Robust registration of 2D and 3D point sets Export

@article{Fitzgibbon03, abstract = {This paper introduces a new method of registering point sets. The registration error is directly minimized using general-purpose non-linear optimization (the Levenberg–Marquardt algorithm). The surprising conclusion of the paper is that this technique is comparable in speed to the special-purpose Iterated Closest Point algorithm, which is most commonly used for this task. Because the routine directly minimizes an energy function, it is easy to extend it to incorporate robust estimation via a Huber kernel, yielding a basin of convergence that is many times wider than existing techniques. Finally, we introduce a data structure for the minimization based on the chamfer distance transform, which yields an algorithm that is both faster and more robust than previously described methods.}, author = {Fitzgibbon, A.}, citeulike-article-id = {4729828}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.imavis.2003.09.004}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0262-8856(03)00183-5}, doi = {10.1016/j.imavis.2003.09.004}, issn = {02628856}, journal = {Image and Vision Computing}, keywords = {icp, matching, non-linear-optimization, point-set, registration, robust}, month = {December}, number = {13-14}, pages = {1145--1153}, posted-at = {2009-10-26 10:11:37}, priority = {2}, title = {Robust registration of 2D and 3D point sets}, url = {http://dx.doi.org/10.1016/j.imavis.2003.09.004}, volume = {21}, year = {2003} }

TY - JOUR ID - Fitzgibbon03 L3 - citeulike-article-id:4729828 N2 - This paper introduces a new method of registering point sets. The registration error is directly minimized using general-purpose non-linear optimization (the Levenberg–Marquardt algorithm). The surprising conclusion of the paper is that this technique is comparable in speed to the special-purpose Iterated Closest Point algorithm, which is most commonly used for this task. Because the routine directly minimizes an energy function, it is easy to extend it to incorporate robust estimation via a Huber kernel, yielding a basin of convergence that is many times wider than existing techniques. Finally, we introduce a data structure for the minimization based on the chamfer distance transform, which yields an algorithm that is both faster and more robust than previously described methods. IS - 13-14 JF - Image and Vision Computing SN - 02628856 EP - 1153 TI - Robust registration of 2D and 3D point sets VL - 21 SP - 1145 KW - icp KW - matching KW - non-linear-optimization KW - point-set KW - registration KW - robust AU - Fitzgibbon, A PY - 2003/12// UR - http://dx.doi.org/10.1016/j.imavis.2003.09.004 ER -