期刊文献+

一种基于连续帧图像相似度的火焰识别方法 被引量:7

A new flame recognition method based on similarity of consecutive frames
下载PDF
导出
摘要 为解决了火焰闪烁频率计算量大、计算结果不准确的问题,首先基于火焰的闪烁特性,选取连续帧图像中可疑区域的相似度作为火焰和干扰源的判别依据,利用正负大样本数据确定了相似度阈值的范围大小;然后,根据火焰的运动特性设计了一种连续帧图像中可疑区域的区域跟踪方法。实验证明:该方法能够跟踪出连续帧图像中的可疑区域,并可排除常见干扰源的影响,准确地进行火灾预警。 A new flame recognition method referring to the similarity of consecutive frames is proposed and the threshold is determined by a large number of sample videos.Besides,a tracking algorithm of suspected areas between consecutive frames is proposed based on the fire moving characteristics.A series of experiment results show that the proposed method can track the suspected areas between consecutive frames exactly and prompt fire warning precisely by eliminating the influence of common interference.
出处 《海军工程大学学报》 CAS 北大核心 2017年第4期48-52,共5页 Journal of Naval University of Engineering
基金 国家自然科学基金资助项目(41471387)
关键词 视频火灾探测 火焰颜色模型 相似度 视频跟踪算法 video fire detection flame color model similarity video tracking algorithm
  • 相关文献

参考文献4

二级参考文献22

  • 1SASIREKHA M S P, RAMYA M S, PRASANTH M R M, et al. A survey about automatic flame/fire detection in videos [ J ]. International Journal of Research in Advent Technolo- gy, 2014, 2(2): 145-150. 被引量:1
  • 2ZHANG L, LIU X. Fire recognition based on multiple fea- tures of video images [ C ]//Proceedings of the 2nd Interna- tional Conference on Computer Science and Electronics Engi- neering. Paris, France, 2013: 1597-1600. 被引量:1
  • 3CHEN L H, HUANG W C. Fire detection using spatial- tem- poral analysis [ C ]//Proceedings of the World Congress on Engineering. London, UK, 2013: 2222-2225. 被引量:1
  • 4CHEN T H, WU P H, CHIOU Y C. An early fire-detection method based on image processing [ C ]//International Con- ference on Image Processing (ICIP). [ S.1. ], China, 2004: 1707-1710. 被引量:1
  • 5HABIBOGLU Y, GUNAY O, CETIN A E. Flame detection method in video using covariance descriptors[ C 1//IEEE In- ternational Conference on Acoustics Speech and Signal Pro- cessing (ICASSP). Prague, Czech, 2011: 1817-1820. 被引量:1
  • 6MENGXIN L I, WEJING X U, KE X U, et al. A new hy- brid feature extraction method based on accurate motion area [J]. Journal of Electrical Engineering, 2013, 11 ( 10): 5563-5570. 被引量:1
  • 7CHEN J, HE Y, WANG J. Multi-feature fusion based fast video flame detection[ J]. Building and Environment, 2010, 45(5) : 1113-1122. 被引量:1
  • 8LEI W, LIU J. Early fire detection in coalmine based on video processing [ C ]//International Conference on Com- munication, Electronics and Automation Engineering. Ber- lin, German, 2013: 239-245. 被引量:1
  • 9YANG X, WANG J, HE S. A SVM approach for vessel fire detection based on image processing[ C]//Proceedings of International Conference on Modelling, Identification & Control (ICMIC). Wuhan, China, 2012: 150-153. 被引量:1
  • 10XI Z, FANG X, ZHEN S, et al. Video flame detection al- gorithm based on multi-feature fusion technique [ C ]/! Con- trol and Decision Conference (CCDC). Guiyang, China, 2012 : 4291-4294. 被引量:1

共引文献59

同被引文献66

引证文献7

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部