Multiresolutional Gaussian Mixture Model for Precise and Stable Foreground Segmentation in Transform Domain

スポンサーリンク

概要

• 論文の詳細を見る

• 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.

• （社）電子情報通信学会の論文
• 2009-03-01

著者

• Tezuka Hiroaki

  Graduate School Of System Design Tokyo Metropolitan University

• NISHITANI Takao

  Graduate School of System Design, Tokyo Metropolitan University

• Nishitani Takao

  Graduate School Of System Design Tokyo Metropolitan University

関連論文

• Efficient Image Enhancement Algorithm Using Multi-Rate Image Processing
• Multiresolutional Gaussian Mixture Model for Precise and Stable Foreground Segmentation in Transform Domain
• Transform Domain Shadow Removal for Foreground Silhouette

スポンサーリンク