基于双目叠加仿生的微换衣行人再识别

doi:10.11896/jsjkx.210600140

摘要/Abstract

摘要： 微换衣行人再识别是以换衣幅度不大的情况为前提,从不同摄像头场景中查找某特定身份的行人的一项计算机视觉技术。现有行人再识别方法的实现通常是基于行人衣着不变的假设,因此它们依赖的是与衣着相关的特征。那么,当此假设不成立时,这些方法就难以实现理想的识别效果。考虑到行人换衣幅度不大时行人体态基本不发生改变这一重要特点,针对微换衣行人再识别展开研究。受生物视觉系统中双目叠加效应的启发,采取仿生思想提出一个自注意力孪生网络,类比生物双眼获取信息的过程。首先,该网络以同一行人不同衣着的两类图像作为双分支输入,并利用孪生架构实现叠加效应。随后对输出的多个特征进行对比学习和融合学习,进而得到具有身份辨别力的行人特征表示。最后,在微换衣行人再识别相关数据集上进行了充分实验,结果表明该方法可达到当前最好的识别性能。

关键词: 孪生网络, 双目叠加效应, 微换衣, 行人再识别, 自注意力

Abstract: Moderate clothes-changing person re-identification is to find the same person from different camera scenes under the premise of considering the moderate change of clothes.The implementation of existing person re-identification methods is usually based on the assumption that the pedestrian’s clothing is invariant,so they rely on clothing-related features.Then,when the above assumptions are not valid,these methods are difficult to achieve the ideal recognition performance.Considering the important characteristic that pedestrian’s shape hardly change when the change of clothes is moderate,the moderate clothes-changing person re-identification is studied.Inspired by the binocular summation in biological vision system,a self-attention siamese network is proposed in this paper.Analogous to biological binocular information acquisition process,the network takes two types of images of the same pedestrian with different clothes as two branch inputs,and then achieves summation effect with siamese architecture.Subsequently,the contrastive learning and fusion learning of multiple features are carried out to obtain the pedestrian feature representation with identity discrimination.Finally,empirical studies show that the proposed method achieves best performance at present on clothes-changing person re-identification benchmark.

Key words: Binocular summation, Moderate clothes-changing, Person re-identification, Self-attention, Siamese network

中图分类号:

TP391

陈坤峰, 潘志松, 王家宝, 施蕾, 张锦. 基于双目叠加仿生的微换衣行人再识别[J]. 计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140

CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin. Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation[J]. Computer Science, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140

参考文献

[1]GHEISSARI N,SEBASTIAN T B,HARTLEY R.Person reidentification using spatiotemporal appearance[C]//2006 IEEEComputer Society Conference on Computer Vision and Pattern Recognition(CVPR’06).IEEE,2006:1528-1535.
[2]FARENZENA M,BAZZANI L,PERINA A,et al.Person re-identification by symmetry-driven accumulation of local features[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.IEEE,2010:2360-2367.
[3]GRAY D,TAO H.Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]//European Confe-rence on Computer Vision.Berlin:Springer,2008:262-275.
[4]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[5]PAISITKRIANGKRAI S,SHEN C,VAN DEN HENGEL A.Learning to rank in person re-identification with metric ensembles[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1846-1855.
[6]SHEN Y,XIAO T,LI H,et al.End-to-end deep kronecker-pro-duct matching for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:6886-6895.
[7]ZHENG Z,YANG X,YU Z,et al.Joint discriminative and gene-rative learning for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:2138-2147.
[8]WEI L,ZHANG S,GAO W,et al.Person transfer gan to bridge domain gap for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:79-88.
[9]RISTANI E,SOLERA F,ZOU R,et al.Performance measures and a data set for multi-target,multi-camera tracking[C]//European Conference on Computer Vision.Cham:Springer,2016:17-35.
[10]ZHENG L,SHEN L,TIAN L,et al.Scalable person re-identification:A benchmark[C]//Proceedings of the IEEE InternationalConference on Computer Vision.2015:1116-1124.
[11]HOU R,CHANG H,MA B,et al.Temporal complementarylearning for video person re-identification[C]//European Conference on Computer Vision.Cham:Springer,2020:388-405.
[12]FAN C,PENG Y,CAO C,et al.Gaitpart:Temporal part-based model for gait recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:14225-14233.
[13]LORENZO-NAVARRO J,CASTRILLÓN-SANTANA M,HERNÁNDEZ-SOSA D.An study on re-identification in RGB-D imagery[C]//International Workshop on Ambient Assisted Li-ving.Berlin:Springer,2012:200-207.
[14]HAQUE A,ALAHI A,FEI-FEI LI F F.Recurrent attentionmodels for depth-based person identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:1229-1238.
[15]WU A,ZHENG W S,LAI J H.Robust depth-based person re-identification[J].IEEE Transactions on Image Processing,2017,26(6):2588-2603.
[16]JIA X,MENG Z,KATIPALLY K,et al.Clothing ChangeAware Person Identification[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).IEEE Computer Society,2018.
[17]YANG Q Z,WU A C,ZHENG W S.Person Re-identification by Contour Sketch under Moderate Clothing Change[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,3(6):2029-2046.
[18]LI Y J,LUO Z Y,WENG X S,et al.Learning shape representations for clothing variations in person re-identification[J].ar-Xiv:2003.07340,2020.
[19]ZHANG J,LI Y,CHEN F Q,et al.X-Net:A Binocular Summation Network for Foreground Segmentation[J].IEEE Access,2019,7:1412-71422.
[20]BLAKE R,WILSON H.Binocular Vision[J].Vision Research,2011,51(7):754-770.
[21]LOWE D G.Distinctive Image Features from Scale-InvariantKeypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[22]REDMON J,FARHADI A.Yolov3:An incremental improve-ment[J].arXiv:1804.02767,2018.
[23]XIE S,TU Z.Holistically-nested edge detection[C]//Procee-dings of the IEEE International Conference on Computer Vision.2015:1395-1403.
[24]HU J,LI S,ALBANIE S.Squeeze-and-Excitation Networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2018.
[25]YE M,SHEN J,LIN G,et al.Deep learning for person re-identification:A survey and outlook[J/OL].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021.https://ieeexplore.ieee.org/abstract/document/9336268.
[26]XIA B N,GONG Y,ZHANG Y,et al.Second-order non-local attention networks for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:3760-3769.
[27]YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].arXiv:1511.07122,2015.
[28]OJALA T,PIETIKÄINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
[29]DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2005:886-893.
[30]KOESTINGER M,HIRZER M,WOHLHART P,et al.Large scale metric learning from equivalence constraints[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2012:2288-2295.
[31]SUN Y,ZHENG L,YANG Y,et al.Beyond part models:Person retrieval with refined part pooling (and a strong convolutional baseline)[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:480-496.

