计算机工程 ›› 2019, Vol. 45 ›› Issue (3): 78-84.doi: 10.19678/j.issn.1000-3428.0050055

• 移动互联与通信技术 • 上一篇    下一篇

大型商场中移动群组识别与位置预测方法

陈娇娇,朱卫平,屠明暄,唐熠杰,孙泽宇   

  1. 武汉大学 国际软件学院,武汉 430070
  • 收稿日期:2018-01-10 出版日期:2019-03-15 发布日期:2019-03-15
  • 作者简介:陈娇娇(1992—),女,硕士研究生,主研方向为传感器网络、群组识别与分析;朱卫平(通信作者),副教授、博士;屠明暄、唐熠杰、孙泽宇,本科生。
  • 基金项目:

    国家自然科学基金(61502351);武汉大学珞珈青年学者基金(1503/600400001);湖北楚天学者项目

Mobile Group Recognition and Location Prediction Method in Large Shopping Mall

CHEN Jiaojiao,ZHU Weiping,TU Mingxuan,TANG Yijie,SUN Zeyu   

  1. International School of Software,Wuhan University,Wuhan 430070,China
  • Received:2018-01-10 Online:2019-03-15 Published:2019-03-15

摘要:

根据大型商场中人员密度大且流动性强的特点,对室内场所中的动态群组进行识别和位置预测,提出移动对象位置和方向特征相结合的空间-时序聚类群组识别方法。在群组位置预测中,考虑数据集的增量更新给出序列树的存储结构,只需扫描一次数据库即可得到频繁区域序列以及对应的关联规则,同时能够进行单步和多步的位置预测。给出结合群组出现时间和人数的位置预测方法,提高群组位置预测的准确度。在ATC数据集进行实验,结果表明,当群组对象检测率达到87.6%时,该方法群组识别准确度可达到90.3%,与LAR、TLAR等算法相比,单步和多步位置预测准确度分别达到91.2%和33.8%。

关键词: 移动群组识别, 空间-时序聚类, 序列树, 频繁区域序列, 关联规则, 群组位置预测

Abstract:

According to the characteristics of large density and strong mobility in large shopping malls,in order to identify and predict the dynamic groups in indoor spaces,a method is proposed to identify the groups by spatial-sequence clustering combined with the moving object position and direction features.In the group location prediction,the sequential tree storage structure is proposed in consideration of the incremental updating of the dataset.This structure can obtain the frequent area sequences and the corresponding association rules by scanning the database only once,and can perform single-step and multi-step position predictions.In order to improve the accuracy of group location prediction,a method based on group appearance time and group number is proposed.Experimental verification is carried out in the ATC data set,and results show that when the detection rate of group objects reaches 87.6% by using this method,the accuracy of group identification reaches 90.3%,compared with the algorithms such as LAR and TLAR,the single-step and multi-step position prediction accuracy reach 91.2% and 33.8% respectively.

Key words: mobile group recognition, spatial-temporal clustering, sequential tree, frequent area sequence, asssociation rules, group location prediction

中图分类号: