Pedestrian Inertial Navigation System with Terrain Characterization using Information Fusion
| Autor: | Ricardo Anacleto, Paulo Novais, Ana de Almeida, Lino Figueiredo, Ant´onio Meireles |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Inertial frame of reference
Artificial neural network business.industry ComputerApplications_COMPUTERSINOTHERSYSTEMS 020302 automobile design & engineering Terrain 02 engineering and technology Pedestrian Units of measurement Geography 0203 mechanical engineering Inertial measurement unit 11. Sustainability Dead reckoning 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Inertial navigation system |
| Zdroj: | Advanced Science and Technology Letters. |
| ISSN: | 2287-1233 |
| DOI: | 10.14257/astl.2015.97.06 |
| Popis: | Pedestrian inertial navigation systems are an alternative to systems that are based on structured environments. However, due to low-cost inertial sensors and pedestrian dead reckoning inherent char- acteristics, these systems provide huge location estimation errors. Thus, we propose a system that uses two inertial measurement units spread in person's body, which measurements are used by a neural network to learn the human gait behavior. In this work we demonstrate how this neural network is used to characterize the step according to the type of terrain, which can be at and ascending or descending stairs. These terrains are the ones that are most encountered inside a building. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|