K. Palaniappan, and
Applied Imagery Pattern Recognition (AIPR),
UAVs in both civil and defense aviation have found numerous application areas in the last decade which resulted in sophisticated systems that extracts high level information utilizing the visual data from UAVs. Camera auto-calibration is always the first step if the intrinsic parameters of the cameras are not available. However, this process is not trivial as the aerial imagery mostly contains planar scenes which constitute a degenerate condition for conventional methods. In this paper, we propose a hybrid approach which incorporates circular point and camera position constraints as a single optimization term to automatically calibrate the camera of the UAV on planar scenes. The experimental results show that our proposed hybrid method is more robust and accurate than the conventional counterparts.
author = "A. Akay and H. AliAkbarpour and K. Palaniappan and G. Seetharaman",
title = "Camera Auto-calibration for Planar Aerial Imagery Supported by Camera Metadata",
year = 2017,
journal = "Applied Imagery Pattern Recognition (AIPR)",
month = "Apr",
keywords = "auto-calibration, planar scene reconstruction, metadata recovery, aerial imagery"
A. Akay, H. AliAkbarpour, K. Palaniappan, and G. Seetharaman. Camera Auto-calibration for Planar Aerial Imagery Supported by Camera Metadata. Applied Imagery Pattern Recognition (AIPR), April 2017.