3D reconstruction of urban environments using in-vehicle fisheye camera

This paper proposes a 3D reconstruction algorithm for urban environments from video sequences taken by an in-vehicle fisheye camera. The proposed algorithm employs (i) fisheye camera calibration to apply the general Structure from Motion to video sequences taken by the fisheye camera and (ii) accurate, dense and robust feature point tracking using phase-based correspondence matching. Experimental evaluation using the video sequence taken by the in-vehicle fisheye camera demonstrates that the proposed algorithm exhibits efficient performance of 3D reconstruction compared with the laser measurement system.