Map matching is to locate GPS trajectories onto the road networks, which is an important preprocessing step for many applications based on GPS trajectories. Currently, hidden Markov model is one of the most widely used methods for map matching. However, both effectiveness and efficiency of conventional map matching methods based on hidden Markov model will decline in the dense road network, as the number of candidate road segments enormously increases around GPS point. To overcome the deficiency, this paper proposes a segment-based hidden Markov model for map matching. The proposed method first partitions GPS trajectory into several GPS sub-trajectories based on the heading homogeneity and length constraint; next, the candidate road segment sequences are searched out for each GPS sub-trajectory; last, GPS sub-trajectories and road segment sequences are matched in hidden Markov model, and the road segment sequences with the maximum probability is identified. A case study is conducted on a real GPS trajectory dataset, and the experiment result shows that the proposed method improves the effectiveness and efficiency of the conventional HMM map matching method.

地图匹配是将GPS轨迹定位到道路网络上，这对于许多基于GPS轨迹的应用来说是重要的预处理步骤。当前，隐马尔可夫模型是地图匹配中使用最广泛的方法之一。然而，由于候选路段的数量在GPS点附近急剧增加，因此在密集的道路网络中，基于隐马尔可夫模型的传统地图匹配方法的有效性和效率都会下降。为克服这一不足，本文提出了一种基于分段的隐马尔可夫模型进行地图匹配。该方法首先基于航向均匀性和长度约束，将GPS轨迹划分为多个GPS子轨迹。接下来，针对每个GPS子轨迹搜索候选路段序列。持续，在隐马尔可夫模型中匹配GPS子轨迹和路段序列，并识别出概率最大的路段序列。对一个真实的GPS轨迹数据集进行了实例研究，实验结果表明，该方法提高了传统HMM地图匹配方法的有效性和效率。