Search

Article

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

Research on eye location algorithm robust to driver's pose and illumination

Zhang Wei Cheng Bo Zhang Bo

Research on eye location algorithm robust to driver's pose and illumination

Zhang Wei, Cheng Bo, Zhang Bo
PDF
Get Citation
  • Driver's drowsiness is one of the major causes of road accidents. The monitoring of a given driver's eye state by the use of a camera is considered to be a promising way to detect driver's drowsiness due to its accuracy and non-intrusiveness. However, eye location remains a challenging vision problem because of the constantly changing of illumination and driver's pose. Active shape model (ASM) is introduced in this paper to align the face. Though the ASM is a powerful statistical tool, it can suffer from changes in illumination and posture. Three contributions are involved in this paper. First, in order to maximize the tolerance of the ASM algorithm to illumination changes, we propose a robust ASM method with a novel local texture model learned from the self-quotient image instead of the original image. Second, a double layer overall shape model is proposed to enhance the adaptability of ASM. Third, strong constraints are achieved by an on-line learning of the distribution characteristics of the model parameters. The results show that the proposed algorithm is robust to the variation of illumination and driver's pose.
      Corresponding author: Cheng Bo, chengbo@tsinghua.edu.cn
    • Funds: Project supported by the National High Technology Research and Development Program of China (Grant No. 2009AA11Z214) and the Program of State Key Laboratory of Automotive Safety and Energy of Tsinghua Univeristy, China (Grant No. ZZ2010032).
    [1]

    Smith P, Shah M, Lobo N V 2003 IEEE Trans. Intell. Transp. Syst. 4 205

    [2]

    Mou Y B, Zhong C W 2005 Acta Phys. Sin. 54 5597 (in Chinese)[牟勇飚, 钟诚文 2005 物理学报 54 5597]

    [3]

    Peng L J, Kang R 2009 Acta Phys. Sin. 58 830 (in Chinese)[彭莉娟, 康瑞 2009 物理学报 58 830]

    [4]

    Zheng L, Ma S F, Jia N 2010 Acta Phys. Sin. 59 4490 (in Chinese)[郑亮, 马寿峰, 贾宁 2010 物理学报 59 4490]

    [5]

    Bergasa L M, Nuevo J, Sotelo M A, Barea R, Lopez M E 2006 IEEE Trans. Intell. Transp. Syst. 7 63

    [6]

    Culp J, Gindy M E, Haque A 2008 Int. J. Heavy Veh. Syst. 15 255

    [7]

    Grace R, Byrne V E, Bierman D M, Legrand J M, Gricourt D, Davis B K, Staszewski J J, Carnahan B 1998 Proceedings of the Digital Avionics Systems Conference Belleview, USA, October 31–November 5, 1998 pI36/1–I36/8

    [8]

    Ji Q, Zhu Z W, Lan P L 2004 IEEE Trans. Veh. Technol. 53 1052

    [9]

    Fase I, Fortenberry B, Movellan J 2005 Comput. Vis. Image Und. 98 182

    [10]

    Park C W, Park K, Moon Y S 2010 Electron. Lett. 46 130

    [11]

    Cheng B, Zhang G Y, Feng R J, Li J W, Zhang X B 2008 Automo. Eng. 30 1001 (in Chinese)[成波, 张广渊, 冯睿嘉, 李家文, 张希波 2008 汽车工程 30 1001]

    [12]

    Choi S, Choi C H, Kwak N 2011 Pattern Recogn. Lett. 32 561

    [13]

    Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese)[许元男, 赵远, 刘丽萍, 张宇, 孙秀冬 2010 物理学报 59 980]

    [14]

    Wu Y Q, Zhang J K 2010 Acta Phys. Sin. 59 5487 (in Chinese)[吴一全, 张金矿 2010 物理学报 59 5487]

    [15]

    Lee M W, Ranganath S 2003 Pattern Recogn. 36 1835

    [16]

    Zhang Y J 2009 Subspace-based Face Recognition (Beijing: Tsinghua University Press) pp62–65 (in Chinese)[章毓晋 2009 基于子空间的人脸识别 (北京: 清华大学出版社)第62—65页]

  • [1]

    Smith P, Shah M, Lobo N V 2003 IEEE Trans. Intell. Transp. Syst. 4 205

    [2]

    Mou Y B, Zhong C W 2005 Acta Phys. Sin. 54 5597 (in Chinese)[牟勇飚, 钟诚文 2005 物理学报 54 5597]

    [3]

    Peng L J, Kang R 2009 Acta Phys. Sin. 58 830 (in Chinese)[彭莉娟, 康瑞 2009 物理学报 58 830]

    [4]

    Zheng L, Ma S F, Jia N 2010 Acta Phys. Sin. 59 4490 (in Chinese)[郑亮, 马寿峰, 贾宁 2010 物理学报 59 4490]

    [5]

    Bergasa L M, Nuevo J, Sotelo M A, Barea R, Lopez M E 2006 IEEE Trans. Intell. Transp. Syst. 7 63

    [6]

    Culp J, Gindy M E, Haque A 2008 Int. J. Heavy Veh. Syst. 15 255

    [7]

    Grace R, Byrne V E, Bierman D M, Legrand J M, Gricourt D, Davis B K, Staszewski J J, Carnahan B 1998 Proceedings of the Digital Avionics Systems Conference Belleview, USA, October 31–November 5, 1998 pI36/1–I36/8

    [8]

    Ji Q, Zhu Z W, Lan P L 2004 IEEE Trans. Veh. Technol. 53 1052

    [9]

    Fase I, Fortenberry B, Movellan J 2005 Comput. Vis. Image Und. 98 182

    [10]

    Park C W, Park K, Moon Y S 2010 Electron. Lett. 46 130

    [11]

