English

应用科学学报 >

2023 , Vol. 41 >Issue 1: 107 - 120

DOI: https://doi.org/10.3969/j.issn.0255-8297.2023.01.009

计算机应用专辑

基于通道特征聚合的行人重识别算法

展开
  • 1. 桂林电子科技大学 数学与计算科学学院, 广西 桂林 541004;
    2. 桂林电子科技大学 计算机与信息安全学院, 广西 桂林 541004;
    3. 桂林安维科技有限公司, 广西 桂林 541010

收稿日期: 2022-06-23

  网络出版日期: 2023-02-03

基金资助

国家自然科学基金（No.61862015）；广西科技基地和人才专项基金（No.2021AC06001）；广西重点研发计划项目基金（No.AB17195025）资助

收起

Person Re-identification Algorithm Based on Channel Feature Aggregation

Expand
  • 1. School of Mathematics and Computing Science, Guilin University of Electronic Technology, Guilin 541004, Guangxi, China;
    2. School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, Guangxi, China;
    3. Anview. ai, Guilin 541010, Guangxi, China

Received date: 2022-06-23

  Online published: 2023-02-03

Fold

摘要

在基于深度学习的行人重识别算法中，通道特征易被忽视而导致模型表达能力降低。为此，以ResNeSt50为骨干网络，借鉴SENet通道注意力特点在残差块末尾接入SE block，增强网络对通道特征的提取能力；针对ReLU函数因缺少控制因子而限制不同通道特征图对激活值的准确响应问题，引入一个动态学习因子来丰富通道特征权重信息，以形成新的加权激活函数Weighted ReLU （WReLU）；基于分组卷积特征图局部而设计新的激活函数LeakyWeighted ReLU （LWReLU），有效提高不同位置的深度特征表达能力；在Split-Attention和SE block中应用LWReLU，改善Split-Attention对各组特征图的权重学习能力；利用circleloss改进损失函数，优化目标收敛过程，从而提高模型精度。实验结果表明：在CUHK03-NP、Market1501和DukeMTMC-ReID数据集上，所提方法的Rank-1比原骨干网络分别提高了19.08%、0.98%、2.02%，且其mAP比原骨干网络分别提高了17.13%、2.11%、2.56%。

关键词： 分组卷积; 通道注意力; 修正线性单元; 激活函数; 动态学习因子

本文引用格式

徐增敏, 陆光建, 陈俊彦, 陈金龙, 丁勇 . 基于通道特征聚合的行人重识别算法[J]. 应用科学学报, 2023 , 41(1) : 107 -120 . DOI: 10.3969/j.issn.0255-8297.2023.01.009

Abstract

In deep-learning person re-identification algorithms, channel characteristics may be neglected, leading to a degraded model-expression ability. Address to the problem, we choose the ResNeSt50 as backbone network, and add an SE block to the end of residual blocks by using characteristics of SENet channel attention for enhancing features extraction of channels in networks. In addition, due to lack of control factors, ReLU function may reduce the correct responses of different feature graphs to activation values. Thus, we present two new activation functions. One is named as Weighted ReLU (WReLU) by combining ReLU with weight bias term, which can effectively improve feature selection ability in neural networks, and the other is Leaky Weighted ReLU (LWReLU), which is applied in Split-Attention and SE block, and enables Split-Attention to promote the weight learning ability from feature maps. Moreover, a new loss function with circle loss is also proposed for optimizing the convergence of objective function. Experimental results show that the proposed algorithm outperforms original backbone by 19.08%, 0.98%, and 2.02% in Rank-1, and 17.13%, 2.11%, and 2.56% in mAP respectively on CUHK03-NP, Market1501, and DukeMTMC-ReID datasets.

Key words： group convolution; channel attention; rectified linear unit; activation function; dynamic learning factor

