Refine
Year of publication
Document Type
- Conference Proceeding (166)
- Article (67)
- Part of a Book (14)
- Doctoral Thesis (11)
- Other Publications (9)
- Working Paper (9)
- Master's Thesis (5)
- Report (3)
- Book (2)
- Bachelor Thesis (1)
Language
- English (288) (remove)
Keywords
- 2 D environment Laser data (1)
- AAL (1)
- Abstract interpretation (1)
- Activity monitoring (1)
- Actuators (1)
- Agenda 2030 (1)
- Algorithm (1)
- Alternative Energy Production (1)
- Ambient assisted living (1)
- Analog-Digital-Umsetzer (1)
Institute
- Fakultät Architektur und Gestaltung (1)
- Fakultät Bauingenieurwesen (1)
- Fakultät Elektrotechnik und Informationstechnik (2)
- Fakultät Informatik (23)
- Fakultät Maschinenbau (5)
- Fakultät Wirtschafts-, Kultur- und Rechtswissenschaften (4)
- Institut für Angewandte Forschung - IAF (5)
- Institut für Optische Systeme - IOS (9)
- Institut für Strategische Innovation und Technologiemanagement - IST (5)
- Institut für Systemdynamik - ISD (15)
Deep 3D
(2017)
Vortrag
In the reverse engineering process one has to classify parts of point clouds with the correct type of geometric primitive. Features based on different geometric properties like point relations, normals, and curvature information can be used, to train classifiers like Support Vector Machines (SVM). These geometric features are estimated in the local neighborhood of a point of the point cloud. The multitude of different features makes an in-depth comparison necessary. In this work we evaluate 23 features for the classification of geometric primitives in point clouds. Their performance is evaluated on SVMs when used to classify geometric primitives in simulated and real laser scanned point clouds. We also introduce a normalization of point cloud density to improve classification generalization.
Vortrag
Posterpräsentation
