Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK)

Qinhuangdao,China,7.9-7.13,2010

ISBN: 978-1-935068-15-0 Scientific Research Publishing, USA

E-Book 840pp Pub. Date: July 2010

Category: Computer Science & Communications

Price: $120

Title: Study on Vision Based Smoke Detection
Source: Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK) (pp 29-32)
Author(s): Mengsi Wang, Institute of Information Science, Beijing Jiaotong University, Beijing
Zhenjiang Miao, Institute of Information Science, Beijing Jiaotong University, Beijing
Zhifu Che, Institute of Information Science, Beijing Jiaotong University, Beijing
Abstract: Vision based smoke detection is potentially a useful technique for avoiding fire disasters. In this paper, we present a smoke-detection method for early fire-alarming system based on video processing. The prominent characteristic of the method is that both static feature and dynamic feature of smoke have been studied in details, and the corresponding recognition algorithms have been given. We can recognize whether there is smoke in the image sequences by taking advantage of these algorithms. Moreover, before it starts to detect, the smoke detector can set the measurement precision parameters in order to meet the demand in different situations. Experimental results show that the proposed method can provide an early alarm at a lower false alarm rate before the fire burns up, and hence this smoke detector has great applicability.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top