Towards Practical Human Motion Prediction with LiDAR Point Clouds

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Xiao, Ren, Yiming, Yao, Yichen, Sun, Yujing, Ma, Yuexin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914961112956928
author Han, Xiao
Ren, Yiming
Yao, Yichen
Sun, Yujing
Ma, Yuexin
author_facet Han, Xiao
Ren, Yiming
Yao, Yichen
Sun, Yujing
Ma, Yuexin
contents Human motion prediction is crucial for human-centric multimedia understanding and interacting. Current methods typically rely on ground truth human poses as observed input, which is not practical for real-world scenarios where only raw visual sensor data is available. To implement these methods in practice, a pre-phrase of pose estimation is essential. However, such two-stage approaches often lead to performance degradation due to the accumulation of errors. Moreover, reducing raw visual data to sparse keypoint representations significantly diminishes the density of information, resulting in the loss of fine-grained features. In this paper, we propose \textit{LiDAR-HMP}, the first single-LiDAR-based 3D human motion prediction approach, which receives the raw LiDAR point cloud as input and forecasts future 3D human poses directly. Building upon our novel structure-aware body feature descriptor, LiDAR-HMP adaptively maps the observed motion manifold to future poses and effectively models the spatial-temporal correlations of human motions for further refinement of prediction results. Extensive experiments show that our method achieves state-of-the-art performance on two public benchmarks and demonstrates remarkable robustness and efficacy in real-world deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08202
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Practical Human Motion Prediction with LiDAR Point Clouds
Han, Xiao
Ren, Yiming
Yao, Yichen
Sun, Yujing
Ma, Yuexin
Computer Vision and Pattern Recognition
Human motion prediction is crucial for human-centric multimedia understanding and interacting. Current methods typically rely on ground truth human poses as observed input, which is not practical for real-world scenarios where only raw visual sensor data is available. To implement these methods in practice, a pre-phrase of pose estimation is essential. However, such two-stage approaches often lead to performance degradation due to the accumulation of errors. Moreover, reducing raw visual data to sparse keypoint representations significantly diminishes the density of information, resulting in the loss of fine-grained features. In this paper, we propose \textit{LiDAR-HMP}, the first single-LiDAR-based 3D human motion prediction approach, which receives the raw LiDAR point cloud as input and forecasts future 3D human poses directly. Building upon our novel structure-aware body feature descriptor, LiDAR-HMP adaptively maps the observed motion manifold to future poses and effectively models the spatial-temporal correlations of human motions for further refinement of prediction results. Extensive experiments show that our method achieves state-of-the-art performance on two public benchmarks and demonstrates remarkable robustness and efficacy in real-world deployments.
title Towards Practical Human Motion Prediction with LiDAR Point Clouds
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.08202