# Map Matching based on Conditional Random Fields and Route Preference Mining for Uncertain Trajectories

arXiv: https://arxiv.org/abs/1410.4461 · HTML: https://mlsanity.com/paper/1410.4461/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2014.

## Built on by (most cited first, 2 of 2)

- [Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach](https://mlsanity.com/paper/2108.00439/) (2021)
- [Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model](https://mlsanity.com/paper/2511.01929/) (2025)

## Abstract (arXiv)

In order to improve offline map matching accuracy of low-sampling-rate GPS, a map matching algorithm based on conditional random fields (CRF) and route preference mining is proposed. In this algorithm, road offset distance and the temporal-spatial relationship between the sampling points are used as features of GPS trajectory in CRF model, which can utilize the advantages of integrating the context information into features flexibly. When the sampling rate is too low, it is difficult to guarantee the effectiveness using temporal-spatial context modeled in CRF, and route preference of a driver is used as replenishment to be superposed on the temporal-spatial transition features. The experimental results show that this method can improve the accuracy of the matching, especially in the case of low sampling rate.