Person Re-Identification by Iterative Re-Weighted Sparse Ranking
Person Re-Identification by Iterative Re-Weighted Sparse Ranking
复制标题
DOI：
10.1109/tpami.2014.2369055
复制
发表时间：
2015-08
影响因子：
23.6
通讯作者：
G. Lisanti;I. Masi;Andrew D. Bagdanov;A. del Bimbo
中科院分区：
文献类型：
--
作者：
G. Lisanti;I. Masi;Andrew D. Bagdanov;A. del Bimbo
在本文中，我们介绍了一种基于已知个体标记库的目标的判别性、稀疏基础扩展的人员重新识别方法。我们提出了对稀疏判别分类器的迭代扩展，能够对许多候选目标进行排名。该方法利用软重新加权和硬重新加权在最相关的贡献元素之间重新分配能量，并确保在每次迭代时对最佳候选者进行排名。我们的方法还利用了一种新颖的视觉描述符，我们证明它具有辨别力，同时对姿势和照明变化保持鲁棒性。广泛的比较评估表明，我们的方法在 VIPeR、i-LIDS、ETHZ 和 CAVIAR4REID 数据集上的单次和多次人员重新识别场景中实现了最先进的性能。与每人使用单个图库图像的其他方法相比，我们的描述符和迭代稀疏基扩展的组合将 VIPeR 上最先进的 Rank-1 性能提高了 6 个百分点，在 CAVIAR4REID 上提高了 20 个百分点。通过每人多个图库和探测图像，我们的方法在 i-LIDS 上的最新技术水平提高了 17 个百分点，在 CAVIAR4REID 上提高了 72 个百分点，排名第一。该方法也非常高效，能够以每秒约 30 次的速度对包含数百人的画廊进行单次人员重新识别。
In this paper we introduce a method for person re-identification based on discriminative, sparse basis expansions of targets in terms of a labeled gallery of known individuals. We propose an iterative extension to sparse discriminative classifiers capable of ranking many candidate targets. The approach makes use of soft- and hard- re-weighting to redistribute energy among the most relevant contributing elements and to ensure that the best candidates are ranked at each iteration. Our approach also leverages a novel visual descriptor which we show to be discriminative while remaining robust to pose and illumination variations. An extensive comparative evaluation is given demonstrating that our approach achieves state-of-the-art performance on single- and multi-shot person re-identification scenarios on the VIPeR, i-LIDS, ETHZ, and CAVIAR4REID datasets. The combination of our descriptor and iterative sparse basis expansion improves state-of-the-art rank-1 performance by six percentage points on VIPeR and by 20 on CAVIAR4REID compared to other methods with a single gallery image per person. With multiple gallery and probe images per person our approach improves by 17 percentage points the state-of-the-art on i-LIDS and by 72 on CAVIAR4REID at rank-1. The approach is also quite efficient, capable of single-shot person re-identification over galleries containing hundreds of individuals at about 30 re-identifications per second.