Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding

 
: Wu, Chengzhi; Pfrommer, Julius; Beyerer, Jürgen; Li, Kangning; Neubert, Boris

:

Institute of Electrical and Electronics Engineers -IEEE-:
Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR) 2020 : 26. - 29.08.2020, Kitakyushu, Japan
Piscataway, NJ: IEEE, 2020
ISBN: 978-1-7281-9332-8
ISBN: 978-1-7281-9331-1
8 S.
International Conference on Informatics, Electronics & Vision (ICIEV) <9, 2020, Kitakyushu>
International Conference on Imaging, Vision & Pattern Recognition (IVPR) <4, 2020, Kitakyushu>
International Conference on Activity and Behavior Computing (ABC) <2, 2020, Kitakyushu>
Englisch
Konferenzbeitrag
Fraunhofer IOSB ()
three-dimensional displays; object detection; feature extraction; Task analysis; proposal; correlation; convolution

Abstract
We present an improved approach for 3D object detection in point clouds data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point features. The newly introduced local neighborhood embedding operation mimics the convolutional operations in 2D neural networks. Thus features of each point are not only computed with the features of its own or of the whole point cloud, but also computed especially with respect to the features of its neighbors. Experiments show that our proposed method achieves better performance than the F-Pointnet baseline on 3D object detection tasks. Contribution-This research improves the 3D object detection performance for point clouds data with local correlation-aware embedding strategies.

: http://publica.fraunhofer.de/dokumente/N-621872.html