Driver's eye region location algorithm

Download: PDF(4961 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks Supporting Info

Guide

Abstract

Driver drowsiness estimates can be realized by analyses of the drivers' eye movements based on a machine vision system. However, the system requires accurate eye region recognition in the driver's facial image. Random, rapid changes of the head posture complicate locating the eye region in real driving scenarios. The active shape model (ASM) can be used to coarsely locate the eye region. This study uses a local ASM model to enhance the head posture adaptability of the ASM algorithm. Then, the average of synthetic exact filters (ASEF) algorithm and the ASM are combined to improve the eye region location precision. A single eye ASEF and a double eyes ASEF are integrated to more robustly identify the iris center location. Tests show that the algorithm has strong head posture adaptability and can robustly and accurately identify the eye region location.

Keywords driver drowsiness machine vision eye location

Issue Date: 15 June 2014

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Bo ZHANG
	Wenjun WANG
	Wei ZHANG
	Shengbo LI
	Bo CHENG

Cite this article:

Bo ZHANG,Wenjun WANG,Wei ZHANG, et al. Driver's eye region location algorithm[J]. Journal of Tsinghua University(Science and Technology), 2014, 54(6): 756-762.

URL:

http://jst.tsinghuajournals.com/EN/ OR http://jst.tsinghuajournals.com/EN/Y2014/V54/I6/756

[1]	Ji Q, Yang X J. Real-ime eye, gaze, and face pose tracking for monitoring driver vigilance[J]. Real-ime Imaging, 2002, 8: 357-377. url: http://dx.doi.org/10.1006/rtim.2002.0279
[2]	Hu S Y, Zheng G T. Driver drowsiness detection with eyelid related parameters by support vector machine[J]. Expert Systems with Applications, 2009, 36: 7651-7658. url: http://dx.doi.org/10.1016/j.eswa.2008.09.030
[3]	张伟. 基于机器视觉的驾驶人疲劳状态识别关键问题研究[D]. 北京: 清华大学, 2011. ZHANG Wei. Research on Key Issues in Computer Vision Based Driver Drowsiness Recognition[D]. Beijing: Tsinghua University, 2011. (in Chinese) url: http://d.wanfangdata.com.cn/Conference_7541131.aspx
[4]	中国交通年鉴社. 中国交通年鉴2011[M]. 北京: 中国交通年鉴社, 2011. Year Book House of China Transportation & Communication. Year Book of China Transportation & Communication 2011[M]. Beijing: Year Book House of China Transportation & Communication, 2011. (in Chinese)
[5]	张伟, 成波, 张波. 驾驶人眼睛定位与跟踪算法的研究[J]. 汽车工程, 2012, 34(10): 889-893. ZHANG Wei, CHENG Bo, ZHANG Bo. A research on the algorithm for driver's eye position and tracking[J]. Automotive Engineering, 2012, 34(10): 889-893. (in Chinese) url: http://www.cnki.com.cn/Article/CJFDTotal-QCGC201210006.htm
[6]	Grace R, Byrne V E, Bierman D M, et al.A drowsy driver detection system for heavy vehicle [C]// Digital Avionics Systems Conference (17th DASC). Bellevue: The Institude of Electrical and Electronics Engineers Inc, 1998: 136-1-136-8
[7]	Yullie A L, Hallian P W, Cohen D S. Feature extraction from faces using deformable templates[J]. International Journal of Computer Vision, 1992, 8(2): 99-111. url: http://dx.doi.org/10.1007/BF00127169
[8]	Fasel I, Fortenberry B, Movellan J. A generative framework for real time object detection and classification[J]. Computer Vision and Image Understanding, 2005, 98(1): 182-210. url: http://dx.doi.org/10.1016/j.cviu.2004.07.014
[9]	Pentland A, Moghaddam B, Starner T. View-ased and modular eigenspaces for face recognition [C]// IEEE Society Conference on Computer Vision and Pattern Recognition. Seattle, WA: IEEE Computer Society Press, 1994: 84-91.
[10]	Cootes T F, Twining C J, Taylor C J. Diffeomorphic statistical shape models[J]. Image and Vision Computing, 2008, 26(3): 326-332. url: http://dx.doi.org/10.1016/j.imavis.2006.12.005
[11]	张伟, 成波, 张波. 驾驶人眼睛区域的鲁棒性定位算法研究[J]. 物理学报, 2012, 61(6): 060701-1-060701-9. ZHANG Wei, CHENG Bo, ZHANG Bo. Research on eye location algorithm robust to driver's pose and illumination [J]. Acta Phys Sin, 2012, 61(6): 060701-1-060701-9. (in Chinese) url: http://www.cnki.com.cn/Article/CJFDTotal-WLXB201206016.htm
[12]	Bolme D S, Draper B A, Beveridge J R. Average of synthetic exact filters [C]// IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009: 2105-2112.
[13]	Vitomir S, Jerneja Z G, Nikola P. Principal directions of synthetic exact filters for robust real-ime eye localization[J]. Biometrics and ID Management, 2011, 6583: 180-192. url: http://dx.doi.org/10.1007/978-3-642-19530-3_17
[14]	Freund Y, Schapire R E. A decision-heoretic generalization of on-ine learning and an application to boosting[J]. Journal of Computed and System Science, 1997, 55(1): 119-139. url: http://dx.doi.org/10.1006/jcss.1997.1504
[15]	GAO Wen, CAO Bo, SHAN Shiguang, et al.The CAS-EAL large-cale Chinese face database and baseline evaluations[J]. IEEE Trans on System Man and Cybernetics: Part A, 2008, 38(1): 149-161. url: http://dx.doi.org/10.1109/TSMCA.2007.909557
[16]	Milborrow S, Morkel J, Nicolls F. The MUCT Landmarked Face Database [DB/OL]. Pattern Recognition Association of South Africa, 2010. http://www.milbo.org/muct.
[17]	Jesorsky O, Kirchberg K J, Frischholz R W. Robust face detection using the Hausdorff distance [C]// Conference on Audio-and Video-ased Biometric Person Authentication. Berlin: Springer, 2001: 90-95.