基于姿态与并行化属性学习的行人再识别方法

doi:10.19678/j.issn.1000-3428.0054092

计算机工程 ›› 2020, Vol. 46 ›› Issue (3): 246-253. doi: 10.19678/j.issn.1000-3428.0054092

基于姿态与并行化属性学习的行人再识别方法

陶飞, 成科扬, 张建明, 汤宇豪

江苏大学计算机科学与通信工程学院, 江苏镇江 212013

收稿日期:2019-03-04 修回日期:2019-04-12 发布日期:2019-05-22
作者简介:陶飞(1993-),女,硕士研究生,主研方向为行人再识别、属性学习;成科扬,副教授、博士;张建明(通信作者),教授、博士;汤宇豪,硕士研究生。
基金资助:
国家自然科学基金"基于数据驱动与语义建模的多摄像拓扑推理与行人再识别研究"（61602215）；江苏省科学基金"大数据驱动下基于深度学习与语义建模的行人再识别研究"（BK20150527）；社会安全风险感知与防控大数据应用国家工程实验室主任基金"跨摄像头逻辑推理与多模态行人再识别技术研究"。

Pedestrian Reidentification Method Based on Posture and Parallel Attribute Learning

TAO Fei, CHENG Keyang, ZHANG Jianming, TANG Yuhao

School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China

Received:2019-03-04 Revised:2019-04-12 Published:2019-05-22

摘要/Abstract

摘要： 行人再识别是当前图像识别领域的一个重要研究分支，在取得众多研究成果的同时，在实际场景中的应用也存在诸多挑战。摄像设备和拍摄场景的差异，以及穿着、尺度、部分遮挡、姿态等对行人外观的影响，给行人再识别带来较大的困难。为此，提出一种行人再识别方法，通过基于姿态的并行化属性学习任务对行人姿态信息进行标注，并将其作为语义属性融入到行人再识别任务中，降低实际场景中属性缺失对模型的影响，加速训练过程。实验结果表明，该方法在VIPeR数据集上达到了90%的识别率。

关键词: 深度学习, 行人再识别, 姿态, 属性学习, 并行化

Abstract: Pedestrian reidentification is an important research branch in the current image recognition field.While many breakthroughs are made,there are also many challenges in the application of actual scenes.The differences of camera equipment and shooting scenes,and the influence of wearing,scale,partial occlusion,posture,etc on pedestrian appearance,bring greater difficulties to pedestrians reidentification.Therefore,this paper proposes a pedestrian reidentification method.The method marks the pedestrian attribute information through the parallel attribute learning task based on posture,and then the labeled attitude information is integrated into the pedestrian reidentification task as a semantic attribute.The method reduces the impact of attribute missing on the model in the actual scenes and accelerates the training process.Experimental results show that the method achieves a 90% recognition accuracy on the VIPeR data set.

Key words: deep learning, pedestrian reidentification, posture, attribute learning, parallelization

中图分类号:

TP391

陶飞, 成科扬, 张建明, 汤宇豪. 基于姿态与并行化属性学习的行人再识别方法[J]. 计算机工程, 2020, 46(3): 246-253.

TAO Fei, CHENG Keyang, ZHANG Jianming, TANG Yuhao. Pedestrian Reidentification Method Based on Posture and Parallel Attribute Learning[J]. Computer Engineering, 2020, 46(3): 246-253.

