期刊论文

Cross-modality Person Re-identification Based on Joint Constraints of Image and Feature

中文

自动化学报

0254-4156

2021

47

08

1943-1950

10.16383/j.aas.c200184

国家自然科学基金面上项目（61977027）； 湖北省科技创新重大专项（2019AAA044）资助~~；

本校为第一机构

近年来,基于可见光与近红外的行人重识别研究受到业界人士的广泛关注.现有方法主要是利用二者之间的相互转换以减小模态间的差异.但由于可见光图像和近红外图像之间的数据具有独立且分布不同的特点,导致其相互转换的图像与真实图像之间存在数据差异.因此,本文提出了一个基于图像层和特征层联合约束的可见光与近红外相互转换的中间模态,不仅实现了行人身份的一致性,而且减少了模态间转换的差异性.此外,考虑到跨模态行人重识别数据集的稀缺性,本文还构建了一个跨模态的行人重识别数据集,并通过大量的实验证明了文章所提方法的有效性,本文所提出的方法在经典公共数据集SYSU-MM01上比D2RL算法在Rank...

In recent years, the research of person re-identification based on visible and near-infrared has attracted widespread attention from the industry. The existing methods mainly use the mutual conversion between them to reduce the difference between their modalities. However, due to the problem of data independence and different distribution between visible image and near-infrared image, there is a large difference between the converted image and the real image, which leads to further improvement of this method. Therefore, this paper proposes a middle modality of conversion between visible and ne...