The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
O reconhecimento de ação usando dados de esqueleto (coordenadas 3D de articulações humanas) é um tópico atraente devido à sua robustez à aparência do ator, ao ponto de vista da câmera, à iluminação e a outras condições ambientais. No entanto, os dados do esqueleto devem ser medidos por um sensor de profundidade ou extraídos de dados de vídeo usando um algoritmo de estimativa, e isso corre o risco de erros de extração e ruído. Neste trabalho, para reconhecimento robusto de ações baseado em esqueleto, propomos um modelo de espaço de estado profundo (DSSM). O DSSM é um modelo generativo profundo da dinâmica subjacente de uma sequência observável. Aplicamos o DSSM proposto aos dados do esqueleto, e os resultados demonstram que ele melhora o desempenho de classificação de um método de linha de base. Além disso, confirmamos que a extração de características com o DSSM proposto torna as classificações subsequentes robustas ao ruído e aos valores faltantes. Em tais ambientes experimentais, o DSSM proposto supera um método de última geração.
Kazuki KAWAMURA
Kobe University
Takashi MATSUBARA
Kobe University
Kuniaki UEHARA
Kobe University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Kazuki KAWAMURA, Takashi MATSUBARA, Kuniaki UEHARA, "Deep State-Space Model for Noise Tolerant Skeleton-Based Action Recognition" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 6, pp. 1217-1225, June 2020, doi: 10.1587/transinf.2019MVP0012.
Abstract: Action recognition using skeleton data (3D coordinates of human joints) is an attractive topic due to its robustness to the actor's appearance, camera's viewpoint, illumination, and other environmental conditions. However, skeleton data must be measured by a depth sensor or extracted from video data using an estimation algorithm, and doing so risks extraction errors and noise. In this work, for robust skeleton-based action recognition, we propose a deep state-space model (DSSM). The DSSM is a deep generative model of the underlying dynamics of an observable sequence. We applied the proposed DSSM to skeleton data, and the results demonstrate that it improves the classification performance of a baseline method. Moreover, we confirm that feature extraction with the proposed DSSM renders subsequent classifications robust to noise and missing values. In such experimental settings, the proposed DSSM outperforms a state-of-the-art method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MVP0012/_p
Copiar
@ARTICLE{e103-d_6_1217,
author={Kazuki KAWAMURA, Takashi MATSUBARA, Kuniaki UEHARA, },
journal={IEICE TRANSACTIONS on Information},
title={Deep State-Space Model for Noise Tolerant Skeleton-Based Action Recognition},
year={2020},
volume={E103-D},
number={6},
pages={1217-1225},
abstract={Action recognition using skeleton data (3D coordinates of human joints) is an attractive topic due to its robustness to the actor's appearance, camera's viewpoint, illumination, and other environmental conditions. However, skeleton data must be measured by a depth sensor or extracted from video data using an estimation algorithm, and doing so risks extraction errors and noise. In this work, for robust skeleton-based action recognition, we propose a deep state-space model (DSSM). The DSSM is a deep generative model of the underlying dynamics of an observable sequence. We applied the proposed DSSM to skeleton data, and the results demonstrate that it improves the classification performance of a baseline method. Moreover, we confirm that feature extraction with the proposed DSSM renders subsequent classifications robust to noise and missing values. In such experimental settings, the proposed DSSM outperforms a state-of-the-art method.},
keywords={},
doi={10.1587/transinf.2019MVP0012},
ISSN={1745-1361},
month={June},}
Copiar
TY - JOUR
TI - Deep State-Space Model for Noise Tolerant Skeleton-Based Action Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1217
EP - 1225
AU - Kazuki KAWAMURA
AU - Takashi MATSUBARA
AU - Kuniaki UEHARA
PY - 2020
DO - 10.1587/transinf.2019MVP0012
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2020
AB - Action recognition using skeleton data (3D coordinates of human joints) is an attractive topic due to its robustness to the actor's appearance, camera's viewpoint, illumination, and other environmental conditions. However, skeleton data must be measured by a depth sensor or extracted from video data using an estimation algorithm, and doing so risks extraction errors and noise. In this work, for robust skeleton-based action recognition, we propose a deep state-space model (DSSM). The DSSM is a deep generative model of the underlying dynamics of an observable sequence. We applied the proposed DSSM to skeleton data, and the results demonstrate that it improves the classification performance of a baseline method. Moreover, we confirm that feature extraction with the proposed DSSM renders subsequent classifications robust to noise and missing values. In such experimental settings, the proposed DSSM outperforms a state-of-the-art method.
ER -