Human Localization via Multi-Cameras and Floor Sensors in Smart Home

2013 IEEE International Conference on Systems, Man, and Cybernetics

Litz

et al. 2013

Abstract-Ambient Assisted Living (AAL) is a field of research aiming to improve the comfort and the safety of aged or disabled people living in their own house. Several AAL approaches require the location of the inhabitant to be tracked or could be improved by considering the real time location of the inhabitant. In this paper, it is proposed to use finite automata to build a model of dynamic tracking of a single person in his house. A method for systematic generation of such a finite automaton, starting from a description of the partition of the house in zones and of the instrumentation of the house, is presented. The evaluation of the relevance of a given instrumentation, based on the analysis of the generated finite automaton, is discussed. Finally, an efficient algorithm for location tracking based on a state estimator is proposed. For the sake of better understanding, an illustrative example is used throughout the paper.

Section: Introductionmentioning

confidence: 99%

Online Location Tracking of a Single Inhabitant Based on a State Estimator

2013 IEEE International Conference on Systems, Man, and Cybernetics

Litz

et al. 2013

“…In most approaches, location tracking is performed by using data mining techniques [1]- [3]. Consequently, a more or less long learning phase is required before the location tracking can be performed.…”

Section: Introductionmentioning

confidence: 99%

A Discrete event model for multiple inhabitants location tracking

2013 IEEE International Conference on Automation Science and Engineering (CASE)

Litz

et al. 2013

Abstract-Smart Home technologies are aiming to improve the comfort and safety of the inhabitants into their houses. To achieve this goal, online indoor location tracking of the inhabitants is often used to monitor the air conditioning, to detect dangerous situations and for many other applications. In this paper, it is proposed an approach to build a model allowing dynamic tracking of several persons in their house. A method to construct such a model by using finite automata and Discrete Event System (DES) paradigms is presented. An approach to reduce the size of the model is also introduced. Finally, an efficient algorithm for location tracking is proposed. For the sake of better understanding, an illustrative example is used throughout the paper.

“…This task consists in finding in real time the location of one or several inhabitants, based on the observation of the signals generated by the different sensors of the house [2]. Different sensor technologies like video cameras [3], radio frequency identification (RFID) tags [4], ultrasonic badges [5]... are used for performing LT. In order to help the users to accept the observation of their every movement and to guarantee the respect of their privacy and the reduction of cost, we choose to only consider non-wearable, non-intrusive and lowcost sensors.…”

Section: Introductionmentioning

confidence: 99%

A DES Simulator for Location Tracking of Inhabitants in Smart Home

Faraut

2013 8th EUROSIM Congress on Modelling and Simulation

et al. 2013

Abstract-In previous works we showed that, in return for some assumptions, indoor Location Tracking (LT) can be formulated as a Discrete Event Systems (DES) problem. We proposed a method for constructing Finite Automata (FA) models on which LT is performed online for single or multiple inhabitants. However, the accuracy of LT strongly depends on the choices of the designer concerning topology (in particular the splitting of the dwelling in zones) and the number and placement of sensors. To evaluate the impact of these choices onto the efficiency of the LT, we proposed an analytical approach that allows determining asymptotic performance criteria. This performance evaluation does not take into account the human behavior (real time moving of inhabitants) which is very difficult to model. In order to include the inhabitants behavior, and thus to improve the performance evaluation by considering dynamic criteria, we propose in this paper a discrete event simulation approach that allows to emulate the smart home and to immerse the human operator into this environment without having to model the human behavior.