摘要
近年来,跨模态行人重识别逐渐成为了计算机视觉领域的热门研究方向之一。然而,在跨模态行人重识别任务中,高效地提取行人特征,进一步实现图像之间的交互融合、挖掘行人图像之间的潜在关系是至关重要的。为了解决这一问题,提出一种基于通道分组重组和注意力机制的双流网络来提取两种模态之间更加稳定且丰富的特征。具体地:首先在主干网络中嵌入模态内特征通道分组重组模块以提取跨模态图像的共享特征,实现模态信息的交互融合;然后,通过聚合特征注意力机制及跨模态自适应图结构来挖掘不同模态行人图像之间的潜在关系,提取更具判别力的局部特征。在主流数据集SYSU-MM01、RegDB上进行的大量实验结果表明,所提算法在多个数据集上具有较好的泛化能力,与现有的主要算法相比,跨模态行人重识别精度达到较高的水准。
In recent years,cross-modal pedestrian re-identification has gradually become one of the hotspots in the field of computer vision.However,it is crucial to effectively extract pedestrian features,further realize the interactive fusion of photos,and mine any potential relationships between pedestrian images while performing cross-modal pedestrian reidentification.To address this issue,a dual stream network based on channel grouping reorganization and attention mechanisms is proposed to extract more stable and rich features between the two modes.Specifically,to extract the shared characteristics of cross-modal images and to achieve the interactive fusion of modal information,the intra-modal feature channel grouping rearrangement module(ICGR)was inserted in the backbone network.Furthermore,to extract additional distinct local features,the possible association between pedestrian images captured using various modes was mined using the aggregated feature attention mechanism and cross-modal adaptive graph structure.A large number of experimental results on mainstream datasets such as SYSU-MM01 and RegDB demonstrate that the proposed algorithm has good generalization ability on multiple datasets.The cross-modal pedestrian re-identification algorithm achieves higher accuracy compared with the existing main algorithms.
作者
霍东东
杜海顺
Huo Dongdong;Du Haishun(School of Artificial Intelligence,Henan University,Zhengzhou 450046,Henan,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2023年第14期65-76,共12页
Laser & Optoelectronics Progress
基金
河南省自然科学基金(202300410093)。
关键词
图像处理
跨模态
行人重识别
通道分组重组
注意力机制
image processing
cross-modal
person re-identification
channel grouping reorganization
attention mechanism
作者简介
通信作者:杜海顺,jddhs@henu.edu.cn。
