Space-Time Representation of People Based on 3D Skeletal Data: A Review

TL;DR

This paper reviews and categorizes space-time human representations based on 3D skeletal data, highlighting their robustness and real-time capabilities, and discusses datasets, devices, and future research directions.

Contribution

It provides a comprehensive survey and analysis of existing 3D skeletal data-based human representations, including categorization, device overview, and future research insights.

Findings

Categorization of methods by information modality and encoding

Analysis of skeleton acquisition devices and datasets

Discussion of future research directions

Abstract

Spatiotemporal human representation based on 3D visual perception data is a rapidly growing research area. Based on the information sources, these representations can be broadly categorized into two groups based on RGB-D information or 3D skeleton data. Recently, skeleton-based human representations have been intensively studied and kept attracting an increasing attention, due to their robustness to variations of viewpoint, human body scale and motion speed as well as the realtime, online performance. This paper presents a comprehensive survey of existing space-time representations of people based on 3D skeletal data, and provides an informative categorization and analysis of these methods from the perspectives, including information modality, representation encoding, structure and transition, and feature engineering. We also provide a brief overview of skeleton acquisition devices and construction methods, enlist a number of public benchmark datasets with skeleton data, and discuss potential future research directions.