Mask-VRDet: A robust riverway panoptic perception model based on dual graph fusion of vision and 4D mmWave radar

Runwei Guan, Shanliang Yao, Lulu Liu, Xiaohui Zhu, Ka Lok Man, Yong Yue, Jeremy S. Smith, Eng Gee Lim, Yutao Yue

Abstract

Highlights•A novel and effective clutter removal algorithm in the point cloud level for 4D mmWave radar.•A novel and high-performance panoptic perception model based on graph convolution network and feature-level fusion.•An effective method for simulating various adverse weather conditions in visual data augmentation to enhance the target representation capability of radar in adverse weather conditions.
BibTeX
@inproceedings{guan2024mask,
  author = {Runwei Guan and Shanliang Yao and Lulu Liu and Xiaohui Zhu and Ka Lok Man and Yong Yue and Jeremy S. Smith and Eng Gee Lim and Yutao Yue},
  title = {{Mask-VRDet: A robust riverway panoptic perception model based on dual graph fusion of vision and 4D mmWave radar}},
  booktitle = {Robotics Auton. Syst},
  year = {2024},
  url = {https://openreview.net/forum?id=VqXsxln0lH},
}

Loading related content...

Figure