Tufts Outdoor Hyperspectral Dataset

Hyperspectral images are represented by numerousnarrow wavelength bands in the visible and near-infrared partsof the electromagnetic spectrum. As hyperspectral imagery gainstraction for general computer vision tasks, there is an increasedneed for large and comprehensive datasets for use as trainingdata.Recent advancements in sensor technology allow us to capturehyperspectral data cubes at higher spatial and temporal reso-lution. However, there are few publicly available multi-purposehyperspectral datasets captured in outdoor terrestrial conditions.Furthermore, there are no publicly available datasets that include3D mesh representations of objects captured in outdoor scenes.This article introduces the first hyperspectral dataset of 3Dobjects and terrestrial outdoor scenes, the Tufts Outdoor Hyper-spectral Dataset (TOHS Dataset). The dataset includes 100 2D +3D hyperspectral scenes, each containing 164 spectral bands.The contributions of this work are 1) Detailed description ofthe content, acquisition procedure, and benchmark results onstate-of-the-art neural networks for 3D object scenes in the TuftsHyperspectral Database; 2) The first-of-its-kind hyperspectral3D dataset of outdoor objects that will be publicly available toresearchers worldwide, which will allow for the assessment andcreation of more robust, consistent, and adaptable AI algorithms;and 3) a comprehensive and up-to-date review on hyperspectralsystems and datasets

高光谱图像通过电磁谱可见光和近红外部分的众多狭窄波长带进行表示。随着高光谱图像在通用计算机视觉任务中的应用逐渐加深，对于作为训练数据的大型且全面的数据库的需求日益增长。传感器技术的最新进展使得我们能够以更高的空间和时间分辨率捕捉高光谱数据立方体。然而，在户外地表条件下，可公开获取的多用途高光谱数据集为数不多。此外，目前尚无公开的数据集包含户外场景中捕获物体的3D网格表示。本文首次介绍了首个三维物体和户外地表场景的高光谱数据集——塔夫茨户外高光谱数据集（TOHS数据集）。该数据集包括100个2D+3D高光谱场景，每个场景包含164个光谱带。本工作的贡献包括：1）对塔夫茨高光谱数据库中三维物体场景的内容、获取流程以及最先进神经网络上的基准结果进行了详细描述；2）首次公开了户外物体的高光谱3D数据集，这将使全球研究人员能够评估和创建更稳健、一致和适应性强的人工智能算法；3）对高光谱系统和数据集进行了全面且最新的综述。