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
본 논문에서는 정지영상에서 인간 검출을 위한 템플릿 히스토그램(HOT)이라는 새로운 기능을 제안합니다. 이미지의 모든 픽셀에 대해 다양한 템플릿이 정의되며, 각 템플릿에는 픽셀 자체와 두 개의 인접 픽셀이 포함됩니다. 3개의 픽셀의 질감과 그라데이션 값이 미리 정의된 공식을 만족하면 중앙 픽셀이 이 공식에 해당하는 템플릿을 충족하는 것으로 간주됩니다. 다양한 템플릿을 충족하는 픽셀의 히스토그램은 일련의 공식에 대해 계산되고 결합되어 감지 기능이 됩니다. 제안된 특징은 다른 특징들과 비교하여 질감뿐만 아니라 기울기 정보도 고려합니다. 게다가 하나의 픽셀에만 초점을 맞추는 것이 아닌 XNUMX개의 픽셀 사이의 관계를 반영합니다. 인간 탐지를 위한 실험은 INRIA 데이터 세트에서 수행되었으며, 이는 제안된 HOT 기능이 동일한 훈련 방법 하에서 HOG(Histogram of Orientated Gradient) 기능보다 더 차별적임을 보여줍니다.
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.
부
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
부
@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},}
부
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 -