Lightweight LiDAR-Based 3D Human Pose Estimation via 2D Depth Images for Autonomous Driving
Sensors · 05.03.2026 · 26 (5) · 1631
DOI: 10.3390/s26051631 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.03.2026. Verfasst von Gyu-Yeon Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Program in Smart Factory, Ewha Womans University, Seoul 03760, Republic of Korea. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Automobile Driving. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT, National Research Foundation of Korea, Ministry of Education.
Abstract (Originalsprache)
Real-world traffic is highly dynamic, with pedestrians exhibiting unpredictable movements. Pedestrians’ poses are essential cues for predicting their actions, enabling vehicles to respond proactively and reduce accident risks. In autonomous driving, the distance between vehicles and pedestrians is critical, making 3D human pose estimation crucial. In this context, pedestrian pose estimation has been actively studied, and recently, light detection and ranging (LiDAR) sensors have attracted attention due to their accurate 3D depth information and privacy benefits. However, existing LiDAR-based 3D pose estimation methods mainly process 3D data directly, requiring high computational cost and memory. In this paper, we propose a lightweight LiDAR-based 3D human pose estimation method specifically designed for deployment in autonomous driving systems. Unlike conventional 3D direct processing methods, our approach strategically reduces computational complexity by projecting point clouds into 2D depth images and leveraging a lightweight MoveNet, followed by efficient 3D lifting. Furthermore, we introduce a self-occlusion correction algorithm to improve robustness under side-view and bending poses, where depth-based projections often suffer from distortion. Experimental results on benchmark datasets demonstrate that the proposed method achieves competitive pose estimation accuracy while substantially improving efficiency, highlighting its practicality and scalability for real-time autonomous vehicle applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate Program in Smart Factory, Ewha Womans University, Seoul 03760, Republic of Korea.
- Division of Electronic & Semiconductor Engineering, Ewha Womans University, Seoul 03760, Republic of Korea.
ORCID-Profile: Bobin Seo, Seon-Han Choi
Förderung
- Ministry of Science and ICT
- National Research Foundation of Korea
- Ministry of Education
- MSIT (Ministry of Science and ICT), Korea
Zitieren
APA
Kim, G. Y., Park, S., Lee, S., Seo, B., Choi, S. H., & Park, S. M. (2026). Lightweight LiDAR-Based 3D Human Pose Estimation via 2D Depth Images for Autonomous Driving. Sensors, 26(5), 1631. https://doi.org/10.3390/s26051631
Vancouver
Kim GY, Park S, Lee S, Seo B, Choi SH, Park SM. Lightweight LiDAR-Based 3D Human Pose Estimation via 2D Depth Images for Autonomous Driving. Sensors. 2026;26(5):1631. doi:10.3390/s26051631
BibTeX
@article{Kim2026,
author = {Kim, Gyu-Yeon and Park, Somi and Lee, Sunkyung and Seo, Bobin and Choi, Seon-Han and Park, Sung-Min},
title = {Lightweight LiDAR-Based 3D Human Pose Estimation via 2D Depth Images for Autonomous Driving},
journal = {Sensors},
year = {2026},
volume = {26},
number = {5},
pages = {1631},
doi = {10.3390/s26051631}
}
EUVIMED