Exploring Event-based Human Pose Estimation with 3D Event Representations

Human pose estimation is a fundamental and appealing task in computer vision. Although traditional cameras are commonly applied, their reliability decreases in scenarios under high dynamic range or heavy motion blur, where event cameras offer a robust solution. Predominant event-based methods accumu...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Yin, Xiaoting, Shi, Hao, Chen, Jiaan, Wang, Ze, Ye, Yaozu, Yang, Kailun, Wang, Kaiwei
Format: Article
Language:English
Subjects:
Blurring
Cameras
Cloud computing
Color imagery
Critical components
Datasets
Orthogonality
Pose estimation
Representations
Robustness (mathematics)
Safety critical
Temporal resolution
Three dimensional models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human pose estimation is a fundamental and appealing task in computer vision. Although traditional cameras are commonly applied, their reliability decreases in scenarios under high dynamic range or heavy motion blur, where event cameras offer a robust solution. Predominant event-based methods accumulate events into frames, ignoring the asynchronous and high temporal resolution that is crucial for distinguishing distinct actions. To address this issue and to unlock the 3D potential of event information, we introduce two 3D event representations: the Rasterized Event Point Cloud (RasEPC) and the Decoupled Event Voxel (DEV). The RasEPC aggregates events within concise temporal slices at identical positions, preserving their 3D attributes along with statistical information, thereby significantly reducing memory and computational demands. Meanwhile, the DEV representation discretizes events into voxels and projects them across three orthogonal planes, utilizing decoupled event attention to retrieve 3D cues from the 2D planes. Furthermore, we develop and release EV-3DPW, a synthetic event-based dataset crafted to facilitate training and quantitative analysis in outdoor scenes. Our methods are tested on the DHP19 public dataset, MMHPSD dataset, and our EV-3DPW dataset, with further qualitative validation via a derived driving scene dataset EV-JAAD and an outdoor collection vehicle. Our code and dataset have been made publicly available at https://github.com/MasterHow/EventPointPose.
ISSN:2331-8422