Supervised classification method combining multi-spectral mixed pixel linear decomposition

A mixed pixel decomposition and mixed pixel technology, which is applied in the field of remote sensing image processing, can solve the problem that the classification effect of small objects and linear objects is not outstanding, and achieve the effect of reducing selection and improving work efficiency.
CN112633374APending Publication Date: 2021-04-09JIANGSU OCEAN UNIV
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JIANGSU OCEAN UNIV
Publication Date
2021-04-09

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

Provided is a supervised classification method combining multi-spectral mixed pixel linear decomposition. The method comprises the following steps: selecting a research area, and obtaining image data; performing image preprocessing on the image data; carrying out mixed pixel linear decomposition on the preprocessed image; collecting training samples to supervise and classify the images after mixed pixel decomposition; evaluating classification accuracy. According to the method, under the condition that the precision is guaranteed, selection of training samples is reduced, fine and linear ground objects are effectively separated, the working efficiency is improved, and a reference effect is achieved on recognition and analysis of the fine ground objects to a certain extent.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of remote sensing image processing, in particular to a supervised classification method combined with linear decomposition of multispectral mixed pixels. Background technique

[0002] Supervised classification methods are usually used to classify multispectral remote sensing images, such as support vector machine method, maximum likelihood method, minimum distance method, etc. does not stand out. Contents of the invention

[0003] The technical problem to be solved by the present invention is to provide a linear decomposition of combined multi-spectral mixed pixels that can classify multi-spectral remote sensing images and has an outstanding classification effect on small and linear features. supervised classification method.

[0004] The technical problem to be solved by the present invention is achieved through the following technical solutions. The invention is a supervised classification method comb...

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