Smoke Recognition and Texture Classification Using Improved Local Ternary Patterns

doi:10.3778/j.issn.1673-9418.1907036

Journal of Frontiers of Computer Science and Technology ›› 2020, Vol. 14 ›› Issue (7): 1221-1231.DOI: 10.3778/j.issn.1673-9418.1907036

Previous Articles Next Articles

Smoke Recognition and Texture Classification Using Improved Local Ternary Patterns

LI Gang, YUAN Feiniu, XIA Xue, ZHANG Lin, LEI Bangjun

1. School of Information Management, Jiangxi University of Finance and Economics, Nanchang 330032, China
2. Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang, Hubei 443002, China
3. College of Mathematics and Computational Science, Yichun University, Yichun, Jiangxi 336000, China
4. College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China
5. School of Mathematics and Computer Science, Jiangxi Science and Technology Normal University, Nanchang 330038, China

Online:2020-07-01 Published:2020-08-12

改进局部三值模式的烟雾识别和纹理分类

李钢，袁非牛，夏雪，章琳，雷帮军

1. 江西财经大学信息管理学院，南昌 330032
2. 水电工程智能视觉监测湖北省重点实验室（三峡大学），湖北宜昌 443002
3. 宜春学院数学与计算机科学学院，江西宜春 336000
4. 上海师范大学信息与机电工程学院，上海 201418
5. 江西科技师范大学数学与计算机科学学院，南昌 330038

Abstract

Abstract:

To improve detection rate and reduce false alarm rate for smoke recognition, this paper presents local ternary pattern based on confidence level (CLLTP), and further presents a novel multi-CLLTP (M_CLLTP) feature extraction model based on CLLTP. CLLTP is an improved local ternary pattern according to the normal distribution of the pixel values on the difference images. M_CLLTP model computes the CLLTPs for the original images, the weighted CLLTPs for the Gabor feature maps and the CLLTPs for the edge feature maps, and then concatenates the three CLLTP features to generate M_CLLTP feature. Comparative experiments show that M_CLLTP method achieves higher detection rates, lower false alarm rates and higher[F1]scores on three smoke datasets, and the highest mean recall rates on two texture databases. Experimental results indicate that the presented method has a good discriminative ability for smoke and texture, and is very suitable for smoke recognition.

Key words: smoke recognition, local ternary pattern, confidence level, Gabor transform, edge feature, texture classification

摘要：

为提高烟雾识别的检测率和降低误报率，首先提出了基于置信水平的局部三值模式（CLLTP），进而提出了基于CLLTP的组合特征模型（M_CLLTP）。CLLTP是依据差分图像的像素值呈正态分布而提出的一种改进的局部三值模式。M_CLLTP模型提取了原图的CLLTP特征、Gabor特征图的加权的CLLTP特征和边缘特征图的CLLTP特征，并融合它们生成M_CLLTP特征。对比实验显示，M_CLLTP方法在三个烟雾数据集上都获得了较高的检测率和[F1]分数、较低的误报率，在两个纹理数据库上获得了最高的平均召回率。实验结果表明，所提方法对烟雾和纹理具有很好的辨识能力，非常适用于烟雾识别。

关键词: 烟雾识别, 局部三值模式, 置信水平, Gabor变换, 边缘特征, 纹理分类

LI Gang, YUAN Feiniu, XIA Xue, ZHANG Lin, LEI Bangjun. Smoke Recognition and Texture Classification Using Improved Local Ternary Patterns[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(7): 1221-1231.

李钢，袁非牛，夏雪，章琳，雷帮军. 改进局部三值模式的烟雾识别和纹理分类[J]. 计算机科学与探索, 2020, 14(7): 1221-1231.

