[1]陈丽枫,王佳斌,郑力新.采用HOG特征和机器学习的行人检测方法[J].华侨大学学报(自然科学版),2018,39(5):768-773.[doi:10.11830/ISSN.1000-5013.201612041]
　CHEN Lifeng,WANG Jiabin,ZHENG Lixin.Pedestrian Detection Using HOG Feature and Machine Learning[J].Journal of Huaqiao University(Natural Science),2018,39(5):768-773.[doi:10.11830/ISSN.1000-5013.201612041]
点击复制

采用HOG特征和机器学习的行人检测方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第39卷
期数:
2018年第5期
页码:
768-773
栏目:
出版日期:
2018-09-20

文章信息/Info

Title:
Pedestrian Detection Using HOG Feature and Machine Learning
文章编号:
1000-5013(2018)05-0768-06
作者:
陈丽枫1; 2;  王佳斌1; 2;  郑力新1; 2
1. 华侨大学 工学院, 福建 泉州 362021;2. 华侨大学 工业智能化技术与系统福建省高校工程研究中心, 福建 泉州 362021
Author(s):
CHEN Lifeng1; 2;  WANG Jiabin1; 2;  ZHENG Lixin1; 2
1. Engineering Institute, Huaqiao University, Quanzhou 362021, China; 2. Industrial Intelligent Technology and System Fujian University Engineering Research Center, Huaqiao University, Quanzhou 362021, China
关键词:
行人检测;  行人候选区域;  梯度方向直方图;  反向传播神经网络;  Adaboost算法
Keywords:
pedestrian detection;  pedestrian candidate region;  histogram of oriented gradient;  back propagation neural network;  Adaboost algorithm
分类号:
TP391.4
DOI:
10.11830/ISSN.1000-5013.201612041
文献标志码:
A
摘要:
针对基于方向梯度直方图(HOG)/线性支持向量机(SVM)算法的行人检测方法中存在检测速度慢的问题,提出一种将HOG特征与Adaboost-BP模型相结合的行人检测方法.利用边缘检测技术快速检测出行人候选区域,提取出多尺度多方向的HOG特征,利用Adaboost算法训练多个反向传播神经网络用于构建强分类器,实现对测试样本图像的检测识别.结果表明:文中方法具有更高的检测率、更低的误报率和漏检率,具有较好的检测效果.
Abstract:
The pedestrian detection method based on the histogram of oriented gradient(HOG)feature and linear support vector machines(SVM)exists a problem with low detection speed. To solve this problem, a pedestrian detection method based on HOG feature and Adaboost-BP model is proposed. Edge detection technology is used to detect pedestrian candidate region rapidly and get multi-scale and multi-direction HOG feature. Adaboost algorithm is used to train multiple back propagation neural network to build strong classifier to realize the detection and recognition of test sample image. Experimental results show that the proposed method has higher detection rate, lower false positive rate and false negative rate has better detection effect.

参考文献/References:

[1] 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.DOI:10.3969/j.issn.0372-2112.2012.04.031.
[2] ENZWEILER M,GAVRILA D.Monocular pedestrian detection: Survey and experiments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2179-2195.
[3] ZHAO Liang,THORPE C E.Stereo-and neural network-based pedestrian detection[J].IEEE Transactions on Intelligent Transportation Systems,2000,1(3):148-154.DOI:10.1109/6979.892151.
[4] VIOLA P,JONES M J,SNOW D.Detecting pedestrian using patterns of motion and appearance[J].Internation Journal of Computer Vision,2005,63(2):153-161.
[5] PAPAGEORGIOU C,POGGIO T.A trainable system for object detection[J].Internation Journal of Computer Vision,2000,38(1):15-33.DOI:10.1023/A:1008162616689.
[6] 姚雪琴,李晓华,周激流.基于边缘对称性和HOG的行人检测方法[J].计算机工程,2012,38(5):179-182.DOI:10.3969/j.issn.1000-3428.2012.05.055.
[7] WALK S,MAJER N,SCHINDLER K,et al.New features and insights for pedestrian detection[J].Conference on Computer Vision and Pattern Recognition,2010,119(5):1030-1037.DOI:10.1109/CVPR.2010.5540102.
[8] 孙锐,陈军,高隽.基于显著性检测与HOG-NMF特征的快速行人检测方法[J]. 电子与信息学报,2013,35(8):1921-1926.DOI:10.3724/SP.J.1146.2012.01700.
[9] 饶钦,谢刚,钦爽.基于颜色自相似性和HOG特征的行人检测[J].小型微型计算机系统,2014,35(11):2582-2585.DOI:10.3969/j.issn.1000-1220.2014.11.040.
[10] SERMANET P,KAVUKCUOGLU K,CHINTALA S,et al.Pedestrian detection with unsupervised multi-stage feature learning[C]//IEEE Conference on Computer Vision and Pattern Recognition.Portland:IEEE Press,2013:3626-3633.DOI:10.1109/CVPR.2013.465.
[11] 田仙仙,鲍泓,徐成.一种改进HOG特征的行人检测算法[J].计算机科学,2014,41(9):320-324.DOI:10.11896/j.issn.1002-137X.2014.09.062.
[12] 刘琳,耿俊梅,顾国华,等.轮廓特征与神经网络相结合的行人检测[J].光电工程,2014,41(7):50-56.DOI:10.3969/j.issn.1003-501X.2014.07.009.
[13] 岳昊,邵春福,赵熠.基于BP神经网络的行人和自行车交通识别方法[J].北京交通大学学报,2008,32(3):46-49.DOI:10.3969/j.issn.1673-0291.2008.03.010.
[14] 曹建芳,陈俊杰,李海芳.基于Adaboost-BP神经网络的图像情感分类方法研究[J].山西大学学报(自然科学版),2013,36(3):331-337.DOI:10.13451/j.cnki.shanxi.univ(nat.sci.).2013.03.002.
[15] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[J].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1(12):886-893.DOI:10.1109/CVPR.2005.177.

备注/Memo

备注/Memo:
收稿日期: 2016-12-21
通信作者: 王佳斌(1974-),男,副教授,主要从事嵌入式系统、物联网的研究.E-mail:fatwang@hqu.edu.cn.
基金项目: 国家自然科学基金青年科学基金资助项目(61505059); 华侨大学研究生科研创新能力培育计划资助项目(1400222001)
更新日期/Last Update: 2018-09-20