Multi-Scale Fusion and Dual Output U-Net Network for Person Re-Identification

doi:10.19678/j.issn.1000-3428.0068317

Abstract

Abstract: Due to variable pedestrian posture, the occlusion of pedestrians, and other adverse factors, Person Re-Identification(Re-ID) models often struggle to extract the key features of pedestrians. To enhance the feature expression ability of the model, this study proposes a Re-ID method based on multi-scale fusion and a dual output U-Net network. The aim is to address the challenges of extracting key pedestrian features and improving feature expression, which are limitations of existing methods. First, a multi-scale fusion dual output U-Net network is proposed, with the output features constrained by both Euclidean and divergence distances. Second, a joint loss function is introduced to address the challenge of the Generative Adversarial Network(GAN) not converging easily during training, thereby improving the convergence speed of the training process. Numerous simulation experiments conducted on three public reference datasets demonstrate that the proposed feature extraction network outperforms classical feature extraction networks, with an improvement in Mean Average Precision (mAP) of over 10%. In addition, the mAP of the proposed Re-ID method improves by approximately 2% compared to that of the mainstream method. The proposed method can enhance the feature expression ability of the model and improve the accuracy of Re-ID.

Key words: Person Re-Identification(Re-ID), Generative Adversarial Network(GAN), feature extraction, multi-scale fusion, joint constraint

摘要： 受行人姿态的多变性和行人被遮挡等因素的影响,行人重识别模型难以提取行人关键特征。为增强模型的特征表达能力,提出一种基于多尺度融合与双输出U-Net网络的行人重识别方法,旨在解决现有方法中难以提取行人关键特征、特征表达能力较低的问题。首先,提出多尺度融合的双输出U-Net网络,并对输出特征进行欧氏距离和散度距离约束;其次,设计联合损失函数,解决生成对抗网络在训练过程中不易收敛的问题,提高训练过程的收敛速度。在3个公共基准数据集上的仿真实验结果表明,相比经典特征提取网络,所提特征提取网络的平均精度均值(mAP)提升超过10%,所提行人重识别方法相比主流方法的mAP提高约2%,该方法能够增强模型的特征表达能力,提高行人重识别的准确率。

关键词: 行人重识别, 生成对抗网络, 特征提取, 多尺度融合, 联合约束

CLC Number:

TP391

HU Qing. Multi-Scale Fusion and Dual Output U-Net Network for Person Re-Identification[J]. Computer Engineering, 2024, 50(6): 102-109.

胡庆. 多尺度融合与双输出U-Net网络的行人重识别[J]. 计算机工程, 2024, 50(6): 102-109.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0068317

https://www.ecice06.com/EN/Y2024/V50/I6/102

References

[1] LI Z J, ZHOU Z W, JIANG N, et al. Spatial preserved graph convolution networks for person re-identification[J]. ACM Transactions on Multimedia Computing, Communications, and Applications,2020,16(1s):26.
[2] XU J, ZHAO R, ZHU F, et al. Attention-aware compositional network for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2018:2119-2128.
[3] ZHU K, GUO H Y, LIU Z W, et al. Identity-guided human semantic parsing for person re-identification[C]//Proceedings of the 16th European Conference on Computer Vision. Berlin, Germany:Springer, 2020:346-363.
[4] LIAO S C, HU Y, ZHU X Y, et al. Person re-identification by local maximal occurrence representation and metric learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2015:2197-2206.
[5] ZHAO H Y, TIAN M Q, SUN S Y, et al. Spindle net:person re-identification with human body region guided feature decomposition and fusion[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2017:907-915.
[6] KALAYEH M M, BASARAN E, GÖKMEN M, et al. Human semantic parsing for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2018:1062-1071.
[7] SONG C F, HUANG Y, OUYANG W L, et al. Mask-guided contrastive attention model for person re-identification[C]//Proceedings of the Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2018:1179-1188.
[8] TIAN M Q, YI S, LI H S, et al. Eliminating background-bias for robust person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2018:5794-5803.
[9] YANG W J, HUANG H J, ZHANG Z, et al. Towards rich feature discovery with class activation maps augmentation for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2019:1389-1398.
[10] LI D W, CHEN X T, ZHANG Z, et al. Learning deep context-aware features over body and latent parts for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA:IEEE Press, 2017:7398-7407.
[11] 刘晓蓉,李小霞,秦昌辉.融合多尺度对比池化特征的行人重识别方法[J].计算机工程, 2022, 48(4):292-298. LIU X R, LI X X, QIN C H. Person re-identification method with multi-scale contrast pooling feature[J]. Computer Engineering, 2022, 48(4):292-298.(in Chinese)
[12] 符进武,范自柱,石林瑞,等.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 J W, FAN Z Z, SHI L R, et al. Person re-identification method based on multi-scale and multi-granularity fusion[J]. Computer Engineering, 2022, 48(3):271-279.(in Chinese)
[13] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany:Springer, 2015:234-241.
[14] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA:IEEE Press, 2016:770-778.
[15] ZHENG L, SHEN L Y, TIAN L, et al. Scalable person re-identification:a benchmark[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D. C., USA:IEEE Press, 2015:1116-1124.
[16] ZHENG Z D, ZHENG L, YANG Y. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D. C., USA:IEEE Press, 2017:3774-3782.
[17] 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.
[18] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Berlin, Germany:Springer, 2018:7132-7141.
[19] TOLSTIKHIN I, HOULSBY N, KOLESNIKOV A, et al. MLP-Mixer:an all-MLP architecture for vision[EB/OL].[2023-07-25]. http://arxiv.org/abs/2105.01601.
[20] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2023-07-25]. https://arxiv.org/pdf/1409.1556.
[21] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA:IEEE Press, 2016:2818-2826.
[22] SUN Y F, ZHENG L, YANG Y, et al. Beyond part models:person retrieval with refined part pooling (and A strong convolutional baseline)[C]//Proceedings of the 15th European Conference Computer Vision. Berlin, Germany:Springer, 2018:501-518.
[23] HERMANS A, BEYER L, LEIBE B. In defense of the triplet loss for person re-identification[EB/OL].[2023-07-25]. https://arxiv.org/pdf/1703.07737.
[24] SUN Y F, ZHENG L, DENG W J, et al. SVDNet for pedestrian retrieval[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D. C., USA:IEEE Press, 2017:3820-3828.
[25] YANG W X, YAN Y, CHEN S. Adaptive deep metric embeddings for person re-identification under occlusions[J]. Neurocomputing, 2019, 340:125-132.
[26] HONG P X, WU T, WU A C, et al. Fine-grained shape-appearance mutual learning for cloth-changing person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA:IEEE Press, 2021:10508-10517.
[27] ZHENG Z D, ZHENG L, YANG Y. Pedestrian alignment network for large-scale person re-identification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29(10):3037-3045.
[28] GARY B. The Opencv Library[J]. Dr. Dobb's Journal:Software Tools for the Professional Programmer, 2000, 25(11):120-123.

Please choose a citation manager

Content to export