基于乘客多运动行为的公交客流计数判定方法  

Bus Passenger Flow Counting Criteria Method Based on Passenger Multi-movement Behavior

作　　者：鲜晓东[1] 石亚麋[1] 唐云建 袁宇鹏[1] 樊宇星 

机构地区：[1]重庆大学自动化学院,重庆400044 [2]重庆市科学技术研究院,重庆400044

出　　处：《计算机工程》2015年第4期176-180,186,共6页Computer Engineering

基　　金：重庆市科技攻关计划基金资助重点项目(cstc2011gg B40015)

摘　　要：针对基于单目视觉的公交乘客人数统计判定方法不稳定、计数结果不准确的现状,结合公交车门附近乘客运动行为的复杂性和多样性,以及乘客运动行为对计数判定方法的干扰,给出一种基于乘客多运动行为分析的计数判定方法。采用轨迹聚类的方式对乘客运动行为进行分析,结合轨迹的空间特征和方向特征计算轨迹距离,并使用层次聚类方法进行聚类。分析聚类结果中每一类别所对应乘客类的运动行为,讨论各乘客类的运动行为对常用计数判定准则的影响,由此提出一种改进的公交车客流计数判定方法。利用采集的乘客上下公交车视频图像进行实验,结果表明,该方法能获得较高的统计精度和较好的稳定性。In view of the instability and inaccuracy of bus passenger statistic with monocular vision based method,a new statistic method based on passengers＇ multi-movement behavior is proposed,w hich combines the complexity and variety of passengers＇ behavior. Passengers＇ movement behavior is analyzed w ith trajectory clustering algorithm. The trajectory distance w hich is clustered w ith hierarchical clustering method is calculated according to the spatial feature and the directional feature of the trajectory. The clustering result corresponds to a certain kind of movement behavior of passenger,the influence of each movement behavior to the common counting criterion is discussed. In a result,the method based on passengers＇ multi-movement behavior for bus passenger statistic is proposed. Experimental results based on the video w hen passengers getting on and getting off show that the method can obtain a high statistical precision and good stability.

关 键 词：乘客人数统计 轨迹聚类 HAUSDORFF距离 层次聚类 乘客运动行为 计数判定 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]