计算机科学 ›› 2022, Vol. 49 ›› Issue (8): 165-171.doi: 10.11896/jsjkx.210600140
陈坤峰, 潘志松, 王家宝, 施蕾, 张锦
CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin
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。
中图分类号:
[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. |
[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 |
|