Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-scale segmentation constrained remote sensing image semantic segmentation method

A multi-scale segmentation, remote sensing image technology, applied in the field of image processing, can solve the problem of unable to directly obtain the semantic information of closed areas, unable to preserve the accurate boundaries of ground objects, etc., and achieve the effect of high merging efficiency.

Pending Publication Date: 2019-08-13
SHANGHAI JIAO TONG UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-scale segmentation constrained remote sensing image semantic segmentation method
  • Multi-scale segmentation constrained remote sensing image semantic segmentation method
  • Multi-scale segmentation constrained remote sensing image semantic segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Such as figure 1 As shown, it is a remote sensing image semantic segmentation method with multi-scale segmentation constraints involved in this embodiment, including the following steps:

[0035] Step A. The scale of the same object in remote sensing images of different resolutions will also change. Therefore, when setting scale parameters for multi-scale segmentation, it is necessary to set appropriate scale parameters for remote sensing images of different resolutions based on past experience. Including start scale, end scale, and scale interval. The starting scale generally starts from scale 10, and if the size of the ground objects in the image is large, you can start from a larger scale. The termination scale is set reasonably based on the largest feature in the image. The scale interval is generally set to 10. Then set the segmentation parameters used to measure regional homogeneity for region merging, mainly including spectral factor and shape factor, and the ...

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

PUM

No PUM Login to View More

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...

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

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/34G06K9/62
CPCG06V10/267G06F18/25
Inventor 霍宏郑双朋鲍腾飞吕亮方涛
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products