Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Generation, Classification and Segmentation of Point Clouds in Logistic Context with PointNet++ and DGCNN

 
: Chai, Keng Yip; Stenzel, Jonas; Jost, Jana

:

Institute of Electrical and Electronics Engineers -IEEE-:
3rd International Conference on Intelligent Robotics and Control Engineering, IRCE 2020 : August 10-12, 2020, Oxford, UK
Piscataway, NJ: IEEE, 2020
ISBN: 978-1-72818-972-7
ISBN: 978-1-72818-971-0
ISBN: 978-1-72818-973-4
S.31-36
International Conference of Intelligent Robotic and Control Engineering (IRCE) <3, 2020, Online>
Englisch
Konferenzbeitrag
Fraunhofer IML ()
deep learning; Point Cloud Classification; Point Cloud Segmentation

Abstract
Many possible use-cases for deep-learning-based 3D object recognition in logistic environments have been proposed [1]. Nonetheless, the applicability of this technology in a logistic context has yet to be explored. Additionally, no dataset regarding point clouds in a logistic setting yet exists. Therefore, this paper investigates the generation of point clouds for logistics and the use of deep learning for classification and segmentation of the generated datasets. First, we generate different datasets regarding logistics with a virtual sensor. Afterwards, two state-of-the-art networks are evaluated and compared: PointNet++ and DGCN [2] [3]. Three different tasks are considered: The classification of logistic objects under the closed-world as well as the open-set assumption is assessed. Finally, the segmentation of logistic scenes is evaluated. Additionally, since simple surfaces can be removed reliably by traditional means, the effect of removing these as preprocessing step is evaluated as well. Both networks are able to reliably classify logistic objects with and without floor, even in the presence of unknown classes. However, while the segmentation performs well on average, some negative outliers do exist. Using transfer learning by pretraining the network with point clouds presenting the complete shape leads to a better performance.

: http://publica.fraunhofer.de/dokumente/N-614589.html