计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (3): 661-668.DOI: 10.3778/j.issn.1673-9418.2010046

• 图形图像 • 上一篇    下一篇

结合注意力和纹理特征增强的行人再识别

李杰+()   

  1. 中国民航大学 信息网络中心,天津 300300
  • 收稿日期:2020-09-14 修回日期:2020-11-16 出版日期:2022-03-01 发布日期:2020-12-08
  • 通讯作者: + E-mail: j-li@cauc.edu.cn
  • 作者简介:李杰(1984—),男,山西原平人,硕士,工程师,主要研究方向为行人再识别、数据挖掘等。
  • 基金资助:
    国家重点研发计划(2016YFB0502405);中国民航大学实验技术创新基金(2018CXJJ28)

Attention and Texture Feature Enhancement for Person Re-identification

LI Jie+()   

  1. Information Network Center, Civil Aviation University of China, Tianjin 300300, China
  • Received:2020-09-14 Revised:2020-11-16 Online:2022-03-01 Published:2020-12-08
  • About author:LI Jie, born in 1984, M.S., engineer. His research interests include person re-identification, data mining, etc.
  • Supported by:
    National Key Research and Development Program of China(2016YFB0502405);Experimental Technology Innovation Fund of Civil Aviation University of China(2018CXJJ28)

摘要:

针对现有行人再识别算法在处理图像分辨率低、光照差异、姿态和视角多样等情况时,准确率低的问题,提出了基于空间注意力和纹理特征增强的多任务行人再识别算法。算法设计的空间注意力模块更注重与行人属性相关的潜在图像区域,融入属性识别网络,实现属性特征的挖掘;提出的行人再识别网络的纹理特征增强模块通过融合不同空间级别所对应的全局和局部特征,减弱了光照、遮挡等对行人再识别的干扰;最后通过多任务加权损失函数将属性特征和行人特征巧妙融合,避免了由属性异质性造成的再识别精度损失。实验结果表明,该方法在Market-1501和DukeMTMC-reID两大主流行人再识别数据集上的平均精度分别可以达到81.1%和70.1%。

关键词: 空间注意力, 纹理特征增强, 行人属性, 行人再识别

Abstract:

In view of the low accuracy of existing person re-identification to deal with low image resolution, illuminative difference, posture and perspective diversity, this paper proposes a multi-task pedestrian recognition algorithm based on spatial attention and texture feature enhancement. The spatial attention module designed by the algorithm pays more attention to the potential image areas related to the pedestrian attributes, which further explores attribute features. The texture feature enhancement module of the person re-identification network reduces the interference of light, occlusion on person re-identification by fusing the global and local features corresponding to different spatial levels. Finally, the multi-stage weighted loss function integrates the attribute features and pedestrian features to avoid the decrease of mean average precision caused by attribute heterogeneity. Experimental results show that the mean average precision can achieve 81.1% and 70.1% respectively on the Market-1501 and DukeMTMC-reID datasets.

Key words: spatial attention, texture feature enhancement, pedestrian attributes, person re-identification

中图分类号: