EUVIMEDEUVIMED entdecken
Crossref

A Non-Line-of-Sight Human Activity Recognition Method Based on Radar Multispectrogram

Congzhang Ding, Shisheng Guo, Guolong Cui, Xiaobo Yang, Chao Jia, Jie Gu

IEEE Transactions on Aerospace and Electronic Systems · 2025-10 · 61 (5) · 13647-13661

DOI: 10.1109/taes.2025.3579771 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2025-10. Verfasst von Congzhang Ding und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Municipal Government of Quzhou.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this article, we investigate a lightweight human activity recognition (HAR) method for non-line-of-sight (NLOS) scenarios. This approach constructs a lightweight multispectrogram parallel feature extraction model to extract time-range (TR) map and time-Doppler (TD) map features from stepped-frequency continuous wave radar, enabling NLOS HAR in L-shaped corner environments. Specifically, the model incorporates a multiscale depthwise separable convolution to extract multipath TR map features at different scales in NLOS scenarios. Simultaneously, it combines depthwise separable convolution with Ghost convolution to extract features from the TD map. Finally, the extracted multispectrogram features are fused and classified, achieving robust HAR in NLOS environments. To validate the effectiveness of the proposed method, we conducted experimental verification using real-world data from eight types of human activities in an L-shaped corner NLOS scenario. The results show that the proposed model achieves a recognition accuracy of 87.12%, which is a 5.82% improvement compared to the State-of-the-Art recognition methods.

Förderung

  • National Natural Science Foundation of China
  • Municipal Government of Quzhou

Zitieren

APA

Ding, C., Guo, S., Cui, G., Yang, X., Jia, C., & Gu, J. (2025). A Non-Line-of-Sight Human Activity Recognition Method Based on Radar Multispectrogram. IEEE Transactions on Aerospace and Electronic Systems, 61(5), 13647-13661. https://doi.org/10.1109/taes.2025.3579771

Vancouver

Ding C, Guo S, Cui G, Yang X, Jia C, Gu J. A Non-Line-of-Sight Human Activity Recognition Method Based on Radar Multispectrogram. IEEE Transactions on Aerospace and Electronic Systems. 2025;61(5):13647-13661. doi:10.1109/taes.2025.3579771

BibTeX
@article{Ding2025,
  author = {Ding, Congzhang and Guo, Shisheng and Cui, Guolong and Yang, Xiaobo and Jia, Chao and Gu, Jie},
  title = {A Non-Line-of-Sight Human Activity Recognition Method Based on Radar Multispectrogram},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2025},
  volume = {61},
  number = {5},
  pages = {13647--13661},
  doi = {10.1109/taes.2025.3579771}
}
Kostenlos starten →