Hidden Markov map matching through noise and sparseness

By Paul Newson, John Krumm. ACM SIGSPATIAL International Workshop on Advances in Geographic Information Systems, 2009

1,106 citations recorded by the source corpus.

Subfields: Building and Construction, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/e573b7076a8a6e1ec8044351e4bd149194ec2e19

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

1. Yu Zheng
2. Xing Xie
3. Jing Yuan
4. Haitao Yuan
5. Guoliang Li
6. Guangzhong Sun
7. Zhifeng Bao
8. Gao Cong

In Electrical and Electronic Engineering

1. Sertac Karaman
2. Xing Xie
3. Gao Cong
4. Daniela Rus
5. Alexander Amini
6. Guy Rosman
7. Yu Zheng
8. Haitao Yuan

Citations in the corpus

• Variational End-to-End Navigation and Localization (2018, methodology): “We implemented our map matching algorithm as an offline pre-processing step as in [29].”
• Singapore in Motion: Insights on Public Transport Service Level Through Farecard and Mobile Data Analytics (2016, methodology): “The main graph-based spatio-temporal functionalities in CiM are: (1) ingestion of the road and rail network; (2) fast shortest-path algorithms on the graph between two points using constrained graph search; (3) Hidden Markov Model (HMM) based map-matching algorithm to identify the most likely trajec”
• A Survey on Trajectory Data Management, Analytics, and Learning (2020, background): “truth is required, and is a problem in its own right. There are three common ways to generate a ground truth for the map-matching problem: 1) using real vehicles equipped with GPS devices on the road [129]; 2) human adjudication [119]; and 3) simulated GPS sampling [89] which is the least costly app”
• An Interactive-Voting Based Map Matching Algorithm (2010, methodology): “In [29], the evaluation shows the error rate is more than 50% when the sampling interval exceeds 5 minutes.”
• Trajectory Data Mining (2015, methodology): “…to the additional categorized into four groups: geometric [Greenfeld 2002], topological [Chen et al. 2003; Yin and Wolfson 2004], probabilistic [Ochieng et al. 2004; Pink and Hummel 2008; Quddus et al. 2006], and other advanced techniques [Lou et al. 2009; Newson and Krumm 2009; Yuan et al. 2010b].”
• A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation (2021, background): “For example, Some works [45] prefer a candidate pair whose distance is similar to the distance between the observation pairs, while others consider velocity changes [48] and turn restriction [50].”