Aguilera Cristhian A, Sappa Angel D, Aguilera Cristhian, Toledo Ricardo
Computer Vision Center, Edifici O, Campus UAB, Bellaterra 08193, Barcelona, Spain.
Computer Science Department, Universitat Autònoma de Barcelona, Campus UAB, Bellaterra 08193,Barcelona, Spain.
Sensors (Basel). 2017 Apr 15;17(4):873. doi: 10.3390/s17040873.
This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.
本文提出了一种基于卷积神经网络（CNN）的新型架构，称为Q-Net，用于学习局部特征描述符，这些描述符有助于匹配来自两个不同光谱带的图像块。给定正确匹配和不匹配的跨光谱图像对，训练一个四元组网络，将输入的图像块映射到一个公共的欧几里得空间，而不管输入的光谱带如何。我们的方法受到三元组网络在可见光谱中最近成功的启发，但适用于跨光谱场景，在这种场景中，对于每个匹配对，总是有两个可能的不匹配块：每个光谱各一个。在一个公共的跨光谱VIS-NIR数据集上的实验评估表明，所提出的方法改进了当前的最优技术。此外，所提出的技术也可以用于单光谱设置，获得与三元组网络描述符相似的性能，但需要的训练数据更少。