    Cheng B, Zhang G Y, Feng R J, Li J W, Zhang X B 2008 Automo. Eng. 30 1001 (in Chinese)[成波, 张广渊, 冯睿嘉, 李家文, 张希波 2008 汽车工程 30 1001]

    [12]

    Choi S, Choi C H, Kwak N 2011 Pattern Recogn. Lett. 32 561

    [13]

    Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese)[许元男, 赵远, 刘丽萍, 张宇, 孙秀冬 2010 物理学报 59 980]

    [14]

    Wu Y Q, Zhang J K 2010 Acta Phys. Sin. 59 5487 (in Chinese)[吴一全, 张金矿 2010 物理学报 59 5487]

    [15]

    Lee M W, Ranganath S 2003 Pattern Recogn. 36 1835

    [16]

    Zhang Y J 2009 Subspace-based Face Recognition (Beijing: Tsinghua University Press) pp62–65 (in Chinese)[章毓晋 2009 基于子空间的人脸识别 (北京: 清华大学出版社)第62—65页]

  • [1] Review of Pedestrian Tracking: Algorithms andApplications. Acta Physica Sinica, 2020, (): . doi: 10.7498/aps.69.20191721
    [2] Wang Fang, Zhao Xing, Yang Yong, Fang Zhi-Liang, Yuan Xiao-Cong. Comparison of the resolutions of integral imaging three-dimensional display based on human vision. Acta Physica Sinica, 2012, 61(8): 084212. doi: 10.7498/aps.61.084212
    [3] Shen Jing, Yao Jun-Cai, Wang Jian-Hua. Experimental research of human vision characteristic in the range of luminance of cathode ray tube display. Acta Physica Sinica, 2008, 57(7): 4034-4041. doi: 10.7498/aps.57.4034
    [4] Zhang Tai-Ning, Meng Chun-Ning, Liu Run-Bei, Chang Sheng-Jiang. Eye gaze tracking based on dark pupil image. Acta Physica Sinica, 2013, 62(13): 134204. doi: 10.7498/aps.62.134204
    [5] CHEN BAO-JIU, QIN WEI-PING, WANG HAI-YU, XU WU, HUANG SHI-HUA. COMPUTER SIMULATION OF ENERGY TRANFER PROCESS. Acta Physica Sinica, 1999, 48(3): 545-549. doi: 10.7498/aps.48.545
    [6] Ma Jian-Tai, Zhang Pei-Feng, Liu Jun, He De-Yan, Zheng Xiao-Ping. Computer simulation of thin-film epitaxy growth. Acta Physica Sinica, 2004, 53(8): 2687-2693. doi: 10.7498/aps.53.2687
    [7] Wang Min, Hu Xiao-Fang. Research on diffraction enhanced imaging computed tomography technique. Acta Physica Sinica, 2007, 56(8): 4989-4993. doi: 10.7498/aps.56.4989
    [8] HAN FU-SEN, FAN HAI-FU. COMPUTER ANALYSIS OF PATTERSON MAP. Acta Physica Sinica, 1981, 30(2): 224-233. doi: 10.7498/aps.30.224
    [9] ZENG JIAN-LIN, BA LONG, HOU JIAN-GUO, WU ZI-QIN. COMPUTER SIMULATION OF AGGREGATION-FRACTALS IN THIN FILMS. Acta Physica Sinica, 1997, 46(1): 28-34. doi: 10.7498/aps.46.28
    [10] WANG TIAN-MIN, WANG YUE-XIA, RONG ZHOU-WEN, WANG BAO-YI. STUDY OF VACANCY MIGRATION IN NiAl BY MOLECULAR DYNAMICS. Acta Physica Sinica, 1998, 47(8): 1325-1331. doi: 10.7498/aps.47.1325
    [11] WU FENG-MIN, ZHU QI-PENG, WU ZI-QIN. COMPUTER SIMULATION OF THE EPITAXY GROWTH IN ULTRA-THIN FILMS. Acta Physica Sinica, 1998, 47(9): 1427-1435. doi: 10.7498/aps.47.1427
  • Citation:
Metrics
  • Abstract views:  1796
  • PDF Downloads:  691
  • Cited By: 0
Publishing process
  • Received Date:  14 June 2011
  • Accepted Date:  09 July 2011
  • Published Online:  20 March 2012

Research on eye location algorithm robust to driver's pose and illumination

    Corresponding author: Cheng Bo, chengbo@tsinghua.edu.cn
  • 1. State Key Laboratory of Automotive Safety and Energy, Department of Automotive Engineering, Tsinghua University, Beijing 100084, China
Fund Project:  Project supported by the National High Technology Research and Development Program of China (Grant No. 2009AA11Z214) and the Program of State Key Laboratory of Automotive Safety and Energy of Tsinghua Univeristy, China (Grant No. ZZ2010032).

Abstract: Driver's drowsiness is one of the major causes of road accidents. The monitoring of a given driver's eye state by the use of a camera is considered to be a promising way to detect driver's drowsiness due to its accuracy and non-intrusiveness. However, eye location remains a challenging vision problem because of the constantly changing of illumination and driver's pose. Active shape model (ASM) is introduced in this paper to align the face. Though the ASM is a powerful statistical tool, it can suffer from changes in illumination and posture. Three contributions are involved in this paper. First, in order to maximize the tolerance of the ASM algorithm to illumination changes, we propose a robust ASM method with a novel local texture model learned from the self-quotient image instead of the original image. Second, a double layer overall shape model is proposed to enhance the adaptability of ASM. Third, strong constraints are achieved by an on-line learning of the distribution characteristics of the model parameters. The results show that the proposed algorithm is robust to the variation of illumination and driver's pose.

Reference (16)

Catalog

    /

    返回文章
    返回