Cross-view transformation based sparse reconstruction for person re-identification
Cross-view transformation based sparse reconstruction for person re-identification
复制标题
DOI：
10.1109/icpr.2016.7900161
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Wei-Xiong He;Ying-Cong Chen;J. Lai
中科院分区：
文献类型：
--
作者：
Wei-Xiong He;Ying-Cong Chen;J. Lai
基于最小重构误差准则和自然数据固有的稀疏性，稀疏表示在各种图像识别任务中表现出了良好的性能。然而，在人的再识别（re-id）领域，目前的最新技术仍然由度量学习或CNN等其他方法主导。这是因为一个视图中的样本可能不足以代表另一个视图中的样本。这样，重建误差可能过大，并且稀疏表示产生的系数无法区分不同的行人。在本文中，我们提出了一种非对称稀疏表示来解决这个问题。不同相机视图的样本（画廊和探针样本）被映射到一个共同的隐空间，并在该隐空间中生成稀疏系数。这样，增强了表示能力，稀疏系数更加可靠。不同样本的相似度由增强的稀疏系数决定，这使得不同相机视图之间的匹配更具区别性。在CAVIAR4REID、iLIDS-VID和PRID 2011数据集上的大量实验证明了我们的方法的优点。
Based on minimum reconstruction error criterion and the intrinsic sparse property of natural data, sparse representation (SR) has shown promising performance on various image recognition tasks. However, in the field of person re-identification (re-id), the state-of-the-art is still dominated by other methods such as metric learning or CNN. It is because samples in one view may not be representative enough to represent samples from another view. As such, the reconstruction error could be excessive, and different pedestrians are indistinguishable with the coefficient produced by sparse representation. In this paper, we proposed an asymmetric sparse representation to address this problem. Samples of different camera views (gallery and probe samples) are mapped to a common latent space and the sparse coefficient is generated in this space. In this way, the representation power is enhanced and the sparse coefficient becomes more reliable. The similarities of different samples are determined by the enhanced sparse coefficient, which allows more discriminative matching across different camera views. Extensive experiments on CAVIAR4REID, iLIDS-VID and PRID 2011 datasets have demonstrated the merits of our approach.