Related Experiment Video
Updated: Mar 16, 2026

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
Published on: February 8, 2019
Conditional Random Field-Based Offline Map Matching for Indoor Environments.
Safaa Bataineh1, Alfonso Bahillo2, Luis Enrique Díez3
1Faculty of Engineering, University of Deusto, Av. Universidades, 24, Bilbao 48007, Spain. safaa.bataineh@deusto.es.
This study introduces an offline map matching technique using conditional random fields (CRF) to improve indoor localization accuracy. The CRF algorithm refines existing localization data by matching it with indoor maps for better positioning.
Area of Science:
- Computer Science
- Geographic Information Science
Background:
- Indoor localization systems often require map matching for accurate positioning.
- Existing localization methods may produce results that need refinement against a map.
Purpose of the Study:
- To investigate the efficiency of conditional random fields (CRF) for offline map matching in indoor localization.
- To evaluate the CRF technique across various scenarios and parameters.
Main Methods:
- Developed an offline map matching technique utilizing conditional random fields (CRF).
- Implemented a loosely coupled approach integrating the CRF algorithm with existing indoor localization systems.
- Applied the algorithm to real and simulated trajectory data of varying lengths.
Main Results:
- The CRF-based map matching technique successfully refined and matched trajectories with the map.
- Demonstrated the algorithm's applicability to diverse indoor localization scenarios.
Conclusions:
- Conditional random fields offer an effective method for offline map matching in indoor localization.
- The proposed technique enhances the accuracy of indoor positioning systems by refining localization data against maps.
Related Concept Videos
Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
Types of Global Positioning System Surveys
Field Application of Global Positioning System
Random Sampling Method
Random Variables
Uppercase letters such as X or Y denote a random variable. Lowercase letters like x or y denote the value of a random variable. If X is a random variable, then X is written in words, and x is given as a number.
For example, let X = the...
Errors in Global Positioning System

