Object reidentification with the goal of matching pedestrian or vehicle images captured from different camera viewpoints is of considerable significance to public security. Quadruple directional deep learning features (QD-DLFs) can comprehensively describe object images. However, the correlation among QD-DLFs is an unavoidable problem, since QD-DLFs are learned with quadruple independent directional deep networks (QIDDNs) driven with the same training data, and each network holds the same basic deep feature learning architecture (BDFLA). The correlation among QD-DLFs is harmful to the complementarity of QD-DLFs, restricting the object reidentification performance. For that, we propose joint quadruple decorrelation directional deep networks (JQD ³ Ns) to reduce the correlation among the learned QD-DLFs. In order to jointly train JQD ³ Ns, besides the softmax loss functions, a parameter correlation cost function is proposed to indirectly reduce the correlation among QD-DLFs by enlarging the dissimilarity among the parameters of JQD ³ Ns. Extensive experiments on three publicly available large-scale data sets demonstrate that the proposed JQD ³ Ns approach is superior to multiple state-of-the-art object reidentification methods.

中文翻译：

---

智能交通中通过联合四重解相关方向深度网络进行对象识别

以匹配从不同摄像机视角捕获的行人或车辆图像为目标的对象重新识别对公共安全具有重要意义。四方向定向深度学习功能（QD-DLF）可以全面描述对象图像。但是，QD-DLF之间的相关性是一个不可避免的问题，因为QD-DLF是通过以相同训练数据驱动的四重独立定向深度网络（QIDDN）来学习的，并且每个网络都具有相同的基本深度特征学习体系结构（BDFLA）。QD-DLF之间的相关性不利于QD-DLF的互补性，从而限制了对象的重新识别性能。为此，我们提出了联合四重解相关定向深度网络（JQD ³ Ns），以减少学习的QD-DLF之间的相关性。为了联合训练JQD ³ Ns，除了softmax损失函数外，还提出了一种参数相关代价函数，通过扩大JQD ³ Ns参数之间的相似度来间接降低QD-DLF之间的相关性 。在三个可公开获得的大规模数据集上的大量实验表明，所提出的JQD ³ Ns方法优于多种最新的对象识别方法。