Geo-Registration of Terrestrial LiDAR Point Clouds with Satellite Images without GNSS

2025-07-08

AI Summary

In GNSS-denied dense urban environments, this paper proposes a ground LiDAR point cloud–satellite image georegistration method that requires no prior positioning information. The method employs an end-to-end framework to jointly extract road skeletons and intersections from both modalities, enabling global rigid alignment; it further incorporates radial basis function (RBF)-based local non-rigid correction and integrates SRTM terrain data to refine elevation estimation. By eliminating reliance on real-time GNSS/IMU measurements or pre-calibration, the approach significantly enhances absolute geolocation robustness. Evaluated on the KITTI dataset, it achieves a planimetric registration standard deviation of 0.84 m—55.3% improvement over baseline methods—and attains 0.96 m on GNSS-denied real-world Perth urban data—a 77.4% improvement. Elevation correlation increases by 30.5% and 50.4%, respectively, demonstrating the method’s effectiveness for absolute 3D georeferencing of urban-scale maps.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Security and Privacy: Large-scale security measurements

Abstract

Accurate geo-registration of LiDAR point clouds presents significant challenges in GNSS signal denied urban areas with high-rise buildings and bridges. Existing methods typically rely on real-time GNSS and IMU data, that require pre-calibration and assume stable positioning during data collection. However, this assumption often fails in dense urban areas, resulting in localization errors. To address this, we propose a structured geo-registration and spatial correction method that aligns 3D point clouds with satellite images, enabling frame-wise recovery of GNSS information and reconstruction of city scale 3D maps without relying on prior localization. The proposed approach employs a pre-trained Point Transformer model to segment the road points and then extracts the road skeleton and intersection points from the point cloud as well as the target map for alignment. Global rigid alignment of the two is performed using the intersection points, followed by local refinement using radial basis function (RBF) interpolation. Elevation correction is then applied to the point cloud based on terrain information from SRTM dataset to resolve vertical discrepancies. The proposed method was tested on the popular KITTI benchmark and a locally collected Perth (Western Australia) CBD dataset. On the KITTI dataset, our method achieved an average planimetric alignment standard deviation (STD) of 0.84~m across sequences with intersections, representing a 55.3% improvement over the original dataset. On the Perth dataset, which lacks GNSS information, our method achieved an average STD of 0.96~m compared to the GPS data extracted from Google Maps API. This corresponds to a 77.4% improvement from the initial alignment. Our method also resulted in elevation correlation gains of 30.5% on the KITTI dataset and 50.4% on the Perth dataset.

Problem

• Aligns LiDAR point clouds with satellite images without GNSS
• Recovers GNSS information in GNSS-denied urban areas
• Improves accuracy of 3D map reconstruction in cities

Innovation

• Aligns LiDAR point clouds with satellite images
• Uses Point Transformer for road segmentation
• Applies RBF interpolation for local refinement