基于多尺度多粒度融合的行人重识别方法

doi:10.19678/j.issn.1000-3428.0060189

摘要/Abstract

摘要： 行人重识别是指利用计算机视觉技术在给定监控的图像中识别目标行人，受拍摄场景视角和姿势变化、遮挡等因素的影响，现有基于局部特征的行人重识别方法所提取的特征辨别力差，从而导致重识别精度较低。为有效地利用特征信息，提出一种多尺度多粒度融合的行人重识别方法MMF-Net。通过多个分支结构学习不同尺度和不同粒度的特征，并利用局部特征学习优化全局特征，以加强全局特征和局部特征的关联性。同时，在网络的低层引入语义监督模块以提取低层特征，并将其作为行人图像相似性度量的补充，实现低层特征和高层特征的优势互补。基于改进的池化层，通过结合最大池化和平均池化的特点获取具有强辨别力的特征。实验结果表明，MMF-Net方法在Market-1501数据集上的首位命中率和mAP分别为95.7%和89.1%，相比FPR、MGN、BDB等方法，其具有较优的鲁棒性。

关键词: 行人重识别, 特征学习, 局部特征, 低层特征, 池化, 多尺度多粒度融合

Abstract: Person re-identification refers to the use of computer vision technology to recognize the target person in a given monitored image.Factors, such as the change of shooting scene angle, posture, and occlusion, among others, result in poor feature discrimination extraction with existing person re-identification methods based on local features, associating these methods with low re-identification accuracy.To make effective use of feature information, this paper proposes a person re-identification method, MMF-Net, based on multi-scale and multi-granularity fusion, whereby features with different scales and granularity are learned by multiple branch structures.Local feature learning is used to optimize global features, thereby enhancing the correlation between global features and local features.A semantic supervision module is also introduced into the lower layer of the network to extract low-level features, which are used as a supplement to person image similarity measurement, to benefit from the complementary advantages of low-level and high-level features.On the improved pooling layer, the features with strong discrimination are obtained by combining the features of maximum and average pooling.The experimental results show that the Rank-1 and mAP of MMF-Net method is 95.7% and 89.1%, respectively.Compared with FPR, MGN, BDB method, it has better robustness.

Key words: person re-identification, feature learning, local feature, low-level feature, pooling, multi-scale and multi-granularity fusion

中图分类号:

TP391

符进武, 范自柱, 石林瑞, 郭心悦, 黄祎婧. 基于多尺度多粒度融合的行人重识别方法[J]. 计算机工程, 2022, 48(3): 271-279.

FU Jinwu, FAN Zizhu, SHI Linrui, GUO Xinyue, HUANG Yijing. Person Re-Identification Method Based on Multi-Scale and Multi-Granularity Fusion[J]. Computer Engineering, 2022, 48(3): 271-279.

