石河子大学信息科学与技术学院;新疆政法学院网络信息中心;
行人重识别又称行人再识别,是一种在跨摄像头环境下识别相同行人的技术。目前,由于行人姿势变化、灯光角度、障碍遮挡等问题影响,导致现有方法提取行人特征受到干扰较大,影响识别效果。针对该问题,提出将NFormer嵌入主干网络的不同层级,构建多尺度注意力模块(Multi-Scale Attention-NFormer, MSAN),提取细节丰富的底层特征与表征能力强的高层特征进行融合;提出结合可学习视觉中心与多层感知器,构建了基于可学习视觉中心与多层感知器的特征融合模块(Feature Fusion with Learnable Visual Centers and Multilayer Perceptron, FFLM),提取关联位置信息的局部特征与长距离依赖的全局特征,并将其融合获取更具辨别性的特征表达。为了使主干网络与头部网络更适用于特征融合任务,对ResNet50的激活函数和搭建架构进行改进,保留了更丰富的特征信息;在头部网络添加BN层和GeM池化,缓解了损失函数优化方向不同步的问题。实验结果表明,所提方法在Market-1501和DukeMTMC-reID数据集上的首位命中率分别达到了95.8%、90.2%,平均精度均值为93.0%、84.7%,所提取的特征更具有判别性,识别率更高。
| 315 | 0 | 19 |
| 下载次数 | 被引频次 | 阅读次数 |
[1]冯霞,杜佳浩,段仪浓,等.基于深度学习的行人重识别研究综述[J].计算机应用研究, 2020,37(11):3220-3226,3240.FENG X, DU J H, DUAN Y N, et al. Research on person re-identification based on deep learning[J]. Application Research of Computers, 2020, 37(11):3220-3226,3240.
[2]张永飞,杨航远,张雨佳,等.行人再识别技术研究进展[J].中国图象图形学报, 2023, 28(6):1829-1862.ZHANG Y F, YANG H Y, ZHANG Y J, et al. Recent progress in person re-ID[J]. Journal of Image and Graphics, 2023, 28(6):1829-1862.
[3] WANG H C, SHEN J Y, LIU Y T, et al. Nformer:robust person re-identification with neighbor transformer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans:IEEE, 2022:7297-7307.
[4]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. A survey on deep learning based person reidentification[J]. Acta Automatica Sinica, 2019, 45(11):2032-2049.
[5] ZHENG Z D, ZHENG L, YANG Y. A discriminatively learned CNN embedding for person reidentification[J].ACM Transactions on Multimedia Computing Communications and Applications, 2017, 14(1):1-20.
[6] LUO H, GU Y Z, LIAO X Y, et al. Bag of tricks and a strong baseline for deep person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Long Beach:IEEE, 2019:1487-1495.
[7] YAN C, PANG G, BAI X, et al. Beyond triplet loss:person re-identification with fine-grained difference-aware pairwise loss[J]. IEEE Transactions on Multimedia, 2021, 24:1665-1677.
[8] ZHANG Z, LAN C, ZENG W, et al. Beyond triplet loss:meta prototypical N-tuple loss for person re-identification[J]. IEEE Transactions on Multimedia, 2021,24:4158-4169.
[9] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017:5998-6008.
[10] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al.An image is worth 16x16 words:Transformers for image recognition at scale[C]//Proceedings of the International Conference on Learning Representations. Vienna:ICLR, 2021:1-22.
[11] HE S, LUO H, WANG P, et al. Transreid:Transformer-based object re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal:IEEE, 2021:15013-15022.
[12] YE M, SHEN J, LIN G, et al. Deep learning for person reidentification:A survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2021, 44(6):2872-2893.
[13] RADENOVIC'F, TOLIAS G, CHUM O. Fine-tuning CNN image retrieval with no human annotation[J].IEEE transactions on pattern analysis and machine intelligence, 2018, 41(7):1655-1668.
[14]张勃兴,马敬奇,张寿明,等.利用全局与局部关联特征的行人重识别方法[J].电子测量与仪器学报,2022,36(6):205-212.ZHANG B X, MA J Q, ZHANG S M, et al. Person reidentification method based on global and local relation features[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(6):205-212.
[15]姚足,龚勋,陈锐,等.面向行人重识别的局部特征研究进展、挑战与展望[J].自动化学报, 2021, 47(12):2742-2760.YAO Z, GONG X, CHEN R, et al. Progress, challenge and prospect of local features for person reidentification[J]. Acta Automatica Sinica, 2021, 47(12):2742-2760.
[16] ZHENG L, SHEN L, TIAN L, et al. Scalable person re-identification:A benchmark[C]//Proceedings of the IEEE international conference on computer vision. Santiago, Chile:IEEE Press, 2015:1116-1124.
[17] RISTANI E, SOLERA F, ZOU R, et al. Performance measures and a data set for multi-target, multi-camera tracking[C]//European conference on computer vision.Amsterdam:Springer Press, Cham, 2016:17-35.
[18] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J].arXiv preprint arXiv:1409. 1556, 2014.
基本信息:
DOI：10.13880/j.cnki.65-1174/n.2025.23.004
中图分类号:TP391.41;TP18
引用信息:
[1]吴宇森,于宝华,荣江等.基于多尺度注意力与特征融合的行人重识别方法研究[J].石河子大学学报(自然科学版),2025,43(01):122-132.DOI:10.13880/j.cnki.65-1174/n.2025.23.004.
基金信息:
新疆生产建设兵团财政科技计划项目(2020DB005)