Building contour extraction method and system, computer equipment and storage medium

Abstract

The invention relates to the technical field of image processing, and discloses a building contour extraction method and system, computer equipment and a storage medium, and the building contour extraction method comprises the steps: obtaining a to-be-processed image, inputting the to-be-processed image into a preset instance segmentation model, and obtaining a building mask and a building bounding box in the to-be-processed image; obtaining an image block of a target building according to the building bounding box, inputting the image block and a corresponding building mask into an image segmentation model to obtain a building pattern spot of the target building, and obtaining a contour pixel point position of the building pattern spot; detecting the main direction of the target building based on the image blocks of the target building, and performing boundary regularization processing on the building pattern spots of the target building based on the main direction to generate a building boundary extraction result; the method has the effect of improving the accuracy of extracting the boundary line of the building from the remote sensing image.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to a building contour extraction method, system, computer equipment and storage medium. Background technique [0002] At present, the common building contour extraction methods based on high-resolution remote sensing images are to first construct a certain type of feature rule set manually, and then use this feature rule set to build a model to extract buildings. Due to the large spectral heterogeneity in the spectral statistical characteristics of similar ground objects in high-resolution remote sensing images, the classification and extraction process is easily disturbed by noises such as shadows, roads, and vegetation, and the robustness of this type of method is not strong. Moreover, the boundary information of buildings cannot be effectively extracted. The method based on deep learning generally establishes a semantic segmentation model to extract buildi...

AI Technical Summary

Problems solved by technology

Due to the large spectral heterogeneity in the spectral statistical characteristics of similar ground objects in high-resolution remote sensing images, the classification and extraction process is easily disturbed by noise such as shadows, roads, and vegetation. The robustness of this type of method is not strong. Moreover, the boundary information of buildings cannot be extracted effectively. The method based on deep learning generally establishes a semantic segmentation model to extract buildings. Similarly, it cannot extract the boundaries of buildings very well.

[0003] In view of the above-mentioned related technologies, the inventor believes that there is a problem of large error in building outline extraction

Images