Automated Calibration of Stereo Camera Systems for Imaging Scoliosis Patients

摘要

The study of external back shape deformity in scoliosis is often dependent on 3D imaging of the torso, which use 3D laser scanners, rasterography etc. Use of a stereo digital camera imaging system to construct the 3D image provides a cheaper alternative. Calibration of the pair of digital cameras is an essential part of this process. Calibration is done to determine the geometry between the pair of cameras and the patient. Firstly, calibration requires acquisition of one or more images of an object containing landmarks of known position and dimensions such as checkerboard, pegboard etc. Then, manual identification of these landmarks are performed. Both of these steps are tedious and time consuming. This paper presents a novel approach of automated template matching on a pegboard image followed by Hartley's 8-Point algorithm to determine the underlying geometry. We use a pair of stereo cameras, the pegboard and the subject in a unique setup to eliminate the need for aquiring images as part of the calibration process. The method was compared to commonly used methods of calibration such as Direct Linear Transform (DLT) and the Camera Calibration Matlab Toolbox developed by Jean-Yves Bouguet. Results indicate that the procedure was atleast 75% faster than the existing methods. It's accuracy ranged from 90-100% compared to 75-100% for existing methods. This work provides a faster alternative to existing calibration processes which are prone to human errors. It is an important step towards making stereo digital camera systems a useful clinical tool in 3D torso imaging.