Re-ranking for person re-identification
Re-ranking for person re-identification
复制标题
DOI：
10.1109/socpar.2013.7054148
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Vu-Hoang Nguyen;T. Ngo;Khang Nguyen;D. Duong;Kien Nguyen;Duy-Dinh Le
中科院分区：
文献类型：
--
作者：
Vu-Hoang Nguyen;T. Ngo;Khang Nguyen;D. Duong;Kien Nguyen;Duy-Dinh Le
人员重新识别问题的目标是在非重叠摄像机网络中匹配人员。当多个探测人同时出现时，人类可以将它们放在一起进行比较，以给出更准确的匹配。然而，现有的方法独立地对待每个探测人，跳过并发信息。在本文中，我们提出了一种重新排序的方法，利用这种信息来细化排名名单产生的任何人重新识别方法，以创建更精确的排名名单。在VIPeR数据集上的实验结果表明，当我们的方法被应用时，性能得到了改善。
Person Re-Identification problem aims at matching people across a network of non-overlapping cameras. When multiple probe people appear concurrently, human could compare them together to give a more accurate matching. However, existing approaches treat each probe person independently, skipping the concurrent information. In this paper, we propose a re-ranking method which utilize that kind of information to refine ranked lists produced by any person re-identification method to create more precise ranked lists. The experimental results on VIPeR dataset show the improved performance when our method is applied.