https://www.ecice06.com/CN/Y2022/V48/I3/271

图/表 11

20220401123646

20220401123649

20220401123653

20220401123656

20220401123700

20220401123704

20220401123707

20220401123711

20220401123714

20220401123718

20220401123722

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, ZHUO L, ZHANG J, et al.Overview of person re-identification technology[J].Acta Automatica Sinica, 2018, 44(9):1554-1568.(in Chinese)
[2] LIAO S, HU Y, ZHU X, et al.Person re-identification by local maximal occurrence representation and metric learning[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:2197-2206.
[3] 姜国权, 肖禛禛, 霍占强.基于RGB与灰度信息融合的行人再识别方法[J].计算机工程, 2021, 47(4):226-233, 240. JIANG G Q, XIAO Z Z, HUO Z Q.Person re-identification based on the fusion of RGB and grayscale information[J].Computer Engineering, 2021, 47(4):226-233, 240.(in Chinese)
[4] ZHENG L, YANG Y, HAUPTMANN A G.Person re-identification:past, present and future[EB/OL].[2020-11-02].https://arxiv.org/pdf/1610.02984.pdf.
[5] LIN Y, ZHENG L, ZHENG Z, et al.Improving person re-identification by attribute and identity learning[J].Pattern Recognition, 2019, 95:151-161.
[6] HERMANS A, BEYER L, LEIBE B.In defense of the triplet loss for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1-15.
[7] ZHENG Z, YANG X, YU Z, et al.Joint discriminative and generative learning for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:2138-2147.
[8] ZHONG Z, ZHENG L, CAO D, et al.Re-ranking person re-identification with k-reciprocal encoding[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1318-1327.
[9] 罗浩, 姜伟, 范星, 等.基于深度学习的行人重识别研究进展[J].自动化学报, 2019, 45(11):2032-2049. LUO H, JIANG W, FAN X, et al.Research progress of person re-identification based on deep learning[J].Acta Automatica Sinica, 2019, 45(11):2032-2049.(in Chinese)
[10] ZHAO H, TIAN M, SUN S, et al.Spindle Net:person re-identification with human body region guided feature decomposition and fusion[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1077-1085.
[11] ZHENG L, HUANG Y, LU H, et al.Pose-invariant embedding for deep person re-identification[J].IEEE Transactions on Image Processing, 2019, 28(9):4500-4509.
[12] 刘紫燕, 万佩佩.基于注意力机制的行人重识别特征提取方法[J].计算机应用, 2020, 40(3):672-676. LIU Z Y, WAN P P.Person re-identification feature extraction method based on attention mechanism[J].Journal of Computer Applications, 2020, 40(3):672-676.(in Chinese)
[13] CHEN T, DING S, XIE J, et al.Abd-Net:attentive but diverse person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:8351-8361.
[14] 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.Berlin, Germany:Springer, 2018:480-496.
[15] WANG G, YUAN Y, CHEN X, et al.Learning discriminative features with multiple granularities for person re-identification[C]//Proceedings of the 26th ACM International Conference on Multimedia.New York, USA:ACM Press, 2018:274-282.
[16] SZEGEDY C, VANHOUCKE V, IOFFE S, et al.Rethinking the inception architecture for computer vision[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:2818-2826.
[17] ZHENG L, SHEN L, TIAN L, et al.Scalable person re-identification:a benchmark[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:1116-1124.
[18] RISTANI E, SOLERA F, ZOU R, et al.Performance measures and a data set for multi-target, multi-camera tracking[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:17-35.
[19] LI W, ZHAO R, XIAO T, et al.Deepreid:deep filter pairing neural network for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2014:152-159.
[20] WEI L, ZHANG S, GAO W, et al.Person transfer GAN to bridge domain gap for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:79-88.
[21] FELZENSZWALB P, MCALLESTER D, RAMANAN D.A discriminatively trained, multiscale, deformable part model[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2008:1-8.
[22] REN S, HE K, GIRSHICK R, et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39:1137-1149.
[23] SUN Y, ZHENG L, DENG W, et al.SVDNet for pedestrian retrieval[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:3800-3808.
[24] SUH Y, WANG J, TANG S, et al.Part-aligned bilinear representations for person re-identification[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:402-419.
[25] CHANG X, HOSPEDALES T M, XIANG T.Multi-level factorisation net for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:2109-2118.
[26] LI W, ZHU X, GONG S.Harmonious attention network for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:2285-2294.
[27] TAY C P, ROY S, YAP K H.AANet:attribute attention network for person re-identifications[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:7134-7143.
[28] ZHENG M, KARANAM S, WU Z, et al.Re-identification with consistent attentive siamese networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:5735-5744.
[29] HOU R, MA B, CHANG H, et al.Interaction-and-aggregation network for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:9317-9326.
[30] YANG W, HUANG H, ZHANG Z, et al.Towards rich feature discovery with class activation maps augmentation for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:1389-1398.
[31] ZHANG Z, LAN C, ZENG W, et al.Densely semantically aligned person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:667-676.
[32] ZHENG F, DENG C, SUN X, et al.Pyramidal person re-identification via multi-loss dynamic training[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:8514-8522.
[33] QUAN R, DONG X, WU Y, et al.Auto-reid:searching for a part-aware convNet for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:3750-3759.
[34] ZHOU K, YANG Y, CAVALLARO A, et al.Omni-scale feature learning for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:3702-3712.
[35] ALEMU L T, PELILLO M, SHAH M.Deep constrained dominant sets for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:9855-9864.
[36] CHEN B, DENG W, HU J.Mixed high-order attention network for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:371-381.
[37] GUO J, YUAN Y, HUANG L, et al.Beyond human parts:dual part-aligned representations for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:3642-3651.
[38] DAI Z, CHEN M, GU X, et al.Batch dropblock network for person re-identification and beyond[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:3691-3701.
[39] HE L, WANG Y, LIU W, et al.Foreground-aware pyramid reconstruction for alignment-free occluded person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:8450-8459.
[40] SU C, LI J, ZHANG S, et al.Pose-driven deep convolutional model for person re-identification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:3960-3969.
[41] WEI L, ZHANG S, YAO H, et al.GLAD:global-local-alignment descriptor for pedestrian retrieval[C]//Proceedings of the 25th ACM International Conference on Multimedia.New York, USA:ACM Press, 2017:420-428.

选择文件类型/文献管理软件名称

选择包含的内容