Advancing Point Cloud Perception: A Focus on People Detection

TL;DR

This paper introduces a method using a Random Forest Classifier to detect people in 3D point cloud data from LiDAR, addressing challenges like sparsity and occlusions.

Contribution

The paper introduces a feature-engineered pipeline with a compact feature set and ground-removal algorithm for efficient human detection in LiDAR data.

Findings

The RFC-based approach achieves good performance in people detection on high-resolution LiDAR data.

The proposed method outperforms MLP and PointNet baselines in real-time human detection.

The pipeline is validated for practical applicability in on-device point-cloud environments.

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.

Figures