A learning approach for real-time temporal scene flow estimation from LIDAR data

Arash K. Ushani; Ryan W. Wolcott; Jeffrey M. Walls; Ryan M. Eustice

ICRA 2017poster76 citations

A learning approach for real-time temporal scene flow estimation from LIDAR data

Arash K. Ushani, Ryan W. Wolcott, Jeffrey M. Walls, Ryan M. Eustice

Abstract

Many autonomous systems require the ability to perceive and understand motion in a dynamic environment. We present a novel algorithm that estimates this motion from raw LIDAR data in real-time without the need for segmentation or model-based tracking. The sensor data is first used to construct an occupancy grid. The foreground is then extracted via a learned background filter. Using the filtered occupancy grid, raw scene flow between successive scans is computed. Finally, we incorporate these measurements in a filtering framework to estimate temporal scene flow. We evaluate our method on the KITTI dataset.

BibTeX

@inproceedings{icra2017_alearningapproac,
  title = {A learning approach for real-time temporal scene flow estimation from LIDAR data},
  author = {Arash K. Ushani and Ryan W. Wolcott and Jeffrey M. Walls and Ryan M. Eustice},
  booktitle = {ICRA 2017},
  year = {2017}
}