A Robust Subset-ICP Method for Point Set Registration
Iterative Closest Point (ICP) is a popular point set registration method often used for rigid registration problems. Because of all points in ICP-based method are processed at each iteration to find their correspondences, the method’s performance is bounded by this constraint. This paper introduces an alternative ICP-based method by considering only subset of points whose boundaries are determined by the context of the inputs. These subsets can be used to sufficiently derive spatial mapping of point’s correspondences between the source and target set even if points have been missing or modified slightly in the target set. A brief description of this method is followed by a comparative analysis of its performance against two ICP-based methods, followed by some experiments on its subset’s sensitivity and robustness against noise.
KeywordsIterative Closest Point (ICP) Correspondences Transformation Registration error Subset Expectation Maximization (EM)
Unable to display preview. Download preview PDF.
- 5.Jost, T., Hügli, H.: A Multi-Resolution ICP with Heuristic Closest Point Search for Fast and Robust 3D Registration of Range Images. In: Proceedings of the 4th International Conference on 3-D Digital Imaging and Modeling, pp. 427–433 (2003)Google Scholar
- 6.Zinßer, T., Schmidt, J., Niemann, H.: A Refined ICP Algorithm for Robust 3-D Correspondence Estimation. In: Proceedings of the IEEE International Conference on Image Processing, pp. 695–698 (2003)Google Scholar
- 10.Chen, J., Liao, I.Y., Belaton, B., Zaman, M.: A Neural Network-Based Registration Method for 3D Rigid Face Image. World Wide Web (2013), doi:10.1007/s11280-013-0213-9Google Scholar
- 12.Rusinkiewicz, S., Levoy, M.: Efficient variants of the ICP Algorithm. In: Proceedings of the 3th International Conference on 3-D Digital Imaging and Modeling, pp. 1–8 (2001)Google Scholar
- 14.Gold, S., Rangarajan, A., Lu, C.-P., Mjolsness, E.: New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence. Pattern Recognition 31, 957–964 (1997)Google Scholar
- 16.Chen, J., Belaton, B.: An Improved Iterative Closest Point Algorithm for Rigid Point Registration. In: Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC), TianJin, pp. 481–485 (2013)Google Scholar
- 17.Latecki, L.J., Lakämper, R., Eckhardt, U.: Shape descriptors for non rigid shapes with a single closed contour. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 424–429 (2000)Google Scholar