http://www.ecice06.com/CN/Y2020/V46/I3/246

图/表 10

20200321091614

20200321091619

20200321091623

20200321091727

20200321091730

20200321091735

20200321092038

20200321092041

20200321092044

20200321092046

参考文献

[1] MIKLASZ M,OLSZEWSKI P,NOWOSIELSKI A,et al.Pedestrian traffic distribution analysis using face recognition technology[C]//Proceedings of International Conference on Transport Systems Telematics.Berlin,Germany:Springer,2013:303-312.
[2] HU Ruimin.Big data smart city and smart security——pedestrian re-identification[J].Intelligent Building,2014,17(5):44-47.(in Chinese)胡瑞敏.大数据智慧城市与智能安防——行人重识别[J].智能建筑,2014,17(5):44-47.
[3] TAKE N,KOSUGI Y,MUSHA T.Estimation of bidirectional information flow in the human brain from evoked potentials by use of dipole tracing method[C]//Proceedings of International Conference of the IEEE Engineering in Medicine & Biology Society.Washington D.C.,USA:IEEE Press,2001:627-630.
[4] BAZZANI L,CRISTANI M,PERINA A,et al.Multiple-shot person re-identification by chromatic and epitomic analyses[J].Pattern Recognition Letters,2012,33(7):898-903.
[5] CHENG D S,CRISTANI M,STOPPA M,et al.Custom pictorial structures for re-identification[C]//Proceedings of British Machine Vision Conference.Surrey,UK:British Machine Vision Association,2011:1-11.
[6] FU Hongpu,JU Beiji.Histogram of oriented gradient and its extension[J].Computer Engineering,2013,39(5):212-217.(in Chinese)傅红普,邹北骥.方向梯度直方图及其扩展[J].计算机工程,2013,39(5):212-217.
[7] FARENZENA M,BAZZANI L,PERINA A,et al.Person re-identification by symmetry-driven accumulation of local features[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2360-2367.
[8] DANACI E G,IKIZLER-CINBIS N.Low-level features for visual attribute recognition:an evaluation[J].Pattern Recognition Letters,2016,84:185-191.
[9] GAO Mu,AI Haizhou,BAI Bo.A feature fusion strategy for person re-identification[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2016:4274-4278.
[10] LAYNE R,HOSPEDALES T M,GONG S,et al.Person re-identification by attributes[C]//Proceedings of British Machine Vision Conference.Surrey,UK:British Machine Vision Association,2012:1-11.
[11] SU Chi,YANG Fan,ZHANG Shiliang,et al.Multi-task learning with low rank attribute embedding for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:3739-3747.
[12] NGUYEN T P,MANZANERA A,KROPATSCH W G,et al.Impact of topology-related attributes from local binary patterns on texture classification[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2014:80-93.
[13] MIN Qiusha,LIU Neng,CHEN Yating,et al.Head pose estimation based on facial feature point localization[J].Computer Engineering,2018,44(6):263-269.(in Chinese)闵秋莎,刘能,陈雅婷,等.基于面部特征点定位的头部姿态估计[J].计算机工程,2018,44(6):263-269.
[14] SAQUIB S M,SCHUMANN A,EBERLE A,et al.A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:420-429.
[15] TOSHEV A,SZEGEDY C.Deeppose:human pose estimation via deep neural networks[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:1653-1660.
[16] CHENG Keyang,XU Fangjie,TAO Fei,et al.Data-driven pedestrian re-identification based on hierarchical semantic representation[EB/OL].[2019-02-28].https://onlinelibrary.wiley.xilesou.top/doi/abs/10.1002/cpe.4403.
[17] LI Dangwei,ZHANG Zhang,CHEN Xiaotang,et al.A richly annotated dataset for pedestrian attribute recognition[EB/OL].[2019-02-28].https://arxiv.xilesou.top/abs/1603.07054.
[18] GRAY D,TAO H.Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2008:262-275.
[19] PISHCHULIN L,INSAFUTDINOV E,TANG S Y,et al.DeepCut:joint subset partition and labeling for multi person pose estimation[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:4929-4937.
[20] ZHAO Rui,OUYANG Wanli,WANG Xiaogang.Unsupervised salience learning for person re-identification[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3586-3593.
[21] UMEDA T,SUN Y Q,IRIE G,et al.Attribute discovery for person re-identification[M]//UMEDA T,SUN Y Q,IRIE G,et al.Multi media modeling.Berlin,Germany:Springer,2016:268-276.
[22] FARENZENA M,BAZZANI L,PERINA A,et al.Person re-identification by symmetry-driven accumulation of local features[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2360-2367.
[23] ROTH P M,HIRZER M,KÖSTINGER M,et al.Mahalanobis distance learning for person re-identification[M]//GONG S,CRISTANI M,YAN S,et al.Person re-identification.Berlin,Germany:Springer,2014:247-267.
[24] ZHENG Liang,HUANG Yujia,LU Huchuan,et al.Pose-invariant embedding for deep person re-identification[J].IEEE Transactions on Image Processing,2019,28(9):4500-4509.

