Sager C, Zschech P, Kühl N (2022)
Publication Language: English
Publication Type: Journal article, Original article
Publication year: 2022
Book Volume: 19
Pages Range: 1191-1206
Issue: 6
Journal Issue: 6
URI: http://cad-journal.net/files/vol_19/CAD_19(6)_2022_1191-1206.pdf
DOI: 10.14733/cadaps.2022.1191-1206
Open Access Link: http://cad-journal.net/files/vol_19/Vol19No6.html
The rapid development of 3D sensors and object detection methods based on 3D point clouds has led to increasing demand for labeling tools that provide suitable training data. However, existing labeling tools mostly focus on a single use case and generate bounding boxes only indirectly from a selection of points, which often impairs the label quality. Therefore, this work describes labelCloud, a generic point cloud labeling tool that can process all common file formats and provides 3D bounding boxes in multiple label formats. labelCloud offers two labeling methods that let users draw rotated bounding boxes directly inside the point cloud. Compared to a labeling tool based on indirect labeling, labelCloud could significantly increase the label precision while slightly reducing the labeling time. Due to its modular architecture, researchers and practitioners can adapt the software to their individual needs. With labelCloud, we contribute to enabling convenient 3D vision research in novel application domains.
APA:
Sager, C., Zschech, P., & Kühl, N. (2022). labelCloud: A Lightweight Labeling Tool for Domain-Agnostic 3D Object Detection in Point Clouds. Computer-Aided Design and Applications, 19(6), 1191-1206. https://doi.org/10.14733/cadaps.2022.1191-1206
MLA:
Sager, Christoph, Patrick Zschech, and Niklas Kühl. "labelCloud: A Lightweight Labeling Tool for Domain-Agnostic 3D Object Detection in Point Clouds." Computer-Aided Design and Applications 19.6 (2022): 1191-1206.
BibTeX: Download