改进型HLBP纹理特征的行人检测

J4 ›› 2016, Vol. 38 ›› Issue (05): 960-967.

改进型HLBP纹理特征的行人检测

周书仁1,2,王刚1,2,徐岳峰1,2

（1.长沙理工大学综合交通运输大数据智能处理湖南省重点实验室，湖南长沙 410114；
2.长沙理工大学计算机与通信工程学院，湖南长沙 410114）

收稿日期:2015-04-08 修回日期:2015-08-19 出版日期:2016-05-25 发布日期:2016-05-25
基金资助:
湖南省教育厅科研项目(13B132)；综合交通运输大数据智能处理湖南省重点实验室项目(2015TP1005)；湖南省交通运输厅科技进步与创新项目(201334)

An improved HLBP texture feature
method for pedestrian detection

ZHOU Shuren1，2,WANG Gang1，2,XU Yuefeng1，2

(1.Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation,
Changsha University of Science & Technology,Changsha 410114;
2.School of Computer and Communication Engineering,Changsha University of Science & Technology,Changsha 410114,China)

Received:2015-04-08 Revised:2015-08-19 Online:2016-05-25 Published:2016-05-25

摘要/Abstract

摘要：

在行人检测中,Haar型LBP(HLBP)特征采用局部统计方式，有效地降低了噪声影响，相比LBP特征对图像纹理描述有明显优势。但是，HLBP特征在计算特征值时，中心点没有参与计算，导致其信息没有被利用。针对这一不足，提出了改进型HLBP（IHLBP）特征，该方法令中心点参与到计算工作中，并赋予其最大权值。首先利用二维离散Haar小波变换，对图像做两级分解处理，得到三种不同尺度图像；然后针对上述三种图像分别提取IHLBP特征并做归一化处理，最后串接三组特征得到最终的特征向量。在INRIA Person数据集上，采用SVM进行测试。实验结果表明，该方法能有效地提高行人检测识别率。

关键词: 行人检测, 图像纹理, IHLBP特征, 二维离散Haar小波, 支持向量机

Abstract:

Compared with the local binary pattern (LBP), the Haarlike LBP (HLBP) can effectively reduce the noise by using local statistics in pedestrian detection. However, when calculating the feature value in the HLBP texture, since the center point is not involved, its information is lost. In order to solve this problem, we propose an improved HLBP (IHLBP) texture feature method, which includes the central point in calculating the feature value with a maximum weight. We realize the two level decomposition operation via the twodimensional discrete Haar wavelet transform before the IHLBP feature extraction, and obtain three images with different scales. The IHLBP features of the three images of different scales are then extracted and normalized. They are series connected and finally the final feature vectors are obtained. Experiments on the INRIA Person data set using support vector machine (SVM) show that the proposed method can effectively improve the recognition rate of pedestrian detection.

Key words: pedestrian detection;image texture;IHLBP features;twodimensional discrete Haar wavelet;support vector machine

周书仁1,2,王刚1,2,徐岳峰1,2. 改进型HLBP纹理特征的行人检测[J]. J4, 2016, 38(05): 960-967.

ZHOU Shuren1，2,WANG Gang1，2,XU Yuefeng1，2. An improved HLBP texture feature
method for pedestrian detection [J]. J4, 2016, 38(05): 960-967.

