Object recognition using point uncertainty regions as pose uncertainty regions

摘要

In this paper, a recognition algorithm based on point features is presented. In this algorithm sets of hypothesized matches between model and image points are generated. From them the pose of the object is estimated and stored in a lookup table. When two similar poses are found the pose is assumed to be correct and the hypothesis is verified. The main contribution of this paper is that poses and their uncertainties are represented by the uncertainty regions of the projections of several 3D points, which are circles in the image. These uncertainty regions are due to the measurement uncertainty of the image features, which result in uncertainty in the recovered pose. When two poses are consistent, the pairs of uncertainty regions of the same 3D point will have a non-empty intersection. The algorithm exploits the fact that these uncertainty regions can be computed easily and accurately. The algorithm has been implemented and tested on real images.