Advancing Point Cloud Perception: A Focus on People Detection
Open Access
- 28 July 2025
- journal article
- Published by Springer Nature in SN Computer Science
- Vol. 6 (6)
Abstract
Point-cloud data have become pivotal for three-dimensional scene analysis, yet robust real-time detection of humans remains challenging due to data sparsity, irregular sampling, and occlusions. In this study, we present a feature-engineered pipeline that uses a Random Forest Classifier (RFC) for efficient people detection in high-resolution LiDAR point clouds. Our contributions include: (1) detailed parameterization of a ground-removal algorithm using region growing; a compact feature set of 15 geometric and intensity-based descriptors; (3) comprehensive evaluation metrics on two datasets; and (4) comparative analysis against MLP and PointNet baselines. Experiments demonstrate that our RFC achieves good results. These results validate the practical applicability of our approach for real-time, on-device human detection in point-cloud environments.Keywords
Funding Information
- H2020 European Research Council (101058477)
- NORCE Research AS
This publication has 13 references indexed in Scilit:
- Reshaping Field of View and Resolution with Segmented Reflectors: Bridging the Gap between Rotating and Solid-State LiDARsSensors, 2020
- PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows2019
- Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data2019
- STD: Sparse-to-Dense 3D Object Detector for Point Cloud2019
- 3D Point Cloud Compression2019
- PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud2019
- Subjective and objective quality evaluation of 3D point cloud denoising algorithms2017
- Random forest in remote sensing: A review of applications and future directionsISPRS Journal of Photogrammetry and Remote Sensing, 2016
- RANDOM FORESTS FOR CLASSIFICATION IN ECOLOGYEcology, 2007
- Human Detection Using Oriented Histograms of Flow and Appearance2006