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

Remote sensing image change detection method based on sparse autoencoder

A sparse automatic coding, remote sensing image technology, applied in the computer field, can solve the problems of poor change detection results, inability to use pixel features, and complicated process of changing methods, and achieve change detection results with rich details, high accuracy, and noise effects. small effect

Active Publication Date: 2018-03-27
XIDIAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the difference map is processed in a variety of ways, which makes the process of changing the method more complicated.
However, the disadvantage of this method is that it directly processes the luminance value of the pixel in the difference image, and the unsupervised classification of the luminance value of the pixel does not take advantage of the characteristics of the pixel, and the details are seriously lost. bad

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 sparse autoencoder
  • Remote sensing image change detection method based on sparse autoencoder
  • Remote sensing image change detection method based on sparse autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] Refer to attached figure 1 , to further describe the implementation steps of the present invention.

[0034] Step 1, input image.

[0035] Input two registered remote sensing images of the same area at different times.

[0036] Step 2, Construct the difference map.

[0037] According to the following formula, the difference map of two remote sensing images that have been registered at different times in the same area is constructed:

[0038]

[0039] Among them, X represents the difference map of two remote sensing images of the same area that have been registered at different times, |·| represents the absolute value operation, log represents the logarithmic operation with base 10, and X 1 and X 2 Respectively represent two registered remote sensing images of the same area at different times.

[0040] Step 3, train the sparse autoencoder.

[0041] Set ...

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 sparse automatic encoding machine, mainly aiming at that in the prior art, there are many missing and wrongly detected pixels in the change detection results, and the direct processing of the difference map cannot use the difference map to imply information shortcomings. The implementation steps are: (1) read in the image; (2) construct the difference map; (3) train the sparse autoencoder; (4) extract features; (5) perform fuzzy clustering on the features; ; (7) output the change detection result. The invention first uses a sparse automatic coding machine to extract a difference map, and then uses the extracted features to detect changes in remote sensing images, thereby reducing the number of missing and false detections of pixels in the change detection results and improving the accuracy of change detection.

Description

technical field [0001] The invention belongs to the technical field of computers, and further relates to a remote sensing image change detection method based on a sparse automatic encoding machine in the technical field of image processing. The invention obtains difference images from two remote sensing images of different time phases, uses a sparse automatic encoding machine to extract features of the difference images, and then classifies the features to complete the change detection of the remote sensing images. The invention can be applied to the change detection of the remote sensing image of the disaster area during natural disaster detection and rescue, urban development planning, geological research and other fields, and completes the detection of the change of the remote sensing image in a specific area. Background technique [0002] Change detection is to detect the change information of the ground objects in the area over time by analyzing the remote sensing image...

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 Patents(China)
IPC IPC(8): G06T7/33G06K9/46G06K9/62
CPCG06T2207/10032G06T2207/20081G06V10/422G06V10/513G06V10/751G06F18/2411
Inventor 公茂果赵秋楠马晶晶刘嘉李豪马文萍牟树根杨海伦
Owner XIDIAN UNIV