[1]邱超,张印辉,王杰琼,等.混合特征行人检测算法[J].机械与电子,2016,(03):9-12.
　QIU Chao,ZHANG Yinhui,WANG Jieqiong,et al.Pedestrian Detection Based on Mixed Features[J].Machinery & Electronics,2016,(03):9-12.
点击复制

混合特征行人检测算法
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2016年03期
页码:
9-12
栏目:
设计与研究
出版日期:
2016-03-25

文章信息/Info

Title:
Pedestrian Detection Based on Mixed Features
作者:
邱超; 张印辉; 王杰琼; 何自芬
（昆明理工大学机电工程学院,云南 昆明 650500）
Author(s):
QIU Chao;  ZHANG Yinhui;  WANG Jieqiong;  HE Zifen
（Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology,Kunming 650500, China）
关键词:
行人检测;  混合特征;  最优权重; 自适应系统
Keywords:
pedestrian detection;  combined feature;  optimal weights;  self-adaptive system
分类号:
TP391
文献标志码:
A
摘要:
为了提高行人检测方法的效果，提出了一种基于混合特征提取的行人检测方法。首先，提取一幅目标图像中的梯度方向直方图和局部二元模式特征。然后，利用一种自适应系统将HOG和LBP特征间的最优权重自动分配给每个特征。并且，通过难例挖掘的方法获取困难的负样本。最后，采用支持向量机对行人和背景进行分类。实验结果表明，这种新的方法优于其他仅使用单一特征或没有分配最优权重的混合特征的方法。
Abstract:
In order to improve the performance of pedestrian detection, a new pedestrian detection method is proposed based on the combined feature extraction approach. First, the histograms of oriented gradients (HOG) and the local binary pattern (LBP) features are extracted from an image. Second, a self-adaptive system is introduced for automatically assigning optimal weights between the HOG and the LBP features. And the hard negative examples are captured by applying a hard-mining approach. Finally, a support vector machine (SVM) is adopted to classify the pedestrian and background. The experimental results show that the proposed method outperforms other approaches using a single feature or non-weighted mixed features.

参考文献/References:

[1]Papageorgiou C，Poggio T.A trainable system for object detection[J]. International Journal of Computer Vision (IJCV), 2000,38(1):15-33.
[2]Viola P，Jones M J，Snow D.Detecting pedestrians using patterns of motion and appearance[J]. International Conference on Computer Vision (ICCV), 2003,63(2):153-161.
[3]Tuzel O,Porokli F, Mee P.Human detection via classification on Riemannian manifolds[J].Computer Vision and Pattern Recognition (CVPR), 2007,101(9):1-8.
[4]Schwartz W R,Kembhavi A, Harwood D et al.Human detection using partial least squares analysis[C]//IEEE International Conference on Computer Vision, 2009:24-31.
[5]Dalal N, Triggs B.Histograms of oriented gradients for human detection[C]//Conference on Computer Vision and Pattern Recognition (CVPR), 2005,1:886-893.
[6]Andrews S, Tsochantaridis I, Hofmann T. Support vector machines for multiple-instance learning[C]//Advances in Neural Information Processing Systems，2002: 561-568.
[7]Zhu Q, Avidan S et al. Fast human detection using a cascade of histograms of oriented gradients[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2006:1491-1498.
[8]Ott P, Everingham M.Implicit color segmentation features for pedestrian and object detection[C]//International conference on computer vision (ICCV), 2009:723-730.
[9]Wang X Y,Han T X,Yan S C.An HOG-LBP human detector with partial occlusion handling[C]//International Conference on Computer Vision (ICCV), 2009:32-39.
[10]Ma L, Wang C, Xiao B. Text detection in natural images based on multi-scale edge detection and classification[C]// 2010 3rd International Congress on Image and Signal Processing (CISP), 2010, 4: 1961-1965.
[11]Ahonen T, Hadid A, Pietik〖AKα¨〗inen M.Face recognition with local binary patterns[M]//Computer Vision-ECCV 2004. Springer Berlin Heidelberg, 2004: 469-481.
[12]王玮, 黄非非, 李见为, 等.使用多尺度 LBP 特征描述与识别人脸[J].光学精密工程, 2008,16(4): 696-705.
[13]王宪, 张彦, 慕鑫, 等. 基于改进的 LBP 人脸识别算法[J].光电工程, 2012, 39(7): 109-114.
[14]Ojala T,Pietik〖AKα¨〗inen M, Harwood D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996 29(1):51-59.
[15]Hung W L, Yang M S, Chen D H.Bootstrapping approach to feature-weight selection in fuzzy c-means algorithms with an application in color image segmentation[J]. Pattern Recognition Letters,2008,29(9):1317 - 1325.

相似文献/References:

[1]朱天明,刘 凯,刘豪志.基于改进ＢＩＮＧ 模型和边缘信息的行人检测算法[J].机械与电子,2019,(06):59.
　,Pedestrian Detection Algorithm Based on Improved BING Model and Edge Information[J].Machinery & Electronics,2019,(03):59.

备注/Memo

备注/Memo:
收稿日期：2016-01-11
基金项目：国家自然科学基金(61461022)；青年科学基金（61302173）
作者简介：邱超（1989-），男，湖北武汉人，硕士研究生，主要研究方向为机器视觉；张印辉（1977-），男，河北衡水人，副教授，博士，主要研究方向为图像处理、模式识别，通信作者；王杰琼（1989-），女，河北石家庄人，硕士研究生，主要研究方向为机器视觉；何自芬，女，河北南宫人，博士，主要研究方向为图像处理。
更新日期/Last Update: 2016-03-25