中国人民武装警察部队海警学院;国防科技大学气象海洋学院;无锡学院电子信息工程学院;
作为实例级识别问题,行人重识别(Person Re-Identification,ReID)中同一行人图像可能因视角条件变化而差异较大,导致相似性判别十分依赖于不同空间尺度的多样化特征。而基于深度卷积神经网络(Deep Convolutional Neural Network,DCNN)的ReID方法存在浅层基础信息易丢失的问题,且单一尺度的特征不能充分描述行人全局关系。因此,为获取多样化的行人特征,提出一种基于跨阶段级联(Cross-Stage Cascade,CSC)与多尺度注意力特征的ReID方法。设计了一种CSC结构,结合上下文关系感知的自注意力(Contextual Transformer Attention Block,CoT)机制,挖掘并融合不同阶段的浅层细节特征,将其作为深度抽象语义的全局先验。通过多尺度卷积操作处理深度全局语义特征,促使模型学习纯净的全局特征,增强卷积模型对全局特征关系的挖掘能力。在多个数据集上的实验表明,网络能够有效提升ReID精度。
| 156 | 0 | 38 |
| 下载次数 | 被引频次 | 阅读次数 |
[1]罗浩.基于深度学习的行人重识别算法研究———从无遮挡到遮挡[D].杭州:浙江大学,2020.
[2] 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.
[3] TAY C P, ROY S,YAP K H. AAnet:Attribute Attention Network for Person Re-Identifications[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach:IEEE,2019:3127-7136.
[4]魏紫薇,屈丹,柳聪.基于连接注意力的行人重识别特征提取方法[J].计算机工程,2022,48(7):220-226.
[5] 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. Las Vegas:IEEE,2016:770-778.
[6] CHEN G Y,GU T P,LU J W,et al. Person Re-Identification via Attention Pyramid[J]. IEEE Transactions on Image Processing,2021,30:7663-7676.
[7] WANG G S,YUAN Y F,CHEN X,et al. Learning Discriminative Features with Multiple Granularities for Person Re-Identification[C]∥Proceedings of the 26th ACM International Conference on Multimedia. New York:ACM,2018:274-282.
[8]王栋,周大可,黄有达,等.基于多尺度多粒度特征的行人重识别[J].计算机科学,2021,48(7):238-244.
[9] YE M,SHEN J B,LIN G J,et al. Deep Learning for Person Re-Identification:A Survey and Outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(6):2872-2893.
[10] DONG H S,YANG Y F,SUN X,et al. Cascaded Attention-guided Multi-granularity Feature Learning for Person Re-Identification[J]. Machine Vision and Applications,2023,34(1):1-16.
[11]郭彤,赵倩,赵琰,等.多分支融合注意力机制的行人重识别方法[J].计算机工程与设计,2022,43(8):2260-2267.
[12] VASWANI A,SHAZEER N,PARMAR N,et al. Attention Is All You Need[C]∥NIPS'17:Proceedings of the 31st International Conference on Neural Information Processing Systems. New York:ACM,2017:6000-6010.
[13] LI Y H,YAO T,PAN Y W,et al. Contextual Transformer Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(2):1489-1500.
[14] HERMANS A,BEYER L,LEIBE B. In Defense of the Triplet Loss for Person Re-Identification[EB/OL].(2017-03-22)[2024-08-19]. https:∥arxiv. org/abs/1703. 07737.
[15] LUO H, GU Y Z,LIAO X Y,et al. Bag of Tricks and a Strong Baseline for Deep Person Re-Identification[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Long Beach:IEEE,2019:1487-1495.
[16] SUN Y F, ZHENG L,YANG Y,et al. Beyond Part Models:Person Retrieval with Refined Part Pooling(and a Strong Convolutional Baseline)[C]∥European Conference on Computer Vision(ECCV). Munich:Springer,2018:501-518.
[17] ZHOU K Y,YANG Y X,CAVALLARO A,et al. Omniscale Feature Learning for Person Re-Identification[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul:IEEE,2019:3701-3711.
[18] ZHENG F,DENG C,SUN X,et al. Pyramidal Person ReIdentification via Multi-loss Dynamic Training[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach:IEEE,2019:8506-8514.
[19] CHEN T L,DING S J,XIE J Y,et al. ABD-Net:Attentive but Diverse Person Re-Identification[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul:IEEE,2019:8351-8361.
基本信息:
DOI：
中图分类号:TP391.41;TP183
引用信息:
[1]沈宇慧,孟鑫,郭随平等.基于跨阶段级联与多尺度注意力特征的行人重识别[J].无线电工程,2025,55(03):500-510.
基金信息:
国家自然科学基金(61673222); 江苏省研究生实践创新计划(SJCX22＿0333); 南京信息工程大学研究生创新实践项目(WXCX202013)~~