Real-Time Camera Parameter Estimation for 3-D annotation on a wearable vision System

摘要

In this paper, we describe a method for esti- mating external camera parameters in real time. We investi- gated the effectiveness of this method for annotating real scenes with 3-D virtual objects on a wearable computer. The proposed method enables determining known natural feature points of ob- jects through multiplied color histogram matching and template matching. This external-camera-parameter calculation method consists of three algorithms for PnP problems, and it uses each algorithm selectively.