• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding
 
  • Details
  • Full
Options
2020
  • Konferenzbeitrag

Titel

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

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.
Author(s)
Wu, Chengzhi
Pfrommer, Julius
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Beyerer, Jürgen
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Li, Kangning
Neubert, Boris
Hauptwerk
Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR) 2020
Konferenz
International Conference on Informatics, Electronics & Vision (ICIEV) 2020
International Conference on Imaging, Vision & Pattern Recognition (IVPR) 2020
International Conference on Activity and Behavior Computing (ABC) 2020
Thumbnail Image
DOI
10.1109/ICIEVicIVPR48672.2020.9306522
Language
Englisch
google-scholar
IOSB
Tags
  • three-dimensional dis...

  • object detection

  • feature extraction

  • Task analysis

  • proposal

  • correlation

  • convolution

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022