A novel map-matching algorithm to improve Vehicle Tracking System accuracy

Abstract

The satellite-based vehicle tracking system accuracy can be improved by augmenting the positional information using road network data, in a process known as map-matching. Map-matching algorithms attempt to pinpoint the vehicle in a particular road map segment (or any restricting track such as rails, etc), in spite of the digital map errors and navigation system inaccuracies. Point-to-curve matching algorithm is not suitable to the problem since it ignores any historical data and often gave unstable, jumping results. The better curve-to-curve matching algorithms considers the road connectivity and measure the similarity between track and the possible road path (hypotheses), but mostly does not have any way to manage multiple track hypotheses which have varying degree of similarity over time. The paper presents a new similarity metric for curve-to-curve map-matching technique, combined with the ability to maintain many possible road hypotheses and picks the most likely hypothesis at a time, enabling future corrections if necessary, therefore providing intelligent guesses with considerable accuracy.