基于多识别区域融合的机动车驾驶员检测框架<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201803010

摘要
图/表
参考文献
相关文章 (2)

全文: PDF (1604 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要受光照条件、图像噪声和复杂背景等因素的影响,在机动车驾驶员检测过程中难以获取不同卡口图像下的驾驶员特征.为了解决上述问题,文中提出基于多识别区域融合的精准驾驶员位置检测框架,用于提高驾驶员识别率.首先基于图像梯度特征算法获得车牌定位,然后使用自适应方法得到车窗区域,最后采用多识别区域融合策略得到准确的驾驶员区域.在10个图像测试库上的测试表明,文中方法可以获得较高的识别率.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	霍星
	檀结庆
	赵峰
	景永俊
	邵堃

关键词 ：图像梯度, 自适应车窗定位, 多识别区域融合, Adaboost算法, 驾驶员检测

Abstract：Features of motor vehicle driver are difficult to be acquired in motor vehicle driver detection due to the various illumination conditions, image noise and complex backgrounds. Therefore, an accurate driver location detection framework based on multi-detected region fusion is proposed in this paper to promote the driver identification rate. In the detection process, license plate location is obtained firstly by the algorithm based on image gradient features. Then, the window area of the vehicle is determined by an adaptive method. Finally, the multi-detected region fusion strategy is introduced to obtain the accurate driver region. Experiments on the testing image library verify the high identification rate of the proposed algorithm.

Key words： Image Gradient Adaptive Window Area Location Multi-detected Region Fusion Adaboost Algorithm Driver Detection

收稿日期: 2017-05-15

ZTFLH:

TP 391.4

基金资助:国家自然科学基金项目(No.61502136,61572167)、科技部国际合作项目(No.2015DFA11450)、安徽省科技强警计划项目(No.1604d0802018)、广东省省级科技计划项目(No.2016B010108002)资助

通讯作者: 邵堃,博士,副教授,主要研究方向为开放网络环境下的信任评估模型、需求工程、软件理论.E-mail:shaokun@hfut.edu.cn

作者简介: 霍星,博士,副教授,主要研究方向为机器学习、图像处理.E-mail:huoxing@hfut.edu.cn.檀结庆,博士,教授,主要研究方向为计算机辅助设计与图形学、图像处理.E-mail:jieqingtan@hfut.edu.cn.赵峰,硕士,高级工程师,主要研究方向为信号与信息处理、智能交通和交通安全.E-mail:zf6489@163.com.景永俊,博士研究生,高级工程师,主要研究方向为软件工程、机器学习.E-mail:jyj@nun.edu.cn.

引用本文:

霍星, 檀结庆, 赵峰, 景永俊, 邵堃. 基于多识别区域融合的机动车驾驶员检测框架^*[J]. 模式识别与人工智能, 2018, 31(3): 283-292. HUO Xing, TAN Jieqing, ZHAO Feng, JING Yongjun, SHAO Kun. Motor Vehicle Driver Detection Framework Based on Multi-detected Region Fusion. , 2018, 31(3): 283-292.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201803010 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2018/V31/I3/283

