# Lightweight LiDAR-Based 3D Human Pose Estimation via 2D Depth Images for Autonomous Driving

## TL;DR

This paper introduces a lightweight method for 3D human pose estimation using LiDAR data, designed for efficient and real-time use in autonomous driving systems.

## Contribution

The novel approach uses 2D depth images and a lightweight neural network to reduce computational costs while maintaining accuracy.

## Key findings

- The method achieves competitive accuracy on benchmark datasets with significantly lower computational requirements.
- A self-occlusion correction algorithm improves robustness for challenging poses like side-view and bending.
- The proposed system is suitable for real-time autonomous driving applications due to its efficiency and scalability.

## Abstract

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.