AmbiTrack - Marker-free Indoor Localization and Tracking of Multiple Users in Smart Environments with a Camera-based Approach

Systems providing tracking and localization of persons in an indoor environment have been continuously proposed in recent years, particularly for Pervasive Computing applications. AmbiTrack is a system that provides marker-free localization and tracking, i.e., it does not require the users to carry any tag with them in order to perform localization. This allows easy application in circumstances where wearing a tag is not viable, e.g. in typical Ambient Assisted Living scenarios, where users may not be well-versed technologically. In this work, we present the AmbiTrack system and its adaptation for the EvAAL competition 2013. We present a marker-free, camera-based system for usage in indoor environments designed for cost-effectiveness and reliability. We adapt our previously presented system to make it more reliable in tracking multiple persons, using context information for improving recognition rate and simplifying the installation.

[1]  Norbert A. Streitz,et al.  Distributed, Ambient, and Pervasive Interactions , 2014, Lecture Notes in Computer Science.

[2]  Neal Patwari,et al.  See-Through Walls: Motion Tracking Using Variance-Based Radio Tomography Networks , 2011, IEEE Transactions on Mobile Computing.

[3]  Stefano Chessa,et al.  Evaluating AAL Systems Through Competitive Benchmarking , 2012, Communications in Computer and Information Science.

[4]  Stefano Chessa,et al.  Evaluating AAL Systems Through Competitive Benchmarking. Indoor Localization and Tracking , 2011, Communications in Computer and Information Science.

[5]  Andreas Braun,et al.  CapFloor - A Flexible Capacitive Indoor Localization System , 2011, EvAAL.

[6]  J. Krumm,et al.  Multi-camera multi-person tracking for EasyLiving , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.

[7]  Andreas Braun,et al.  Marker-Free Indoor Localization and Tracking of Multiple Users in Smart Environments Using a Camera-Based Approach , 2013, HCI.

[8]  Yukang Guo,et al.  Localising speech, footsteps and other sounds using resource-constrained devices , 2011, Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks.

[9]  Diego López-de-Ipiña,et al.  TRIP: A Low-Cost Vision-Based Location System for Ubiquitous Computing , 2002, Personal and Ubiquitous Computing.

[10]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[11]  Douglas E. Sturim,et al.  Tracking multiple talkers using microphone-array measurements , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[12]  Paolo Barsocchi,et al.  EvAAL, Evaluating AAL Systems through Competitive Benchmarking, the Experience of the 1st Competition , 2011, EvAAL.

[13]  Michael S. Brandstein,et al.  A practical methodology for speech source localization with microphone arrays , 1997, Comput. Speech Lang..

[14]  Bodhi Priyantha,et al.  The Cricket indoor location system , 2005 .