A rapid building density survey method based on improved unet

How to rapidly obtain building density information in a large range is a key problem for architecture and planning. This is because architectural design or urban planning is not isolated, and the environment of the building is influenced by the distribution of other buildings in a larger area. For areas where building density data are not readily available, the current methods to estimate building density are more or less inadequate. For example, the manual survey method is relatively slow and expensive, the traditional satellite image processing method is not very accurate or needs to purchase high-precision multispectral remote sensing image from satellite companies. Based on the deep neural network, this paper proposes a method to quickly extract large-scale building density information by using open satellite images platforms such as Baidu map, Google Earth, etc., and optimizes the application in the field of building and planning. Compared with the traditional method, it has the advantages of less time and money, higher precision, and can provide data support for architectural design and regional planning rapidly and conveniently.