3D-Yoga: A 3D Yoga Dataset for Visual-based Hierarchical Sports Action Analysis

Jianwei Li, Haiqing Hu, Jinyang Li, Xiaomei Zhao; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 434-450

Abstract


Visual-based human action analysis is an important research topic in the field of computer vision, and has great application prospect in sports performance analysis. Currently available 3D action analysis datasets have a number of limitations in sports application, including the lack of special sports actions, distinct class or score labels and variety of samples. Existing researches mainly use various special RGB videos for sports action analysis, but analysis with 2D features is less effective than 3D representation. In this paper, we introduce a new 3D yoga pose dataset (3D-Yoga) with more than 3,792 action samples and 16,668 RGB-D key frames, collected from 22 subjects performing 117 kinds of yoga poses with two RGB-D cameras. We have reconstructed 3D yoga poses with sparse multi-view data and carried out experiments with the proposed cascade two-stream adaptive graph convolutional neural network (Cascade 2S-AGCN) to recognize and assess these poses. Experimental results have shown the advantage of applying our 3D skeleton fusion and hierarchical analysis methods on 3D-Yoga, and the accuracy of Cascade 2S-AGCN outperforms the state-of-the-art methods. The introduction of 3D-Yoga will enable the community to apply, develop and adapt various methods for visual-based sports activity analysis.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Li_2022_ACCV, author = {Li, Jianwei and Hu, Haiqing and Li, Jinyang and Zhao, Xiaomei}, title = {3D-Yoga: A 3D Yoga Dataset for Visual-based Hierarchical Sports Action Analysis}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {434-450} }