EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A Novel Score-Based LiDAR Point Cloud Degradation Analysis Method

Sepeedeh Shahbeigi, Jonathan Robinson, Valentina Donzella

IEEE Access · 2024 · 12 · 22671-22686

DOI: 10.1109/access.2024.3359300 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Sepeedeh Shahbeigi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: European Union, Innovate U.K., Centre for Doctoral Training to Advance the Deployment of Future Mobility Technologies (CDT FMT) at The University of Warwick.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Assisted and automated driving systems critically depend on high-quality sensor data to build accurate situational awareness. A key aspect of maintaining this quality is the ability to quantify the perception sensor degradation through detecting dissimilarities in sensor data. Amongst various perception sensors, LiDAR technology has gained traction, due to a significant reduction of its cost and the benefits of providing a detailed 3D understanding of the environment (point cloud). However, measuring the dissimilarity between LiDAR point clouds, especially in the context of data degradation due to noise factors, has been underexplored in the literature. A comprehensive point cloud dissimilarity score metric is essential for detecting severe sensor degradation, which could lead to hazardous events due to the compromised performance of perception tasks. Additionally, this score metric plays a central role in the use of virtual sensor models, where a thorough validation of sensor models is required for accuracy and reliability. To address this gap, this paper introduces a novel framework that evaluates point clouds dissimilarity based on high-level geometries. Contrasting with traditional methods like the computationally expensive Hausdorff metric which involves correspondence-search algorithms, our framework uses a tailored downsampling method to ensure efficiency. This is followed by condensing point clouds into shape signatures which results in efficient comparison. In addition to controlled simulations, our framework demonstrated repeatability, robustness, and consistency, in highly noisy real-world scenarios, surpassing traditional methods.

Förderung

  • European Union
  • Innovate U.K.
  • Centre for Doctoral Training to Advance the Deployment of Future Mobility Technologies (CDT FMT) at The University of Warwick

Zitieren

APA

Shahbeigi, S., Robinson, J., & Donzella, V. (2024). A Novel Score-Based LiDAR Point Cloud Degradation Analysis Method. IEEE Access, 12, 22671-22686. https://doi.org/10.1109/access.2024.3359300

Vancouver

Shahbeigi S, Robinson J, Donzella V. A Novel Score-Based LiDAR Point Cloud Degradation Analysis Method. IEEE Access. 2024;12:22671-22686. doi:10.1109/access.2024.3359300

BibTeX
@article{Shahbeigi2024,
  author = {Shahbeigi, Sepeedeh and Robinson, Jonathan and Donzella, Valentina},
  title = {A Novel Score-Based LiDAR Point Cloud Degradation Analysis Method},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {22671--22686},
  doi = {10.1109/access.2024.3359300}
}
Kostenlos starten →