2018 IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)
Lake Tahoe, NV, USA
Mar 12, 2018 to Mar 15, 2018
In order to continuously estimate camera pose with known line features correspondences between 3D lines in the real world and 2D lines in the image plane, we present a novel non-linear optimization method utilizing Plücker coordinates and a minimal representation of rigid motion. Inspired by the bundle adjustment pose estimation method, we use a minimal 6 Degree of Freedom (DoF) vector to denote rigid motion based on the Lie Algebra and Lie group theory. For the first time, we deduct the Jacobian matrix of the line's Plücker coordinates over the motion vector. Thus we are able to optimize the reprojection error to the minimal to find the solution with all the orthogonormality contraints fully considered. Benefited from the use of non-redundant representation of 6-DoF motion, our method requires only at least 3 lines correspondences, which makes our method applicable with limited matching pairs. Experiments in both simulation and real world images show that our method is fast, accurate, robust and suitable for motion-only Bundle Adjustment pose estimation in SLAM applications.
cameras, image matching, image motion analysis, image representation, image sensors, Jacobian matrices, Lie algebras, Lie groups, optimisation, pose estimation, robot vision, SLAM (robots)
Y. Cao, H. Tan and F. Zhou, "Minimal Non-Linear Camera Pose Estimation Method Using Lines for SLAM Application," 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, 2018, pp. 947-954.