Deep learning optimized single-pixel LiDAR
Open Access
- 2 December 2019
- journal article
- conference paper
- Published by AIP Publishing in Applied Physics Letters
- Vol. 115 (23) , 231101
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.Keywords
Funding Information
- H2020 European Research Council (340507, 804626)
- Engineering and Physical Sciences Research Council (EP/M01326X/1)
This publication has 21 references indexed in Scilit:
- Principles and prospects for single-pixel imagingNature Photonics, 2018
- Deep learning for real-time single-pixel videoScientific Reports, 2018
- Lidar System Architectures and CircuitsIEEE Communications Magazine, 2017
- An introduction to ghost imaging: quantum and classicalPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2017
- A Russian Dolls ordering of the Hadamard basis for compressive single-pixel imagingScientific Reports, 2017
- Single-pixel three-dimensional imaging with time-based depth resolutionNature Communications, 2016
- Study on fast linear scanning for a new laser scannerOptics & Laser Technology, 2010
- A single-pixel terahertz imaging system based on compressed sensingApplied Physics Letters, 2008
- Single-pixel imaging via compressive samplingIEEE Signal Processing Magazine, 2008
- Hadamard transform image codingProceedings of the IEEE, 1969