Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
土木工程、水利工程、交通工程     
面向驾驶员注视区域划分的DBSCAN-MMC方法
孙文财, 杨志发, 李世武, 徐艺, 郭梦竹, 魏学新
吉林大学 交通学院,吉林 长春 130022
Driver fixation area division oriented DBSCAN-MMC method
SUN Wen-cai, YANG Zhi-fa, LI Shi-wu, XU Yi, GUO Meng-zhu, WEI Xue-xin
Transportation School, Jilin University, Changchun 130022, China
 全文: PDF(1548 KB)   HTML
摘要：

 针对典型密度聚类（DBSCAN）受参数影响较大和数学形态学聚类（MMC）需大量人工干预的问题,将DBSCAN与改进的MMC相结合,提出面向驾驶员注视点离散、注视集中区域不规则特点的DBSCAN-MMC聚类方法.实例验证结果表明，该方法充分利用DBSCAN和MMC的不规则形状聚类优势并较好地弥补2种聚类方法的缺陷.通过比较证明DBSCAN-MMC在进行驾驶员注视区域划分时聚类效果优于常规K-means聚类方法和DBSCAN聚类方法,提高驾驶员注视区域划分质量.
Abstract:

The result of density based spatial clustering of applications with noise (DBSCAN) is largely impacted by parameters and the mathematical morphology clustering (MMC) needs large artificial intervention. The driver’s fixation points are discrete and driver’s centralized fixation areas are irregularity. A driver fixation area division oriented method DBSCAN-MMC that combines the DBSCAN and the MMC is proposed to take advantage of the DBSCAN and the MMC, and to solve the problems of driver’s fixation areas division. The results of examples show that the proposed method took advantages of irregular clustering in the DBSCAN and the MMC, and the method made up for deficiencies of the DBSCAN and the MMC. It is verified through comparing results of division that the clustering effect of the DBSCAN-MMC in dividing driver’s fixation area is better than the effects of conventional K-means and DBSCAN, and the DBSCAN-MMC improved the dividing quality of the driver’s fixation area.
出版日期: 2015-08-01
:  U 495  
基金资助:

国家自然科学基金青年基金资助项目（51308250）；吉林省科技发展计划重点科技攻关资助项目（20140204021SF）；吉林省交通运输科技资助项目（2014-1-3）；科学前沿与交叉学科资助项目（2013ZY06）；中国博士后基金特别资助项目（2014T70292）；西华大学重点实验室开放基金资助项目（s2jj2012-038）.
通讯作者: 李世武,男,教授.     E-mail: lshiwu@163.com
作者简介: 孙文财（1981—）,男,副教授,主要从事交通环境与安全技术研究.E-mail: swcai@163.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

孙文财, 杨志发, 李世武, 徐艺, 郭梦竹, 魏学新. 面向驾驶员注视区域划分的DBSCAN-MMC方法[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2015.08.008.

SUN Wen-cai, YANG Zhi-fa, LI Shi-wu, XU Yi, GUO Meng-zhu, WEI Xue-xin. Driver fixation area division oriented DBSCAN-MMC method. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2015.08.008.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2015.08.008    或    http://www.zjujournals.com/eng/CN/Y2015/V49/I8/1455

［1］ 郭应时.交通环境及驾驶经验对驾驶员眼动和工作负荷影响的研究［D］. Xián: 长安大学, 2009.
GUO Ying-shi. Study on effects of traffic environment and driving experience on driver’s eye movement and workload ［D］. Chang’an University, 2009.
［2］ 袁伟.城市道路环境中汽车驾驶员动态视觉特性试验研究［D］.Xián: 长安大学, 2008.
YUAN Wei. Study on Car Driver’s Dynamic visual characters test on city road ［D］. Chang’an University, 2008.
［3］ ESTER M, KRIEGEL H P, SANDER J, et al. A Density-based algorithm for discovering clusters in large spatial databases with noise ［C］∥ Proc of 2nd Int’ l Conf on Knowledge Discovering in Databases and Data Mining (KDD-96). Portland: AAAI Press, 1996.
［4］ ANKERST M, BREUNIG M M, KRIEGEL H P. OPTICS: ordering points to identify the clustering structure ［C］∥ Alex Delis, Christos Faloutsos, Shahram Ghandeharizadeh eds. Proceedings of the ACM SIGMOD’99 Int Conf on Management of Data. Philaelphia Pennsylvanis: ACM Press, 1999: 49-60.
［5］ LIN C Y, CHANG C C, LIN C C. A new density-based scheme for clustering based on genetic algorithm ［J］. Fundamenta Informaticae, 2005, 68 (4): 315-331.
［6］ FENG P J, GE L D. Adaptive DBSCAN-based algorithm for constellation reconstruction and modulation identification ［C］∥ Proceedings of Radio Science Conference 2004. Beijing: Pub House of Electronics Industry, 2004: 177-180.
［7］ XU X, ESTER M, KRIEGEL H P, et al. A distribution-based clustering algorithm for mining in large spatial databases ［C］∥ eds. Proceedings of the 14th International Conference On Data Engineering (ICDE’98). Orlando: IEEE Computer Society Press, 1998: 324-331.
［8］ 蔡颖琨,谢昆青,马修军.屏蔽了输入参数敏感性的DBSCAN改进算法［J］.北京大学学报: 自然科学版, 2004, 40(3): 480-486.
CAI Ying-kun, XIE Kun-qing, MA Xiu-jun. An improved DBSCAN algorithm which is insensitive to input parameters ［J］. Acta Scientiarum Naturalium Universitatis Pekinensis, 2012, 36(5): 911-915.
［9］ 夏鲁宁,荆继武.SA-DBSCAN:一种自适应基于密度聚类算法［J］.中国科学院研究生院报, 2009, 26(4): 530-538.
XIA Lu-ning, JING Ji-wu. SA-DBSCAN: A self-adaptive density2based clustering algorithm ［J］. Journal of the Graduate School of the Chinese Academy of Sciences, 2009, 26(4): 530-538.
［10］ POSTAIRE J G, ZHANG R D C. Lecocq-botte. cluster analysis by binary morphology ［J］. IEEE Computer Society, 1993, 15(2): 170-180.
［11］ STAROVOITOV V.. A clustering technique based on the distance transform ［J］. Pattern Recognition Letters, 1996, 17: 231-239.
［12］ 罗会兰,孔繁胜,杨小兵,等.基于数学形态学的聚类分析 ［J］.模式识别与人工智能, 2006, 19(6): 727-733.
LUO Hui-Lan, KONG Fan-sheng, YANG Xiao-bing, et al. Cluster analysis based on mathematical morphology ［J］. PR&AI, 2006, 19(6): 727-733.
［13］ 罗会兰,危辉.基于数学形态学的聚类集成算法［J］.计算机科学,2010, 37(8): 214-218.
LUO Hui-lan, WEI Hui. Clustering ensemble algorithm based on mathematical morphology ［J］. Computer Science, 2010, 37(8): 214-218.
［14］ 邸凯昌,李德仁,李德毅.从空间数据库发现聚类:一种基于数学形态学的算法 ［J］. 中国图象图形学报, 1998, 3(3): 173-183.
DI Kai-chang, LI De-ren, LI De-yi. A mathematical morphology based algorithm for discovering clusters in spatial databases ［J］. Journal of Image and Graphics, 1998, 3(3): 173-183.
[1] 李世武, 徐艺, 王琳虹, 孙文财, 别一鸣. 基于万有引力搜索算法的低排放自适应配时[J]. 浙江大学学报(工学版), 2015, 49(7): 1313-1318.