从具有先验类别信息的 RGB 图像重建高光谱数据

摘要：使用 RGB 图像进行高光谱恢复最近在许多成像和计算机视觉应用中引起了相当大的关注，因为它能够以低成本 的方式获取自然场景的光谱特征。当前通过 RGB 测量恢复高光谱信息的方法可能会对具有相似 RGB 特征的物体失效。 在本文中，我们介绍了一种基于 U-net 架构的新框架，即 C2H-Net，用于从 RGB 测量中重建高质量的高光谱图像。C2H- Net 还利用了由特定感兴趣对象的类别和坐标信息组成的先验信息来解决现有方法的限制。C2H-Net 非常准确，可以输 出物体/场景的“真实”光谱信息。此外，本文还开发了一个新的高光谱数据集 C2H-Data（可在 Github 上获得），用于对 所提出的框架进行进一步的广泛评估。C2H-Data 包含各种物体，具有大量图像和类别信息，对研究界很有用。我们使用 三个不同的数据集进行实验，以证明 C2H-Net 的有效性。实验结果表明，我们提出的方法优于现有的几种方法。 索引词：深度卷积神经网络 (CNN)、高光谱成像、图像合成、多通道图像重建。

期刊：IEEE explorer

设备：GaiaField

Reconstruction of Hyperspectral Data from RGB Images with Prior Category Information

Abstract：Hyperspectral recovery using RGB images has recently attracted considerable attention in many imaging and computer vision applications because of its ability to equip a low cost tool in acquiring spectral signatures of natural scenes. Current methods of recovering hyperspectral information via RGB measurements may fail for objects sharing similar RGB features. In this paper, we introduce a novel framework with the U-net-based architecture, namely C2H-Net, which is used to reconstruct high quality hyperspectral images from their RGB measurements. C2H-Net also exploits prior information comprising of category and coordinate information of specific objects of interest to address the restriction of the existing methods. C2H-Net is highly accurate and outputs “true” spectral information of objects/scenes. In addition, a new hyperspectral dataset namely C2H-Data (available at Github) is developed in this work and used for additional extensive evaluation on the proposed framework. The C2H-Data contains a variety of objects with large number of images and category information which would be useful for the research community. We conduct experiments using three different datasets to show the effectiveness of C2H-Net. The experimental results show that our proposed method outperforms several existing methods.

Keywords：Deep convolution neural network (CNN), hyperspectral imaging, image synthesis, multichannel image reconstruction.