IEEE Trans Cybern. 2021 Mar;51(3):1478-1492. doi: 10.1109/TCYB.2019.2917713. Epub 2021 Feb 17.
The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not only adversely affected by common issues in traditional single-object Re-ID problems, such as viewpoint and human pose variations, but also suffers from changes in group layout and group membership. In this paper, we propose a novel concept of group granularity by characterizing a group image by multigrained objects: individual people and subgroups of two and three people within a group. To achieve robust group Re-ID, we first introduce multigrained representations which can be extracted via the development of two separate schemes, that is, one with handcrafted descriptors and another with deep neural networks. The proposed representation seeks to characterize both appearance and spatial relations of multigrained objects, and is further equipped with importance weights which capture variations in intragroup dynamics. Optimal group-wise matching is facilitated by a multiorder matching process which, in turn, dynamically updates the importance weights in iterative fashion. We evaluated three multicamera group datasets containing complex scenarios and large dynamics, with experimental results demonstrating the effectiveness of our approach.
在不同摄像机视角下重新识别人群的任务是一个重要但研究较少的问题。群体重识别（Re-ID）是一项极具挑战性的任务，因为它不仅受到传统单目标 Re-ID 问题中常见问题（如视角和人体姿势变化）的不利影响，还受到群体布局和群体成员变化的影响。在本文中，我们通过将群体图像特征化为多粒度对象（个体和群体内的两人和三人小组）来提出群体粒度的新概念。为了实现稳健的群体 Re-ID，我们首先引入了多粒度表示，可以通过两种单独的方案来提取，即一种是基于手工描述符的方案，另一种是基于深度神经网络的方案。所提出的表示旨在描述多粒度对象的外观和空间关系，并进一步配备了重要性权重，以捕获群体内动态的变化。通过多阶匹配过程来促进最佳的群组匹配，该过程反过来以迭代的方式动态更新重要性权重。我们评估了三个包含复杂场景和大动态性的多摄像机群体数据集，实验结果表明了我们方法的有效性。
