Method for recognizing building based on deep learning algorithm

Abstract

The invention discloses a method for recognizing a building based on a deep learning algorithm, and the method comprises the steps: a remote sensing image containing the building is obtained, the preprocessing of the image is carried out, and a processed satellite image map with a coordinate system is obtained; specific classification is carried out according to specific features of the ground features needing intelligent identification, and table records are made; according to the previously made classification, sample label data checking of each sample is carried out, and various sample databases are established; building extraction is carried out by using a deep learning algorithm; and precision verification is performed on the building extraction result by using the confusion matrix. According to the invention, intelligent interpretation and extraction of buildings are carried out on remote sensing images by using a deep learning method, so that full-intelligent accurate recognition and interpretation without manual intervention are realized, and the purpose of saving time and labor is achieved; the obtained building remote sensing image and the sample of each building meet a unified spectral feature, texture feature and spatial feature relationship; and the result precision of the deep learning extraction algorithm is more accurate.

Description

technical field [0001] The invention belongs to the technical field of intelligent interpretation of remote sensing images, and in particular relates to a method for identifying buildings based on a deep learning algorithm. Background technique [0002] In recent years, with the continuous expansion of cities, urban land use, spatial planning, infrastructure construction, monitoring and evaluation of urban environmental pollution, and spatialization of urban population data have all raised various problems for urban managers. As the most important part of the city, various buildings are the targets that we most need to accurately detect and manage. However, with the acceleration of the urbanization process, the number and density of buildings in the city are increasing, and timely and accurate realization of the generation or update of building information in two-dimensional or three-dimensional urban space is an inevitable requirement for the construction of "smart cities"....

AI Technical Summary

Problems solved by technology

However, these methods often require more time and greater cost, and are far from meeting the requirements of high efficiency and low cost in actual work.

Images