Camera recovery of an omnidirectional multi-camera system using GPS positions

This paper describes a novel method for estimating positions and postures of an omnidirectional multi-camera system from its multiple image sequences and sparse position data acquired by GPS. The proposed method is based on a structure-from-motion technique which is enhanced by using multiple image sequences as well as GPS position data. Moreover, the position data are also used to remove mis-tracked features. The proposed method allows us to estimate position and posture without accumulative errors and annoying effects due to moving objects in outdoor environments. The validity of the method is demonstrated through experiments using both synthetic and real outdoor scenes.
First Korea-Japan Joint Workshop on Pattern Recognition , Nov 23-24, 2006 , Jeju, Korea