Paper Info
Title
Improved actionSLAM for long-term indoor tracking with wearable motion sensors
Abstract
We present an indoor tracking system based on two wearable inertial measurement units for tracking in home and workplace environments. It applies simultaneous localization and mapping with user actions as landmarks, themselves recognized by the wearable sensors. The approach is thus fully wearable and no pre-deployment effort is required. We identify weaknesses of past approaches and address them by introducing heading drift compensation, stance detection adaptation, and ellipse landmarks. Furthermore, we present an environment-independent parameter set that allows for robust tracking in daily-life scenarios. We assess the method on a dataset with five participants in different home and office environments, totaling 8.7h of daily routines and 2500m of travelled distance. This dataset is publicly released. The main outcome is that our algorithm converges 87% of the time to an accurate approximation of the ground truth map (0.52m mean landmark positioning error) in scenarios where previous approaches fail.
Year
DOI
Venue
2013
10.1145/2493988.2494328
ISWC
Keywords
Field
DocType
long-term indoor tracking,drift compensation,different home,indoor tracking system,improved actionslam,wearable sensor,daily routine,algorithm converges,accurate approximation,wearable inertial measurement unit,wearable motion sensor,robust tracking,daily-life scenario
Inertial frame of reference,Computer vision,Units of measurement,Computer science,Wearable computer,Tracking system,Ground truth,Artificial intelligence,Ellipse,Landmark,Simultaneous localization and mapping
Conference
Citations 
PageRank 
References 
19
0.86
18
Authors
3
Name
Order
Citations
PageRank
Michael Hardegger11308.89
Gerhard Tröster22493250.70
Daniel Roggen31851137.05