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
Neste artigo, propomos um novo recurso denominado histograma de modelo (HOT) para detecção humana em imagens estáticas. Para cada pixel de uma imagem, vários modelos são definidos, cada um contendo o próprio pixel e dois de seus pixels vizinhos. Se os valores de textura e gradiente dos três pixels satisfizerem uma fórmula predefinida, considera-se que o pixel central atende ao modelo correspondente para esta fórmula. Histogramas de pixels que atendem a vários modelos são calculados para um conjunto de fórmulas e combinados para formar o recurso de detecção. Comparado com os outros recursos, o recurso proposto leva em consideração a textura e também as informações de gradiente. Além disso, reflete a relação entre 3 pixels, em vez de focar em apenas um. Experimentos para detecção humana são realizados no conjunto de dados INRIA, o que mostra que o recurso HOT proposto é mais discriminativo do que o recurso de histograma de gradiente orientado (HOG), sob o mesmo método de treinamento.
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
Shaopeng TANG, Satoshi GOTO, "Histogram of Template for Pedestrian Detection" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 7, pp. 1737-1744, July 2010, doi: 10.1587/transinf.E93.D.1737.
Abstract: In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the texture and gradient values of the three pixels satisfy a pre-defined formula, the central pixel is regarded to meet the corresponding template for this formula. Histograms of pixels meeting various templates are calculated for a set of formulas, and combined to be the feature for detection. Compared to the other features, the proposed feature takes texture as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1737/_p
Copiar
@ARTICLE{e93-d_7_1737,
author={Shaopeng TANG, Satoshi GOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Histogram of Template for Pedestrian Detection},
year={2010},
volume={E93-D},
number={7},
pages={1737-1744},
abstract={In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the texture and gradient values of the three pixels satisfy a pre-defined formula, the central pixel is regarded to meet the corresponding template for this formula. Histograms of pixels meeting various templates are calculated for a set of formulas, and combined to be the feature for detection. Compared to the other features, the proposed feature takes texture as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.},
keywords={},
doi={10.1587/transinf.E93.D.1737},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Histogram of Template for Pedestrian Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1737
EP - 1744
AU - Shaopeng TANG
AU - Satoshi GOTO
PY - 2010
DO - 10.1587/transinf.E93.D.1737
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2010
AB - In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the texture and gradient values of the three pixels satisfy a pre-defined formula, the central pixel is regarded to meet the corresponding template for this formula. Histograms of pixels meeting various templates are calculated for a set of formulas, and combined to be the feature for detection. Compared to the other features, the proposed feature takes texture as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.
ER -