C5.4 - Increasing the Reliability of Applications in AAL by Distinguishing Moving Persons from Pets by Means of a Sensor Floor
- Event
- AMA Conferences 2015
2015-05-19 - 2015-05-21
Nürnberg, Germany - Band
- Proceedings SENSOR 2015
- Chapter
- C5 - Medical Systems
- Author(s)
- R. Hoffmann, A. Steinhage, C. Lauterbach - Future-Shape GmbH, Höhenkirchen-Siegertsbrunn (Germany)
- Pages
- 436 - 440
- DOI
- 10.5162/sensor/C5.4
- ISBN
- 978-3-9813484-8-4
- Price
- free
Abstract
We introduce a method to track movement in indoor environments and distinguish persons from pets. The system uses sensor data from SensFloor®, a capacitive sensor that is installed in large areas under the floor and whish is capable of detecting the presence and location of persons and animals moving on it. Our algorithm determines the locations of entities on the floor in a first step, and then further analyses the location changes for typical movement patterns by humans or small animlas. Tests with cats and persons walking over a SensFloor installation showed that our algorithm can reliably separate the cat and person activation patterns. We propose that applications in the area of Ambient Assisted Living (AAL) and Smart Homes that depend on information about the locations of pesons, can benefit from the additional information if a tacked object is a person or a pet.