Generative models for road network reconstruction
Generative models for road network reconstruction
复制标题
DOI：
10.1080/13658816.2015.1092151
复制
发表时间：
2016-05-03
影响因子：
5.7
通讯作者：
Brenner, Claus
中科院分区：
文献类型：
--
作者：
Kuntzsch, Colin;Sester, Monika;Brenner, Claus
这项工作旨在从GPS轨迹推断交通网络。我们在一个多步骤的过程中执行网络的几何和拓扑重建。我们的主要贡献是制定了一个明确的交叉模型，该模型带有一个分数函数，该分数函数考虑了与原始跟踪数据的一致性，以及拓扑先验和使用马尔可夫链蒙特卡罗采样器通过最大化该分数函数来搜索最佳模型。我们通过对不同大小和数据质量的GPS数据集进行实验，证明了基于模型的方法的可行性，然后与其他启发式方法获得的结果进行了比较。
This work aims at the inference of traffic networks from GPS trajectories. We perform geometry and topology reconstruction of the network in a multistep process. Our main contributions are the formulation of an explicit intersection model with a score function that accounts for consistency with the raw tracking data, as well as for a topology prior and the search for the best model by maximization of this score function using a Markov chain Monte Carlo sampler. We demonstrate the viability of our model-based approach with experiments on GPS data sets of varying size and data quality, followed by a comparison with results achieved by alternative, heuristic approaches.