Remote sensing image building accurate segmentation method

Abstract

The invention discloses a remote sensing image building accurate segmentation method. The method comprises the following steps: constructing a building extraction network comprising a feature extraction module, a cavity convolution module, an attention module, an up-sampling module and a convolution prediction module; based on the training sample set, adopting a multi-scale composite loss function combining Dice Loss and BCE Loss to train the constructed building extraction network; and inputting a remote sensing image to be extracted into the trained building extraction network to obtain a building extraction result. The method has the remarkable effects that the feature learning and generalization ability is high; the network is low in complexity and easy to train; and the building extraction precision is high.

Description

technical field

[0001] The invention relates to the technical field of automatic extraction of remote sensing image information, in particular to a method for accurately segmenting remote sensing image buildings. Background technique

[0002] Building extraction is a classic problem in the field of automatic extraction of remote sensing image information. Its main purpose is to identify and extract building areas in remote sensing images. The results of building extraction are widely used in many fields, such as military reconnaissance, environmental protection, cartography and geographic analysis, etc. Therefore, building extraction has important research value.

[0003] Most of the traditional methods use recognition algorithms based on the linear features of building edges. This type of method has the advantages of simplicity and high efficiency, but has defects such as low recognition rate and many errors. Such methods often cause misjudgment of building shadows, and l...

Images