The invention relates to the technical field of data processing, in particular to a traffic flow statistical method based on urban moving vehicle detection. The method comprises the following steps: acquiring a traffic data set of a to-be-counted city, and calculating the traffic data set of the to-be-counted city according to the difference between a date corresponding to missing data and a first sub-data sequence corresponding to a to-be-analyzed date and the difference between a road section corresponding to the missing data and a second sub-data sequence corresponding to a to-be-analyzed road section; obtaining a reference factor of a first sub-data sequence corresponding to each to-be-analyzed date and a reference factor of a second sub-data sequence corresponding to each to-be-analyzed road section; according to the spatial difference of the corresponding average speed data in the preset neighborhood of the missing data, the confusion degree of the collection moment corresponding to the missing data is obtained; and based on the reference factor and the confusion degree, determining the optimal completion value of the missing data, and further predicting the traffic flow data at the future moment. According to the invention, the credibility of the traffic flow data prediction result is improved.
本发明涉及数据处理技术领域,具体涉及一种基于城市运动车辆检测的车流量统计方法。方法包括:获取待统计城市的交通数据集,根据缺失数据所对应日期与待分析日期对应的第一子数据序列之间的差异、以及缺失数据所对应路段与待分析路段对应的第二子数据序列之间的差异,得到各待分析日期对应的第一子数据序列的参考因子和各待分析路段对应的第二子数据序列的参考因子;根据缺失数据的预设邻域内对应的平均速度数据的空间差异,得到缺失数据对应的采集时刻的混乱程度;基于参考因子和混乱程度,确定缺失数据的最优补全值,进而预测未来时刻的车流量数据。本发明提高了车流量数据预测结果的可信度。
Traffic flow statistical method based on urban moving vehicle detection
一种基于城市运动车辆检测的车流量统计方法
2023-04-25
Patent
Electronic Resource
Chinese
Vehicle detection method, traffic flow statistical method and device
European Patent Office | 2023
|Airborne Moving Vehicle Detection for Video Surveillance of Urban Traffic
British Library Conference Proceedings | 2009
|