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 인간 탐지 방법을 개발한다. 외관 기반 탐지기와 움직임 기반 탐지기가 각각 제안되었다. 템플릿 기능의 다중 스케일 블록 히스토그램(MB-HOT)을 사용하여 외관으로 사람을 감지합니다. Gray 값 정보와 Gradient 값 정보를 통합하여 세 블록의 관계를 표현합니다. INRIA 데이터 세트에 대한 실험에서는 이 기능이 HOG(방향 그라데이션 히스토그램)와 같은 다른 기능보다 더 차별적이라는 것을 보여줍니다. 인체의 상대적인 움직임을 포착하기 위해 모션 기반 기능도 제안되었습니다. 이 기능은 광학 흐름 영역에서 계산되며 데이터 세트의 실험 결과는 이 기능이 다른 모션 기반 기능보다 성능이 우수하다는 것을 보여줍니다. 두 가지 특징으로 얻은 탐지 응답을 결합하여 잘못된 탐지를 줄입니다. 두 가지 기능의 계산을 가속화하고 실시간 애플리케이션에 적합하도록 GPU(그래픽 프로세스 장치) 기반 구현이 제안되었습니다.
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, "Accurate Human Detection by Appearance and Motion" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 10, pp. 2728-2736, October 2010, doi: 10.1587/transinf.E93.D.2728.
Abstract: In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2728/_p
부
@ARTICLE{e93-d_10_2728,
author={Shaopeng TANG, Satoshi GOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Accurate Human Detection by Appearance and Motion},
year={2010},
volume={E93-D},
number={10},
pages={2728-2736},
abstract={In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.},
keywords={},
doi={10.1587/transinf.E93.D.2728},
ISSN={1745-1361},
month={October},}
부
TY - JOUR
TI - Accurate Human Detection by Appearance and Motion
T2 - IEICE TRANSACTIONS on Information
SP - 2728
EP - 2736
AU - Shaopeng TANG
AU - Satoshi GOTO
PY - 2010
DO - 10.1587/transinf.E93.D.2728
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2010
AB - In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.
ER -