A multi-source typical land cover classification dataset of the Field Park in Wuhan (2020)

The dataset was collected using unmanned aerial vehicles (UAVs) equipped with a multispectral camera and a dual-light thermal infrared camera over the Feild Park in Wuhan. Data processing and annotation were conducted using ArcGIS and Labelme software. The geographical scope is around 114.01°E, 30.45°N. The specific areas include the Field Park and its surrounding areas in Wuhan, Hubei Province, China. The data volume is 334 MB. This dataset includes three types of data sources: visible light, thermal infrared, and five single-band multispectral data, with spatial resolutions of 0.0700 m, 0.2684 m, and 0.1540 m, respectively. It covers six typical land cover types: water bodies, vegetation, bare land, buildings, brick roads, and asphalt roads. In total, it contains a total of 612 image tiles and corresponding labels. The imagery provided in this dataset features both a high spatial resolution of 7 centimeters and contains rich spectral information in visible light, multispectral, and thermal infrared bands, enabling a more comprehensive description of land cover characteristics.