[1]刘 东,胡峻林*.基于度量学习的步态识别比较研究[J].计算机技术与发展,2022,32(09):89-94.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 014]
　LIU Dong,HU Jun-lin *.Comparative Study of Gait Recognition Based on Metric Learning[J].,2022,32(09):89-94.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 014]
点击复制

基于度量学习的步态识别比较研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年09期
页码:
89-94
栏目:
人工智能
出版日期:
2022-09-10

文章信息/Info

Title:
Comparative Study of Gait Recognition Based on Metric Learning
文章编号:
1673-629X(2022)09-0089-06
作者:
刘 东1 ; 胡峻林2*
1. 北京化工大学 信息科学与技术学院,北京 100029
2. 北京航空航天大学 软件学院,北京 100191
Author(s):
LIU Dong1 ; HU Jun-lin2 *
1. School of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China
2. School of Software,Beihang University,Beijing 100191,China
关键词:
步态识别; 度量学习; 特征提取; 人体生物特征; 模式识别
Keywords:
gait recognition; metric learning; feature extraction; biometrics; pattern recognition
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 09. 014
摘要:
步态识别是一项根据人在行走中的动作特征进行身份识别的技术,与其他生物特征识别方法相比,其可以实现远距离、非接触识别,在监控、安防等领域有着广泛的应用。 度量学习在模式识别任务中起着非常重要的作用,其从训练样本中学习出合适的距离函数来度量样本间的相似性,以提高识别率。 为此,从度量学习视角对步态识别问题进行研究,比较分析几种经典的度量学习方法在步态识别中的性能表现。 首先从步态序列中提取步态能量图作为行人的步态特征,然后使用度量学习方法学习距离度量,使得在该度量下同一类样本间的距离最小化和不同类样本间的距离最大化,以提升步态识别的正确识别率。 在广泛使用的 CASIA-B 与 CASIA-C 步态数据集上进行了一系列的对比实验,实验结果展示了几种度量学习方法的识别性能,为今后的步态识别研究提供了一些基准结果。
Abstract:
Gait recognition is a kind of technology for human identification based on the characteristics of a person’s movement during walking. Compared with other biometrics methods,gait recognition can realize non-contactless recognition at a distance,which has beenwidely used? ? in the fields of surveillance,security and so on. Metric learning plays a quite important role in pattern recognition tasks,which aims to learn appropriate distance functions from training data itself to measure the similarity between samples,there by improving recognition accuracy.? We investigate the gait recognition problem from the perspective of metric learning,and compare and analyze the performance of several classic metric learning methods for gait recognition. The gait energy image ( GEI) of each gait sequence is extracted to obtain the robust gait feature representation. Then the metric learning methods are utilized to learn the distance metrics,underwhich the distance between the samples from the same class is minimized and that of samples from different classes is maximized simultaneously,to improve the correct recognition accuracy of gait recognition. Extensive experiments are carried out on the widely used CASIA-B and CASIA-C gait datasets,which show the recognition performance of several metric learning methods and provide benchmark results for gait recognition.

相似文献/References:

[1]谢林海[] 刘相滨 佟施[].基于步态的身份识别技术[J].计算机技术与发展,2007,(09):106.
　XIE Lin-hai,LIU Xiang-bin,TONG Shi.Survey of Gait- Based Identification[J].,2007,(09):106.
[2]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(09):100.
[3]史作婷,吴 迪,荆晓远,等.类不平衡稀疏重构度量学习软件缺陷预测[J].计算机技术与发展,2018,28(06):125.[doi:10.3969/ j. issn.1673-629X.2018.06.028]
　SHI Zuo-ting,WU Di,JING Xiao-yuan,et al.Prediction of Defect of Class-imbalance Sparse Reconstruction Metric Learning Software[J].,2018,28(09):125.[doi:10.3969/ j. issn.1673-629X.2018.06.028]
[4]王晴[],荆晓远[][],朱阳平[],等. 基于局部稀疏重构度量学习的软件缺陷预测[J].计算机技术与发展,2016,26(11):54.
　WANG Qing[],JING Xiao-yuan[][],ZHU Yang-ping[],et al. Software Defect Prediction of Metric Learning Based on Local Sparse Reconstruction[J].,2016,26(09):54.
[5]刘 军,孙 庆,刘 玮,等.基于 U-Net 网络和椭圆度量学习的防震锤锈蚀识别[J].计算机技术与发展,2020,30(11):163.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 030]
　LIU Jun,SUN Qing,LIU Wei,et al.Identification of Anti-vibration Hammer Corrosion of High-voltage Transmission Lines Based on U-Net Network and Elliptic Metric Learning[J].,2020,30(09):163.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 030]
[6]江雨燕,吕 魏,李 平,等.基于无监督的非对称度量学习优化行人再识别[J].计算机技术与发展,2022,32(09):126.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 020]
　JIANG Yu-yan,LYU Wei,LI Ping,et al.Unsupervised Asymmetric Metric Learning for Person Re-identification Optimization[J].,2022,32(09):126.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 020]
[7]行阳阳,张索非,宋 越,等.一种面向商品检索的多尺度度量学习方法[J].计算机技术与发展,2024,34(01):65.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 010]
　XING Yang-yang,ZHANG Suo-fei,SONG Yue,et al.A Multi-scale Metric Learning Approach for Product Retrieval[J].,2024,34(09):65.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 010]

更新日期/Last Update: 2022-09-10