English

Person-MinkUNet: 3D Person Detection with LiDAR Point Cloud

Computer Vision and Pattern Recognition 2021-07-15 v1 Robotics

Abstract

In this preliminary work we attempt to apply submanifold sparse convolution to the task of 3D person detection. In particular, we present Person-MinkUNet, a single-stage 3D person detection network based on Minkowski Engine with U-Net architecture. The network achieves a 76.4% average precision (AP) on the JRDB 3D detection benchmark.

Keywords

Cite

@article{arxiv.2107.06780,
  title  = {Person-MinkUNet: 3D Person Detection with LiDAR Point Cloud},
  author = {Dan Jia and Bastian Leibe},
  journal= {arXiv preprint arXiv:2107.06780},
  year   = {2021}
}

Comments

accepted as an extended abstract in JRDB-ACT Workshop at CVPR21