Urban landscape classification optimization method and device, equipment and medium

Abstract

The embodiment of the invention provides an urban landscape classification optimization method and device, equipment and a medium, and the method comprises the steps: S1, obtaining an urban landscaperemote sensing image, and recognizing a current land cover type based on the urban landscape remote sensing image; S2, obtaining a current spatial structure type corresponding to the urban landscape remote sensing image based on the current land cover type; S3, determining a current functional area type corresponding to the urban landscape remote sensing image based on the current spatial structure type; and S4, performing feedback adjustment on the current land cover type by utilizing the current functional area type to obtain a new current land cover type, and entering the step S2 until a preset stop condition is reached. According to the method, the identified land cover type is adjusted and identified again by utilizing the identified functional area type feedback, so that forward identification and feedback adjustment are combined, the identification result is more accurate, and landscapes in a city can be classified more accurately.

Description

technical field [0001] The invention relates to the technical field of machine identification, in particular to a method and device, device and medium for urban landscape classification optimization. Background technique [0002] Surface land cover and functional areas in remote sensing images form a hierarchical structure: each urban landscape can be divided into different functional areas; and each functional area is composed of different land cover features. This hierarchical structure expresses the relationship between land cover and functional areas, and this hierarchical structure is very important for optimal identification of the two categories. For the classification of functional areas, the category and spatial structure of land cover are the basic clues to identify the types of functional areas. For example, buildings, roads, vegetation and soil form a functional area, so according to their category proportion and spatial structure, the area can be classified and...

AI Technical Summary

Problems solved by technology

[0003] However, the classification of existing remote sensing images is not accurate enough, and sometimes manual correction is required, which greatly increases the difficulty and workload of map drawing, and also reduces the accuracy of maps

Images