基于相机感知的域自适应行人重识别模型

doi:10.16451/j.cnki.issn1003-6059.202405001

摘要
图/表
参考文献
相关文章 (10)

全文: PDF (1359 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对行人重识别在损坏场景下训练集和测试集分布差距过大、背景复杂度过高和噪声种类过多导致识别性能过低的问题,提出基于相机感知的域自适应行人重识别模型,引入并充分利用相机信息,在训练阶段对齐不同摄像机的图像分布,在测试阶段利用时序信息进行排序优化,减少训练集和测试集分布差异带来的影响,有效应对背景复杂度和噪声种类的问题.模型不仅从数据集处理角度有效减轻损坏图像的影响,还对排序优化进行二次加权,显著提高其在损坏场景中的性能.在Market-1501、DukeMTMC-reID、CUHK03数据集上的实验表明文中模型的有效性.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杨章静
	吴数立
	黄璞
	杨国为

关键词 ：行人重识别, 损坏场景, 时序信息, 批量标准化

Abstract：To solve the problem of low performance in person re-identification caused by large distribution differences between the training and testing sets in corruption scenarios, high background complexity and excessive noise types, a domain adaptive person re-identification model based on camera perception is proposed. The model aligns the image distribution of different cameras during the training phase by introducing and fully utilizing camera information. During the testing phase, temporal information is employed for ranking optimization, reducing the impact of distribution differences between the training and testing sets. The issues of background complexity and noise types are effectively addressed. The model not only effectively mitigates the impact of damaged images from the perspective of dataset processing but also significantly improves the performance of the model in corruption scenarios through quadratic weighting of sorting optimization. Experiments on Market-1501, DukeMTMC-reID and CUHK03 datasets demonstrate the effectiveness of the proposed algorithm.

Key words： Person Re-identification Corruption Scenario Temporal Information Batch Normalization

收稿日期: 2024-03-06

ZTFLH:

TP391.4

基金资助:国家自然科学基金项目(No.62172229)、江苏省自然科学基金项目(No.BK20221349)资助

通讯作者: 黄璞,博士,副教授,主要研究方向为模式识别、机器学习.E-mail:huangpu3355@163.com.

作者简介: 杨章静,博士,副教授,主要研究方向为计算机视觉、模式识别.E-mail:yzj@nau.edu.cn.吴数立,硕士研究生,主要研究方向为模式识别、机器学习.E-mail:244581258@qq.com. 杨国为,博士,教授,主要研究方向为机器智能理论与方法、智能系统、模式识别.E-mail:ygw_ustb@163.com.

引用本文:

杨章静, 吴数立, 黄璞, 杨国为. 基于相机感知的域自适应行人重识别模型[J]. 模式识别与人工智能, 2024, 37(5): 383-397. YANG Zhangjing, WU Shuli, HUANG Pu, YANG Guowei. Domain Adaptive Person Re-identification Model Based on Camera Perception. Pattern Recognition and Artificial Intelligence, 2024, 37(5): 383-397.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202405001 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2024/V37/I5/383

