EUVIMEDEUVIMED entdecken
Crossref

Spatial transformer network on skeleton‐based gait recognition

Cun Zhang, Xing‐Peng Chen, Guo‐Qiang Han, Xiang‐Jie Liu

Expert Systems · 2023-07 · 40 (6)

DOI: 10.1111/exsy.13244 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Expert Systems, online erschienen am 30.01.2023. Verfasst von Cun Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 87-mal zitiert (Crossref) und nennt 48 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skeleton‐based gait recognition models suffer from the robustness problem, as the rank‐1 accuracy varies from 90% in normal walking cases to 70% in walking with coats cases. In this work, we propose a state‐of‐the‐art robust skeleton‐based gait recognition model called Gait‐TR, which is based on the combination of spatial transformer frameworks and temporal convolutional networks. Gait‐TR achieves substantial improvements over other skeleton‐based gait models with higher accuracy and better robustness on the well‐known gait dataset CASIA‐B. Particularly in walking with coats cases, Gait‐TR gets a ∼90% accuracy rate. This result is higher than the best result of silhouette‐based models, which usually have higher accuracy than the skeleton‐based gait recognition models. Moreover, our experiment on CASIA‐B shows that the spatial transformer network can extract gait features from the human skeleton better than the widely used graph convolutional network.

Zitieren

APA

Zhang, C., Chen, X., Han, G., & Liu, X. (2023). Spatial transformer network on skeleton‐based gait recognition. Expert Systems, 40(6). https://doi.org/10.1111/exsy.13244

Vancouver

Zhang C, Chen X, Han G, Liu X. Spatial transformer network on skeleton‐based gait recognition. Expert Systems. 2023;40(6). doi:10.1111/exsy.13244

BibTeX
@article{Zhang2023,
  author = {Zhang, Cun and Chen, Xing‐Peng and Han, Guo‐Qiang and Liu, Xiang‐Jie},
  title = {Spatial transformer network on skeleton‐based gait recognition},
  journal = {Expert Systems},
  year = {2023},
  volume = {40},
  number = {6},
  doi = {10.1111/exsy.13244}
}
Kostenlos starten →