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
Propomos um método para identificar pessoas com precisão usando mudanças temporais e espaciais em movimentos locais medidos a partir de sequências de vídeo de oscilação corporal. Os métodos existentes identificam pessoas usando características de marcha que representam principalmente o grande balanço dos membros. O uso de recursos de marcha introduz um problema, pois o desempenho de identificação diminui quando as pessoas param de andar e mantêm uma postura ereta. Para extrair características informativas, nosso método mede pequenas oscilações do corpo, conhecidas como oscilação corporal. Extraímos a densidade espectral de potência como uma característica dos movimentos locais de oscilação do corpo, dividindo o corpo em regiões. Para avaliar o desempenho de identificação usando nosso método, coletamos três conjuntos de dados de vídeo originais de sequências de oscilação corporal. O primeiro conjunto de dados continha um grande número de participantes em postura ereta. O segundo conjunto de dados incluiu variação no longo prazo. O terceiro conjunto de dados representou a oscilação corporal em diferentes posturas. Os resultados nos conjuntos de dados confirmaram que nosso método utilizando movimentos locais medidos a partir da oscilação corporal pode extrair características informativas para identificação.
Takuya KAMITANI
Tottori University
Hiroki YOSHIMURA
Tottori University
Masashi NISHIYAMA
Tottori University
Yoshio IWAI
Tottori 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
Takuya KAMITANI, Hiroki YOSHIMURA, Masashi NISHIYAMA, Yoshio IWAI, "Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 1, pp. 165-174, January 2019, doi: 10.1587/transinf.2018EDP7182.
Abstract: We propose a method for accurately identifying people using temporal and spatial changes in local movements measured from video sequences of body sway. Existing methods identify people using gait features that mainly represent the large swinging of the limbs. The use of gait features introduces a problem in that the identification performance decreases when people stop walking and maintain an upright posture. To extract informative features, our method measures small swings of the body, referred to as body sway. We extract the power spectral density as a feature from local body sway movements by dividing the body into regions. To evaluate the identification performance using our method, we collected three original video datasets of body sway sequences. The first dataset contained a large number of participants in an upright posture. The second dataset included variation over the long term. The third dataset represented body sway in different postures. The results on the datasets confirmed that our method using local movements measured from body sway can extract informative features for identification.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7182/_p
Copiar
@ARTICLE{e102-d_1_165,
author={Takuya KAMITANI, Hiroki YOSHIMURA, Masashi NISHIYAMA, Yoshio IWAI, },
journal={IEICE TRANSACTIONS on Information},
title={Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People},
year={2019},
volume={E102-D},
number={1},
pages={165-174},
abstract={We propose a method for accurately identifying people using temporal and spatial changes in local movements measured from video sequences of body sway. Existing methods identify people using gait features that mainly represent the large swinging of the limbs. The use of gait features introduces a problem in that the identification performance decreases when people stop walking and maintain an upright posture. To extract informative features, our method measures small swings of the body, referred to as body sway. We extract the power spectral density as a feature from local body sway movements by dividing the body into regions. To evaluate the identification performance using our method, we collected three original video datasets of body sway sequences. The first dataset contained a large number of participants in an upright posture. The second dataset included variation over the long term. The third dataset represented body sway in different postures. The results on the datasets confirmed that our method using local movements measured from body sway can extract informative features for identification.},
keywords={},
doi={10.1587/transinf.2018EDP7182},
ISSN={1745-1361},
month={January},}
Copiar
TY - JOUR
TI - Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People
T2 - IEICE TRANSACTIONS on Information
SP - 165
EP - 174
AU - Takuya KAMITANI
AU - Hiroki YOSHIMURA
AU - Masashi NISHIYAMA
AU - Yoshio IWAI
PY - 2019
DO - 10.1587/transinf.2018EDP7182
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2019
AB - We propose a method for accurately identifying people using temporal and spatial changes in local movements measured from video sequences of body sway. Existing methods identify people using gait features that mainly represent the large swinging of the limbs. The use of gait features introduces a problem in that the identification performance decreases when people stop walking and maintain an upright posture. To extract informative features, our method measures small swings of the body, referred to as body sway. We extract the power spectral density as a feature from local body sway movements by dividing the body into regions. To evaluate the identification performance using our method, we collected three original video datasets of body sway sequences. The first dataset contained a large number of participants in an upright posture. The second dataset included variation over the long term. The third dataset represented body sway in different postures. The results on the datasets confirmed that our method using local movements measured from body sway can extract informative features for identification.
ER -