###
:2019,28(1):127-133
本文二维码信息
码上扫一扫!
基于特征融合网络的行人重识别
(南京理工大学 电子工程与光电技术学院, 南京 210094)
Person Re-Identification by Feature Fusion Network
(School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 430次   下载 231
投稿时间:2018-07-12    修订日期:2018-08-09
中文摘要: 行人重识别旨在大规模的分布式监控系统中进行行人目标匹配,紧凑且具有鲁棒性的特征表达对其至关重要,为此,本文提出了一种基于特征融合网络的特征提取方法.首先,利用STEL算法增强了LOMO特征对背景噪声的抗噪性能,利用KPCA算法降低维度以便于后续融合.随后,本文探索了手工特征和CNN特征的互补性,将改进LOMO特征融入至卷积神经网络之中,得到了区分度更高的融合特征.在VIPeR和CUHK01数据集上的测试结果表明,本文融合特征的区分度明显高于单一特征和级联特征,Rank-1较级联特征分别提高了3.73%和2.36%.
Abstract:Person re-identification aims at pedestrian target matching under distributed monitoring systems. Compact and robust feature is critical to it. For this reason, this study proposes a feature extraction method based on feature fusion network. Firstly, the STEL algorithm is used to enhance the immunity of LOMO feature to background noise, and the KPCA algorithm is used to reduce dimension. Subsequently, we explore the complementarity between manual features and Convolutional Neural Network (CNN) features, and integrate the improved LOMO feature into the CNN to obtain a fusion feature with better performance. Experiments on two datasets (VIPeR and CUHK01) validate the effectiveness of our proposal, the Rank-1 of fusion feature is 3.73% and 2.36% higher than the cascade feature, respectively.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
种衍杰,方琰,沙涛.基于特征融合网络的行人重识别.计算机系统应用,2019,28(1):127-133
CHONG Yan-Jie,FANG Yan,SHA Tao.Person Re-Identification by Feature Fusion Network.COMPUTER SYSTEMS APPLICATIONS,2019,28(1):127-133

用微信扫一扫

用微信扫一扫