[1] ZAHRA A, PERWAIZ N, SHAHZAD M, et al. Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends. Pattern Recognition, 2023. DOI: 10.1016/j.patcog.2023.109669.
[2] WANG G C, LAI J H, LIANG W Q, et al. Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-identification // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 10565-10574.
[3] 王鹏,宋晓宁,吴小俊,等. 用于行人重识别的多类型特征网络.模式识别与人工智能, 2020, 33(10): 879-888.
(WANG P, SONG X N, WU X J, et al. Multi-type Features Network for Person Re-identification. Pattern Recognition and Artificial Intelligence, 2020, 33(10): 879-888.)
[4] HE S T, LUO H, WANG P C, et al. TransReID: Transformer-Based Object Re-identification // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 14993-15002.
[5] TAN F G, LIU W M, HUANG L, et al. Person Re-identification Across Multiple Non-overlapping Cameras by Grouping Similarity Comparison Model. Chinese Journal of Electronics, 2017, 26(5): 905-911.
[6] 张磊,吴晓富,张索非,等. 基于多分支协作的行人重识别网络.模式识别与人工智能, 2021, 34(9): 853-862.
(ZHANG L, WU X F, ZHANG S F, et al. Muti-branch Cooperative Network for Person Re-identification. Pattern Recognition and Artificial Intelligence, 2021, 34(9): 853-862.)
[7] BUADES A, COLL B, MOREL J M. A Review of Image Denoising Algorithms, with a New One. Multiscale Modeling and Simulation, 2005, 4(2): 490-530.
[8] ELAD M, AHARON M. Image Denoising via Sparse and Redundant Representations over Learned Dictionaries. IEEE Transactions on Image Processing, 2006, 15(12): 3736-3745.
[9] BUADES A, COLL B, MOREL J M. A Non-Local Algorithm for Image Denoising // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2005. DOI: 10.1109/CVPR.2005.38.
[10] XIE J Y, XU L L, CHEN E H. Image Denoising and Inpainting with Deep Neural Networks // Proc of the 25th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2012, I: 341-349.
[11] GONG Y P, ZENG Z Y. An Effective Data Augmentation for Person Re-identification[C/OL]. [2024-02-17].https://arxiv.org/pdf/2101.08533v1.
[12] FORD N, GILMER J, CARLINI N, et al. Adversarial Examples Are a Natural Consequence of Test Error in Noise[C/OL].[2024-02-17]. https://arxiv.org/pdf/1901.10513.
[13] MIKOŁAJCZYK A, GROCHOWSKI M. Data Augmentation for Improving Deep Learning in Image Classification Problem // Proc of the International Interdisciplinary PhD Workshop. Washington, USA: IEEE, 2018: 117-122.
[14] HENDRYCKS D, MU N, CUBUK E D, et al. AUGMIX: A Simple Data Processing Method to Improve Robustness and Uncertainty[C/OL].[2024-02-17]. https://arxiv.org/abs/1912.02781.
[15] CUBUK E D, ZOPH B, MANÉ D, et al. AutoAugment: Learning Augmentation Strategies from Data // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 113-123.
[16] 彭锦佳,宋鹏鹏,王辉兵. 面向隐私保护的联邦域泛化行人重识别方法.模式识别与人工智能, 2023, 36(7): 634-646.
(PENG J J, SONG P P, WANG H B, et al. Federated Domain Generalization Person Re-identification with Privacy Preserving. Pattern Recognition and Artificial Intelligence, 2023, 36(7): 634-646.)
[17] HENDRYCKS D, BASART S, MU N, et al. The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 8320-8329.
[18] CALIAN D A, STIMBERG F, WILES O, et al. Defending Against Image Corruptions through Adversarial Augmentations[C/OL].[2024-02-17]. https://arxiv.org/pdf/2104.01086.
[19] ZHANG R. Making Convolutional Networks Shift-Invariant Again. Journal of Machine Learning Research, 2019, 97: 7324-7334.
[20] XIE Q Z, LUONG M T, HOVY E, et al. Self-Training with Noisy Student Improves ImageNet Classification // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Wa-shington, USA: IEEE, 2020: 10684-10695.
[21] WANG H T, XIAO C W, KOSSAIFI J, et al. AugMax: Adversa-rial Composition of Random Augmentations for Robust Training[C/OL].[2024-02-17]. https://openreview.net/pdf?id=P5MtdcVdFZ4.
[22] GEIRHOS R, TEMME C R M, RAUBER J, et al. Generalisation in Humans and Deep Neural Networks // Proc of the 32nd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2018: 7549-7561.
[23] DATTA R, JOSHI D, LI J, et al. Image Retrieval: Ideas, Influences, and Trends of the New Age. ACM Computing Surveys, 2008, 40(2). DOI: 10.1145/1348246.1348248.
[24] LUO H, JIANG W, GU Y Z, et al. A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification. IEEE Tran- sactions on Multimedia, 2019, 22(10): 2597-2609.
[25] HERMANS A, BEYER L, LEIBE B. In Defense of the Triplet Loss for Person Re-Identification[C/OL]. [2024-02-17].https://arxiv.org/pdf/1703.07737.
[26] IOFFE S, SZEGEDY C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift // Proc of the 32nd International Conference on Machine Learning. San Diego, USA: JMLR, 2015: 448-456.
[27] ZHONG Z, ZHENG L, CAO D L, et al. Re-ranking Person Re-identification with k-Reciprocal Encoding // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 3652-3661.
[28] LIAO S C, SHAO L. Interpretable and Generalizable Person Re-identification with Query-Adaptive Convolution and Temporal Lif-ting // Proc of the 16th European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 456-474.
[29] ZHANG Z L, SABUNCU M. Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels // Proc of the 32nd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2018: 8792-8802.
[30] CHEN M H, WANG Z Q, ZHENG F. Benchmarks for Corruption Invariant Person Re-identification[C/OL]. [2024-02-17].https://arxiv.org/pdf/2111.00880.
[31] ZHENG L, SHEN L Y, TIAN L, et al. Scalable Person Re-identification: A Benchmark // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 1116-1124.
[32] LI W, ZHAO R, XIAO T, et al. DeepReID: Deep Filter Pairing Neural Network for Person Re-identification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 152-159.
[33] RISTANI E, SOLERA F, ZOU R, et al. Performance Measures and a Data Set for Multi-target, Multi-camera Tracking // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 17-35.
[34] WEI L H, ZHANG S L, GAO W, et al. Person Transfer GAN to Bridge Domain Gap for Person Re-identification // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 79-88.
[35] HU J, SHEN L, SUN G. Squeeze-and-Excitation Networks // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2018: 7132-7141.
[36] PAN X G, LUO P, SHI J P, et al. Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 484-500.
[37] LUO H, JIANG W, ZHANG X, et al. AlignedReID++: Dynamically Matching Local Information for Person Re-identification. Pa-ttern Recognition, 2019, 94: 53-61.
[38] HERZOG F, JI X B, TEEPE T, et al. Lightweight Multi-branch Network for Person Re-identification // Proc of the IEEE International Conference on Image Processing. Washington, USA: IEEE, 2021: 1129-1133.
[39] QUISPE R, PEDRINI H. Top-DB-Net: Top Dropblock for Activation Enhancement in Person Re-identification // Proc of the 25th International Conference on Pattern Recognition. Washington, USA: IEEE, 2021: 2980-2987.
[40] XIE B, WU X F, ZHANG S F, et al. Learning Diverse Features with Part-Level Resolution for Person Re-identification // Proc of the 3rd Chinese Conference on Pattern Recognition and Computer Vision. Berlin, Germany: Springer, 2020: 16-28.
[41] GONG Y P, ZENG Z Y, CHEN L W, et al. A Person Re-identification Data Augmentation Method with Adversarial Defense Effect[C/OL].[2024-02-17]. https://arxiv.org/pdf/2101.08783.
[42] YE M, SHEN J B, LIN G J, et al. Deep Learning for Person Re-identification: A Survey and Outlook. IEEE Transactions on Pa-ttern Analysis and Machine Intelligence, 2022, 44(6): 2872-2893.
[43] ZHOU K Y, YANG Y X, CAVALLARO A, et al. Omni-Scale Feature Learning for Person Re-identification // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 3701-3711.