Abstract
The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem.Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership. In this paper, we propose a novel conceptof group granularity by characterizing a group image by multi-grained objects: individual persons and sub-groups of two andthree people within a group. To achieve robust group Re-ID,we first introduce multi-grained representations which can beextracted via the development of two separate schemes, i.e. onewith hand-crafted descriptors and another with deep neuralnetworks. The proposed representation seeks to characterize bothappearance and spatial relations of multi-grained objects, and isfurther equipped with importance weights which capture varia-tions in intra-group dynamics. Optimal group-wise matching isfacilitated by a multi-order matching process which in turn,dynamically updates the importance weights in iterative fashion.We evaluated on three multi-camera group datasets containingcomplex scenarios and large dynamics, with experimental resultsdemonstrating the effectiveness of our approach.
Abstract (translated)
对不同视角下的人群进行重新识别是一个重要但研究较少的问题，群体重新识别是一个非常具有挑战性的任务，因为它不仅受到传统问题中常见问题的不利影响，而且还受到视点和人的位置等单一对象重新识别问题的影响，而且还受到变化的影响。n组布局和组成员身份。本文提出了一种新的群体粒度概念，通过多粒度对象来表征群体图像：个体和两个群体中的两个和三个群体中的子群体。为了实现健壮的组RE ID，我们首先引入了多粒度表示，通过开发两个独立的方案来提取，一个方案是手工制作的描述符，另一个方案是深度神经网络。所提出的表示方法旨在描述多粒度对象的形状和空间关系，并进一步配置重要权重，以捕捉组内动力学中的变量。通过一个多阶匹配过程来促进优化的群体匹配，该过程反过来以迭代的方式动态更新重要性权重。我们对包含复杂场景和大动态的三个多摄像机群体数据集进行了评估，实验结果证明了我们的方法的有效性。
URL
https://arxiv.org/abs/1905.07108
