Spatial-temporal division based on peak hour traffic flow rate is used in the detection of a traffic anomaly. A spatial-temporal subzone is created by dividing one day into several time segments of 30 minutes, each defined as a time subzone; dividing one implemented area into several spatial segments of 200m x 200m or 400m x 400 m according as the peak hour flow rate is greater or less than 1000 vehicles per hour, each defined as a spatial subzone; and defining an intersection of one time subzone and one spatial subzone as a spatial-temporal subzone. Historical and real-time GNSS positioning data of floating vehicles is respectively pre-processed into sampled vehicle speed data relating to historical and real-time trajectories. These are used in a finite mixed modelling method to establishing respective historical and real-time travel speed probability distributions. Jensen-Shannon divergence is then used to measure a difference between said probability distributions and an anomaly index of traffic conditions is determined from said difference. The accuracy of said anomaly index is then evaluated.
展开▼
机译:基于交通高峰时间的时空划分被用于交通异常的检测。通过将一天分为30分钟的几个时间段来创建时空分区,每个时间段都定义为一个时间分区;根据高峰时流量大于或小于每小时1000辆的速度,将一个实施区域划分为200m x 200m或400m x 400 m的几个空间段,每个空间段定义为一个空间分区;将一个时间子区域和一个空间子区域的交集定义为时空子区域。将浮动车辆的历史和实时GNSS定位数据分别预处理为与历史和实时轨迹有关的采样车速数据。这些用于有限混合建模方法中,以建立各自的历史和实时行进速度概率分布。然后,使用詹森-香农(Jensen-Shannon)散度来测量所述概率分布之间的差异,并根据所述差异确定交通状况的异常指数。然后评估所述异常指数的准确性。
展开▼