高光谱遥感影像分类数据集主要用于辅助高光谱遥感分类算法的精度验证、效率评价及性能评估，一般包括高光谱遥感影像、影像对应地物类别标注以及相关信息文档等内容。常用的高光谱遥感影像分类数据集以欧美为主，如India Pines、Salinas、KSC等。随着中国高光谱遥感传感器技术发展和学术交流机制的日臻完善，国内也发布了高光谱遥感分类数据集，如江苏省常州的茶树数据集。较于欧美高光谱遥感分类数据集的广泛应用，中国高光谱遥感分类数据集的发布与应用仍偏少。近年来，中国高质量高光谱遥感数据获取能力大幅增强，提升了中国高光谱遥感共享数据源的数量及质量，为促进中国高光谱遥感应用研究及业务化能力提供了支撑。本分类数据集包括雄安新区马蹄湾村高光谱影像数据，由中国科学院上海技术物理研究所研制高分专项航空系统全谱段多模态成像光谱仪采集，光谱范围为400—1000 nm，波段250个，影像大小为3750×1580像元，空间分辨率0.5 m；同步实地调研地类分布19种，包括水稻茬、草地、榆树、白蜡、国槐、菜地、杨树、大豆、刺槐、水稻、水体、柳树、复叶槭、栾树、桃树、玉米、梨树、荷叶、建筑。利用随机森林分类方法对该数据进行了分类验证，分类精度可达97%。该数据集（下载方式：http：//www.hrs-cas.com/a/share/shujuchanpin/2019/ 0501/1049.html）可为中国经济作物高光谱精细分类研究提供良好的数据支持，更可为中国高光谱遥感载荷业务化应用发展提供有力促进。

An aerial hyperspectral remote sensing dataset plays an important role on the research of hyperspectral images, including classification. However, few studies have been conducted on the establishment of a standard hyperspectral dataset. This study introduced a standard hyperspectral dataset that includes a hyperspectral remote sensing image, a land cover map, and sensor parameters. This dataset was acquired by using a newly designed airborne hyperspectral sensor accompanied with synchronous ground survey experiments.An aerial hyperspectral remote sensing image of Xiongan New Area was acquired using the visible and near-infrared imaging spectrometer designed by Shanghai Institute of Technical Physics, Chinese Academy of Sciences on October 2017. The total field of view angle of the spectrometer is 40.6°, the instantaneous field of view is 0.25 mrad, the effective push-scan pixel is 2834, and the maximum speed-to-height ratio is 0.04. The flight height is 2000 m, and the flight areas cover the Xiong County, An County, Rong County, and Baiyangdian Lake. The east-west length is 48 km, the north-south width is 27.5 km, and the total area is 1320 km². Twenty-one flight lines are found on the east-west direction, and Matiwan Village is located in the 10th and 11th flight lines. The flying weather is clear and cloudless, and the visibility condition is good. Radiation correction, geometric correction, and image mosaic and clipping were conducted before data classification.The spectral range of the aerial hyperspectral remote sensing image of Xiongan New Area (Matiwan Village) is 400—1000 nm, with 250 bands and a spatial resolution of 0.5 m. The image size is 3750 × 1580 pixels. The land cover types labeled here are 19, which are mainly cash crops.The aerial hyperspectral remote sensing image of Matiwan Village in Xiongan New Area was classified using random forest classification. The first three principal components of the spectrum and its corresponding eight spatial texture features and vegetation indices, such as normalized difference water index and normalized difference vegetation index were utilized. The total classification accuracy is 97%, and the kappa coefficient is 0.98. In accordance with the confusion matrix, the confusion of Robinia pseudoacacia, pear tree, and Acer complex is serious. This condition causes the low classification accuracy of Robinia pseudoacacia.An aerial hyperspectral remote sensing dataset of Xiongan New Area (Matiwan Village) with high spatial and spectral resolution was used in this study. The dataset was classified using random forest classification. The total classification accuracy is 97%. This finding shows that the dataset can provide good data support for hyperspectral classification research and can serve as reference for the design and demonstration of hyperspectral imaging spectrometer.