众源车辆轨迹加油停留行为探测与加油站点提取

发布时间：2018-01-24 10:23

本文关键词： 车辆轨迹加油站加油行为 Stop/Move模型语义增强　出处：《测绘学报》2017年07期 　论文类型：期刊论文

【摘要】：针对当前加油站点信息采集成本高、更新周期长等问题,提出了运用车辆轨迹数据提取加油站点的方法。首先,从轨迹运动特征、几何模式等方面分析个体和群体加油行为轨迹特征。其次,基于Stop/Move模型,集成加油轨迹运动特征提出速度序列线性聚类算法提取加油停留轨迹。最后,运用Delaunay三角网层次聚类加油停留轨迹线,综合运用傅里叶形状识别、语义约束等方法识别、提取加油站点。运用北京市7d的出租车轨迹数据进行试验分析,共提取482个加油站,正确率为93.1%,且位置精度高。
[Abstract]:In order to solve the problems such as high cost of information collection and long renewal period, a method of extracting refueling station using vehicle track data is proposed. Firstly, the characteristics of track motion are analyzed. Geometric patterns and other aspects of the analysis of individual and group refueling behavior trajectory characteristics. Secondly, based on the Stop/Move model. Integrating the motion characteristics of the oil trajectory, the velocity sequence linear clustering algorithm is proposed to extract the oil stay trajectory. Finally, the Delaunay triangular network hierarchical clustering is used to cluster the oil stay trajectory. Comprehensive use of Fourier shape recognition, semantic constraints and other methods to identify, extract refueling station, using 7d taxi track data for experimental analysis, a total of 482 gas stations extracted. The accuracy is 93. 1 and the position accuracy is high.
【作者单位】：国土资源部城市土地资源监测与仿真重点实验室;武汉大学资源与环境科学学院;
【基金】：国土资源部城市土地资源监测与仿真重点实验室开放基金(KF-2015-01-038) 国家自然科学基金(41531180)~~
【分类号】：P208;U495
【正文快照】： 随着城乡道路建设的快速发展,道路基础设施(如加油站、停车场等)新建、拆建频繁,导致交通基础地理数据更新滞后、完整度低。目前,包括加油站、停车场在内的交通基础设施POI点主要依靠人工调绘、专业测量采集。但传统方法成本高、更新周期长,难以满足实际应用需求[1]。众源志愿

【参考文献】