Thin and Slow Smoke Detection in Image Sequence using Color Histogram

カテゴリ: 部門大会

論文No: GS11-4

グループ名: 【C】平成21年電気学会電子・情報・システム部門大会講演論文集

発行日: 2009/09/03

タイトル(英語): Thin and Slow Smoke Detection in Image Sequence using Color Histogram

著者名: 鄭光 (徳島大学),センチョウ ネイ(徳島大学),大恵俊一郎 (四国大学),寺田 賢治(徳島大学)

著者名(英語): Zheng Guang(Tokushima University),Chan Chao-Ning(Tokushima University),OE Shunichiro(Shikoku University),Terada Kenji(Tokushima University)

キーワード: smoke detection|frequency image

要約(日本語): In this paper, we propose a new method to detect thin and slow smoke using color histogram. In fire security, the earlier fire detected, the less loss can be reduced. The feature of early fire is smoke, especially thin and slow smoke. Color histogram which shows the frequency of RGB values of pixels of a color image is used for image processing widely. The frequency image presents the frequency information and the position information of pixel to each point plotted to RGB color histogram space, due to this merit, the frequency image is sensitive when there is some changing of RGB value.

PDFファイルサイズ: 4,478 Kバイト