References

[1] Shi J T, Yuan F N, Xia X. Video smoke detection: a litera-ture survey[J]. Journal of Image and Graphics, 2018, 23(3): 303-322. 史劲亭, 袁非牛, 夏雪. 视频烟雾检测研究进展[J]. 中国图象图形学报, 2018, 23(3): 303-322.
[2] Zhao Y, Li Q, Gu Z. Early smoke detection of forest fire video using CS Adaboost algorithm[J]. Optik-International Journal for Light and Electron Optics, 2015, 126(19): 2121-2124.
[3] He D C, Lou X P, Tang H. Dynamic features based real-time video smoke detection[J]. Computer Applications and Soft-ware, 2014, 31(2): 201-204.何大超, 娄小平, 唐辉. 基于动态特性的实时视频烟雾检测[J]. 计算机应用与软件, 2014, 31(2): 201-204.
[4] Yuan F N, Xia X, Li G, et al. GaborNet for smoke recogni-tion and texture classification[J]. Journal of Image and Gra-phics, 2019, 24(2): 269-281. 袁非牛, 夏雪, 李钢, 等. 面向烟雾识别与纹理分类的Gabor网络[J]. 中国图象图形学报, 2019, 24(2): 269-281.
[5] Yuan F N, Li G, Xia X, et al. Smoke recognition by combin-ing aggregated Gabor kernels and local binary patterns[J]. Journal of Chinese Computer Systems, 2019, 40(4): 827-833.袁非牛, 李钢, 夏雪, 等. 采用聚合Gabor核和局部二元模式的烟雾识别方法[J]. 小型微型计算机系统, 2019, 40(4): 827-833.
[6] Yuan F N. Video-based smoke detection with histogram sequ-ence of LBP and LBPV pyramids[J]. Fire Safety Journal, 2011, 46(3): 132-139.
[7] Yuan F N, Shi J T, Xia X, et al. Sub oriented histograms of local binary patterns for smoke detection and texture classifi-cation[J]. KSII Transactions on Internet and Information Sys-tems, 2016, 10(4): 1807-1823.
[8] Yuan F N, Shi J T, Xia X, et al. High-order local ternary pat-terns with locality preserving projection for smoke detec-tion and image classification[J]. Information Sciences, 2016, 372(C): 225-240.
[9] Gürcan M N, Yardimci Y, ?etin A E. Influence function based Gaussianity tests for detection of microcalcifications in ma-mmogram images[C]//Proceedings of the 6th International Conference on Image Processing, Kobe, Oct 24-28, 1999. Piscataway: IEEE, 1999: 407-411.
[10] Li B, Yao C L, Li W, et al. A novel motion object detection algorithm using adjacent frame and background frame[J]. Acta Electronica Sinica, 2008, 36(11): 2154-2159.李波, 姚春莲, 李炜, 等. 利用相邻帧和背景信息的运动对象检测[J]. 电子学报, 2008, 36(11): 2154-2159.
[11] Qi X B, Xiao R, Li C G, et al. Pairwise rotation invariant co-occurrence local binary pattern[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(11): 2199-2211.
[12] Mehta R, Egiazarian K. Texture classification using dense micro-block difference[J]. IEEE Transactions on Image Pro-cessing, 2016, 25(4): 1604-1616.
[13] Yuan F N, Xia X, Shi J T. Mixed co-occurrence of local binary patterns and Hamming-distance-based local binary patterns [J]. Information Sciences, 2018, 460/461(C): 202-222.
[14] Guo Z H, Zhang L, Zhang D. A completed modeling of local binary pattern operator for texture classification[J]. IEEE Transactions on Image Processing, 2010, 19(6): 1657-1663.
[15] Murala S, Maheshwari R P, Balasubramanian R. Local tetra patterns: a new feature descriptor for content-based image retrieval[J]. IEEE Transactions on Image Processing, 2012, 21(5): 2874-2886.
[16] Qian X M, Hua X S, Chen P, et al. PLBP: an effective local binary patterns texture descriptor with pyramid representa-tion[J]. Pattern Recognition, 2011, 44(10/11): 2502-2515.
[17] Zhang B C, Gao Y S, Zhao S Q, et al. Local derivative patt-ern versus local binary pattern: face recognition with high-order local pattern descriptor[J]. IEEE Transactions on Image Processing, 2010, 19(2): 533-544.
[18] Ahonen T, Matas J, He C, et al. Rotation invariant image description with local binary pattern histogram Fourier fea-tures[C]//LNCS 5575: Proceedings of the 16th Scandinavian Conference on Image Analysis, Oslo, Jun 15-18, 2009. Berlin, Heidelberg: Springer, 2009: 61-70.
[19] Zhang J, Liang J M, Zhao H. Local energy pattern for tex-ture classification using self-adaptive quantization thresholds [J]. IEEE Transactions on Image Processing, 2015, 22(1): 31-42.
[20] Sharma G, Hussain S U, Jurie F. Local higher-order statis-tics (LHS) for texture categorization and facial analysis[C]// LNCS 7578: Proceedings of the 12th European Conference on Computer Vision, Florence, Oct 7-13, 2012. Berlin, Hei-delberg: Springer, 2015: 1-12.
[21] Hong X P, Zhao G Y, Pietik?inen M, et al. Combining LBP difference and feature correlation for texture description[J]. IEEE Transactions on Image Processing, 2014, 23(6): 2557-2568.
[22] Ryu J, Hong S, Yang H S. Sorted consecutive local binary pattern for texture classification[J]. IEEE Transactions on Image Processing, 2015, 24(7): 2254-2265.

Smoke Recognition and Texture Classification Using Improved Local Ternary Patterns

改进局部三值模式的烟雾识别和纹理分类

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 1

Recommended Articles

Metrics