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 subtração de fundo é amplamente utilizada na detecção de objetos em movimento; no entanto, as mudanças nas condições de iluminação, a similaridade de cores e o desempenho em tempo real continuam sendo problemas importantes. Neste artigo, apresentamos um método sequencial para estimar adaptativamente componentes de fundo usando filtros de Kalman e um novo método para detectar objetos usando correlação de sinal marginal (MSC). Ao aplicar o MSC ao nosso modelo de fundo adaptativo, o sistema proposto pode realizar a detecção de objetos de forma robusta e precisa. O método proposto é adequado para implementação em uma unidade de processamento gráfico (GPU) e, como tal, o sistema obtém desempenho em tempo real de forma eficiente. Resultados experimentais demonstram o desempenho do sistema proposto.
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
Ayaka YAMAMOTO, Yoshio IWAI, Hiroshi ISHIGURO, "Real-Time Object Detection Using Adaptive Background Model and Margined Sign Correlation" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 2, pp. 325-335, February 2011, doi: 10.1587/transinf.E94.D.325.
Abstract: Background subtraction is widely used in detecting moving objects; however, changing illumination conditions, color similarity, and real-time performance remain important problems. In this paper, we introduce a sequential method for adaptively estimating background components using Kalman filters, and a novel method for detecting objects using margined sign correlation (MSC). By applying MSC to our adaptive background model, the proposed system can perform object detection robustly and accurately. The proposed method is suitable for implementation on a graphics processing unit (GPU) and as such, the system realizes real-time performance efficiently. Experimental results demonstrate the performance of the proposed system.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.325/_p
Copiar
@ARTICLE{e94-d_2_325,
author={Ayaka YAMAMOTO, Yoshio IWAI, Hiroshi ISHIGURO, },
journal={IEICE TRANSACTIONS on Information},
title={Real-Time Object Detection Using Adaptive Background Model and Margined Sign Correlation},
year={2011},
volume={E94-D},
number={2},
pages={325-335},
abstract={Background subtraction is widely used in detecting moving objects; however, changing illumination conditions, color similarity, and real-time performance remain important problems. In this paper, we introduce a sequential method for adaptively estimating background components using Kalman filters, and a novel method for detecting objects using margined sign correlation (MSC). By applying MSC to our adaptive background model, the proposed system can perform object detection robustly and accurately. The proposed method is suitable for implementation on a graphics processing unit (GPU) and as such, the system realizes real-time performance efficiently. Experimental results demonstrate the performance of the proposed system.},
keywords={},
doi={10.1587/transinf.E94.D.325},
ISSN={1745-1361},
month={February},}
Copiar
TY - JOUR
TI - Real-Time Object Detection Using Adaptive Background Model and Margined Sign Correlation
T2 - IEICE TRANSACTIONS on Information
SP - 325
EP - 335
AU - Ayaka YAMAMOTO
AU - Yoshio IWAI
AU - Hiroshi ISHIGURO
PY - 2011
DO - 10.1587/transinf.E94.D.325
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2011
AB - Background subtraction is widely used in detecting moving objects; however, changing illumination conditions, color similarity, and real-time performance remain important problems. In this paper, we introduce a sequential method for adaptively estimating background components using Kalman filters, and a novel method for detecting objects using margined sign correlation (MSC). By applying MSC to our adaptive background model, the proposed system can perform object detection robustly and accurately. The proposed method is suitable for implementation on a graphics processing unit (GPU) and as such, the system realizes real-time performance efficiently. Experimental results demonstrate the performance of the proposed system.
ER -