--- _id: '1966' abstract: - lang: eng text: Point cloud registration is often used in fields like SLAM where the overlap of two consecutive point clouds is large. But in fields like multi-sensor fusion of point clouds and LiDAR-based localization, there is a high chance of registering non-overlapping point cloud pairs. Since in such cases, the result will always be a wrong transformation, it is useful to evaluate the alignability of the point cloud pairs prior to the registration. In this paper, an algorithm is presented that predicts the alignability of two point clouds based on the minimum distances of descriptors. It calculates statistical measures describing the minimum distances and classifies the point cloud pairs. The paper shows that it is possible to predict the alignability and evaluates the runtime compared to registration algorithms, as well as the ignoring of the largest minimum distances. author: - first_name: André full_name: Kirsch, André id: '229807' last_name: Kirsch - first_name: Andrei full_name: Günter, Andrei id: '225747' last_name: Günter orcid: 0000-0002-7836-9700 - first_name: Matthias full_name: König, Matthias id: '213498' last_name: König orcid: 0000-0002-4915-0750 citation: alphadin: 'Kirsch, André ; Günter, Andrei ; König, Matthias: Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features. In: 12th International Conference on Pattern Recognition Systems : IEEE, 2022' ama: 'Kirsch A, Günter A, König M. Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features. In: 12th International Conference on Pattern Recognition Systems. IEEE; 2022. doi:10.1109/ICPRS54038.2022.9854071' apa: 'Kirsch, A., Günter, A., & König, M. (2022). Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features. In 12th International Conference on Pattern Recognition Systems. Saint-Étienne: IEEE. https://doi.org/10.1109/ICPRS54038.2022.9854071' bibtex: '@inproceedings{Kirsch_Günter_König_2022, title={Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features}, DOI={10.1109/ICPRS54038.2022.9854071}, booktitle={12th International Conference on Pattern Recognition Systems}, publisher={IEEE}, author={Kirsch, André and Günter, Andrei and König, Matthias}, year={2022} }' chicago: Kirsch, André, Andrei Günter, and Matthias König. “Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features.” In 12th International Conference on Pattern Recognition Systems. IEEE, 2022. https://doi.org/10.1109/ICPRS54038.2022.9854071. ieee: A. Kirsch, A. Günter, and M. König, “Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features,” in 12th International Conference on Pattern Recognition Systems, Saint-Étienne, 2022. mla: Kirsch, André, et al. “Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features.” 12th International Conference on Pattern Recognition Systems, IEEE, 2022, doi:10.1109/ICPRS54038.2022.9854071. short: 'A. Kirsch, A. Günter, M. König, in: 12th International Conference on Pattern Recognition Systems, IEEE, 2022.' conference: end_date: 2022-06-10 location: Saint-Étienne name: 12th International Conference on Pattern Recognition Systems start_date: 2022-06-07 date_created: 2022-05-24T13:55:09Z date_updated: 2023-06-16T11:32:43Z doi: 10.1109/ICPRS54038.2022.9854071 keyword: - alignability prediction - point cloud registration - overlap metric - descriptors language: - iso: eng main_file_link: - url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9854071 project: - _id: A838A474-C7DA-11E9-B0AE-1F4CB252D58D name: 'DORIOT: Dynamische Laufzeitumgebung für organisch (dis-)aggregierende IoT-Prozesse' publication: 12th International Conference on Pattern Recognition Systems publication_status: published publisher: IEEE quality_controlled: '1' status: public title: Predicting Alignability of Point Cloud Pairs for Point Cloud Registration Using Features type: conference user_id: '216459' year: '2022' ...