Lane-Level Road Information Mining from Vehicle GPS Trajectories Based on Naive Bayesian Classification
Lane-Level Road Information Mining from Vehicle GPS Trajectories Based on Naive Bayesian Classification
复制标题
基于朴素贝叶斯分类的车辆GPS轨迹车道级道路信息挖掘
DOI：
10.3390/ijgi4042660
复制
发表时间：
2015-12-01
影响因子：
3.4
通讯作者：
Li, Qingquan
中科院分区：
文献类型：
--
作者：
Tang, Luliang;Yang, Xue;Li, Qingquan
在本文中，我们提出了一种新的方法来挖掘车道级的道路网络信息，从低精度的车辆GPS轨迹（MLIT），其中包括交通车道的数量和转向规则的基础上朴素贝叶斯分类。首先，所提出的方法（MLIT）使用自适应密度优化方法，以消除离群点从原始GPS轨迹的时空分布和密度聚类的基础上。其次，MLIT分两步获取车道数。第一步根据训练样本中道路平面和道路轮廓的轨迹特征以及真实的车道数建立朴素贝叶斯分类器。第二步使用测试样本的已知迹线特征参考朴素贝叶斯分类器来确认使用测试样本的泳道数。第三，MLIT通过跟踪GPS轨迹推断每个车道的转弯规则。利用武汉市出租车的GPS轨迹进行了实验。与人工判读结果相比，自动生成的车道级道路网络信息在显示详细的道路网络、车道数和每条车道的转弯规则方面具有更高的质量。
In this paper, we propose a novel approach for mining lane-level road network information from low-precision vehicle GPS trajectories (MLIT), which includes the number and turn rules of traffic lanes based on naive Bayesian classification. First, the proposed method (MLIT) uses an adaptive density optimization method to remove outliers from the raw GPS trajectories based on their space-time distribution and density clustering. Second, MLIT acquires the number of lanes in two steps. The first step establishes a naive Bayesian classifier according to the trace features of the road plane and road profiles and the real number of lanes, as found in the training samples. The second step confirms the number of lanes using test samples in reference to the naive Bayesian classifier using the known trace features of test sample. Third, MLIT infers the turn rules of each lane through tracking GPS trajectories. Experiments were conducted using the GPS trajectories of taxis in Wuhan, China. Compared with human-interpreted results, the automatically generated lane-level road network information was demonstrated to be of higher quality in terms of displaying detailed road networks with the number of lanes and turn rules of each lane.