A practical indoor tracking system should be accurate, affordable, portable and easy-to-use. However, most of the current tracking applications lack in at least one of these properties. To fill this gap, we present such a 3D tracking system. Built around two to four wireless Nintendo Wii Remotes, the system can simultaneously track up to four infrared LEDs carried by multiple users. The set up and calibration takes only a few minutes. A semiautomatic calibration method is used, where the user places the infrared LED marker sequentially on the four corners of a freely defined square in the tracking area. Within a cube with an edge length of 2.5 m, the system was found to be able to track both a static and a moving target with an accuracy of 3 cm. In addition to discussing the developed system, this paper presents computational methods for improving the positioning accuracy by altering the assumed optical centers of the Wii Remote cameras, which vary due to intrinsic differences in them.

Accurate, simple and affordable methods for passive indoor tracking of human beings are still missing. In this article, we describe the development of an unobtrusive two-dimensional human positioning system based on low-frequency electric fields. The system's operation is based on measuring the capacitance between multiple floor tiles and a receiving electrode. The presented system is invisible to the user and uses a single-chip solution to measure the capacitances. The implemented system is evaluated with two different types of receiving electrodes and the results are presented. With the used tiles, the system can locate a standing human with at least 15 cm accuracy and track a walking person with at least 41 cm accuracy. The update rate of the system is 10 Hz.

In this paper we describe a simple, cheap, and unobtrusive demo system that can track multiple persons with low-frequency electric fields. The system's operation is based on measuring the capacitance between multiple floor tiles and a receiving electrode. The presented system is invisible to the user and uses a single-chip solution to measure the capacitances. The system was provided for hands-on evaluation for conference attendees with a 3.0 times 1.8 m floor space. The position and the track of the persons walking on the floor were projected on a screen. The floor of the demo system is divided to two different sections that are built of two different sizes of floor tiles to show how the tile size affects the positioning accuracy and the update rate of the system.

In this paper we describe a context-sensitive way to change an active mobile phone profile. We present a method to create a proactive and adaptive phone profile control system that automatically adapts the profile to the best alternative based on the current context. The adaptation is based on recognizing patterns of human practices, which may change over time. The control system is implemented with a fuzzy controller that supports reinforcement learning. The operation of the system is demonstrated with a mobile phone that is controlled by a PC. The PC lets a user to simulate the context parameters, and the phone works as a user interface for profile selection and display.