Machine Learning-Based Material Classification on Spectral Data for a New Multispectral LiDAR Design

Authors

William Collins, SAIC
Anelle Adams, Air Force Research Laboratory
Richard K. Martin, Air Force Institute of Technology
Trevor Courtney, SAIC
Daniel E. Leaird, Torch Technologies
Alexander Noble, University of West Florida
Daniel Carvalho, SAIC
Jarrod Brown, Air Force Research Laboratory
Darrell Card, Air Force Research Laboratory
Christian Keyser, Air Force Research Laboratory

Document Type

Conference Proceeding

Publication Date

8-13-2025

Abstract

This study presents a machine learning framework for material classification using multispectral LiDAR reflectivity data. The classification results support the prototyping of a Raman-source multispectral LiDAR operating within high atmospheric transmission windows, enabling real-time range and spectral measurements to enhance material differentiation and object classification.

Comments

This IEEE conference paper is accessible by subscription or purchase at the DOI link below.

DOI

10.1109/RAPID64712.2025.11151336

Source Publication

2025 IEEE Research and Applications of Photonics in Defense Conference (RAPID)

Recommended Citation

W. Collins et al., "Machine Learning-Based Material Classification on Spectral Data for a New Multispectral LiDAR Design," 2025 IEEE Research and Applications of Photonics in Defense Conference (RAPID), Miramar Beach, FL, USA, 2025, pp. 1-2, doi: 10.1109/RAPID64712.2025.11151336.