吉林大学学报(工学版) ›› 2015, Vol. 45 ›› Issue (5): 1688-1695.doi: 10.13229/j.cnki.jdxbgxb201505044

• • 上一篇    下一篇

基于机器视觉的驾驶人使用手持电话行为检测

张波,王文军,魏民国,成波   

  1. 清华大学 汽车安全与节能国家重点实验室,北京 100084
  • 收稿日期:2014-03-06 出版日期:2015-09-01 发布日期:2015-09-01
  • 通讯作者: 成波(1962-),男,教授,博士生导师.研究方向:人机工程与智能安全.E-mail:chengbo@tsinghua.edu.cn
  • 作者简介:张波(1987-),男,博士研究生.研究方向:机器视觉与模式识别.E-mail:jsxyzb163@163.com
  • 基金资助:
    交通运输部信息化科技项目(2012-364-835-110); 国家自然科学基金项目(51205228)

Detection handheld phone use by driver based on machine vision

ZHANG Bo, WANG Wen-jun, WEE Minkooc, CHENG Bo   

  1. State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing 100084, China
  • Received:2014-03-06 Online:2015-09-01 Published:2015-09-01

摘要: 为了对驾驶过程中使用手持电话行为实施监控和预警,提出了一种基于机器视觉的驾驶人使用手持电话行为检测方法。该方法使用ASM算法分割出面部肤色区域,并运用F-B Error算法在头部发生偏转时对肤色区域进行跟踪。在此基础上,提出用自适应肤色范围提取算法进行肤色检测,并确定手部图像候选区域。提出了CMOG特征描述手部图像,并综合使用CMOG特征与HOG特征在手部图像候选区域中确定驾驶人的手部图像。最后,运用三模式逻辑判别方法判别驾驶人使用手持电话的行为。实验结果表明:该方法能够有效检测出驾驶人在驾驶过程中使用手持电话的行为。

关键词: 信息处理技术, 驾驶行为, 机器视觉, 手持电话

Abstract: A machine vision based method is proposed to detect handheld phone use behavior. In this method, first, Active Shape Model (ASM) algorithm is used to segment the skin-color region of the driver face, and the region is tracked by F-B error algorithm when the head moves. Second, an adaptive skin-color range extraction algorithm is proposed to detect the skin-color pixels and determine the candidates of hand images. Third, Co-occurrence Matrix of Oriented Gradients (CMOG) is proposed, which combined with Histogram Oriented Gradient (HOG) feature is used to detect the real hand image from the candidates. Finally, three modes logic discriminating method is used to identify the driver state. Experiment results show that the proposed machine vision based method can detect the handheld phone use behavior effectively.

Key words: information processing technology, driving behavior, machine vision, handheld phone

中图分类号: 

  • TN971
[1] Davis M, Payne N, Mozee S. Cell phone use while driving becoming a deadly problem[J]. The MURC Digest, 2010, 6(1):1-4.
[2] Mattews R, Legg S, Charlton S. The effect of cell phone type on drivers subjective workload during concurrent driving and conversing[J]. Accident Analysis and Prevention, 2003(35): 451-457.
[3] 李平凡,王殿海,刘东波,等. 驾驶中拨打手机对驾驶人脑力负荷及驾驶行为的影响分析[J]. 交通信息与安全,2010, 28(4): 103-107. Li Ping-fan, Wang Dian-hai, Liu Dong-bo, et al. Effect of using cell phone while driving on mental workload and driving behavior[J]. Journal of Transportation Information and Safety, 2010, 28(4): 103-107.
[4] Tornros J E B, Bolling A K. Mobile phone use-effects of handheld and handsfree phones on driving performance[J]. Accident Ayalysis and Prevention, 2005, 37(5):902-909.
[5] Ishigami Y, Klein P M. Is a hands-free phone safer than a handheld phone?[J]. Journal of Safety Research, 2009, 40(2):157-164.
[6] Choi Jung-hee. Method of controlling prohibition of cellular phone in vehicle[P]. Korea:1020040094926,2004-11-12.
[7] Kakumanu P,Makrogiannis S,Bourbakis N.A survey of
skin-color modeling and detection methods[J]. Pattern Recognition, 2007 (40):1106-1122.
[8] Dadgostar F, Sarrafzadeh A. An adaptive real-time skin detector based on hue thresholding: a comparison on two motion tracking methods[J]. Pattern Recognition Letters, 2006(27):1342-1352.
[9] Cootes T F, Twining C J, Taylor C J. Diffeomorphic statistical shape model[J]. Image and Vision Computing, 2008, 26(3):326-332.
[10] 林立, 黄磊, 刘昌平. 一种有效的儿童照合成方法[J]. 自动化学报, 2012, 38(12): 1941-1949. Lin Li, Huang Lei, Liu Chang-ping. An effective method for child picture synthesi[J]. Acta Automatica Sinica, 2012, 38(12): 1941-1949.
[11] Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]∥Conference on Computer Vision and Pattern Recognition, Kauai, USA, 2001, I-511- I-518.
[12] Kalal Z, Mikolajczyk K, Matas J. Forward-backward error automatic detection of tracking failures[C]∥International Conference on Pattern Recognition, Istanbul, Turkey, 2010:2756-2759.
[13] Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]∥Proceeding of 7th International Joint Conference on Artificial Intelligence, Columbia, British, 1981:674-679.
[14] Zhu Q, Cheng K T, Wu C T, et al. Adaptive learning of an accurate skin-color model[C]∥International Conference on Automatic Face and Gesture Recognition, South Korea, Seoul, 2004:37-42.
[15] Kovac J, Peer P, Solina F. Human skin color clustering for face detection[C]∥Proceedings of EUROCON 2003, Ljubljana, Slovenia, 2003:144-148.
[16] Cheng Y Z. Mean shift, mode seeking, and clustering[C]∥IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, 1995:790-799.
[17] Cho K M, Jang J H, Hong K S. Adaptive skin-color filter[J]. Pattern Recognition, 2001(34):1067-1073.
[18] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]∥Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005:886-893.
[19] 张毓晋. 图像分析[M]. 北京: 清华大学出版社, 2005: 282-289.
[1] 刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[2] 苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[3] 徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[4] 黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[5] 李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[6] 应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[7] 陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[8] 刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[9] 单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.
[10] 姚海洋, 王海燕, 张之琛, 申晓红. 双Duffing振子逆向联合信号检测模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1282-1290.
[11] 全薇, 郝晓明, 孙雅东, 柏葆华, 王禹亭. 基于实际眼结构的个性化投影式头盔物镜研制[J]. 吉林大学学报(工学版), 2018, 48(4): 1291-1297.
[12] 林金花, 王延杰, 王璐, 姚禹. 全局相机姿态优化下的快速表面重建[J]. 吉林大学学报(工学版), 2018, 48(3): 909-918.
[13] 陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[14] 陈涛, 崔岳寒, 郭立民. 适用于单快拍的多重信号分类改进算法[J]. 吉林大学学报(工学版), 2018, 48(3): 952-956.
[15] 孟广伟, 李荣佳, 王欣, 周立明, 顾帅. 压电双材料界面裂纹的强度因子分析[J]. 吉林大学学报(工学版), 2018, 48(2): 500-506.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!