删除或更新信息,请邮件至freekaoyan#163.com(#换成@)

一种基于等距度量学习策略的行人重识别改进算法

本站小编 Free考研考试/2022-01-03

瀵偓闁瓘IP閿涙矮绔剧粔宥堚偓鍐埡閼板啳鐦夌憴鍡涱暥闂呭繋绌堕惇瀣剁礉濮e繑婀版稉宥呭煂娑撯偓閸掑棝鎸�
547閹碘偓闂勩垺鐗庨懓鍐埡閼板啫宕�1130缁夊秵瀵氱€规碍鏆€閺夋劗娈戦崡鍐х稇缁夊秹鍘ゆ總妤咁暯鎼存挶鈧浇顫嬫0鎴礉濞戠數娲婇懟杈嚔閵嗕胶绮″ù搴涒偓浣界槈閸掓悶鈧線鍣鹃摶宥冣偓浣烘倞瀹搞儯鈧胶顓搁悶鍡愨偓浣恒仦娴兼哎鈧浇鍌ㄦ导姘モ偓浣规殌閼叉彃绺鹃悶鍡愨偓浣疯厬閺傚洢鈧浇澹撻張顖樷偓浣规煀闂傝绱堕幘顓溾偓浣圭《鐎涳负鈧礁灏扮€涳负鈧浇顓哥粻妤佹簚閵嗕礁宸婚崣灞傗偓浣告勾閻炲棎鈧焦鏂傚▽姹団偓浣告懍鐎涳负鈧椒缍嬮懖鑼缁涳拷28缁顒熺粔鎴礉VIP娴兼艾鎲虫担搴ゅ殾128.00閸忓喛绱�
周智恒,,
刘楷怡,
黄俊楚,
陈增群
华南理工大学电子与信息学院 ??广州 ??510000
基金项目:国家自然科学基金(U1401252, 61871188),国家重点研发计划(2018YFC0309400),中央高校基本科研业务费专项资金(2017MS062),广州市产学研协同创新重大专项(201604016133)

详细信息
作者简介:周智恒:男,1977年生,教授,博士生导师,研究方向为模式识别与人工智能
刘楷怡:女,1994年生,硕士生,研究方向为图像处理与模式识别
黄俊楚:男,1994年生,博士生,研究方向为图像处理与模式识别
陈增群:男,1995年生,本科生,研究方向为图像处理与模式识别
通讯作者:周智恒 zhouzh@scut.edu.cn
中图分类号:TP391.41

计量

文章访问数:1514
HTML全文浏览量:450
PDF下载量:66
被引次数:0
出版历程

收稿日期:2018-04-11
修回日期:2018-09-13
网络出版日期:2018-09-20
刊出日期:2019-02-01

Improved Metric Learning Algorithm for Person Re-identification Based on Equidistance

Zhiheng ZHOU,,
Kaiyi LIU,
Junchu HUANG,
Zengqun CHEN
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510000, China
Funds:The National Natural Science Foundation of China (U1401252,61871188), The National Key R&D Program of China (2018YFC0309400), The Fundamental Research Funds for the Central Universities SCUT (2017MS062), Guangzhou City Science and Technology Research Projects (201604016133)


摘要
摘要:为了提高行人重识别距离度量MLAPG算法的鲁棒性,该文提出基于等距度量学习策略的行人重识别Equid-MLAPG算法。 MLAPG算法中正负样本对在映射空间的分布不均衡导致间距超参数受负样本对距离影响更大,因此该文设计的Equid-MLAPG算法要求正样本对映射成为变换空间中的一个点,即正样本对在变换空间中距离为零,使算法收敛时正负样本对距离分布不存在交叉部分。实验表明Equid-MLAPG算法能在常用的行人重识别数据集上取得良好的实验效果,具有更好的识别率和广泛的适用性。
关键词:行人重识别/
等距度量/
MLAPG算法
Abstract:In order to improve the robustness of MLAPG algorithm, a person re-identification algorithm, called Equid-MLAPG algorithm is proposed, which is based on the equidistance measurement learning strategy. Due to the imbalanced distribution of positive and negative sample pairs in the mapping space, sample spacing hyper-parameter of MLAPG algorithm is more affected by the distance of negative sample pairs. Therefore, Equid-MLAPG algorithm tends to map the positive sample pair to be a point in the transform space. That is, the distance of a positive sample pair in the transform space is mapped to be zero, resulting in no intersection in the distribution of positive and negative sample pairs in the transform space when algorithm convergences. Experiments show that the Equid-MLAPG algorithm can achieve better experimental results on commonly used person re-identification datasets with better recognition rate and wide applicability.
Key words:Person re-identification/
Equidistance/
MLAPG algorithm



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=750904f5-5412-4fe7-bc33-c2fab73bc6f4
相关话题/空间 实验 华南理工大学 创新 博士生导师