参考文献

[1] Luo H, Jiang W, Fan X, et al. A survey on deep learning based person re-identification[J]. Acta Automatica Sinic, 2019, 45(11):2032-2049.
[2] Zhang H, Wu C, Zhang Z, et al. ResNeSt:split-attention networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2022:2736-2746.
[3] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018:7132-7141.
[4] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[5] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society, 2005:886-893.
[6] Zhao R, Ouyang W, Wang X. Learning mid-level filters for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2014:144-151.
[7] Li W, Zhao R, Xiao T, et al. Deepreid:deep filter pairing neural network for person reidentification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2014:152-159.
[8] Geng M, Wang Y, Xiang T, et al. Deep transfer learning for person reidentification[DB/OL]. arXiv preprint arXiv:1611.05244, 2016. (2016-11-16)[2022-06-23] https://arxiv.org/abs/1611.05244v1.
[9] 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, 2019:667-676.
[10] Zhang Z, Lan C, Zeng W, et al. Relation-aware global attention for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2020:3183-3192.
[11] Varior R R, Haloi M, Wang G. Gated siamese convolutional neural network architecture for human re-identification[C]//Proceedings of European Conference on Computer Vision, 2016:791-808.
[12] Schroff F, Kalenichenko D, Philbin J. Facenet:a unified embedding for face recognition and clustering[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2015:815-823.
[13] Liu H, Feng J, Qi M, et al. End-to-end comparative attention networks for person reidentification[J]. IEEE Transactions on Image Processing, 2017:3492-3506.
[14] Cheng D, Gong Y, Zhou S, et al. Person re-identification by multichannel parts-based CNN with improved triplet loss function[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016:1335-1344.
[15] Chen W, Chen X, Zhang J, et al. Beyond triplet loss:a deep quadruplet network for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2017:403-412.
[16] Xiao Q, Luo H, Zhang C. Margin sample mining loss:a deep learning based method for person re-identification[DB/OL]. arXiv preprint arXiv:1710.00478, 2017. (2017-10-02)[2022-06-23]. https://arxiv.org/abs/1710.00478v3.
[17] 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, 2017:1077-1085.
[18] Fan X, Luo H, Zhang X, et al. SCPNet:spatial-channel parallelism network for joint holistic and partial person re-identification[C]//Proceedings of Asian Conference on Computer Vision. Cham:Springer, 2018:19-34.
[19] 金翠, 王洪元, 陈首兵. 基于随机擦除行人对齐网络的行人重识别方法[J]. 山东大学学报(工学版), 2018, 48(6):71-77. Jin C, Wang H Y, Chen S B. Person re-identification based on random erasing pedestrian alignment network method[J]. Journal of Shandong University (Engineering Science), 2018, 48(6):71-77. (in Chinese)
[20] Sun Y, Cheng C, Zhang Y, et al. Circle loss:a unified perspective of pair similarity optimization[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2020:6398-6407.
[21] Liang Z. Scalable person re-identification:a benchmark[C]//Proceedings of IEEE International Conference on Computer Vision, 2015:1116-1124.
[22] Zheng Z, Zheng L, Yang Y. Unlabeled samples generated by GAN improve the person reidentification baseline in vitro[C]//Proceedings of IEEE International Conference on Computer Vision, 2017:3774-3782.
[23] Ristani E, Solera F. Performance measures and a data set for multi-target, multi-camera tracking[C]//Proceedings of European Conference on Computer Vision Workshops, 2016:17-35.
[24] Zhong Z, Zheng L, Cao D, et al. Re-ranking person re-identification with k-reciprocal encoding[C]//Proceedings of IEEE Computer Vision and Pattern Recognition, 2017:3652-3661.
[25] Li W, Zhao R, Xiao T, et al. DeepReID:deep filter pairing neural network for person reidentification[C]//Proceedings of IEEE Computer Vision and Pattern Recognition, 2014:152-159.
[26] Zheng Z, Zheng L, Yang Y. Pedestrian alignment network for large-scale person reidentification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 29(10):3037-3045.
[27] Wei L, Zhang S, Yao H, et al. GLAD:global-local-alignment descriptor for scalable person re-identification[J]. IEEE Transactions on Multimedia, 2019, 21(4):986-999.
[28] Xu J, Zhao R, Zhu F, et al. Attention-aware compositional network for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018:2119-2128.
[29] Li W, Zhu X, Gong S. Harmonious attention network for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018:2285-2294.
[30] Fan X, Luo H, Zhang X, et al. SCPNet:spatial-channel parallelism network for joint holistic and partial person re-identification[C]//Proceedings of Asian Conference on Computer Vision, 2018:19-34.
[31] 孙义博, 张文靖, 王蓉, 等. 基于通道注意力机制的行人重识别方法[J]. 北京航空航天大学学报, 48(5):881-889. Sun Y B, Zhang W J, Wang R, et al. Person re-identification method based on channel attention mechanism[J]. Journal of Beijing University of Aeronautics and Astronautics, 48(5):881-889. (in Chinese)
[32] Wang Y, Wang L, You Y, et al. Resource aware person re-identification across multiple resolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018:8042-8051.
[33] Chen X, Fu C, Zhao Y, et al. Salience-guided cascaded suppression network for person reidentification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2020:3297-3307.
Options
文章导航

/

〈 〉