相关文章 15

[1]	吴子仪, 李邵梅, 姜梦函, 张建朋. 基于自注意力模型的本体对齐方法 Ontology Alignment Method Based on Self-attention 计算机科学, 2022, 49(9): 215-220. https://doi.org/10.11896/jsjkx.210700190
[2]	方义秋, 张震坤, 葛君伟. 基于自注意力机制和迁移学习的跨领域推荐算法 Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning 计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011
[3]	金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[4]	张嘉淏, 刘峰, 齐佳音. 一种基于Bottleneck Transformer的轻量级微表情识别架构 Lightweight Micro-expression Recognition Architecture Based on Bottleneck Transformer 计算机科学, 2022, 49(6A): 370-377. https://doi.org/10.11896/jsjkx.210500023
[5]	赵丹丹, 黄德根, 孟佳娜, 董宇, 张攀. 基于BERT-GRU-ATT模型的中文实体关系分类 Chinese Entity Relations Classification Based on BERT-GRU-ATT 计算机科学, 2022, 49(6): 319-325. https://doi.org/10.11896/jsjkx.210600123
[6]	韩洁, 陈俊芬, 李艳, 湛泽聪. 基于自注意力的自监督深度聚类算法 Self-supervised Deep Clustering Algorithm Based on Self-attention 计算机科学, 2022, 49(3): 134-143. https://doi.org/10.11896/jsjkx.210100001
[7]	赵越, 余志斌, 李永春. 基于互注意力指导的孪生跟踪算法 Cross-attention Guided Siamese Network Object Tracking Algorithm 计算机科学, 2022, 49(3): 163-169. https://doi.org/10.11896/jsjkx.210300066
[8]	胡艳丽, 童谭骞, 张啸宇, 彭娟. 融入自注意力机制的深度学习情感分析方法 Self-attention-based BGRU and CNN for Sentiment Analysis 计算机科学, 2022, 49(1): 252-258. https://doi.org/10.11896/jsjkx.210600063
[9]	徐少伟, 秦品乐, 曾建朝, 赵致楷, 高媛, 王丽芳. 基于多级特征和全局上下文的纵膈淋巴结分割算法 Mediastinal Lymph Node Segmentation Algorithm Based on Multi-level Features and Global Context 计算机科学, 2021, 48(6A): 95-100. https://doi.org/10.11896/jsjkx.200700067
[10]	程旭, 崔一平, 宋晨, 陈北京, 郑钰辉, 史金钢. 基于时空注意力机制的目标跟踪算法 Object Tracking Algorithm Based on Temporal-Spatial Attention Mechanism 计算机科学, 2021, 48(4): 123-129. https://doi.org/10.11896/jsjkx.200800164
[11]	王习, 张凯, 李军辉, 孔芳, 张熠天. 联合自注意力和循环网络的图像标题生成 Generation of Image Caption of Joint Self-attention and Recurrent Neural Network 计算机科学, 2021, 48(4): 157-163. https://doi.org/10.11896/jsjkx.200300146
[12]	周小诗, 张梓葳, 文娟. 基于神经网络机器翻译的自然语言信息隐藏 Natural Language Steganography Based on Neural Machine Translation 计算机科学, 2021, 48(11A): 557-564. https://doi.org/10.11896/jsjkx.210100015
[13]	张世豪, 杜圣东, 贾真, 李天瑞. 基于深度神经网络和自注意力机制的医学实体关系抽取 Medical Entity Relation Extraction Based on Deep Neural Network and Self-attention Mechanism 计算机科学, 2021, 48(10): 77-84. https://doi.org/10.11896/jsjkx.210300271
[14]	唐一星, 刘学亮, 胡社教. 多方向分区网络结构的行人再识别 Multi-orientation Partitioned Network for Person Re-identification 计算机科学, 2021, 48(10): 204-211. https://doi.org/10.11896/jsjkx.210300128
[15]	于文家, 丁世飞. 基于自注意力机制的条件生成对抗网络 Conditional Generative Adversarial Network Based on Self-attention Mechanism 计算机科学, 2021, 48(1): 241-246. https://doi.org/10.11896/jsjkx.200700187

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed