LiDAR-based Human Activity Recognition through Laplacian Spectral Analysis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sharifipour, Sasan, Casado, Constantino Álvarez, Nguyen, Le, Ekanayake, Tharindu, Cañellas, Manuel Lage, Nguyen, Nhi, López, Miguel Bordallo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915519150424064
author Sharifipour, Sasan
Casado, Constantino Álvarez
Nguyen, Le
Ekanayake, Tharindu
Cañellas, Manuel Lage
Nguyen, Nhi
López, Miguel Bordallo
author_facet Sharifipour, Sasan
Casado, Constantino Álvarez
Nguyen, Le
Ekanayake, Tharindu
Cañellas, Manuel Lage
Nguyen, Nhi
López, Miguel Bordallo
contents Human Activity Recognition supports applications in healthcare, manufacturing, and human-machine interaction. LiDAR point clouds offer a privacy-preserving alternative to cameras and are robust to illumination. We propose a HAR method based on graph spectral analysis. Each LiDAR frame is mapped to a proximity graph (epsilon-graph) and the Laplacian spectrum is computed. Eigenvalues and statistics of eigenvectors form pose descriptors, and temporal statistics over sliding windows yield fixed vectors for classification with support vector machines and random forests. On the MM-Fi dataset with 40 subjects and 27 activities, under a strict subject-independent protocol, the method reaches 94.4% accuracy on a 13-class rehabilitation set and 90.3% on all 27 activities. It also surpasses the skeleton-based baselines reported for MM-Fi. The contribution is a compact and interpretable feature set derived directly from point cloud geometry that provides an accurate and efficient alternative to end-to-end deep learning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23255
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LiDAR-based Human Activity Recognition through Laplacian Spectral Analysis
Sharifipour, Sasan
Casado, Constantino Álvarez
Nguyen, Le
Ekanayake, Tharindu
Cañellas, Manuel Lage
Nguyen, Nhi
López, Miguel Bordallo
Computer Vision and Pattern Recognition
Human-Computer Interaction
Human Activity Recognition supports applications in healthcare, manufacturing, and human-machine interaction. LiDAR point clouds offer a privacy-preserving alternative to cameras and are robust to illumination. We propose a HAR method based on graph spectral analysis. Each LiDAR frame is mapped to a proximity graph (epsilon-graph) and the Laplacian spectrum is computed. Eigenvalues and statistics of eigenvectors form pose descriptors, and temporal statistics over sliding windows yield fixed vectors for classification with support vector machines and random forests. On the MM-Fi dataset with 40 subjects and 27 activities, under a strict subject-independent protocol, the method reaches 94.4% accuracy on a 13-class rehabilitation set and 90.3% on all 27 activities. It also surpasses the skeleton-based baselines reported for MM-Fi. The contribution is a compact and interpretable feature set derived directly from point cloud geometry that provides an accurate and efficient alternative to end-to-end deep learning.
title LiDAR-based Human Activity Recognition through Laplacian Spectral Analysis
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2509.23255