行人再识别中基于无监督学习的粗细粒度特征提取

doi:10.19678/j.issn.1000-3428.0060811

摘要/Abstract

摘要： 行人再识别研究中存在特征判别信息不够丰富的情况，并且遮挡、光照等因素会干扰有效特征的准确提取，对后续相似性度量、度量结果排序等工作都有较大影响。此外，监督学习需要使用标签信息，在面对大型数据集时工作量很大。通过引入无监督学习框架，提出一种粗细粒度判别性特征提取方法。构建基于细粒度和粗粒度特征学习的模型框架，其中包含局部和全局2个分支。在局部分支中，对图像学习到的特征映射提取补丁块，并在未标记数据集上学习不同位置的细粒度补丁特征；在全局分支中，使用无标注数据集的相似度和多样性作为信息来学习粗粒度特征。在此基础上，利用相吸和相斥2个损失函数分别增加类别内相似度和类别间多样性，并结合最小距离准则计算特征之间的相似度，进行无监督的聚类合并。在Market-1501和DukeMTMC-reID数据集上的实验结果表明，该方法对于完成行人再识别任务具有较好的判别性能和鲁棒性，相比所有对比方法的最优结果，其Rank-1指标分别提高5.76%和5.07%，平均精度均值分别提高3.2%和5.6%。

关键词: 计算机视觉, 行人再识别, 无监督学习, 特征学习, 损失函数, 最小距离准则

Abstract: In the research of pedestrian re-identification, there is not enough feature discrimination information, and factors such as occlusion and illumination will interfere with the accurate extraction of effective features, having a decisive impact on the subsequent similarity measurement and ranking of measurement results.In addition, supervised learning models need label information, imposing a heavy workload for large datasets.In view of this, a coarse-grained and fine-grained discriminant feature extraction method is proposed based on unsupervised learning.A model framework is built based on fine-grained and coarse-grained feature learning for local and global feature extraction.For local features, patch blocks are extracted from the feature map learned from the image, and fine-grained patch features at different locations are learned from the unlabeled data set.For global features, the similarity and diversity of unlabeled data sets provide the information for coarse-grained feature learning.On this basis, the two loss functions of attraction and repulsion are used to increase the similarity within categories and the diversity between categories respectively, and the similarity between features is calculated combined with the minimum distance criterion for unsupervised clustering.The experimental results on Market-1501 and DukeMTMC-reID datasets show that this method has good discrimination performance and robustness for solving the pedestrian re-indentification task, whereby the Rank-1 index is improved by 5.76% and 5.07%, respectively, and the mean Average Precision(mAP) is improved by 3.2% and 5.6%, respectively compared with the optimal results of all comparison methods.

Key words: computer vision, pedestrian re-identification, unsupervised learning, feature learning, loss function, minimum distance criterion

中图分类号:

TP391.41

唐佳敏, 韩华, 黄丽. 行人再识别中基于无监督学习的粗细粒度特征提取[J]. 计算机工程, 2022, 48(4): 269-275,283.

TANG Jiamin, HAN Hua, HUANG Li. Coarse-grained and Fine-grained Features Extraction Based on Unsupervised Learning in Pedestrian Re-identification[J]. Computer Engineering, 2022, 48(4): 269-275,283.

