Abstract | ||
---|---|---|
We propose a methodology for lidar super-resolution with ground vehicles driving on roadways, which relies completely on a driving simulator to enhance, via deep learning, the apparent resolution of a physical lidar. To increase the resolution of the point cloud captured by a sparse 3D lidar, we convert this problem from 3D Euclidean space into an image super-resolution problem in 2D image space, which is solved using a deep convolutional neural network. By projecting a point cloud onto a range image, we are able to efficiently enhance the resolution of such an image using a deep neural network. Typically, the training of a deep neural network requires vast real-world data. Our approach does not require any real-world data, as we train the network purely using computer-generated data. Thus our method is applicable to the enhancement of any type of 3D lidar theoretically. By novelly applying Monte-Carlo dropout in the network and removing the predictions with high uncertainty, our method produces high accuracy point clouds comparable with the observations of a real high resolution lidar. We present experimental results applying our method to several simulated and real-world datasets. We argue for the method's potential benefits in real-world robotics applications such as occupancy mapping and terrain modeling. (C) 2020 Elsevier B.V. All rights reserved. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.robot.2020.103647 | ROBOTICS AND AUTONOMOUS SYSTEMS |
Keywords | DocType | Volume |
Lidar super-resolution,Range sensing,Perception & driving systems | Journal | 134 |
ISSN | Citations | PageRank |
0921-8890 | 1 | 0.40 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tixiao Shan | 1 | 13 | 4.33 |
Jinkun Wang | 2 | 7 | 5.91 |
Chen Fanfei | 3 | 1 | 0.40 |
Szenher Paul | 4 | 1 | 0.74 |
Brendan Englot | 5 | 221 | 21.53 |