Vision-Aided Indoor Pedestrian Dead Reckoning

Vision-aided inertial navigation has become a very popular method for indoor navigation recently. This popularity is basically due to the development of light-weighted and low-cost Micro Electro-Mechanical Systems (MEMS) as well as advancement and availability of Charged-Couple-Device (CCD) cameras in public indoor areas. While the use of inertial sensors and cameras are challenging due to drift accumulation and object detection in line of sight, respectively, the integration of these two sensors can compensate their drawbacks and provide more accurate positioning solutions. This study examines this hypothesis by evaluating the accuracy of the vision-aided systems for indoor positioning and tracking. The novel aspect of this study is to implement inertial and visual sensors in independent platforms other than attached together on the same platform. The other novelty is to integrate digitized floor plans for absolute position information. The mean accuracy of this positioning system is 11% higher than uncalibrated inertial positioning during experiment.