Urban land function recognition method based on remote sensing picture and interest point data

A technology of urban functions and identification methods, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of people's activities and behaviors without considering the spatial relationship of ground objects, improve the ability of model similarity discrimination, and avoid manual selection. Bias and inefficiencies in features, effects of strong adaptive capacity
CN113111691AActive Publication Date: 2021-07-13SICHUAN UNIV
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
SICHUAN UNIV
Publication Date
2021-07-13

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The invention provides an urban land function recognition method based on remote sensing pictures and interest point data. A conventional urban functional area recognition method only aims at single remote sensing image data or social perception data, and neglects overall functional attribute information of an urban area to a certain extent. In order to solve the problem, a multi-mode urban land function recognition framework is provided. The method comprises the following steps: constructing a deep multi-channel residual neural network for urban remote sensing image recognition, and exploring spatial geographic features in a remote sensing image; secondly, frequency function density of interest point distribution of different functional areas of the city is researched, and function distribution characteristics of the city area are extracted based on metric learning; and finally, fusing two features of different dimensions in the heterogeneous feature fusion module, thereby further improving the urban land function recognition performance. Experiments prove that the method has good practicability and can be widely applied to recognition of urban functional areas.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the problem of image and text data recognition in the field of deep learning, in particular to a method for recognizing functions of urban land based on remote sensing pictures and point-of-interest data. Background technique

[0002] In recent years, the urbanization of countries in the world has developed rapidly. As an important part of urbanization, land use and land cover play an extremely important role in environmental protection, infrastructure construction and urban planning. Due to the development of urbanization and the impact of human activities, different urban areas often have complex urban land functions, such as commercial areas, residential areas, and industrial areas. The function and scope of an urban area not only depends on the government's planning and deployment, but also depends on people's actual way of life. The actual geographical distribution of urban functional areas is of great significance for s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More