Cross-View Projective Dictionary Learning for Person Re-Identification
Cross-View Projective Dictionary Learning for Person Re-Identification
复制标题
DOI：
--
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Sheng Li;Ming Shao;Y. Fu
中科院分区：
文献类型：
--
作者：
Sheng Li;Ming Shao;Y. Fu
人员再识别在许多安全关键应用中起着重要作用。现有的工作主要集中在提取补丁级特征或学习距离度量。然而，由于现实中行人图像的各种观看条件，提取的特征表示能力可能会受到限制。为了提高特征的表示能力，本文通过字典学习来学习判别和鲁棒表示。首先，我们提出了一种跨视图投影字典学习（CPDL）方法，该方法可以学习跨不同视图的人的有效特征。CPDL是一个用于多视图字典学习的通用框架。其次，利用CPDL框架设计了两个目标，分别在patch级和image级学习每个行人的低维表示。所提出的目标可以捕获不同设置下不同表示系数的内在关系。我们设计了高效的优化算法来解决这些问题。最后，采用融合策略生成相似度分数。在公共VIPeR和中大校园数据集上的实验表明，我们的方法达到了最先进的性能。
Person re-identification plays an important role in many safety-critical applications. Existing works mainly focus on extracting patch-level features or learning distance metrics. However, the representation power of extracted features might be limited, due to the various viewing conditions of pedestrian images in reality. To improve the representation power of features, we learn discriminative and robust representations via dictionary learning in this paper. First, we propose a cross-view projective dictionary learning (CPDL) approach, which learns effective features for persons across different views. CPDL is a general framework for multiview dictionary learning. Secondly, by utilizing the CPDL framework, we design two objectives to learn low-dimensional representations for each pedestrian in the patch-level and the image-level, respectively. The proposed objectives can capture the intrinsic relationships of different representation coefficients in various settings. We devise efficient optimization algorithms to solve the objectives. Finally, a fusion strategy is utilized to generate the similarity scores. Experiments on the public VIPeR and CUHK Campus datasets show that our approach achieves the state-of-the-art performance.