本文已被:浏览 149次 下载 852次
Received:March 04, 2024 Revised:April 03, 2024
Received:March 04, 2024 Revised:April 03, 2024
中文摘要: 跨模态行人重识别任务旨在匹配同一行人的可见光图像和红外图像, 在智能安全监控系统中广泛应用. 由于可见光模态和红外模态存在固有的模态差异, 给跨模态行人重识别任务在实际应用过程中带来了巨大的挑战. 为了缓解模态差异, 研究人员提出了很多有效的解决方法. 但是由于这些方法提取的是不同模态之间的特征, 彼此缺少对应的模态信息, 导致特征缺少充分的鉴别性. 为了提高模型提取特征的鉴别性, 本文提出基于注意力特征融合的跨模态行人重识别方法. 通过设计高效的特征提取网络和注意力融合模块, 并在多种损失函数的优化下, 实现不同模态信息的融合和模态对齐, 从而促进模型匹配行人准确度的提升. 实验结果表明, 本方法在多个数据集上都取得了很好的性能.
Abstract:Cross-modality person re-identification is widely used in intelligent safety monitoring systems, aiming to match visible light images and infrared images of the same person. Due to the inherent modality differences between visible and infrared modalities, cross-modality person re-identification poses significant challenges in practical applications. To alleviate modality differences, researchers have proposed many effective solutions. However, existing methods extract different modality features without corresponding modality information, resulting in insufficient discriminability of the features. To improve the discriminability of the features extracted from models, this study proposes a cross-modality person re-identification method based on attention feature fusion. By designing an efficient feature extraction network and attention feature fusion module, and optimizing multiple loss functions, the fusion and alignment of different modality information can be achieved, thereby promoting the model matching accuracy for persons. Experimental results show that this method achieves great performance on multiple datasets.
keywords: cross-modality person re-identification attention mechanism feature fusion modality difference modality alignment
文章编号: 中图分类号: 文献标志码:
基金项目:江苏省研究生科研创新计划(KYCX23_1369)
引用文本:
邓淑雅,李浩源.基于注意力特征融合的跨模态行人重识别.计算机系统应用,2024,33(9):269-275
DENG Shu-Ya,LI Hao-Yuan.Cross-modality Person Re-identification Based on Attention Feature Fusion.COMPUTER SYSTEMS APPLICATIONS,2024,33(9):269-275
邓淑雅,李浩源.基于注意力特征融合的跨模态行人重识别.计算机系统应用,2024,33(9):269-275
DENG Shu-Ya,LI Hao-Yuan.Cross-modality Person Re-identification Based on Attention Feature Fusion.COMPUTER SYSTEMS APPLICATIONS,2024,33(9):269-275