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
A resposta de frequência da função log-Gabor corresponde bem à resposta de frequência dos neurônios visuais de primatas. Nesta carta, regiões salientes de movimento são extraídas com base na transformada wavelet 2D log-Gabor da forma espaço-temporal das ações. Uma técnica de classificação supervisionada é então usada para classificar as ações. O método proposto é robusto à segmentação irregular de atores. Além disso, a wavelet 2D log-Gabor permite uma representação mais compacta das ações do que os modelos neurobiológicos recentes usando a wavelet Gabor.
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
Ning LI, De XU, "2D Log-Gabor Wavelet Based Action Recognition" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 11, pp. 2275-2278, November 2009, doi: 10.1587/transinf.E92.D.2275.
Abstract: The frequency response of log-Gabor function matches well the frequency response of primate visual neurons. In this letter, motion-salient regions are extracted based on the 2D log-Gabor wavelet transform of the spatio-temporal form of actions. A supervised classification technique is then used to classify the actions. The proposed method is robust to the irregular segmentation of actors. Moreover, the 2D log-Gabor wavelet permits more compact representation of actions than the recent neurobiological models using Gabor wavelet.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2275/_p
Copiar
@ARTICLE{e92-d_11_2275,
author={Ning LI, De XU, },
journal={IEICE TRANSACTIONS on Information},
title={2D Log-Gabor Wavelet Based Action Recognition},
year={2009},
volume={E92-D},
number={11},
pages={2275-2278},
abstract={The frequency response of log-Gabor function matches well the frequency response of primate visual neurons. In this letter, motion-salient regions are extracted based on the 2D log-Gabor wavelet transform of the spatio-temporal form of actions. A supervised classification technique is then used to classify the actions. The proposed method is robust to the irregular segmentation of actors. Moreover, the 2D log-Gabor wavelet permits more compact representation of actions than the recent neurobiological models using Gabor wavelet.},
keywords={},
doi={10.1587/transinf.E92.D.2275},
ISSN={1745-1361},
month={November},}
Copiar
TY - JOUR
TI - 2D Log-Gabor Wavelet Based Action Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 2275
EP - 2278
AU - Ning LI
AU - De XU
PY - 2009
DO - 10.1587/transinf.E92.D.2275
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2009
AB - The frequency response of log-Gabor function matches well the frequency response of primate visual neurons. In this letter, motion-salient regions are extracted based on the 2D log-Gabor wavelet transform of the spatio-temporal form of actions. A supervised classification technique is then used to classify the actions. The proposed method is robust to the irregular segmentation of actors. Moreover, the 2D log-Gabor wavelet permits more compact representation of actions than the recent neurobiological models using Gabor wavelet.
ER -