Change detection method for remote sensing images based on multi-resolution nmf and treelet fusion

A remote sensing image and change detection technology, applied in the field of image processing, can solve problems such as being easily affected by noise, missed detection or many false alarms, and cannot handle nonlinear related data well, so as to achieve reasonable data interpretation and improve accuracy , the effect of suppressing adverse effects

CN102831598BInactive Publication Date: 2014-10-01XIDIAN UNIV
2 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2014-10-01
Estimated Expiration
Not applicable · inactive patent

Smart Images

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

Abstract

The invention discloses a remote sensing image change detecting method with the combination of multi-resolution NMF (non-negative matrix factorization) and Treelet, aiming at solving the problem that the balance is often hard to make when image details and smooth regions are considered in terms of single resolution, and also aiming at keeping both the detailed information of an image and the information of a smooth region in the image change detection. The implementation process of the method is as follows: inputting two time-phase images, and constructing a differential image and carrying out median filter by using a direct differential value; subsequently extracting images of different resolution by using a NMF algorithm; obtaining thresholds of the filtered differential image and images of different resolution respectively; combining threshold images by using a Treelet algorithm; and dividing the combined image by using a region growing method so as to obtain a final change detection result. With the adoption of the method, the problem that an adjacent region structure of the image is likely to be affected by independent noise points is solved, both the detailed information of the image and the information of the smooth region can be kept, the independent noise can be eliminated, the change detection precision is improved, and so that the method can be used in fields of disaster monitoring, land utilization, agricultural investigation and the like.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of image processing, relates to remote sensing image change detection, mainly relates to multi-resolution non-negative matrix factorization (Non-negative Matrix Factorization, NMF) and Treelet fusion remote sensing image change detection, specifically a multi-resolution NMF and A method for change detection in remote sensing images based on Treelet fusion. It is used to detect the changing regions of remote sensing images. Background technique

[0002] Remote sensing image change detection can obtain the dynamic development and change information of ground objects by analyzing the differences in spectral characteristics or spatial structure characteristics of remote sensing images in different time periods in the same area. The change detection of remote sensing images has been widely used, such as resource monitoring of land, forest, grassland, etc., crop yield estimation and pest monitoring, map data corr...

Examples

Embodiment 1

[0062] The present invention is a remote sensing image change detection method that combines multi-resolution NMF and Treelet. The experimental simulation environment is: MATLAB R2010a, CPU Inter Core2 1.80GHz, memory 2G, Windows XP Professional, refer to figure 1 , the remote sensing image change detection method includes the following steps:

[0063] (1) Take two registered remote sensing images of size P×Q acquired at different times in the same area, and the phase 1 image is X 1 ={X 1 (p,q), 1≤p≤P, 1≤q ≤Q}, see figure 2 (a) and image 3 (a), phase 2 image is X 2 ={X 2 (p,q), 1≤p≤P, 1≤q≤Q}, see figure 2 (b) and image 3 (b), where X 1 (p,q) and X 2 (p, q) are the gray value of the pixel at the spatial position (p, q) of the phase 1 image and the phase 2 image, respectively. Subtract the gray value of the pixel corresponding to the spatial position of the input two-temporal remote sensing image to obtain the absolute value, and obtain a difference image X’ D (X' D...

Embodiment 2

[0098] The remote sensing image change detection method of multi-resolution NMF and Treelet fusion is the same as embodiment 1, wherein in step (3), the calculation for threshold is:

[0099] First, estimate the filtered difference image X D noise standard deviation

[0100] σ X D = Median ( | X D | ) / 0.6745 - - - ( 8 )

[0101] Among them, Median(·) represents the operation of taking the median value.

[0102] Select threshold If the gray value of the image is less than the threshold T x , then set the value to 0, if the gray value of the image is greater than the threshold T x , the value is retained. Obtain an image Y in which the gray value of the background pixel is 0 and t...

Embodiment 3

[0111] The remote sensing image change detection method of multi-resolution NMF and Treelet fusion is the same as embodiment 1-2, wherein the value of the maximum number of iterations e in step 2b) is 50, and the value of stop precision ε is 10 -4 , the value of the current iteration number b is 50, in this case, the calculation speed is faster, and the detection accuracy is slightly lower.

[0112] In addition, the threshold T in step (5) R A value of 20 can also get better change detection results.