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

Remote-sensing image change detection method based on safety semi-supervised support vector machine

A technology of support vector machine and remote sensing image, applied in the field of multispectral remote sensing image change detection, which can solve the problems of difficulty in determining the decision plane, promotion performance and classification accuracy decline.

Inactive Publication Date: 2014-01-01
HOHAI UNIV +1
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The disadvantage of S3VM for change detection of remote sensing images is: when the classification decision plane generated by learning is not unique, since S3VM chooses one of many decision planes to classify difference images, its generalization performance and classification accuracy there is a risk of falling
In addition, it is also difficult to determine which decision plane is optimal without further prior information to distinguish these decision planes

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
  • Remote-sensing image change detection method based on safety semi-supervised support vector machine
  • Remote-sensing image change detection method based on safety semi-supervised support vector machine
  • Remote-sensing image change detection method based on safety semi-supervised support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0030] like Figure 1-2 As shown in , the remote sensing image change detection method based on secure semi-supervised support vector machine includes the following steps:

[0031] Step 1 Input two multispectral images with different time phases.

[0032] Step 2 construct difference image

[0033]The construction of the difference image can be divided into the following steps. First, the two multispectral remote sensing image data X obtained through step 1 1 , X 2 , respectively carry out PCA ...

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 a remote-sensing image change detection method based on a safety semi-supervised support vector machine. The method includes two steps: firstly, different images are formed in the mode that principal component analysis (PCA) conversion is combined with a correlation coefficient fusing method, and secondly, dichotomy is carried out on the different images through an S4VM, and change detection of multispectral remote-sensing images is achieved. Classification precision of the different images of the multidate remote-sensing images can be improved through the S4VM, and accordingly accuracy of change detection is improved.

Description

technical field [0001] The invention relates to a method for detecting changes in multispectral remote sensing images, in particular to a method for detecting changes in multispectral remote sensing images based on a secure semi-supervised support vector machine (S4VM). The problem belongs to the technical field of remote sensing image processing. Background technique [0002] The change detection of remote sensing images is to identify the state change process of the observed objects or phenomena based on the remote sensing images of different time phases in the same area. It has been widely used in resource management and planning, environmental protection and many other fields, and provides scientific decision-making basis for relevant departments. The current remote sensing image change detection methods mainly include: algebraic method, transformation method, classification comparison method, advanced model method, GIS integration method, visual analysis method and oth...

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): G06T7/00G06T5/40
Inventor 石爱业夏晨阳申邵洪吴国宝程学军文雄飞陈鹏霄
Owner HOHAI UNIV