Unlock instant, AI-driven research and patent intelligence for your innovation.

NSCT (nonsubsampled contourlet transform)-based active contour remote sensing image segmentation method

A technology for remote sensing images and active contours, applied in the field of remote sensing image processing, can solve problems such as high computational complexity, and achieve the effect of strong robustness and improved segmentation accuracy.

Inactive Publication Date: 2016-06-01
LIAONING NORMAL UNIVERSITY
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since only the spatial features of the image are used, the active contour model also contains a lot of irrelevant information, resulting in high computational complexity

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
  • NSCT (nonsubsampled contourlet transform)-based active contour remote sensing image segmentation method
  • NSCT (nonsubsampled contourlet transform)-based active contour remote sensing image segmentation method
  • NSCT (nonsubsampled contourlet transform)-based active contour remote sensing image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Such as figure 1 Shown: the embodiment of the present invention carries out as follows:

[0024] Convention: I refers to the remote sensing image to be segmented; the number of decomposition layers of NSCT transformation is n; c is the evolution curve of the active contour model; and is a positive weighting coefficient; For a piecewise constant function:

[0025] ,

[0026] in and Indicates a constant value related to the contour curve c, taking the average gray value inside and outside the contour curve;

[0027] a. Obtain the remote sensing image to be segmented and initialize the variables;

[0028] b. Perform n-layer NSCT transformation of image I,

[0029] c. For each transformed layer i (i=1,2,...n), obtain the low-frequency component, high-frequency component and image i, retain the high-frequency subband coefficients of each layer, and obtain the multi-resolution of the remote sensing image to be segmented means I={I 1 , I 2 ..., I i ,...,I n...

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 discloses an NSCT (nonsubsampled contourlet transform)-based active contour remote sensing image segmentation method. The active contour remote sensing image segmentation method comprises the following steps that: firstly, an image to be segmented is expressed with multiresolution through the non-subsampled contourlet transfor; secondly, a probability model of a multiresolution coefficient is established; and finally, integration operation of the multiresolution coefficient (singularity information) is carried out by utilizing a region-based active contour model, so that the purpose of image segmentation is achieved. The experimental results show that the active contour remote sensing image segmentation method can nicely carry out remote sensing image segmentation, comprehensiveness of a segmentation model is ensured, and specific detail information of the remote sensing image can be segmented.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to an NSCT-based active contour remote sensing image segmentation method that can not only ensure the globality of segmented remote sensing images, but also segment remote sensing image detail information and reduce computational complexity. Background technique [0002] Due to the characteristics of large amount of data, relatively low spatial resolution, complex and diverse shapes and fine structures, and rich types of ground objects, remote sensing images have brought great difficulties to the segmentation of remote sensing images. Currently, multi-resolution analysis methods and active contour models are popular image segmentation methods. The image segmentation technology of multi-resolution analysis is to transform the input image first, and then perform statistical analysis on the transformed coefficients according to certain rules; finally, the inverse transfor...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00
CPCG06T2207/10032G06T2207/20116
Inventor 方玲玲王相海
Owner LIAONING NORMAL UNIVERSITY