帮助 关于我们

返回检索结果

基于DBSCAN 聚类算法的异常轨迹检测
Trajectory outlier detection based on DBSCAN clustering algorithm

查看参考文献22篇

周培培 1   丁庆海 1   罗海波 2   侯幸林 1  
文摘 现有的异常轨迹检测算法往往侧重于检测轨迹的空域异常,忽略了对轨迹时域异常的检测,并且检测精确度不高,针对此类问题,提出了基于增强聚类的异常轨迹检测算法。首先,采用基于速度的最小描述长度(VMDL)准则把轨迹简化成有序线段;然后,使用改进的线段间的距离定义,基于DBSCAN算法把线段分为不同的类,以建模局部正常运动模式;最后,采用先检测空间异常性再检测时间异常性的二级检测算法,检测时空异常轨迹点。在多个测试集上的实验结果表明:该算法可以检测位置、角度、速度等三种时空异常轨迹点,相对于其他算法,明显提高了异常轨迹检测的精确度。
其他语种文摘 Existing traditional trajectory outlier detection algorithms always focus on spatial outliers and ignore temporal outliers, and the accuracy is relatively low. To solve these problems, a simple and effective approach based on enhanced clustering algorithm was proposed to detect spatio-temporal trajectory outliers. Firstly, each original trajectory was simplified into a set of sequential line segments with the velocity-based minimum description length (VMDL) partition principle. Secondly, the distance formula between line segments was improved to enhance the clustering performance. Using DBSCAN algorithm, the line segments were classified into different groups which could represent local normal behaviors. Thirdly, outliers were detected using two-level detection algorithm which first detected spatial outliers and then detected temporal outliers. Experimental results on multiple trajectory data sets demonstrate that the proposed algorithm could successfully detect three kinds of spatio-temporal outliers, position, angle and velocity. Compared with other methods, the precision and accuracy make great improvement.
来源 红外与激光工程 ,2017,46(5):0528001-1-0528001-8 【核心库】
DOI 10.3788/IRLA201746.0528001
关键词 时空异常轨迹检测 ; VMDL 分割准则 ; DBSCAN 聚类算法 ; 二级检测算法
地址

1. 中国科学院沈阳自动化研究所, 辽宁, 沈阳, 110016  

2. 中国科学院沈阳自动化研究所, 中国科学院光电信息处理重点实验室, 辽宁, 沈阳, 110016

语种 中文
文献类型 研究性论文
ISSN 1007-2276
学科 自动化技术、计算机技术
文献收藏号 CSCD:6000360

参考文献 共 22 共2页

1.  Bamnett V. Outliers in Statistical Data,1995:584 被引 1 次    
2.  崔雄文. 子空间模型下的仿射不变目标跟踪. 红外与激光工程,2015,44(2):769-774 被引 6 次    
3.  Hi H. Real time robust l1 tracker using accelerated proximal gradient approach. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 157(10),2012:1830-1837 被引 1 次    
4.  Milan A. Joint tracking and segmentation of multiple targets. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015:5397-5406 被引 1 次    
5.  Lee J G. Trajectory outlier detection: A partition-and-detect framework. IEEE 24th International Conference on Data Engineering,2008:140-149 被引 2 次    
6.  Yuan G. Trajectory outlier detection algorithm based on structural features. Journal of Computational Information Systems,2011,11(7):4137-4144 被引 1 次    
7.  De Aquino A R. Towards semantic trajectory outlier detection. Proceedings of Geo Info,2013:115-126 被引 1 次    
8.  Liu Z. Density-based trajectory outlier detection algorithm. Journal of Systems Engineering and Electronics,2013,24(2):335-340 被引 5 次    
9.  Hu H Y. Multi-level trajectory learning for traffic behavior detection and analysis. Journal of the Chinese Institute of Engineers,2014,37(8):995-1006 被引 1 次    
10.  Zhang L. Trajectory outlier detection based on multi-factors. IEICE Transactions on Information and Systems,2014,E97D(8):2170-2173 被引 1 次    
11.  Lee J G. Trajectory clustering: a partition-and-group framework. Proceedings of the 2007 ACM SIGMOD International Conference on Management of Data,2007:593-604 被引 36 次    
12.  Kut A. Spatio-temporal outlier detection in large databases. CIT Journal of Computing and Information Technology,2006,14(4):291-297 被引 1 次    
13.  Alvar M. Abnormal behavior detection using dominant sets. Machine Vision and Applications,2014,25(5):1351-1368 被引 1 次    
14.  Wang Y. Abnormal behavior detection using trajectory analysis in camera sensor networks. International Journal of Distributed Sensor Networks,2014,2014(1):1-9 被引 3 次    
15.  Jeong H. Modeling of moving object trajectory by spatio-temporal learning for abnormal behavior detection. 2011 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS),2011:119-123 被引 1 次    
16.  Lee J G. TraClass: trajectory classification using hierarchical region -based and trajectory- based clustering. Proceedings of the VLDB Endowment,2008,1(1):1081-1094 被引 9 次    
17.  Fontes V C. Discovering trajectory outliers between regions of interest. Proceedings of Geo Info,2013:49-60 被引 1 次    
18.  Ester M. A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of Kdd Location,1996:226-231 被引 1 次    
19.  Chen J. Noisy logo recognition using line segment Hausdorff distance. Pattern Recognition,2003,36(4):943-955 被引 8 次    
20.  Li Weixin. Anomaly detection and localization in crowded scenes,2016 被引 1 次    
引证文献 1 篇

1 周培培 视频监控中的人群异常行为检测与定位 光学学报,2018,38(8):0815007-1-0815007-9
被引 7 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号