Cargando…
“Reading Pictures Instead of Looking”: RGB-D Image-Based Action Recognition via Capsule Network and Kalman Filter
This paper proposes an action recognition algorithm based on the capsule network and Kalman filter called “Reading Pictures Instead of Looking” (RPIL). This method resolves the convolutional neural network’s over sensitivity to rotation and scaling and increases the interpretability of the model as...
Autores principales: | Zhao, Botong, Wang, Yanjie, Su, Keke, Ren, Hong, Sun, Haichao |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8005215/ https://www.ncbi.nlm.nih.gov/pubmed/33810140 http://dx.doi.org/10.3390/s21062217 |
Ejemplares similares
-
Kalman Filtering Application for Track Recognition and Reconstruction in ALICE Tracking System
por: Belikov, Yu, et al.
Publicado: (1997) -
Kalman filtering : theory and practice using MATLAB /
por: Grewal, Mohinder S.
Publicado: (2001) -
RGB-D Data-Based Action Recognition: A Review
por: Shaikh, Muhammad Bilal, et al.
Publicado: (2021) -
Mathematics of Kalman-Bucy filtering
por: Ruymgaart, Peter A, et al.
Publicado: (1985) -
Kalman filtering and neural networks
por: Haykin, Simon S
Publicado: (2001)