Development of a Change Detection Method with Low-Performance Point Cloud Data for Updating Three-Dimensional Road Maps

Three-dimensional (3D) road maps have garnered significant attention recently because of applications such as autonomous driving. For 3D road maps to remain accurate and up-to-date, an appropriate updating method is crucial. However, there are currently no updating methods with both satisfactorily high frequency and accuracy. An effective strategy would be to frequently acquire point clouds from regular vehicles, and then take detailed measurements only where necessary. However, there are three challenges when using data from regular vehicles. First, the accuracy and density of the points are comparatively low. Second, the measurement ranges vary for different measurements. Third, tentative changes such as pedestrians must be discriminated from real changes. The method proposed in this paper consists of registration and change detection methods. We first prepare the synthetic data obtained from regular vehicles using mobile mapping system data as a base reference. We then apply our proposed change detection method, in which the occupancy grid method is integrated with Dempster–Shafer theory to deal with occlusions and tentative changes. The results show that the proposed method can detect road environment changes, and it is easy to find changed parts through visualization. The work contributes towards sustainable updates and applications of 3D road maps