参考文献［17］

［1］	Li B, Yao Q, Wang K. A review on visionbased pedestrian detection in intelligent transportation systems［C］∥Proc of the 9th IEEE International Conference on Networking,Sensing and Control (ICNSC),2012:393398.
［2］	Su Songzhi, Li Shaozi, Chen Shuyuan, et al.A survey on pedestrian detection［J］.Acta Electronica Sinica,2012,40(4):814820.(in Chinese)
［3］	Dalal N,Triggs B.Histograms of oriented gradients for human detection［C］∥Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2005),2005:886893.
［4］	Ojala T,Pietikinen M,Harwood D.A comparative study of texture measures with classification based on featured distributions［J］.Pattern Recognition,1996,29(1):5159.
［5］	Wang X, Han T X, Yan S. An HOGLBP human detector with partial occlusion handling［C］∥Proc of IEEE 12th International Conference on Computer Vision,2009:3239.
［6］	Gan G,Cheng J.Pedestrian detection based on hoglbp feature［C］∥Proc of 2011 7th International Conference onComputational Intelligence and Security (CIS),2011:11841187.
［7］	Shao Fengxian, Li Feng, Zhou Shuren. Research on pedestrian detection of discrete wavelet transform HaarLL［J］.Computer Engineering,2014,40(9):204209.(in Chinese)
［8］	Parca G,Teixeira P,Teixeira A.Alloptical image processing and compression based on Haar wavelet transform［J］.Applied Optics,2013,52(12):29322939.
［9］	Zhou Shuren, Yin Jianping. LBP texture feature based on Haar characteristics［J］.Journal of Software,2013,24(8):19091926.(in Chinese)
［10］	Viola P, Jones M. Rapid object detection using a boosted cascade of simple features［C］∥Proc of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2001),2001:511518.
［11］	Roncancio H, Hernandes A C, Becker M. Visionbased system for pedestrian recognition using a tuned svm classifier［C］∥Proc of 2012 Workshop on Engineering Applications (WEA),2012:16.
［12］	Li Shuling, Liu Rong, Zhang Liuqin, et al.Speech emotion recognition algorithm based on modified SVM［J］.Journal of Computer Applications,2013,33(7):19381941.(in Chinese)
［13］	Guo L,Ge P S,Zhang M H,et al.Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine［J］.Expert Systems with Applications,2012,39(4):42744286.
［14］	Tang D, Liu Y, Kim T K. Fast pedestrian detection by cascaded random forest with dominant orientation templates［C］∥Proc of BMVC,2012:111.
［15］	Tian H, Duan Z, Abraham A,et al.A novel multiplex cascade classifier for pedestrian detection［J］.Pattern Recognition Letters,2013,34(14):16871693.
［16］	Jin H, Liu Q, Lu H, et al.Face detection using improved LBP under Bayesian framework［C］∥Proc of 2004 IEEE 1st Symposium on MultiAgent Security and Survivability,2004:306309.
［17］	Song Kechen, Yan Yunhui, Chen Wenhui, et al.Research and perspective on local binary pattern［J］.Acta Automatic Sinica,2013,39(6):730744.(in Chinese)
［18］	Dollar P,Wojek C,Schiele B,et al.Pedestrian detection:An evaluation of the state of the art［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):743761.
	附中文参考文献：
［2］	苏松志,李绍滋,陈淑媛,等.行人检测技术综述［J］.电子学报,2012,40(4):814820.
［7］	邵逢仙，李峰,周书仁.离散小波变换HaarLL的行人检测研究［J］.计算机工程,2014,40(9):204209.
［9］	周书仁,殷建平.基于Haar特性的LBP纹理特征［J］.软件学报,2013,24(8):19091926.
［12］	李书玲,刘蓉,张鎏钦,等.基于改进型SVM算法的语音情感识别［J］.计算机应用,2013,33(7):19381941.
［17］	宋克臣,颜云辉,陈文辉,等.局部二值模式方法研究与展望［J］.自动化学报,2013,39(6):730744.

[1]	刘屹成, 刘晓燕, 严馨. 并行平衡级联支持向量机[J]. 计算机工程与科学, 2023, 45(07): 1170-1177.
[2]	曹玉东, 陈冬昊, 曹睿, 赵朗. 融合Mask R-CNN的在线多目标行人跟踪方法[J]. 计算机工程与科学, 2023, 45(07): 1216-1225.
[3]	唐宇, 代琪, 杨梦园, 陈丽芳, . 改进麻雀搜索算法优化SVM的异常点检测[J]. 计算机工程与科学, 2023, 45(02): 346-354.
[4]	仲臣, 余学祥, 邰晓曼, 韩雨辰, 肖星星, 刘清华, . 萤火虫算法优化支持向量机室内定位研究[J]. 计算机工程与科学, 2022, 44(11): 1968-1975.
[5]	李兰, 刘杰, 张洁. 基于YOLOv4改进算法的复杂行人检测模型研究[J]. 计算机工程与科学, 2022, 44(08): 1449-1456.
[6]	马汉达, 朱敏. 改进SVM不平衡数据分类的IGWOSMOTE方法[J]. 计算机工程与科学, 2022, 44(06): 1133-1140.
[7]	韦修喜1，黄华娟1，周永权1,2. 基于AP聚类的约简孪生支持向量机快速分类算法[J]. 计算机工程与科学, 2019, 41(10): 1899-1904.
[8]	张思宇1,2，张轶1,2. 基于多尺度特征融合的小目标行人检测[J]. 计算机工程与科学, 2019, 41(09): 1627-1634.
[9]	王云艳1,2，罗冷坤1，王重阳1. 基于流形学习的光学遥感图像分类[J]. 计算机工程与科学, 2019, 41(07): 1212-1219.
[10]	冯璋，裴东,王维. 基于改进灰狼算法优化支持向量机的人脸识别[J]. 计算机工程与科学, 2019, 41(06): 1057-1063.
[11]	崔建双，车梦然. 基于多分类支持向量机的优化算法智能推荐系统与实证分析[J]. 计算机工程与科学, 2019, 41(01): 153-160.
[12]	田勋，汪西莉. 基于聚类标签均值的半监督支持向量机[J]. 计算机工程与科学, 2018, 40(12): 2265-2272.
[13]	颜学龙，龚流青，汪斌斌. 基于DCQGA-SMKL-SVM的模拟电路故障诊断方法[J]. 计算机工程与科学, 2018, 40(11): 1944-1950.
[14]	张和杰,马维华. 基于贴近度等级的链路质量评估方法[J]. 计算机工程与科学, 2018, 40(11): 1991-1999.
[15]	王志华,罗齐,刘绍廷. 基于混沌灰狼优化算法的SVM分类器研究[J]. 计算机工程与科学, 2018, 40(11): 2040-2046.