Skeleton-based human activity analysis using deep neural networks with adaptive representation transformation

Jiahui Yu, Hongwei Gao, Qing Gao, Dalin Zhou, Zhaojie Ju

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Downloads (Pure)

Abstract

Compared with RGB-D-based human action analysis, skeleton-based works reach higher robustness and better performance, which are widely applied in the real world. However, the diversity of action observation perspectives hinders the improvement of recognition accuracy. Most of the existing works solve this problem by increasing the amount of training data, which brings a huge computational cost and cannot improve the robustness of the models. This paper proposes an adaptive model to obtain high-performance representations to improve human action recognition accuracy. First, a skeleton representation transfer scheme is proposed to transform the input skeleton-based body model to the best perspective, in which all parameters can be adaptively learned. This is more robust and cost-effective than hand-crafted features. Next, a re-designed backbone is proposed to train the model with a small computational cost based on the 3D-CNN. In the training process, a data enhancement method is also introduced to enhance robustness. Finally, extensive experimental evaluations are conducted on two benchmarks. The results show that this deep model can effectively and adaptively obtain high-performance skeleton representation and its performance is better than other state-of-the-art methods.
Original languageEnglish
Title of host publicationProceedings of the 6th IEEE International Conference on Advanced Robotics and Mechatronics
PublisherIEEE
Pages278-282
ISBN (Electronic)9781665439091
ISBN (Print)9781665445962
DOIs
Publication statusPublished - 15 Sep 2021
EventThe 6th IEEE International Conference on Advanced Robotics and Mechatronics - Chongqing, China
Duration: 3 Jul 20215 Jul 2021
http://www.ieee-arm.org

Conference

ConferenceThe 6th IEEE International Conference on Advanced Robotics and Mechatronics
CountryChina
CityChongqing
Period3/07/215/07/21
Internet address

Fingerprint

Dive into the research topics of 'Skeleton-based human activity analysis using deep neural networks with adaptive representation transformation'. Together they form a unique fingerprint.

Cite this