A HMM map-matching approach enhancing indoor positioning performances of an inertial measurement system
Abstract
Map matching is defined as the process of correlating two sets of geographical positional information. Combined to dead-reckoning estimation approach, the map-matching improves significantly the overall positioning accuracy. In this paper, a new map-matching is proposed. This approach is derived from the Hidden Markov Model (HMM) theory and tailored to map-matching technique. The efficiency of the adopted approach is demonstrated thanks to the use of an inertial positioning system over large experiments. The adopted approach shows that improvement is achieved in terms of positioning accuracy as well as in computation cost compared to common techniques.