Single pan and tilt camera indoor positioning and tracking system

Abstract

An inexpensive single pan and tilt camera based indoor positioning and tracking system is proposed, supported on an architecture where three main modules can be identified: one related to the interface with the camera, tackled with parameter estimation techniques; other, responsible for isolating and identifying the target, based on advanced image processing techniques, and a third, that resorting to nonlinear dynamic system suboptimal state estimation techniques, performs the tracking of the target and estimates its position, and linear and angular velocities. The contributions of this work are fourfold: i) a new indoor positioning and tracking system architecture; ii) a new lens distortion calibration method, that preserves generic straight lines in images; iii) suboptimal nonlinear multiple-model adaptive estimation techniques, for the adopted target model, to tackle the positioning and tracking tasks, and iv) the implementation and validation in real time of a complex tracking system, based on a low cost single camera. To assess the performance of the proposed system, a series of indoor experimental tests for a range of operation of up to ten meter were carried out. An accuracy of 20 cm was obtained under realistic conditions.