	95.67	96.97
7	94.13	94.37	94.89	94.46
10	96.62	96.42	95.03	96.02
12	95.34	97.51	96.07	96.31
15	97.27	97.08	96.12	96.82
平均	96.12	96.51	95.37	96.00