arXiv:2507.05999v3 Announce Type: replace 
Abstract: Accurate geo-registration of LiDAR point clouds remains a significant challenge in urban environments where Global Navigation Satellite System (GNSS) signals are denied or degraded. Existing methods typically rely on real-time GNSS and Inertial Measurement Unit (IMU) data, which require pre-calibration and assume stable signals. However, this assumption often fails in dense cities, resulting in localization errors. To address this, we propose a structured geo-registration method that accurately aligns LiDAR point clouds with satellite images, enabling frame-wise geo-registration and city-scale 3D reconstruction without prior localization. Our method uses a pre-trained Point Transformer to segment road points, then extracts road skeletons and intersections from the point cloud and the satellite image. Global alignment is achieved through rigid transformation using corresponding intersection points, followed by local non-rigid refinement with radial basis function (RBF) interpolation. Elevation discrepancies are corrected using terrain data from the Shuttle Radar Topography Mission (SRTM). To evaluate geo-registration accuracy, we measure the absolute distances between the roads extracted from the two modalities. Our method is validated on the KITTI benchmark and a newly collected dataset of Perth, Western Australia. On KITTI, our method achieves a mean planimetric alignment error of 0.69m, representing 50% improvement over the raw KITTI data. On Perth dataset, it achieves a mean planimetric error of 2.17m from GNSS values extracted from Google Maps, corresponding to 57.4% improvement over rigid alignment. Elevation correlation improved by 30.5% (KITTI) and 55.8% (Perth). A demonstration video is available at: https://youtu.be/0wkACAB-O6E.

تم تطوير طريقة جديدة لتسجيل بيانات LiDAR مع الصور الساتلية، مما يعالج التحديات في المناطق الحضرية حيث تكون إشارات GNSS غير موثوقة. تتيح هذه الطريقة إعادة بناء ثلاثية الأبعاد دقيقة على مستوى المدينة دون الحاجة إلى تحديد الموقع مسبقًا، حيث تحقق خطأ متوسطًا في المحاذاة يبلغ 0.69 متر، مما يمثل تحسينًا بنسبة 50% مقارنة بالطرق الحالية. هذه التطورات مهمة للتخطيط الحضري وتقنيات الملاحة.

Se ha desarrollado un nuevo método para el geo-registro de nubes de puntos LiDAR con imágenes satelitales, abordando desafíos en áreas urbanas donde las señales GNSS son poco confiables. Este enfoque permite una reconstrucción 3D precisa a escala de ciudad sin localización previa, logrando un error de alineación medio de 0.69 metros, lo que representa una mejora del 50% sobre los métodos existentes. Este avance es significativo para la planificación urbana y las tecnologías de navegación.

Une nouvelle méthode de géo-enregistrement des nuages de points LiDAR avec des images satellites a été développée, répondant aux défis dans les zones urbaines où les signaux GNSS sont peu fiables. Cette approche permet une reconstruction 3D précise à l'échelle de la ville sans localisation préalable, atteignant une erreur d'alignement moyenne de 0,69 mètre, représentant une amélioration de 50 % par rapport aux méthodes existantes. Cette avancée est significative pour la planification urbaine et les technologies de navigation.

A new method for geo-registering LiDAR point clouds with satellite images has been developed, addressing challenges in urban areas where GNSS signals are unreliable. This approach allows for accurate city-scale 3D reconstruction without prior localization, achieving a mean alignment error of 0.69 meters, which represents a 50% improvement over existing methods. This advancement is significant for urban planning and navigation technologies.

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

Was this article worth reading? Share it

GPTHumanizer

Supametas.AI

LexiStock AI

Zemith-3bda3b

Com.locatelloapp

Dyad

Ready to build your own newsroom?