VOXEL-BASED POINT CLOUD LOCALIZATION FOR SMART SPACES MANAGEMENT

Abstract. This paper proposes a voxel-based approach for creating digital twin of an urban environment that is capable efficiently managing smart spaces. The explains the registration and localization procedure point cloud dataset, which uses KISS ICP scan combination RANSAC method initial alignment combined cloud. mobile mapping using Riegl VMX-250 serves as reference map, Velodyne scans are used purposes. point-to-plane iterative closest-point then employed to refine alignment. evaluates efficacy proposed by calculating errors between estimated ground truth positions. results indicate accurately estimating position sensor platform, applicable various use cases. A specific case in context parking space management, described visualization shown.