[1]赵敏,张为,王鑫,等.时空背景模型下结合多种纹理特征的烟雾检测[J].西安交通大学学报,2018,52(08):067-73.[doi:10.7652/xjtuxb201808011]
 ZHAO Min,ZHANG Wei,WANG Xin,et al.A Smoke Detection Algorithm with MultiTexture Feature Exploration Under a SpatioTemporal Background Model[J].Journal of Xi'an Jiaotong University,2018,52(08):067-73.[doi:10.7652/xjtuxb201808011]
点击复制

时空背景模型下结合多种纹理特征的烟雾检测
分享到:

《西安交通大学学报》[ISSN:0253-987X/CN:61-1069/T]

卷:
52
期数:
2018年第08期
页码:
067-73
栏目:
出版日期:
2018-08-10

文章信息/Info

Title:
A Smoke Detection Algorithm with MultiTexture Feature Exploration
Under a SpatioTemporal Background Model
文章编号:
0253-987X(2018)08-0067-07
作者:
赵敏1张为1王鑫2刘艳艳3
1.天津大学微电子学院,300072,天津;2.公安部消防局天津火灾物证鉴定中心,300381,天津;
3.南开大学电子信息与光学工程学院,300071,天津
Author(s):
ZHAO Min1ZHANG Wei1WANG Xin2LIU Yanyan3
1. School of Microelectronics, Tianjin University, Tianjin 300072, China; 2. Tianjin Fire Research Institute of MPS, Tianjin
300381, China; 3. College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300071, China
关键词:
烟雾检测时空背景建模纹理特征支持向量机
Keywords:
smoke detection spatiotemporal model texture feature support vector machine
分类号:
TP391.41
DOI:
10.7652/xjtuxb201808011
文献标志码:
A
摘要:
针对复杂场景的烟雾检测准确性低等问题,提出了一种基于多种纹理特征的烟雾检测算法。首先,为了提取出完整的烟雾前景区域,在背景建模时融合了视频像素点的时间和空间信息。然后,在研究和改进局部二值图特征的基础上,提出了3种新的具有高辨别力和鲁棒性的纹理特征,分别为梯度局部二值图特征、多量级局部二值图特征以及局部共生二值图特征。通过提取前景区域局部图像块的这3种纹理特征,利用支持向量机分类器进行分类。最终,通过对3种纹理特征的综合决策检测出准确的烟雾区域。在烟雾图像数据库的测试下,该算法的平均检测出率、误报率及错误率分别为0.978、0.014及0.016,与现有最优算法相比,性能分别提高了0.6%、0.97%、0.83%。大量视频实验结果表明,该算法对复杂场景适应性强,检测准确率高,对比现有视频烟雾检测算法检测率提高了2%~4%。
Abstract:
A novel smoke detection algorithm based on the multitexture features is proposed to solve the problem of low detection rate of smoke in complex scenes. In order to extract the complete smoke foreground area, both temporal and spatial information of the pixels are fused in the background modelling process. Three novel discriminative and robust texture features are proposed by carefully studying and improving the local binary pattern feature, and are further utilized for support vector machine training in the foreground patch area. Finally, the accurate smoke area is detected through a comprehensive decision making on these features. Test results on smoke image data sets show that the average detection rate, false alarm rate and error rate of the proposed algorithm are 0.978, 0.145 and 0.162, respectively, which gain improvements of 0.6%、0.97% and 0.83%, respectively, compared with the existing optimal algorithm. Extensive experiments on challenging scenes show that the proposed algorithm outperforms other videobased smoke detection methods by 2%4% in the detection rate.

参考文献/References:

[1]WANG Hanzi, SUTER D. Background subtraction based on a robust consensus method [C]∥Proceedings of the International Conference on Pattern Recognition. Piscataway, NJ, USA: IEEE, 2006: 223226.
[2]BARNICH O, DROOGENBROECK M V. ViBe: a universal background subtraction algorithm for video sequences [J]. IEEE Transactions on Image Processing, 2011, 20(6): 17091724.
[3]刘鑫, 张钊强, 姚佳文, 等. 低秩矩阵和结构化稀疏分解的视频背景差分方法 [J]. 西安交通大学学报, 2016, 50(6): 2329.
LIU Xin, ZHANG Zhaoqiang, YAO Jiawen. A background subtraction method based on decomposition of low rank and sparsity matrices [J]. Journal of Xi’an Jiaotong University, 2016, 50(6): 2329.
[4]BESBES O, BENAZZABENYAHIA A. A novel videobased smoke detection method based on color invariants [C]∥Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ, USA: IEEE, 2016: 19111915.
[5]WANG Y, WU A, ZHANG J, et al. Fire smoke detection based on texture features and optical flow vector of contour [C]∥Proceedings of the World Congress on Intelligent Control and Automation. Piscataway, NJ, USA: IEEE, 2016: 28792883.
[6]WANG S, HE Y, YANG H, et al. Video smoke detection using shape, color and dynamic features [J]. Journal of Intelligent & Fuzzy Systems, 2017, 33(1): 305313.
[7]李笋, 石永生, 汪渤, 等. 基于颜色增强变换和MSER检测的烟雾检测算法 [J]. 北京理工大学学报, 2016, 36(10): 10721078.
SUN LI, SHI Y S, Bo W, et al. Video smoke detection based on color transformation and MSER [J]. Transactions of Beijing Institute of Technology, 2016, 36(10): 10721078.
[8]OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution grayscale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24(7): 971987.
[9]DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]∥IEEE Computer Society Conference on Computer Vision & Pattern Recognition. Piscataway, NJ, USA: IEEE, 2005: 886893.
[10]HARALICK R M. Texture features for image classification [J]. IEEE Transactions on Systems Man & Cybernetics, 1973, 3(6): 610621.
[11]YUAN F, SHI J, XIA X, et al. Sub oriented histograms of local binary patterns for smoke detection and texture classification [J]. KSII Transactions on Internet & Information Systems, 2016, 10(4): 18071823.
[12]QIAN X, HUA X S, CHEN P, et al. PLBP: an effective local binary patterns texture descriptor with pyramid representation [J]. Pattern Recognition, 2011, 44(10/11): 25022515.
[13]REN J, JIANG X, YUAN J. Noiseresistant local binary pattern with an embedded errorcorrection mechanism [J]. IEEE Transactions on Image Processing, 2013, 22(10): 40494060.
[14]ZHANG B, GAO Y, ZHAO S, et al. Local derivative pattern versus local binary pattern: face recognition with highorder local pattern descriptor [J]. IEEE Transactions on Image Processing, 2010, 19(2): 533544.
[15]QI X, XIAO R, GUO J, et al. Pairwise rotation invariant cooccurrence local binary pattern [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 36(11): 21992213.
[16]BARMPOUTIS P, DIMITROPOULOS K, GRAMMALIDIS N. Smoke detection using spatiotemporal analysis, motion modeling and dynamic texture recognition [C]∥Proceedings of the 22nd European Signal Processing Conference. Barcelona, Spain: EURASIP, 2014: 10781082.

备注/Memo

备注/Memo:
国家自然科学基金资助项目(61474080);公安部技术研究计划竞争性遴选项目(2016JSYJD04-03)
更新日期/Last Update: