基于图像空间金字塔SURF-BoW的步态识别

doi:10.3969/j.issn.1000-3428.2017.09.047

计算机工程

基于图像空间金字塔SURF-BoW的步态识别

史东承,贾令尧,梁超,王新颖

(长春工业大学图像处理与视频通信实验室,长春 130012)

收稿日期:2016-08-11 出版日期:2017-09-15 发布日期:2017-09-15
作者简介:史东承(1959—),男,教授,主研方向为图像处理、模式识别;贾令尧,硕士研究生;梁超,讲师;王新颖,副教授。
基金资助:
国家自然科学基金(61303132);吉林省教育厅“十三五”科学研究规划项目(吉教科合字［2016］第349号)。

Gait Recognition Based on SURF-BoW of Image Space Pyramid

SHI Dongcheng,JIA Lingyao,LIANG Chao,WANG Xinying

(Image Processing and Video Communication Laboratory,Changchun University of Technology,Changchun 130012,China)

Received:2016-08-11 Online:2017-09-15 Published:2017-09-15

摘要/Abstract

摘要： 在步态识别中,衣着的变化易降低步态识别效果。为此,提出一种保留步态特征空间分布信息的步态识别方法。提取步态能量图像各级空间金字塔网格的加速鲁棒特征,采用偏最小二乘空间金字塔表示方法对各自级层的特征加权后进行聚类,构建词袋模型,用该模型统计直方图表征步态特征。使用直方图相交核支持向量机在CASIA步态数据库进行实验,结果表明,该方法具有较好的识别效果,平均识别率优于四元数小波变换、掩模能量图、局部二值模式和局部纹理分析步态识别方法。

关键词: 步态能量图像, 图像空间金字塔, 加速鲁棒特征, 词袋, 直方图

Abstract: In gait recognition,the performance is easily weakened by the change of clothing.In this respect,a gait recognition method is proposed by preserving the space distribution information of gait features.The Speeded-Up Robust Features(SURF) are extracted from each mesh at all levels of image spatial pyramid of gait energy image.The Partial least squares Spatial Pyramid Representation(PlsSPR)method is used to represent the weight of characteristics of each level to construct Bag of Words(BoW) and the gait feature is expressed by its statistic histogram.The Histogram Intersection Kernel Support Vector Machine(HIKSVM) is tested on CASIA gait database and the results show that the method presented has better recognition performance and the average recognition rate is significantly higher than gait recognition methods through quaternion wavelet transform,mask energy image,local binary patterns and local texture analysis.

Key words: gait energy image, image space pyramid, Speeded-Up Robust Features(SURF), Bag of Words(BoW), histogram

中图分类号:

TP391.4

史东承,贾令尧,梁超,王新颖. 基于图像空间金字塔SURF-BoW的步态识别[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2017.09.047.

SHI Dongcheng,JIA Lingyao,LIANG Chao,WANG Xinying. Gait Recognition Based on SURF-BoW of Image Space Pyramid[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.09.047.

http://www.ecice06.com/CN/Y2017/V43/I9/270

参考文献

参考文献［1］HAN J,BHANU B B.Individual Recognition Using Gait Energy Image［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence,2006,28(2):316-322. ［2］YANG Q,QIU K.Gait Recognition Based on Active Energy Image and Parameter-adaptive Kernel PCA［C］//Proceedings of the 6th IEEE Joint International Information Technology and Artificial Intelligence Conference.Washington D.C.,USA:IEEE Press,2011:156-159. ［3］YANG Y,TU D,LI G.Gait Recognition Using Flow Histogram Energy Image［C］//Proceedings of International Conference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:444-449. ［4］ARORA P,SRIVASTAVA S.Gait Recognition Using Gait Gaussian Image［C］//Proceedings of International Conference on Signal Processing and Integrated Networks.Washington D.C.,USA:IEEE Press,2015:791-794. ［5］LI Chaorong,LI Jianping,YANG Xingchun,et al.Gait Recognition Using the Magnitude and Phase of Quaternion Wavelet Transform［C］//Proceedings of International Conference on Wavelet Active Media Technology and Information Processing.Washington D.C.,USA:IEEE Press,2012:322-324. ［6］RIDA I,ALMAADEED S,BOURIDANE A.Improved Gait Recognition Based on Gait Energy Images［C］//Proceedings of International Conference on Microelectronics.Washington D.C.,USA:IEEE Press,2014:40-43. ［7］MOHAN KUMAR H P,NAGENDRASWAMY H S.LBP for Gait Recognition:A Symbolic Approach Based on GEI Plus RBL of GEI［C］//Proceedings of International Conference on Electronics and Communication Systems.Washington D.C.,USA:IEEE Press,2014:1-5. ［8］张元元,李静,姜树明,等.步态能量图的局部纹理特征分析方法［J］.吉林大学学报(工学版),2013,43(z1):193-198. ［9］YANG Jun,JIANG Yu-gang,HAUPTMANN A G,et al.Evaluating Bag-of-visual-words Representations in Scene Classification［C］//Proceedings of ACM Sigmm International Workshop on Multimedia Information Retrieval.New York,USA:ACM Press,2007:197-206. ［10］ZHANG Chunjie,LIU Jing,WANG Jinqiao,et al.Image Classification Using Spatial Pyramid Coding and Visual Word Reweighting［C］//Proceedings of Asian Conference on Computer Vision.Queenstown,New Zealand:［s.n.］,2010:239-249. ［11］余思泉,曹江涛,李平,等.基于空间金字塔特征包的手势识别算法［J］.智能系统学报,2015(3):429-435. ［12］HARADA T,USHIKU Y,YAMASHITA Y,et al.Discriminative Spatial Pyramid［C］//Proceedings of IEEE Conference on Computer Vision & Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:1617-1624. ［13］BAY H,ESS A,TUYTELAARS T,et al.Speeded-Up Robust Features(SURF)［J］.Computer Vision & Image Understanding,2008,110(3):346-359. ［14］林晓帆,林立文,邓涛.基于SURF描述子的遥感影像配准［J］.计算机工程,2010,36(12):216-218. ［15］WU Jianxin.Efficient HIK SVM Learning for Image Classification［J］.IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society,2012,21(10):4442-4453. 编辑刘冰

[1]	王春智, 牛宏侠. 基于直方图均衡化与MSRCR的沙尘降质图像增强算法[J]. 计算机工程, 2022, 48(9): 223-229.
[2]	李莉, 王新强, 银珊. 基于衰减补偿与直方图拉伸的水下图像增强算法[J]. 计算机工程, 2022, 48(6): 222-227.
[3]	任方, 薛斐元, 姚雪梅. 基于中值预测的四轮嵌入可逆信息隐藏算法[J]. 计算机工程, 2022, 48(6): 124-131.
[4]	张智豪, 范九伦. 基于S分量指数加权H分量的圆形直方图阈值法[J]. 计算机工程, 2022, 48(10): 238-244.
[5]	王书朋, 贺瑞, 王瑜婧, 赵瑶. 中值直方图均衡的动态场景多曝光图像融合算法[J]. 计算机工程, 2022, 48(10): 224-229.
[6]	官洪运, 欧阳江坤, 杨益伟, 吴炜. 基于特征融合的改进LCT跟踪算法[J]. 计算机工程, 2019, 45(8): 241-247.
[7]	张景莲, 彭艳兵. 基于特征融合的恶意代码分类研究[J]. 计算机工程, 2019, 45(8): 281-286,295.
[8]	雷翔霄,欧阳红林,肖乐意,范朝冬. 基于等价三维熵与鲸鱼优化算法的图像分割研究[J]. 计算机工程, 2019, 45(4): 217-222.
[9]	李志佳, 夏玮. 基于差值直方图平移的密文域可逆信息隐藏算法[J]. 计算机工程, 2019, 45(11): 152-158.
[10]	朱琛琛, 齐林, 帖云. 基于弧长密度的自动邻域半径鉴别FPFH提取算法[J]. 计算机工程, 2019, 45(10): 253-259.
[11]	朱良宽,刘亮,东旭,景维鹏. 基于改进三维Otsu法的森林冠层图像分割[J]. 计算机工程, 2019, 45(1): 253-258,263.
[12]	张志凡,谢世朋,傅鹏. 基于颜色表示的尺度自适应实时目标跟踪[J]. 计算机工程, 2018, 44(7): 225-229.
[13]	刘玉环,唐庭龙,陈胜勇. 基于词袋特征算法的药品分层缺陷检测[J]. 计算机工程, 2018, 44(6): 249-252,258.
[14]	杜翠,张千里,刘杰. 基于HCA与KAZE的铁路路基GPR图像配准算法[J]. 计算机工程, 2018, 44(3): 264-269,274.
[15]	陈新荃,陈晓东,蒋林华. 基于Spark平台的人脸图像检索系统[J]. 计算机工程, 2018, 44(2): 251-256.

选择文件类型/文献管理软件名称

选择包含的内容

基于图像空间金字塔SURF-BoW的步态识别

Gait Recognition Based on SURF-BoW of Image Space Pyramid

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于图像空间金字塔SURF-BoW的步态识别

Gait Recognition Based on SURF-BoW of Image Space Pyramid

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价