[1] GUO H W, LIN H, ZHANG S H, et al. Image-Based Seat Belt Detection // Proc of the IEEE International Conference on Vehicular Electronics and Safety. Washington, USA: IEEE, 2011: 161-164.
[2] 高新波,王楠楠,彭春蕾,等.基于三元空间融合的人脸图像模式识别.模式识别与人工智能, 2015, 28(9): 811-821.
(GAO X B, WANG N N, PENG C L, et al. Facial Image Pattern Recognition Based on Triple Space Fusion. Pattern Recognition and Artificial Intelligence, 2015, 28(9): 811-821.)
[3] 王亚南,苏剑波.基于图像合成的多姿态人脸图像识别方法.模式识别与人工智能, 2015, 28(9): 848-856.
(WANG Y N, SU J B. Multipose Face Image Recognition Based on Image Synthesis. Pattern Recognition and Artificial Intelligence, 2015, 28(9): 848-856.)
[4] 杨章静,黄璞,张凡龙,等.中心线邻域鉴别嵌入算法及其在人脸识别中的应用.模式识别与人工智能, 2015, 28(12): 1100-1109.
(YANG Z J, HUANG P, ZHANG F L, et al. Center-Based Line Neighborhood Discriminant Embedding Algorithm and Its Application to Face Recognition. Pattern Recognition and Artificial Intelligence, 2015, 28(12): 1100-1109.)
[5] DO T T, DOAN K N, LE T H, et al. Boosted of Haar-like Features and Local Binary Pattern Based Face Detection // Proc of the International Conference on Computing and Communication Technologies. Washington, USA: IEEE, 2009. DOI: 10.1109/RIVF.2009.5174627.
[6] 吴法.图像处理与机器学习在未系安全带驾车检测中的应用.博士学位论文.杭州:浙江大学, 2013.
(WU F. Seatbelt Unfasten Driving Detection Based on Image Processing and Machine Learning. Ph.D. Dissertation. Hangzhou, China: Zhejiang University, 2013.)
[7] 黎华东.智能交通中的违章识别算法研究.硕士学位论文.哈尔滨:哈尔滨工业大学, 2014.
(LI H D. Research on Illegal Identification Algorithm in Intelligent Traffic System. Master Dissertation. Harbin, China: Harbin Institute of Technology, 2014.)
[8] 葛如海,胡满江,符凯.基于灰度积分投影的安全带佩戴识别方法.汽车工程, 2012, 34(9): 787-790.
(GE R H, HU M J, FU K. A Method of Recognizing Seat-Belt Wear Based on Gray Scale Integral Projection. Automotive Enginee-ring, 2012, 34(9): 787-790.)
[9] 徐兵,李振德.基于图像分析的安全带识别算法研究.电子技术与软件工程, 2014(6): 120-121.
(XU B, LI Z D. Research on Seat Belt Identification Algorithm Based on Image Analysis. Electronic Technology & Software Engineering, 2014(6): 120-121.)
[10] 李赓.基于Adaboost的安全带检测方法.硕士学位论文.合肥:合肥工业大学, 2015.
(LI G. Seat Belt Detection Based on the Adaboost. Master Dissertation. Hefei, China: Hefei University of Technology, 2015.)
[11] 石时需,秦勇,蔡昭权,等.基于高速公路交通图像的安全带自动识别算法.计算机与现代化, 2014(5): 118-121.
(SHI S X, QIN Y, CAI Z Q, et al. Seatbelt Automatic Recognition Algorithm Based on Highway Traffic Image. Jisuanji yu Xiandaihua, 2014(5): 118-121.)
[12] 肖淑琴,刘锦高.基于纹理特征和连通域分析的车牌定位.计算机科学, 2009, 36(4A): 290-293.
(XIAO S Q, LIU J G. Location of the Vehicle Plate Based on the Texture Properties and Connected Analysis. Computer Science, 2009, 36(4A): 290-293.)
[13] 李孟歆,吴成东,夏兴华.一种车牌识别系统中的混合车牌定位方法.微计算机信息, 2008, 24(9-3): 280-282.
(LI M X, WU C D, XIA X H. A Hybrid License Plate Position Method for Vehicle Plate Recognition System. Microcomputer Information, 2008, 24(9-3): 280-282.)
[14] 连静,王珂,杨兆升.多尺度图像边缘检测技术在车辆识别中的应用.公路交通科技, 2007, 24(9): 87-91.
(LIAN J, WANG K, YANG Z S. The Technique of Multi-scale Image Edge Detection Applying to Vehicle Recognition. Journal of Highway and Transportation Research and Development, 2007, 24(9): 87-91.)
[15] 侯殿福.车窗检测技术研究.硕士学位论文.北京:北京交通大学, 2012.
(HOU D F. Study on Vehicle Window Detection Technology. Master Dissertation. Beijing, China: Beijing Jiaotong University, 2012.)
[16] LAHIRI A, BISWAS P K. A Scalable Model for Knowledge Sharing Based Supervised Learning Using AdaBoost // Proc of the 8th International Conference on Advances in Pattern Recognition. Washington, USA: IEEE, 2015. DOI: 10.1109/ICAPR.2015.7050684.
[17] GE K B, WEN J, FANG B. Adaboost Algorithm Based on MB-LBP Features with Skin Color Segmentation for Face Detection // Proc of the International Conference on Wavelet Analysis and Pa-ttern Recognition. Berlin, Germany: Springer, 2011: 40-43.
[18] LIU M H. Fingerprint Classification Based on Adaboost Learning from Singularity Features. Pattern Recognition, 2010, 43(3):1062-1070.
[19] WANG C C R, LIEN J J J. AdaBoost Learning for Human Detection Based on Histograms of Oriented Gradients // Proc of the 8th Asian Conference on Computer Vision. Berlin, Germany: Sprin-ger, 2007: 885-895.
[20] 田仙仙,鲍泓,徐成.一种改进HOG特征的行人检测算法.计算机科学, 2014, 41(9): 320-324.
(TIAN X X, BAO H, XU C. Improved HOG Algorithm of Pedestrian Detection. Computer Science, 2014, 41(9): 320-324.)
[21] 周柯.基于HOG特征的图像人体检测技术的研究与实现.硕士学位论文.武汉:华中科技大学, 2008.
(ZHOU K. Research and Implementation of HOG Based Human Detection in Image. Master Dissertation. Wuhan, China: Huazhong University of Science and Technology, 2008.)
[22] 曹莹,苗启广,刘家辰,等.Adaboost算法研究进展与展望.自动化学报, 2013, 39(6): 745-758.
(CAO Y, MIAO Q G, LIU J C, et al. Advance and Prospects of AdaBoost Algorithm. Acta Automatica Sinica, 2013, 39(6): 745-758.)
[23] 龙敏.基于多示例学习的Adaboost算法及其在人脸检测中的应用.硕士学位论文.上海:上海交通大学. 2007.
(LONG M. Multiple Instance Learning Based Adaboost Algorithm and Its Application in Face Detection. Master Dissertation. Shanghai, China: Shanghai Jiaotong University, 2007.)
[24] 张驰.基于粒子群的AdaBoost算法及其在人脸检测中的应用研究.硕士学位论文.武汉:华中师范大学, 2010.
(ZHANG C. Study for Adaboost Algorithm Based on PSO and Its Application in Human Face Detection. Master Dissertation. Wuhan, China: Central China Normal University, 2010.)
[25] 林景亮,唐杰.一种融合肤色和Haar特征的人脸检测方法.微型机与应用, 2013, 32(8): 35-37.
(LIN J L, TANG J. A Method of Face Detection Used Skin Color and Haar Features. Microcomputer and Its Applications, 2013, 32(8): 35-37.)
[26] 刘军.人脸图像识别关键技术的研究.博士学位论文.北京:北京邮电大学, 2015.
(LIU J. Research on the Key Technology of Face Recognition. Ph.D. Dissertation. Beijing, China: Beijing University of Posts and Telecommunications, 2015.)
[27] 胡元奎.可变光照和可变姿态条件下的人脸图像识别研究.博士学位论文.合肥:中国科学技术大学, 2006.
(HU Y K. Face Recognition with Variant Illumination and Poses. Ph.D. Dissertation. Hefei, China: University of Science and Technology of China, 2006.)