EUVIMEDEUVIMED entdecken
Crossref

Task-Specific Feature Purifying in Radar-Based Human Pose Estimation

Zhongping Cao, Jianxiong Zhang, Rihui Chen, Xuemei Guo, Guoli Wang

IEEE Transactions on Aerospace and Electronic Systems · 2023-12 · 59 (6) · 9285-9298

DOI: 10.1109/taes.2023.3317816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2023-12. Verfasst von Zhongping Cao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research of Guangdong Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, radar-based human pose estimation has attracted increasing attention, which aims to reconstruct the human skeleton from the radar signals with the advanced deep neural networks. However, one fundamental challenge is the interferences from task-irrelevant ingredients due to the propagation characteristics of radar signals during feature learning. In this article, we present a two-stage framework for task-specific feature purifying to distill the feature representation with high discriminability specific to the pose estimation task but less interpersonal discrepancy, which is essential to handle the difficulties arising from the task-irrelevant interferences in reconstructing the human skeleton. The logic behind the proposed two-stage feature purifying architecture is that the discrepancy among individual personal data is first eliminated with an adversarial auto-encoder module to distill the interpersonal-independent features, and then the pose-irrelevant components are removed through a feature disentanglement module to form task-specific features for human pose estimations. The two-stage architecture turns out to be considerably effective for feature purifying against the interferences due to the task-irrelevant ingredients involved in the feature learning process. The experimental study is presented to illustrate the effectiveness of the proposed approach.

Förderung

  • National Natural Science Foundation of China
  • Basic and Applied Basic Research of Guangdong Province, China

Zitieren

APA

Cao, Z., Zhang, J., Chen, R., Guo, X., & Wang, G. (2023). Task-Specific Feature Purifying in Radar-Based Human Pose Estimation. IEEE Transactions on Aerospace and Electronic Systems. https://doi.org/10.1109/taes.2023.3317816

Vancouver

Cao Z, Zhang J, Chen R, Guo X, Wang G. Task-Specific Feature Purifying in Radar-Based Human Pose Estimation. IEEE Transactions on Aerospace and Electronic Systems. 2023. doi:10.1109/taes.2023.3317816

BibTeX
@article{Cao2023,
  author = {Cao, Zhongping and Zhang, Jianxiong and Chen, Rihui and Guo, Xuemei and Wang, Guoli},
  title = {Task-Specific Feature Purifying in Radar-Based Human Pose Estimation},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2023},
  doi = {10.1109/taes.2023.3317816}
}
Kostenlos starten →