Multi-scale segmentation constrained remote sensing image semantic segmentation method

Abstract

The invention relates to a multi-scale segmentation constrained remote sensing image semantic segmentation method, which comprises the following steps: carrying out multi-scale region merging on a remote sensing image, carrying out fusion processing on a merging result to obtain a multi-scale segmentation result, and carrying out semantic prediction through a deep learning network to obtain a remote sensing image ground object accurate boundary and semantic information. According to the method, a multi-scale segmentation result is used as a constraint, so that on one hand, a remote sensing image ground object accurate boundary can be obtained; on the other hand, the semantic information of the closed area can be obtained, and the problems that the semantic information of the closed area cannot be directly obtained through a traditional multi-scale segmentation method and the accurate boundary of the ground object cannot be well reserved through a semantic segmentation method based on deep learning are solved.

Description

technical field [0001] The present invention relates to a technique in the field of image processing, in particular to a remote sensing image semantic segmentation method with multi-scale segmentation constraints. Background technique [0002] Remote sensing images generally contain various ground features of different sizes, and it is often impossible to simultaneously and completely extract ground features of multiple scales at a single scale. Multi-scale segmentation generally considers the characteristics of the spectrum, space, and texture of pixels, and divides remote sensing images from multiple scales to obtain many regions of different sizes and irregular boundaries. These regions generally have homogeneity inside and heterogeneity between adjacent regions. Multi-scale segmentation adopts the combination of region growth and region merging, and can obtain closed regions with a high degree of coincidence with the boundaries of ground objects. Although multi-scale s...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes a semantic segmentation method of remote sensing images constrained by multi-scale segmentation, using multi-scale segmentation results as constraints, on the one hand, it can obtain the accurate boundary of remote sensing image features; on the other hand, it can Obtain the semantic information of the closed area, solve the problem that the traditional multi-scale segmentation method cannot directly obtain the semantic information of the closed area, and the problem that the semantic segmentation method based on deep learning cannot preserve the accurate boundary of the ground object well

Images