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 정확하고 안정적인 전경 분할을 위한 다중 해상도 가우스 혼합 모델(GMM)에 대해 설명합니다. Walsh 변환(WT) 도메인에서 수행되는 다중 블록 크기 GMM과 계산적으로 효율적인 미세-대략 전략이 GMM 방식에 새로 도입되었습니다. 가변 크기 블록 기반 GMM 세트를 사용하여 정확하고 안정적인 처리가 실현됩니다. 우리의 미세한 것부터 거친 것까지의 전략은 계산 단계를 대폭 줄이는 WT 스펙트럼 특성에서 비롯됩니다. 또한 제안된 접근 방식의 총 계산량은 원래 픽셀 기반 GMM 접근 방식의 10% 미만만 필요합니다. 실험 결과에 따르면 우리의 접근 방식은 빛에 반대되는 어두운 전경 물체, 전역 조명 변화, 폭설이 내리는 풍경 등 다양한 조건에서 안정적인 성능을 제공하는 것으로 나타났습니다.
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
Hiroaki TEZUKA, Takao NISHITANI, "Multiresolutional Gaussian Mixture Model for Precise and Stable Foreground Segmentation in Transform Domain" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 3, pp. 772-778, March 2009, doi: 10.1587/transfun.E92.A.772.
Abstract: This paper describes a multiresolutional Gaussian mixture model (GMM) for precise and stable foreground segmentation. A multiple block sizes GMM and a computationally efficient fine-to-coarse strategy, which are carried out in the Walsh transform (WT) domain, are newly introduced to the GMM scheme. By using a set of variable size block-based GMMs, a precise and stable processing is realized. Our fine-to-coarse strategy comes from the WT spectral nature, which drastically reduces the computational steps. In addition, the total computation amount of the proposed approach requires only less than 10% of the original pixel-based GMM approach. Experimental results show that our approach gives stable performance in many conditions, including dark foreground objects against light, global lighting changes, and scenery in heavy snow.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.772/_p
부
@ARTICLE{e92-a_3_772,
author={Hiroaki TEZUKA, Takao NISHITANI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multiresolutional Gaussian Mixture Model for Precise and Stable Foreground Segmentation in Transform Domain},
year={2009},
volume={E92-A},
number={3},
pages={772-778},
abstract={This paper describes a multiresolutional Gaussian mixture model (GMM) for precise and stable foreground segmentation. A multiple block sizes GMM and a computationally efficient fine-to-coarse strategy, which are carried out in the Walsh transform (WT) domain, are newly introduced to the GMM scheme. By using a set of variable size block-based GMMs, a precise and stable processing is realized. Our fine-to-coarse strategy comes from the WT spectral nature, which drastically reduces the computational steps. In addition, the total computation amount of the proposed approach requires only less than 10% of the original pixel-based GMM approach. Experimental results show that our approach gives stable performance in many conditions, including dark foreground objects against light, global lighting changes, and scenery in heavy snow.},
keywords={},
doi={10.1587/transfun.E92.A.772},
ISSN={1745-1337},
month={March},}
부
TY - JOUR
TI - Multiresolutional Gaussian Mixture Model for Precise and Stable Foreground Segmentation in Transform Domain
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 772
EP - 778
AU - Hiroaki TEZUKA
AU - Takao NISHITANI
PY - 2009
DO - 10.1587/transfun.E92.A.772
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2009
AB - This paper describes a multiresolutional Gaussian mixture model (GMM) for precise and stable foreground segmentation. A multiple block sizes GMM and a computationally efficient fine-to-coarse strategy, which are carried out in the Walsh transform (WT) domain, are newly introduced to the GMM scheme. By using a set of variable size block-based GMMs, a precise and stable processing is realized. Our fine-to-coarse strategy comes from the WT spectral nature, which drastically reduces the computational steps. In addition, the total computation amount of the proposed approach requires only less than 10% of the original pixel-based GMM approach. Experimental results show that our approach gives stable performance in many conditions, including dark foreground objects against light, global lighting changes, and scenery in heavy snow.
ER -