IEEE Trans Image Process. 2021;30:8913-8925. doi: 10.1109/TIP.2021.3120054. Epub 2021 Oct 28.
Person re-identification (re-ID) tackles the problem of matching person images with the same identity from different cameras. In practical applications, due to the differences in camera performance and distance between cameras and persons of interest, captured person images usually have various resolutions. This problem, named Cross-Resolution Person Re-identification, presents a great challenge for the accurate person matching. In this paper, we propose a Deep High-Resolution Pseudo-Siamese Framework (PS-HRNet) to solve the above problem. Specifically, we first improve the VDSR by introducing existing channel attention (CA) mechanism and harvest a new module, i.e., VDSR-CA, to restore the resolution of low-resolution images and make full use of the different channel information of feature maps. Then we reform the HRNet by designing a novel representation head, HRNet-ReID, to extract discriminating features. In addition, a pseudo-siamese framework is developed to reduce the difference of feature distributions between low-resolution images and high-resolution images. The experimental results on five cross-resolution person datasets verify the effectiveness of our proposed approach. Compared with the state-of-the-art methods, the proposed PS-HRNet improves the Rank-1 accuracy by 3.4%, 6.2%, 2.5%,1.1% and 4.2% on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets, respectively, which demonstrates the superiority of our method in handling the Cross-Resolution Person Re-ID task. Our code is available at https://github.com/zhguoqing.
行人再识别（re-ID）旨在解决从不同摄像机匹配具有相同身份的行人图像的问题。在实际应用中，由于摄像机性能和摄像机与感兴趣行人之间距离的差异，捕获的行人图像通常具有不同的分辨率。这个问题被称为跨分辨率行人再识别，给准确的行人匹配带来了巨大的挑战。在本文中，我们提出了一种深度高分辨率伪孪生框架（PS-HRNet）来解决上述问题。具体来说，我们首先通过引入现有的通道注意力（CA）机制改进 VDSR，获得一个新的模块，即 VDSR-CA，以恢复低分辨率图像的分辨率，并充分利用特征图的不同通道信息。然后，我们通过设计一个新的表示头 HRNet-ReID 来改进 HRNet，以提取判别特征。此外，开发了一个伪孪生框架来减少低分辨率图像和高分辨率图像之间的特征分布差异。在五个跨分辨率行人数据集上的实验结果验证了我们所提出方法的有效性。与最先进的方法相比，所提出的 PS-HRNet 在 MLR-Market-1501、MLR-CUHK03、MLR-VIPeR、MLR-DukeMTMC-reID 和 CAVIAR 数据集上的 Rank-1 精度分别提高了 3.4%、6.2%、2.5%、1.1%和 4.2%，这表明了我们的方法在处理跨分辨率行人再识别任务方面的优越性。我们的代码可在 https://github.com/zhguoqing 上获取。
