指数加重ヒストグラムを用いた背景モデリング(ポスターセッション,パターン認識・メディア理解の基礎と境界領域,環境・エネルギーの課題,ポスターセッション)

Translated title of the contribution: Background Modeling using Exponentially Weighted Histogram

峰松 翼, 五十嵐 正樹, 島田 敬士, 長原 一, 谷口 倫一郎

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a nonparametric background modeling for background subtraction using exponentially weighted histograms. Our background model is constructed by using exponentially increasing weights. We express our model by using recurrence formula. In our model, recently observed pixels have a bigger influence on the background model than older ones. The proposed model need not hold past pixel values in order to remove an old value from the model for updating. We confirmed that the proposed method is processed in real time experimentally and the accuracy of the background subtraction using our background model is comparable to that of conventional methods.
Translated title of the contributionBackground Modeling using Exponentially Weighted Histogram
Original languageJapanese
Pages (from-to)99-100
Number of pages2
Journal電子情報通信学会技術研究報告. PRMU, パターン認識・メディア理解
Volume113
Issue number431
Publication statusPublished - Feb 6 2014

Fingerprint Dive into the research topics of 'Background Modeling using Exponentially Weighted Histogram'. Together they form a unique fingerprint.

Cite this