3D City Modeling from Street-Level Data for Augmented Reality Applications
Citations Over TimeTop 10% of 2012 papers
Abstract
We present a method for automatically creating compact and accurate 3D city models needed for enhanced Augmented Reality applications. The input data are panorama images and LIDAR scans collected at street level and positioned using an IMU and a GPS. Our method corrects for the GPS error and the IMU drift to produce a globally consistent and well registered dataset for the whole city. We use structure from motion and skyline detection to complement the limited range of LIDAR data. Additionally, we propose a novel reconstruction technique that exploits architectural properties of urban environments to create an accurate 3D city model from incomplete data. Our method is able to process an entire city, or several terabytes of data, in a matter of days. We show that our reconstruction achieves higher accuracy than a commercial solution.
Related Papers
- → 3D object detection and state estimation method based on stereo vision and LIDAR fusion(2021)3 cited
- → Research on Fusion Method of Lidar and Visual Image Based on Surface Vehicle(2019)2 cited
- → Monocular Visual-inertial Localization in a Point Cloud Map Using Feature-to-Distribution Registration(2021)2 cited
- → Improved real-time odometry estimation method for incremental RGB-D mapping by fusing IMU data(2016)1 cited
- → Low-Cost GPS-Aided LiDAR State Estimation and Map Building(2019)2 cited