Building sampling and labeling dataset of UAV images in rural China

As an agricultural country like China, timely and accurate extraction of rural buildings from high-resolution remote sensing images is crucial to rural development and rural planning. With the recent advancements of computer vision and computing capabilities, deep learning has achieved considerable achievements in many applications such as building extraction due to its automatic learning features and strong applicability.

Deep learning usually requires large amounts of training data. At present, the datasets commonly used in deep learning to identify buildings are mainly international open-source building datasets, including Massachusetts, INRIA, WHU, etc. These datasets are based on foreign buildings, lacking sampling data of buildings that are open-source, high-precision, wide-covered, and suitable for the architectural style of rural areas in China.