Evaluating the Accuracy of Tram Positioning System in High-Rise Building Environment Using Data from Visual Geoinformation Systems

This article describes an approach to evaluating the localization accuracy of a tram moving in an urban environment. The tram needs to be localized with a submeter level of accuracy. Since GPS information in urban environment does not provide such a level of accuracy, a solution based on the use of vision system information is proposed. By using keypoints, it is possible to estimate the motion of an object between images taken in different route passes, whereas this motion can also be calculated using the data from the on-board navigation system. The comparison of these motions will enable the assessment of the accuracy of the navigation system on board. The article provides the accuracy values obtained, as well as a description of the experiment conducted to evaluate the accuracy of the navigation algorithm.