基于残差网络的特征加权行人重识别研究

张伟信; 刘斌

Chinese

您当前的位置：

首页 >

文章列表页 >

基于残差网络的特征加权行人重识别研究

更新时间：2026-09-04

- 基于残差网络的特征加权行人重识别研究
- Person Re-identification based on residual network with weightedfeatures
- 微电子学与计算机 2020年37卷第4期页码：26-31
- 作者机构：
  
  南京工业大学机构计算机科学与技术学院,江苏,南京,210000
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61672279
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
张伟信, 刘斌. 基于残差网络的特征加权行人重识别研究[J]. 微电子学与计算机, 2020, 37(4): 26-31.

ZHANG Wei-xin, LIU Bin. Person Re-identification based on residual network with weightedfeatures[J]. 2020, 37(4): 26-31.
张伟信, 刘斌. 基于残差网络的特征加权行人重识别研究[J]. 微电子学与计算机, 2020, 37(4): 26-31. DOI：

ZHANG Wei-xin, LIU Bin. Person Re-identification based on residual network with weightedfeatures[J]. 2020, 37(4): 26-31. DOI：

摘要

文章讨论了基于视频到视频的行人重识别的深度学习方法，提出的网络模型主要由特征表示子网络和相似性度量子网络两部分组成.首先利用残差网络提取视频的每帧图像的特征，再该特征输入到长短期记忆网络中获取时空特征，在长短期记忆网络层后添加权重模块，在该模块中使用帧质量注意力机制为视频的每一帧分配适当的权重.进一步将加权后的特征向量传入相似性度量子网络进行距离度量学习，在该框架中

将特征表示与相似性度量使用全连接层进行连接，同时学习和优化特征表示和相似度度量学习.最后在两个公共数据集上进行实验，通过一系列对比实验验证了该网络模型的能提高行人重识别准确率和性能.

Abstract

In this paper

we address the video-to-video person re-id. The proposed network is mainly composed of the feature representation subnetwork and the similarity measure network. First

the residual network is used to extract features from each frame of video

and then the features are inputtedinto the Long Short-Term Memory network to obtain features which contain information of time and space. Aweight module isappliedon the upper layer of Long Short-Term Memory network.Inthis model

applying an attentive quality mechanism to assign appropriate weight for each frame.Then

the weighted feature of each video sequence will be inputted into the similaritymeasure sub-network to measure similarity. In this framework

use fully connected layers to connect feature representation subnetwork and the similarity measure network

so the feature representation and similarity metric learning can be learned and optimized at the same time. Finally

we do experiments on two public datasets to prove that our network model can improve pedestrian recognition accuracy and performance.

关键词

Keywords

references

DING S, LIN L, WANG G, et al. Deep featurelearning with relative distance comparison for personre-identification[J]. Pattern Recog-nition, 2015, 48(10):2993-3003. DOI: 2993

ZUO W, WANG F, ZHANG D, et al. Distance Metric Learning via Iterated Support Vector Ma-chines[J]. IEEE Transactions on Image Processing, 2017:1-1. DOI: 1

ZHANG W, MA B, LIU K, et al. Video-Based Pedestrian Re-Identification by Adaptive Spatio-Temporal Appearance Model[J]. IEEE Transactions on Image Processing, 2017, 26(4):2042-2054. DOI: 2042

ZHENG L, SHEN L, TIAN L, et al. Scalable Person Re-identification: A Benchmark[C]// 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015.

MCLAUGHLIN N, RINCON J M D, MILLER P. Recurrent Convolutional Network for Video-Based Person Re-identification[C]// 2016 IEEE Con-ference on Computer Vision and Pattern Rec-ognition (CVPR). IEEE, 2016.

WANG T, GONG S, ZHU X, et al. Person Re-Identification by Discriminative Selection in Video Ranking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016:1-1. DOI: 1

ZHANG D, LIN L, CHEN T, et al. Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning[J]. IEEE Transactions on Image Processing, 2016:1-1. DOI: 1

IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// International Conference on International Conference on Machine Learning. JMLR.org, 2015.

CHEN L, YANG H, GAO Z. Joint Attentive Spatial-Temporal Feature Aggregation for Video-Based Person Re-Identification[J]. IEEE Access, 2019:1-1. DOI: 1

LIN L, WANG G, ZUO W, et al. Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016:1-1. DOI: 1

HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2016.

HINTON G E. Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair[C]// International Conference on International Conference on Machine Learning. Omnipress, 2010.

NICOL N. Schraudolph. Centering Neural Network Gradient Factors[M]. 1997.

LIAO S, HU Y, ZHU X, et al. Person re-identification by Local Maximal Occurrence representation and metric learning [C]. Computer Vision and Pattern Recognition. IEEE, 2015: 2197-2206.

WANG T, GONG S, ZHU X, et al. Person Re-Identification by Video Ranking[C]// European Conference on Computer Vision. Springer, Cham, 2014.

SAHA B, RAM K S, MUKHOPADHYAY J, et al. Video Based Person Re-Identification by Re-Ranking Attentive Temporal Information in Deep Recurrent Convolutional Networks[C]//2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018: 1663-1667.

SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A Simple Way to Prevent Neural Networks from Overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958. DOI: 1929

ZHANG D, WU W, CHENG H, et al. Image-to-Video Person Re-Identification with Temporally Memorized Similarity Learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017:1-1. DOI: 1

ZUO W, WU X, LIN L, et al. Learning Support Correlation Filters for Visual Tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018:1-1. DOI: 1

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合网格掩膜和残差坐标注意力的行人重识别

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究

超低功耗实时时钟电路的设计

一种用于极低压boost系统的高效率电荷泵

注意力机制与改进密集卷积引导的信息隐藏模型