基于多信息流动卷积神经网络的行人再识别

doi:10.3969/j.issn.0372-2112.2019.02.014

电子学报 ›› 2019, Vol. 47 ›› Issue (2): 351-357.DOI: 10.3969/j.issn.0372-2112.2019.02.014

基于多信息流动卷积神经网络的行人再识别

桑海峰¹, 王传正¹, 吕应宇¹, 何大阔², 刘晴²

1. 沈阳工业大学信息科学与工程学院, 辽宁沈阳 110870;
2. 东北大学信息科学与工程学院, 辽宁沈阳 110819

收稿日期:2018-03-28 修回日期:2018-05-22 出版日期:2019-02-25
- 通讯作者:
- 王传正
- 作者简介:
- 桑海峰 男,1978年生于辽宁沈阳,博士,沈阳工业大学教授,主要研究方向为视觉检测技术与图像处理.E-mail:sanghaif@163.com
- 基金资助:
- 国家自然科学基金 (No.61773105）; 辽宁省自然科学基金 (No.20170540675）; 辽宁省教育厅科研项目 (No.LQGD2017023）

Person Re-identification Based on Multi-information Flow Convolutional Neural Network

SANG Hai-feng¹, WANG Chuan-zheng¹, LÜ Ying-yu¹, HE Da-kuo², LIU Qing²

1. School of Information Science & Engineering, Shenyang University of Technology, Shenyang, Liaoning 110870, China;
2. College of Information Science & Engineering, Northeastern University, Shenyang, Liaoning 110819, China

Received:2018-03-28 Revised:2018-05-22 Online:2019-02-25 Published:2019-02-25

摘要/Abstract

摘要： 行人再识别问题中，由于视角、光照和行人姿态等因素的变化，导致难以提取有效的行人特征，降低识别精度.而深度神经网络在训练样本较少的情况下较难训练，易出现过拟合现象.针对上述问题，本文提出一种多信息流动卷积神经网络（Multi-information Flow Convolutional Neural Network，MiF-CNN）模型，模型中包含一个特殊的卷积结构，该结构中每层卷积层提取到的特征与后续所有卷积层的输入相连接，增强了网络的特征信息流动性和梯度的反向传播效率，使得模型提取到的行人特征更具判别力.采用多损失函数组合方式训练网络模型，更好的区分行人类别.最后利用欧氏距离对行人特征相似性进行排序.在标准行人再识别数据集VIPeR和CUHK01上的实验表明，本文方法进一步提高了行人再识别精度，并有效改善了深度神经网络的过拟合现象.

关键词: 行人再识别, 多信息流动, 特征提取, 卷积神经网络

Abstract: It is challenging to learn efficient features in person re-identification task due to complex variations of viewpoints,illumination,pose etc.In addition,deep neural network still suffers from overfitting with a small training set.To solve these problems,a Multi-information Flow Convolutional Neural Network(MiF-CNN)is designed for person re-identification which contains a specific convolutional architecture.In this architecture,features from each convolution layer are concatenated with all subsequent convolution layers so that it can improve the flowability of feature information and the efficiency of backpropagation gradient.In this way,the proposed network can learn more discriminative features.Moreover,a combination of three loss functions is used to train proposed network.Finally,the identification accuracy is obtained by ranking the similarity of extracted features measured by Euclidean distance.Experimental results on the VIPeR and CUHK01 datasets demonstrate that MiF-CNN outperform most of existing methods of person re-identification and reduce overfitting more effectively.

Key words: person re-identification, multi-information flow, feature extraction, convolutional neural network

中图分类号:

TP391

桑海峰, 王传正, 吕应宇, 何大阔, 刘晴. 基于多信息流动卷积神经网络的行人再识别[J]. 电子学报, 2019, 47(2): 351-357.

SANG Hai-feng, WANG Chuan-zheng, LÜ Ying-yu, HE Da-kuo, LIU Qing. Person Re-identification Based on Multi-information Flow Convolutional Neural Network[J]. Acta Electronica Sinica, 2019, 47(2): 351-357.

