教師資料查詢 | 類別: 會議論文 | 教師: 洪文斌 Horng Wen-bing (瀏覽個人網頁)

標題:Image-Based Fire Detection Using Neural Networks
學年95
學期1
發表日期2006/10/08
作品名稱Image-Based Fire Detection Using Neural Networks
作品名稱(其他語言)
著者Horng, Wen-Bing; Peng, Jian-Wen
作品所屬單位淡江大學資訊工程學系
出版者
會議名稱9th Joint Conference on Information Sciences
會議地點高雄, 臺灣
摘要An image-based fire detection method using neural networks is proposed in this paper. First, flame color features, based on the HSI color model, are trained by a backpropagation neural network for flame recognition. Then, based on the learned flame color features, regions with fire-like colors are roughly separated from an image. Besides segmenting flame regions, background objects with similar fire colors or resulted from the reflection of fire flames are also separated from the image. In order to get rid of these spurious fire-like regions, the image difference method and the invented color masking technique are applied. Finally, a compact method is devised to estimate the burning degree of fire flames so that users could be informed with a proper warning alarm. The proposed system can achieve 96.47% fire detection rate on average.
關鍵字Burning degree estimation;Color masking;Fire flame detection;Neural network
語言英文
收錄於
會議性質國際
校內研討會地點
研討會時間20061008~20061011
通訊作者
國別中華民國
公開徵稿Y
出版型式紙本
出處Proceedings of 9th Joint Conference on Information Sciences4頁
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!