A Fully Projective Formulation to Improve the Accuracy of Lowe's Pose-Estimation Algorithm

摘要

Both the original version of David Lowe's influential and classic algorithm for tracking known objects and a reformulation of it implemented by Ishiiet al. rely on (different) approximated imaging models. Removing their simplifying assumptions yields a fully projective solution with significantly improved accuracy and convergence, and arguably better computation-time properties.