一种基于多种特征组合的烟雾检测方法
A Method of Smoke Detection Based on Various Features Combination

DOI: 10.12677/CSA.2013.35041, PP. 239-243

Keywords: 小波特征；纹理特征；BP神经网络分类器；烟雾检测
Wavelet Feature, Texture Feature, BP Neural Network Classifier, Smoke Detection

Full-Text   Cite this paper   Add to My Lib

Abstract:

视频中类似烟雾的区域很大程度上增加了烟雾检测的误差，为了提高烟雾检测的准确性，利用BP神经网络分类器，一种基于小波特征、烟雾纹理特征以及Y分量均值特征相结合的烟雾检测方法被提出。首先对视频序列进行运动区域提取；然后对疑似区域提取小波特征、纹理特征以及Y分量均值特征，形成一种新的多特征组合向量；最后将特征向量输入到BP神经网络分类器进行检测。实验表明，通过这种组合特征的方法，检测结果更有效。
Smoke-like regions greatly increase smoke detection errors in the video. In order to improve the accuracy of smoke detection, a smoke detection method based on BP neural network is proposed, combining the wavelet feature, smoke texture feature and mean of Y component pixel value. Firstly, moving regions in the video sequences are ex- tracted; secondly, the wavelet feature and texture feature of suspected regions are extracted, then a new kind of multi-feature vector is formed. Finally, feature vector is input into the BP neural network classifier for smoke detection. The experiments show that smoke detection results are more effective by combing various features.

References

[1]	P. Piccinini, S, Calderara and R. Cucchiara. Reliable smoke detection in the domains of image energy and color. 15th IEEE International Conference on Image Processing, 2008: 1376- 1379.
[2]	B. U. Toreyin, Y. Dedeoglu and A. E. Cetin. Wavelet based real-time smoke detection in video. European Signal Processing Conference, 2005: 4-8.
[3]	B. U. Toreyin, Y. Dedeoglu and A. E. Cetin. Contour based smoke detection in video using wavelets. European Signal Proc- essing Conference, 2006: 123-128.
[4]	T. H. Chen, Y. H. Yin, S. F. Huang, et al. The smoke detection for early fire-alarming system base on video processing. IEEE International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2006: 427-430.
[5]	袁非牛, 张永明, 刘士兴. 基于累积量和主运动方向的视频烟雾检测方法[J]. 中国图像图形学报, 2008, (4): 808-813.
[6]	J. Gubbi, S. Marusic and M. Palaniswami. Smoke detection in video using wavelets and support vector machines. Fire Safety Journal, 2009, 44(8): 1110-1115.
[7]	邓辉斌等. 基于隔帧差分区域光流法的运动目标检测[J]. 光电技术应用, 2009, 30(2): 300-304.
[8]	万缨, 韩毅, 卢汉清. 运动目标检测算法的探讨[J]. 计算机仿真, 2006, 23(10): 221-226.
[9]	于成忠, 朱骏, 袁晓辉. 基于背景差法的运动目标检测[J]. 东南大学学报: 自然科学版, 2005, 35(3): 159-161.
[10]	C. Stauffer, W. Grimson. Adaptive background mixture models for real-time tracking. Proceedings of IEEE International Confer- ence on Computer Vision and Pattern Recognition, 1999: 246- 252.
[11]	C. Stauffer, W. Grimson. Learning pattern of activity using real-time tracking. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000, 22(8): 747-757.
[12]	R. M. Haralick, K. Shanmugam and I. H. Dinstein. Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics, 1973, (6): 610-621.
[13]	郭炜强, 燕飞, 黄儒乐, 韩宁. 基于视频图像的森林火灾烟雾识别方法[J]. 仪器仪表学报, 2011, 32(6): 116-120.
[14]	C. J. Xue. The road tunnel fire detection of multi-parameters based on BP neural network. 2nd International Asia Conference on Informatics in Control, Automation and Robotics, 2010, 246-249.

Full-Text