首页 > 论文 > 激光与光电子学进展 > 56卷 > 14期(pp:141504--1)

基于多尺度卷积特征融合的行人重识别

Person Reidentification Based on Multiscale Convolutional Feature Fusion

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对现有的基于卷积神经网络的行人重识别方法对于遮挡和复杂背景引起的判别信息缺失问题,提出了一种基于多尺度卷积特征融合的行人重识别算法。在训练阶段,使用金字塔池化方法对卷积特征图进行分块和池化,获得包含全局特征和多尺度局部特征的多个特征向量;对每一个特征向量进行独立分类,并在各个分类的最后内积层上归一化权重和特征,以提升分类性能;最后使用梯度下降法优化全部的分类损失。在识别阶段,将池化后的多个特征向量融合成一个新向量,使用新向量在库中进行相似性匹配。在Market-1501、DukeMTMC-reID数据库上对所提算法的有效性进行实验验证。结果表明,本文模型提取的特征具有更好的识别效果,Rank-1精度和平均准确率也优于大多数先进算法。

Abstract

Existing methods of person reidentification based on convolutional neural network lack discriminative information, due to occlusion and complex backgrounds. To solve these problems, a method based on multi-scale convolutional feature fusion is proposed herein. In the training phase, pyramid pooling is used to extract multiple eigenvectors containing global features and multi-scale local features for blocking and pooling of the convolutional feature map. Afterward, each feature vector is classified independently, and the weights and features on the last inner layer of each class are normalized to improve the classification performance. Finally, a gradient descent algorithm is applied to optimize the sum of losses for each classification. In the recognition phase, pooled multiple feature vectors are concatenated into a new vector for similarity matching. The efficiency of the proposed algorithm is verified on datasets Market-1501 and DukeMTMC-reID, in which the results indicate that features obtained by the proposed model are more discriminative and that the Rank-1 accuracy and average accuracy are both better than most state-of-the-art algorithms.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.141504

所属栏目:机器视觉

基金项目:国家自然科学基金、教育部-中国移动科研基金、江苏省博士后科研资助计划;

收稿日期:2019-01-04

修改稿日期:2019-02-26

网络出版日期:2019-07-01

作者单位    点击查看

徐龙壮:江南大学物联网工程学院物联网应用技术教育部工程中心, 江苏 无锡 214122
彭力:江南大学物联网工程学院物联网应用技术教育部工程中心, 江苏 无锡 214122

联系人作者:彭力(pengli@jiangnan.edu.cn)

备注:国家自然科学基金、教育部-中国移动科研基金、江苏省博士后科研资助计划;

【1】Chen B, Zha Y F, Li Y Q et al. Person re-identification based on convolutional neural network discriminative feature learning. Acta Optica Sinica. 38(7), (2018).
陈兵, 查宇飞, 李运强 等. 基于卷积神经网络判别特征学习的行人重识别. 光学学报. 38(7), (2018).

【2】Huang X Y, Xu J L, Guo G et al. Real-time pedestrian reidentification based on enhanced aggregated channel features. Laser & Optoelectronics Progress. 54(9), (2017).
黄新宇, 许娇龙, 郭纲 等. 基于增强聚合通道特征的实时行人重识别. 激光与光电子学进展. 54(9), (2017).

【3】Ahmed E, Jones M and Marks T K. An improved deep learning architecture for person re-identification. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 3908-3916(2015).

【4】Chen W H, Chen X T, Zhang J G et al. A multi-task deep network for person re-identification[C]∥Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix. 3988-3994(2016).

【5】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, October 23-27, 2017, Mountain View, California. New York: ACM. 420-428(2017).

【6】Sun Y F, Zheng L, Yang Y et al. Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). ∥Ferrari V, Hebert M, Sminchisescu C, et al. Lecture notes in computer science. Cham: Springer. 11208, 501-518(2018).

【7】Zheng L, Shen L Y, Tian L et al. Scalable person re-identification: a benchmark. [C]∥2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: IEEE. 1116-1124(2015).

【8】Zheng Z D, Zheng L and Yang Y. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 3774-3782(2017).

【9】Zhu X B and Che J. Personre-identification algorithm based on feature fusion and subspace learning. Laser & Optoelectronics Progress. 56(2), (2019).
朱小波, 车进. 基于特征融合与子空间学习的行人重识别算法. 激光与光电子学进展. 56(2), (2019).

【10】He K M, Zhang X Y, Ren S Q et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 37(9), 1904-1916(2015).

【11】Wu M, Zha Y F, Zhang Y Q et al. Visual tracking algorithm based on classification-validation model. Acta Optica Sinica. 38(5), (2018).
吴敏, 查宇飞, 张园强 等. 基于分类-验证模型的视觉跟踪算法研究. 光学学报. 38(5), (2018).

【12】Felzenszwalb F and Girshick B. McAllester D, et al. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 32(9), 1627-1645(2010).

【13】Deng J, Dong W, Socher R et al. ImageNet: a large-scale hierarchical image database. [C]∥2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE. 248-255(2009).

【14】Zhong Z, Zheng L, Zheng Z D et al. Camera style adaptation for person re-identification. [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 5157-5166(2018).

【15】Zheng Z D, Zheng L and Yang Y. A discriminatively learned CNN embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications. 14(1), (2018).

【16】Zhong Z, Zheng L, Cao D L et al. Re-ranking person re-identification with k-reciprocal encoding. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 3652-3661(2017).

【17】Sarfraz M S, Schumann A, Eberle A et al. A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 420-429(2018).

【18】Sun Y F, Zheng L, Deng W J et al. SVDNet for pedestrian retrieval. [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 3820-3828(2017).

【19】Chen Y B, Zhu X T and Gong S G. Person re-identification by deep learning multi-scale representations. [C]∥2017 IEEE International Conference on Computer Vision Workshops (ICCVW), October 22-29, 2017, Venice, Italy. New York: IEEE. 2590-2600(2017).

【20】Chang X B, Hospedales T M and Xiang T. Multi-level factorisation net for person re-identification. [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2109-2118(2018).

【21】Li W, Zhu X T and Gong S G. Harmonious attention network for person re-identification. [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2285-2294(2018).

引用该论文

Longzhuang Xu, Li Peng. Person Reidentification Based on Multiscale Convolutional Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141504

徐龙壮, 彭力. 基于多尺度卷积特征融合的行人重识别[J]. 激光与光电子学进展, 2019, 56(14): 141504

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF