Fast Classification and Depth Estimation for Multispectral Single-Photon LiDAR Data

Mohamed Amir Alaa Belmekki; Stephen McLaughlin; Abderrahim Halimi

doi:10.1109/SSPD51364.2021.9541510

Fast Classification and Depth Estimation for Multispectral Single-Photon LiDAR Data

Mohamed Amir Alaa Belmekki, Stephen McLaughlin, Abderrahim Halimi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

106 Downloads (Pure)

Abstract

Multispectral 3D LiDAR imaging plays an important role in the remote sensing community as it can provide rich spectral and depth information from targets. This paper proposes a fast pixel-wise classification algorithm for multispectral single-photon LiDAR imaging. The algorithm allows the detection of histograms containing surfaces with specific spectral signatures (i.e., specific materials) and discarding those histograms without reflective surfaces. The proposed Bayesian model is carefully built to allow the marginalization of latent variables leading to a tractable formulation and fast estimation of the parameters of interest, together with their uncertainties. Results on simulated and real single-photon data illustrates the robustness and good performance of this approach.

Original language	English
Title of host publication	2021 Sensor Signal Processing for Defence Conference (SSPD)
Publisher	IEEE
ISBN (Electronic)	9781665433143
DOIs	https://doi.org/10.1109/SSPD51364.2021.9541510
Publication status	Published - 23 Sept 2021
Event	10th International Conference in Sensor Signal Processing for Defence: from Sensor to Decision - Edinburgh, United Kingdom Duration: 14 Sept 2021 → 15 Sept 2021

Conference

Conference	10th International Conference in Sensor Signal Processing for Defence
Abbreviated title	SSPD2021
Country/Territory	United Kingdom
City	Edinburgh
Period	14/09/21 → 15/09/21

Keywords

3D Multispectral imaging
Bayesian estimation
Multispectral classification.
Poisson statistics
Single-photon LiDAR

ASJC Scopus subject areas

Signal Processing
Safety, Risk, Reliability and Quality
Instrumentation

Access to Document

10.1109/SSPD51364.2021.9541510

Download pdfSubmitted manuscript, 0.98 MB

Cite this

@inproceedings{79f4dac4e3f14808bdcc1cf4eb6078ee,

title = "Fast Classification and Depth Estimation for Multispectral Single-Photon LiDAR Data",

abstract = "Multispectral 3D LiDAR imaging plays an important role in the remote sensing community as it can provide rich spectral and depth information from targets. This paper proposes a fast pixel-wise classification algorithm for multispectral single-photon LiDAR imaging. The algorithm allows the detection of histograms containing surfaces with specific spectral signatures (i.e., specific materials) and discarding those histograms without reflective surfaces. The proposed Bayesian model is carefully built to allow the marginalization of latent variables leading to a tractable formulation and fast estimation of the parameters of interest, together with their uncertainties. Results on simulated and real single-photon data illustrates the robustness and good performance of this approach.",

keywords = "3D Multispectral imaging, Bayesian estimation, Multispectral classification., Poisson statistics, Single-photon LiDAR",

author = "Belmekki, {Mohamed Amir Alaa} and Stephen McLaughlin and Abderrahim Halimi",

note = "Funding Information: This work was supported by the UK Royal Academy of Engineering Research Fellowship Scheme (RF/201718/17128), and EPSRC Grants EP/T00097X/1, EP/S000631/1, EP/S026428/1, the Dasa project DSTLX1000147844 and the MOD University Defence Research Collaboration (UDRC) in Signal Processing. We thank the single-photon group led by Prof. G. S. Buller for providing the real single-photon data used in this work. Publisher Copyright: {\textcopyright} 2021 IEEE.; 10th International Conference in Sensor Signal Processing for Defence : from Sensor to Decision, SSPD2021 ; Conference date: 14-09-2021 Through 15-09-2021",

year = "2021",

month = sep,

day = "23",

doi = "10.1109/SSPD51364.2021.9541510",

language = "English",

booktitle = "2021 Sensor Signal Processing for Defence Conference (SSPD)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Fast Classification and Depth Estimation for Multispectral Single-Photon LiDAR Data

AU - Belmekki, Mohamed Amir Alaa

AU - McLaughlin, Stephen

AU - Halimi, Abderrahim

N1 - Funding Information: This work was supported by the UK Royal Academy of Engineering Research Fellowship Scheme (RF/201718/17128), and EPSRC Grants EP/T00097X/1, EP/S000631/1, EP/S026428/1, the Dasa project DSTLX1000147844 and the MOD University Defence Research Collaboration (UDRC) in Signal Processing. We thank the single-photon group led by Prof. G. S. Buller for providing the real single-photon data used in this work. Publisher Copyright: © 2021 IEEE.

PY - 2021/9/23

Y1 - 2021/9/23

N2 - Multispectral 3D LiDAR imaging plays an important role in the remote sensing community as it can provide rich spectral and depth information from targets. This paper proposes a fast pixel-wise classification algorithm for multispectral single-photon LiDAR imaging. The algorithm allows the detection of histograms containing surfaces with specific spectral signatures (i.e., specific materials) and discarding those histograms without reflective surfaces. The proposed Bayesian model is carefully built to allow the marginalization of latent variables leading to a tractable formulation and fast estimation of the parameters of interest, together with their uncertainties. Results on simulated and real single-photon data illustrates the robustness and good performance of this approach.

AB - Multispectral 3D LiDAR imaging plays an important role in the remote sensing community as it can provide rich spectral and depth information from targets. This paper proposes a fast pixel-wise classification algorithm for multispectral single-photon LiDAR imaging. The algorithm allows the detection of histograms containing surfaces with specific spectral signatures (i.e., specific materials) and discarding those histograms without reflective surfaces. The proposed Bayesian model is carefully built to allow the marginalization of latent variables leading to a tractable formulation and fast estimation of the parameters of interest, together with their uncertainties. Results on simulated and real single-photon data illustrates the robustness and good performance of this approach.

KW - 3D Multispectral imaging

KW - Bayesian estimation

KW - Multispectral classification.

KW - Poisson statistics

KW - Single-photon LiDAR

UR - http://www.scopus.com/inward/record.url?scp=85116506518&partnerID=8YFLogxK

U2 - 10.1109/SSPD51364.2021.9541510

DO - 10.1109/SSPD51364.2021.9541510

M3 - Conference contribution

BT - 2021 Sensor Signal Processing for Defence Conference (SSPD)

PB - IEEE

T2 - 10th International Conference in Sensor Signal Processing for Defence

Y2 - 14 September 2021 through 15 September 2021

ER -

Fast Classification and Depth Estimation for Multispectral Single-Photon LiDAR Data

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this