https://www.ecice06.com/CN/Y2022/V48/I4/269

图/表 14

20230131202501

20230131202504

20230131202507

20230131202510

20230131202513

20230131202517

20230131202520

20230131202523

20230131202526

20230131202529

20230131202532

20230131202535

20230131202538

20230131202541

参考文献

[1] 李幼蛟, 卓力, 张菁, 等.行人再识别技术综述[J].自动化学报, 2018, 44(9):1554-1568. LI Y J, ZHOU L, ZHANG J, et al.A survey of person re-identification[J].Acta Automatica Sinica, 2018, 44(9):1554-1568.(in Chinese)
[2] JIN X, LAN C, ZENG W, et al.Style normalization and restitution for generalizable person re-identification[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:3140-3149.
[3] ZHANG Z, LAN C, ZENG W, et al.Relation-aware global attention for person re-identification[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:3183-3192.
[4] CHEN X, FU C, ZHAO Y, et al.Salience-guided cascaded suppression network for person re-identification[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:3297-3307.
[5] ZHAO S, GAO C, ZHANG J, et al.Do not disturb me:person re-identification under the interference of other pedestrians[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2020:647-663.
[6] FU Y, WEI Y, WANG G, et al.Self-similarity grouping:a simple unsupervised cross domain adaptation approach for person re-identification[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:6111-6120.
[7] YAN Y, QIN J, CHEN J, et al.Learning multi-granular hypergraphs for video-based person re-identification[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:2896-2905.
[8] ZHU J Y, PARK T, ISOLA P, et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2242-2251.
[9] WEI L, ZHANG S, GAO W, et al.Person transfer GAN to bridge domain gap for person re-identification[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:79-88.
[10] QIAN X, FU Y, XIANG T, et al.Pose-normalized image generation for person re-identification[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:650-667.
[11] WU Y, LIN Y, DONG X, et al.Progressive learning for person re-identification with one example[J].IEEE Transactions on Image Processing, 2019, 28:2872-2881.
[12] DENG W, ZHENG L, YE Q, et al.Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:994-1003.
[13] ZHONG Z, ZHENG L, LI S, et al.Generalizing a person retrieval model hetero- and homogeneously[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:176-192.
[14] 李佳宾, 李学伟, 刘宏哲, 等.基于局部特征关联与全局注意力机制的行人重识别[J].计算机工程, 2022, 48(1):245-252. LI J B, LI X W, LIU H Z, et al.Person re-identification based on local feature relation and global attention mechanism[J].Computer Engineering, 2022, 48(1):245-252.(in Chinese)
[15] 库浩华, 周萍, 蔡晓东, 等.基于区域特征对齐与k倒排编码的行人再识别方法[J].计算机工程, 2019, 45(3):207-211. KU H H, ZHOU P, CAI X D, et al.Person re-identification method based on regional feature alignment and k-reciprocal encoding[J].Computer Engineering, 2019, 45(3):207-211.(in Chinese)
[16] LIAO S, HU Y, ZHU X, et al.Person re-identification by local maximal occurrence representation and metric learning[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:2197-2206.
[17] ZHENG L, SHEN L, TIAN L, et al.Scalable person re-identification:a benchmark[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:1116-1124.
[18] PENG P, XIANG T, WANG Y, et al.Unsupervised cross-dataset transfer learning for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:1306-1315.
[19] YU H X, WU A, ZHENG W S.Cross-view asymmetric metric learning for unsupervised person re-identification[C]//Proceedings of ICCV'17.Washington D.C., USA:IEEE Press, 2017:994-1002.
[20] FAN H, ZHENG L, YAN C, et al.Unsupervised person re-identification:clustering and fine-tuning[EB/OL].(2017-06-29)[2021-01-02].https://arxiv.org/pdf/1705.10444v2.pdf.
[21] WANG J, ZHU X, GONG S, et al.Transferable joint attribute-identity deep learning for unsupervised person re-identification[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:2275-2284.
[22] LIN S, LI H, LI C T, et al.Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification[EB/OL].(2018-07-11)[2021-01-02].https://arxiv.org/pdf/1807.01440.pdf.
[23] ZHONG Z, ZHENG L, ZHENG Z D, et al.CamStyle:a novel data augmentation method for person re-identification[J].IEEE Transactions on Image Processing, 2019, 28(3):1176-1190.
[24] YU H X, ZHENG W S, WU A C, et al.Unsupervised person re-identification by soft multilabel learning[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:2143-2152.

选择文件类型/文献管理软件名称

选择包含的内容