An Improved Iterative Solution to the PnP Problem

Abstract

The PnP (perspective-n-point) problem is very important in pose estimation technique based on computer vision. Aiming at this issue, an improved iterative solution is proposed. By the means of expressing the 3D point coordinates as a weighted sum of four control points, a system of homogeneous linear equations was established and then the optimized projections on the normalized image plane were obtained. The final estimation result was achieved by a relaxation-based iterative approach. Both simulations and experiments certify that the proposed algorithm can improve the computing accuracy and depress the image noise. Compared with other solutions to the PnP problem, the proposed algorithm can reduce the computational complexity while maintaining high precision with noise depression capability.