Li Jia, Zhou Yu-Qian, Zhang Qiu-Yan
College of Applied Mathematics, Chengdu University of Information Technology, Chengdu, Sichuan, China.
Front Neurorobot. 2023 Aug 9;17:1234129. doi: 10.3389/fnbot.2023.1234129. eCollection 2023.
Metric learning, as a fundamental research direction in the field of computer vision, has played a crucial role in image matching. Traditional metric learning methods aim at constructing two-branch siamese neural networks to address the challenge of image matching, but they often overlook to cross-source and cross-view scenarios.
In this article, a multi-branch metric learning model is proposed to address these limitations. The main contributions of this work are as follows: Firstly, we design a multi-branch siamese network model that enhances measurement reliability through information compensation among data points. Secondly, we construct a non-local information perception and fusion model, which accurately distinguishes positive and negative samples by fusing information at different scales. Thirdly, we enhance the model by integrating semantic information and establish an information consistency mapping between multiple branches, thereby improving the robustness in cross-source and cross-view scenarios.
Experimental tests which demonstrate the effectiveness of the proposed method are carried out under various conditions, including homologous, heterogeneous, multi-view, and crossview scenarios. Compared to the state-of-the-art comparison algorithms, our proposed algorithm achieves an improvement of ~1, 2, 1, and 1% in terms of similarity measurement Recall@10, respectively, under these four conditions.
In addition, our work provides an idea for improving the crossscene application ability of UAV positioning and navigation algorithm.
度量学习作为计算机视觉领域的一个基础研究方向，在图像匹配中发挥了关键作用。传统的度量学习方法旨在构建双分支连体神经网络来应对图像匹配的挑战，但它们往往忽略了跨源和跨视角场景。
在本文中，提出了一种多分支度量学习模型来解决这些局限性。这项工作的主要贡献如下：首先，我们设计了一种多分支连体网络模型，通过数据点之间的信息补偿来提高测量可靠性。其次，我们构建了一个非局部信息感知与融合模型，通过融合不同尺度的信息来准确区分正样本和负样本。第三，我们通过整合语义信息来增强模型，并在多个分支之间建立信息一致性映射，从而提高在跨源和跨视角场景下的鲁棒性。
在同源、异源、多视角和跨视角等各种条件下进行了实验测试，以证明所提方法的有效性。与当前最先进的比较算法相比，在这四种条件下，我们提出的算法在相似度测量召回率@10方面分别提高了约1%、2%、1%和1%。
此外，我们的工作为提高无人机定位与导航算法的跨场景应用能力提供了一种思路。
