Towards Open-World Person Re-Identification by One-Shot Group-Based Verification
Towards Open-World Person Re-Identification by One-Shot Group-Based Verification
复制标题
DOI：
10.1109/tpami.2015.2453984
复制
发表时间：
2016-03
影响因子：
23.6
通讯作者：
Weishi Zheng;S. Gong;T. Xiang
中科院分区：
文献类型：
--
作者：
Weishi Zheng;S. Gong;T. Xiang
解决跨非重叠多摄像机视图的人匹配问题，被称为人重新识别（re-id），在计算机视觉中受到越来越多的关注。在现实世界的应用场景中，少数已知目标人的观察列表（图库集）被提供有每个目标的非常少的（在许多情况下仅单个）图像（镜头）。现有的re-id方法在很大程度上不适合解决这种开放世界的re-id挑战，因为它们被设计用于（1）封闭世界场景，其中画廊和探针集被假设为包含完全相同的人，（2）个人识别，其中模型试图针对画廊集中的每个人进行详尽的验证，以及（3）使用多镜头学习匹配模型。本文提出了一种新的转移局部相对距离比较（t-LRDC）模型，通过一次性的基于组的验证来解决开放世界中的人员重新识别问题。该模型旨在从标记的开放世界非目标数据集中挖掘和传输有用的信息。大量的实验表明，该方法优于非迁移学习和现有的基于迁移学习的re-id方法。
Solving the problem of matching people across non-overlapping multi-camera views, known as person re-identification (re-id), has received increasing interests in computer vision. In a real-world application scenario, a watch-list (gallery set) of a handful of known target people are provided with very few (in many cases only a single) image(s) (shots) per target. Existing re-id methods are largely unsuitable to address this open-world re-id challenge because they are designed for (1) a closed-world scenario where the gallery and probe sets are assumed to contain exactly the same people, (2) person-wise identification whereby the model attempts to verify exhaustively against each individual in the gallery set, and (3) learning a matching model using multi-shots. In this paper, a novel transfer local relative distance comparison (t-LRDC) model is formulated to address the open-world person re-identification problem by one-shot group-based verification. The model is designed to mine and transfer useful information from a labelled open-world non-target dataset. Extensive experiments demonstrate that the proposed approach outperforms both non-transfer learning and existing transfer learning based re-id methods.