IEEE Trans Image Process. 2021;30:2060-2071. doi: 10.1109/TIP.2021.3050839. Epub 2021 Jan 21.
Person re-identification is a crucial task of identifying pedestrians of interest across multiple surveillance camera views. For person re-identification, a pedestrian is usually represented with features extracted from a rectangular image region that inevitably contains the scene background, which incurs ambiguity to distinguish different pedestrians and degrades the accuracy. Thus, we propose an end-to-end foreground-aware network to discriminate against the foreground from the background by learning a soft mask for person re-identification. In our method, in addition to the pedestrian ID as supervision for the foreground, we introduce the camera ID of each pedestrian image for background modeling. The foreground branch and the background branch are optimized collaboratively. By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to backgrounds, which greatly reduces the negative impact of changing backgrounds on pedestrian matching across different camera views. Notably, in contrast to existing methods, our approach does not require an additional dataset to train a human landmark detector or a segmentation model for locating the background regions. The experimental results conducted on three challenging datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, demonstrate the effectiveness of our approach.
行人重识别是跨多个监控摄像机视图识别感兴趣行人的关键任务。对于行人重识别，行人通常使用从矩形图像区域中提取的特征表示，该区域不可避免地包含场景背景，这会导致难以区分不同的行人，并降低准确性。因此，我们提出了一种端到端的前景感知网络，通过学习用于行人重识别的软掩模来区分前景和背景。在我们的方法中，除了行人 ID 作为前景的监督外，我们还为每个行人图像引入了摄像机 ID 来进行背景建模。前景分支和背景分支协同优化。通过引入目标注意力损失，从前景分支提取的行人特征对背景变得不那么敏感，这大大降低了背景变化对跨不同摄像机视图的行人匹配的负面影响。值得注意的是，与现有方法相比，我们的方法不需要额外的数据集来训练人体地标检测器或用于定位背景区域的分割模型。在三个具有挑战性的数据集，即 Market-1501、DukeMTMC-reID 和 MSMT17 上进行的实验结果证明了我们方法的有效性。