选择文件类型/文献管理软件名称

选择包含的内容

基于姿态与并行化属性学习的行人再识别方法

Pedestrian Reidentification Method Based on Posture and Parallel Attribute Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	江雨燕, 陶承凤, 李平. 数据增强和自适应自步学习的深度子空间聚类算法[J]. 计算机工程, 2023, 49(8): 96-103, 110.
[2]	李泽水, 冀俊忠, 杨翠翠. 基于边权重信息深度网络嵌入的PPIN功能模块检测[J]. 计算机工程, 2023, 49(8): 69-76.
[3]	王可铮, 徐玉芬, 周尚波. 结合对比感知损失和融合注意力的图像去雾模型[J]. 计算机工程, 2023, 49(8): 207-214.
[4]	刘俊豪, 王美林, 谢兴, 宋烨兴, 许莉花. 基于改进YOLOv5的皮革瑕疵检测算法[J]. 计算机工程, 2023, 49(8): 240-249.
[5]	闫兴亚, 匡娅茜, 白光睿, 李月. 基于深度学习的学生课堂行为识别方法[J]. 计算机工程, 2023, 49(7): 251-258.
[6]	刘豪, 吴红兰, 房宇轩. 结合全局上下文信息的高效人体姿态估计[J]. 计算机工程, 2023, 49(7): 102-109.
[7]	李军侠, 王星驰, 殷梓, 石德硕. 边缘深度挖掘的弱监督显著性目标检测[J]. 计算机工程, 2023, 49(7): 169-178.
[8]	吴珊, 周凤. 基于改进SSD算法的小目标检测[J]. 计算机工程, 2023, 49(7): 179-188.
[9]	席建锐, 唐红梅, 梁春阳, 刘鑫. 基于改进隐函数的点云物体重建[J]. 计算机工程, 2023, 49(7): 214-222.
[10]	王款, 宣士斌, 何雪东, 李紫薇, 李嘉祥. 基于交叉注意力Transformer的人体姿态估计方法[J]. 计算机工程, 2023, 49(7): 223-231.
[11]	齐咏生, 杜晓旭, 朱俊峰, 高胜利, 刘利强. 基于增强型轻量深度网络的牧区牲畜高效检测[J]. 计算机工程, 2023, 49(7): 278-287.
[12]	谌雨章, 黄逸姿, 张钧涵. 基于多速率空洞卷积的多尺度水下小目标检测[J]. 计算机工程, 2023, 49(6): 257-264.
[13]	张博旭, 蒲智, 程曦. 基于提示学习的维吾尔语文本分类研究[J]. 计算机工程, 2023, 49(6): 292-299,313.
[14]	于海洋, 景鹏, 张文涛, 谢赛飞, 滑志华, 宋草原. 基于残差与注意力机制的道路裂缝检测U-Net改进模型[J]. 计算机工程, 2023, 49(6): 265-273.
[15]	王爱玲, 马文臻, 邹自明, 钟佳. 基于领域自适应的卫星工程参数异常检测[J]. 计算机工程, 2023, 49(5): 29-37,47.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于姿态与并行化属性学习的行人再识别方法

Pedestrian Reidentification Method Based on Posture and Parallel Attribute Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价