Deep learning optimized single-pixel LiDAR

Tools

Radwell, Neal and Johnson, Steven D. and Edgar, Matthew P. and Higham, Catherine F. and Murray-Smith, Roderick and Padgett, Miles J. (2019) Deep learning optimized single-pixel LiDAR. Applied Physics Letters, 115 (23). 231101. ISSN 0003-6951 (https://doi.org/10.1063/1.5128621)

[thumbnail of Radwell-etal-APL-2019-Deep-learning-optimized-single-pixel-LiDAR]
Preview
 Text. Filename: Radwell-etal-APL-2019-Deep-learning-optimized-single-pixel-LiDAR.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

Interest in autonomous transport has led to a demand for 3D imaging technologies capable of resolving fine details at long range. Light detection and ranging (LiDAR) systems have become a key technology in this area, with depth information typically gained through time-of-flight photon-counting measurements of a scanned laser spot. Single-pixel imaging methods offer an alternative approach to spot-scanning, which allows a choice of sampling basis. In this work, we present a prototype LiDAR system, which compressively samples the scene using a deep learning optimized sampling basis and reconstruction algorithms. We demonstrate that this approach improves scene reconstruction quality compared to an orthogonal sampling method, with reflectivity and depth accuracy improvements of 57% and 16%, respectively, for one frame per second acquisition rates. This method may pave the way for improved scan-free LiDAR systems for driverless cars and for fully optimized sampling to decision-making pipelines.

ORCID iDs

Radwell, Neal, Johnson, Steven D. ORCID logoORCID: https://orcid.org/0000-0002-6181-8303, Edgar, Matthew P., Higham, Catherine F., Murray-Smith, Roderick and Padgett, Miles J.;
  • Item type:Article
    ID code:89717
    Dates:
    Date
    Event
    2 December 2019
    Published
    29 October 2019
    Accepted
    Subjects:Science > Physics
    Department:Faculty of Science > Physics
    Depositing user: Pure Administrator
    Date deposited:24 Jun 2024 12:34
    Last modified:11 Nov 2024 14:22
    URI:https://strathprints.strath.ac.uk/id/eprint/89717
CORE (COnnecting REpositories)