National Key Laboratory of Science and Technology on Multi-spectral Information Processing, School of Automation, Huazhong University of Science and Technology, Wuhan, China.
Department of Computer Science and Engineering, University of California, Riverside, CA, USA.
IEEE Trans Neural Netw Learn Syst. 2017 Nov;28(11):2763-2774. doi: 10.1109/TNNLS.2016.2602082.
Matching people across nonoverlapping cameras, also known as person re-identification, is an important and challenging research topic. Despite its great demand in many crucial applications such as surveillance, person re-identification is still far from being solved. Due to drastic view changes, even the same person may look quite dissimilar in different cameras. Illumination and pose variations further aggravate this discrepancy. To this end, various feature descriptors have been designed for improving the matching accuracy. Since different features encode information from different aspects, in this paper, we propose to effectively leverage multiple off-the-shelf features via multi-hypergraph fusion. A hypergraph captures not only pairwise but also high-order relationships among the subjects being matched. In addition, different from conventional approaches in which the matching is achieved by computing the pairwise distance or similarity between a probe and a gallery subject, the similarities between the probe and all gallery subjects are learned jointly via hypergraph optimization. Experiments on popular data sets demonstrate the effectiveness of the proposed method, and a superior performance is achieved as compared with the most recent state-of-the-arts.Matching people across nonoverlapping cameras, also known as person re-identification, is an important and challenging research topic. Despite its great demand in many crucial applications such as surveillance, person re-identification is still far from being solved. Due to drastic view changes, even the same person may look quite dissimilar in different cameras. Illumination and pose variations further aggravate this discrepancy. To this end, various feature descriptors have been designed for improving the matching accuracy. Since different features encode information from different aspects, in this paper, we propose to effectively leverage multiple off-the-shelf features via multi-hypergraph fusion. A hypergraph captures not only pairwise but also high-order relationships among the subjects being matched. In addition, different from conventional approaches in which the matching is achieved by computing the pairwise distance or similarity between a probe and a gallery subject, the similarities between the probe and all gallery subjects are learned jointly via hypergraph optimization. Experiments on popular data sets demonstrate the effectiveness of the proposed method, and a superior performance is achieved as compared with the most recent state-of-the-arts.
跨非重叠相机匹配人员，也称为人员重识别，是一个重要且具有挑战性的研究课题。尽管在监控等许多关键应用中对其有很大的需求，但人员重识别仍然远未得到解决。由于视角的剧烈变化，即使是同一个人在不同的相机中也可能看起来非常不同。光照和姿势的变化进一步加剧了这种差异。为此，设计了各种特征描述符来提高匹配精度。由于不同的特征从不同的方面编码信息，因此在本文中，我们通过多超图融合来有效地利用多个现成的特征。超图不仅可以捕获匹配的主体之间的成对关系，还可以捕获高阶关系。此外，与传统方法不同，传统方法通过计算探针和图库主体之间的成对距离或相似性来实现匹配，而是通过超图优化来共同学习探针与所有图库主体之间的相似性。在流行数据集上的实验证明了所提出方法的有效性，并且与最新的最先进方法相比，实现了卓越的性能。