参考文献

[1] 杨钰源.基于度量学习和深度学习的行人重识别研究[D].重庆:重庆大学,2016.
[2] Liao S,Hu Y,Zhu X,et al.Person re-identification by local maximal occurrence representation and metric learning[A].Computer Vision and Pattern Recognition[C].IEEE,2015.2197-2206.
[3] Tahir S F,Cavallaro A.Cost-effective features for reidentification in camera networks[J].IEEE Transactions on Circuits & Systems for Video Technology,2014,24(8):1362-1374.
[4] Yang Y,Yang J,Yan J,et al.Salient color names for person re-identification[A].European Conference on Computer Vision[C].Springer,Cham,2014.536-551.
[5] Zheng W S,Gong S,Xiang T.Person re-identification by probabilistic relative distance comparison[A].Computer Vision and Pattern Recognition[C].IEEE,2011.649-656.
[6] Li Z,Chang S,Liang F,et al.Learning locally-adaptive decision functions for person verification[A].Computer Vision and Pattern Recognition[C].IEEE,2013.3610-3617.
[7] Engel C,Baumgartner P,Holzmann M,et al.Person re-identification by support vector ranking[A].British Machine Vision Conference,BMVC 2010[C].Aberystwyth,UK,August 31-September 3,2010.Proceedings.DBLP,2010.1-11.
[8] Li W,Zhao R,Xiao T,et al.DeepReID:Deep filter pairing neural network for person re-identification[A].Computer Vision and Pattern Recognition[C].IEEE,2014.152-159.
[9] Cheng D,Gong Y,Zhou S,et al.Person re-identification by multi-channel parts-based CNN with improved triplet loss function[A].Computer Vision and Pattern Recognition[C].IEEE,2016.1335-1344.
[10] Ahmed E,Jones M,Marks T K.An improved deep learning architecture for person re-identification[A].Computer Vision and Pattern Recognition[C].IEEE,2015.3908-3916.
[11] Chen W,Chen X,Zhang J,et al.Beyond triplet loss:a deep quadruplet network for person re-identification[A].The Conference on Computer Vision and Pattern Recognition[C].2017.1320-1329.
[12] Wen Y,Zhang K,Li Z,et al.A Discriminative Feature Learning Approach for Deep Face Recognition[M].Computer Vision-ECCV 2016.Springer International Publishing,2016.499-515.
[13] Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[A].IEEE Conference on Computer Vision and Pattern Recognition[C].IEEE Computer Society,2015.1-9.
[14] Gray D,Tao H.Viewpoint invariant pedestrian recognition with an ensemble of localized features[A].Computer Vision-ECCV 2008,European Conference on Computer Vision[C].Marseille,France,October 12-18,Proceedings.DBLP,2008.262-275.
[15] Li W,Zhao R,Wang X.Human reidentification with transferred metric learning[A].Asian Conference on Computer Vision[C].Springer,Berlin,Heidelberg,2012.31-44.
[16] Li D,Chen X,Zhang Z,et al.Learning deep context-aware features over body and latent parts for person re-identification[A].Computer Vision and Pattern Recognition[C].IEEE,2017.384-393.
[17] Wang F,Zuo W,Lin L,et al.Joint learning of single-imag.age and cross-image representations for person re-identifi-cation[A].Computer Vision and Pattern Recognition[C].IEEE,2016.1288-1296.
[18] Xiao T,Li H,Ouyang W,et al.Learning deep feature representations with domain guided dropout for person re-identification[A].Computer Vision and Pattern Recognition[C].IEEE,2016.1249-1258.
[19] Varior R R,Haloi M,Wang G.Gated siamese convolutional neural network architecture for human re-identification[A].European Conference on Computer Vision[C].Springer International Publishing,2016.79-808.
[20] Ding S,Lin L,Wang G,et al.Deep feature learning with relative distance comparison for person re-identification[J].Pattern Recognition,2015,48(10):2993-3003.
[21] Chen S Z,Guo C C,Lai J H.Deep ranking for person re-identification via joint representation learning[J].IEEE Transactions on Image Processing,2015,25(5):2353-2367.
[22] Huang Y,Sheng H,Zheng Y,et al.DeepDiff:Learning deep difference features on human body parts for person re-identification[J].Neurocomputing,2017,241:191-203.

基于多信息流动卷积神经网络的行人再识别

Person Re-identification Based on Multi-information Flow Convolutional Neural Network

PDF

可视化

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

[1]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[2]	毛国君, 王者浩, 黄山, 王翔. 基于剪边策略的图残差卷积深层网络模型[J]. 电子学报, 2022, 50(9): 2205-2214.
[3]	袁海英, 曾智勇, 成君鹏. 面向灵活并行度的稀疏卷积神经网络加速器[J]. 电子学报, 2022, 50(8): 1811-1818.
[4]	王相海, 赵晓阳, 王鑫莹, 赵克云, 宋传鸣. 非抽取小波边缘学习深度残差网络的单幅图像超分辨率重建[J]. 电子学报, 2022, 50(7): 1753-1765.
[5]	张志文, 刘天歌, 聂鹏举. 基于实景数据增强和双路径融合网络的实时街景语义分割算法[J]. 电子学报, 2022, 50(7): 1609-1620.
[6]	丁毅, 沈薇, 李海生, 钟琼慧, 田明宇, 李洁. 面向CNN的区块链可信隐私服务计算模型[J]. 电子学报, 2022, 50(6): 1399-1409.
[7]	张波, 陆云杰, 秦东明, 邹国建. 一种卷积自编码深度学习的空气污染多站点联合预测模型[J]. 电子学报, 2022, 50(6): 1410-1427.
[8]	曲立国, 陈国豪, 胡俊, 陈鹏. 单次扫描连通域分析算法研究综述[J]. 电子学报, 2022, 50(6): 1521-1536.
[9]	廖勇, 李玉杰. 一种轻量化低复杂度的FDD大规模MIMO系统CSI反馈方法[J]. 电子学报, 2022, 50(5): 1211-1217.
[10]	张云, 化青龙, 姜义成, 徐丹. 基于混合型复数域卷积神经网络的三维转动舰船目标识别[J]. 电子学报, 2022, 50(5): 1042-1049.
[11]	崔亚奇, 何友, 唐田田, 熊伟. 一种深度学习航迹关联方法[J]. 电子学报, 2022, 50(3): 759-763.
[12]	伍邦谷, 张苏林, 石红, 朱鹏飞, 王旗龙, 胡清华. 基于多分支结构的不确定性局部通道注意力机制[J]. 电子学报, 2022, 50(2): 374-382.
[13]	陈文俊, 杨春玲. 图像压缩感知的特征域优化及自注意力增强神经网络重构算法[J]. 电子学报, 2022, 50(11): 2629-2637.
[14]	肖斌, 陈嘉博, 毕秀丽, 张俊辉, 李伟生, 王国胤, 马旭. 基于一维卷积神经网络与循环神经网络串联的心音分析方法[J]. 电子学报, 2022, 50(10): 2425-2432.
[15]	周登文, 李文斌, 李金新, 黄志勇. 一种轻量级的多尺度通道注意图像超分辨率重建网络[J]. 电子学报, 2022, 50(10): 2336-2346.