Indoor human localization: a sensor fusion approach using long distance capacitive and infrared sensors.

Nowadays technology is increasingly present in our lives: the furniture in our homes becomes increasingly smarter and interacts with us, robots are replacing us in carrying out a lot of works, even in the assistance and monitoring of people in need of care. In this context to localize people inside a closed environment arouses a lot of interest since it could lead to numerous improvements in everyday life. Indoor human localization can be used in smart homes for predicting the needs of the inhabitants based on their location and movements, adjusting the lights, the heating or a sound system in the proximity of the person. In the entertainment field, video-games could take advantage of the position of the player, for example to move an avatar in a virtual world. Considering also more serious arguments, indoor human localization would be for example a huge help, for people with visual impairments, in finding the way inside an unknown building while in hospitals and hospices it can help monitoring patients remotely. For these and more other applications a growing interest in this field has developed during the last years. In this context, the present thesis work aims to design a low cost, easy to use, un-obtrusive, passive, tag-less and privacy aware indoor location system that can be safely and easily installed in smart homes and assisted living environments. This thesis is part of a larger project a research team at the Department of electronics and telecommunications (DET) of POLITO is working on. The project has the aim of inferring the indoor position and the trajectory of a person using long range capacitive sensors, digital filters, and neural networks. This system presents a lot of advantages but it is affected by noise that reduce the reliability of the system itself. In order to make an improvement, it was decided to implement a complementary sensor fusion technique between the capacitive system and an infrared sensor based system . During the thesis work an analysis of the state of art technologies for the indoor human localization has been made. Among all the various indoor location systems studied, the infrared sensors based system has been chosen because it is affected by kinds of noise that are often complementary to the ones of capacitive sensors. Moreover, it is a tagless, not expensive, privacy aware and safe localization system that can be easily placed in the target environments. After testing all system components separately , a complete experiment has been set up using 4 capacitive sensors , the infrared sensor and an ultrasound sensor as reference. The data from all the sensors have been acquired simultaneously and the obtained results have been analyzed. From the results has been observed that the sensor fusion approach has led to an improvement of the performance, reliability and accuracy of the overall system by dampen the weak points of a technique with the advantages of the other and viceversa.