Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Heterogeneous remote sensing image change detection method based on multi-scale self-coding

A remote sensing image and change detection technology, which is applied in the field of heterogeneous remote sensing image change detection, can solve problems such as the inability to obtain SAR images, the difficulty of obtaining difference maps, and the difficulty in computing heterogeneous images

Active Publication Date: 2022-03-11
XIAN UNIV OF TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In such cases, pre-disaster SAR images are usually not available, nor are high-quality optical images immediately after the disaster
However, due to the difficulty in computing the pixel difference between heterogeneous images, there are few studies based on heterogeneous images
A major challenge in dealing with heterogeneous images is the different feature representations of ground objects in different types of images, which increases the difficulty of obtaining difference maps

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
  • Heterogeneous remote sensing image change detection method based on multi-scale self-coding
  • Heterogeneous remote sensing image change detection method based on multi-scale self-coding
  • Heterogeneous remote sensing image change detection method based on multi-scale self-coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0144] Effect of the present invention can be specified by simulation experiment:

[0145] 1. Experimental conditions

[0146] The microcomputer CPU used in the experiment is Intel Pentium 43.0GHz memory 16GB, and the programming platform is Python. The SAR images and optical images used in the experiment are the Tianhe airport dataset and the Yellow River dataset.

[0147] 2. Experimental content

[0148] The first is the preprocessing stage. Firstly, normalize the registered pair of SAR images and optical remote sensing images to ensure that the value of each pixel is between [-1,1]. The second is the stage of generating the difference map, put the obtained normalized image into the multi-scale neural network for training, and use the trained neural network to generate the difference map. Finally, it is the stage of analyzing the difference map to generate the change map, and the final change map is obtained through the threshold method.

[0149] 3. Experimental results ...

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 heterogeneous remote sensing image change detection method based on multi-scale self-coding. The method specifically comprises the following steps: step 1, preprocessing an image; 2, putting the image preprocessed in the step 1 into a multi-scale neural network for training, and generating a difference graph by using the trained neural network; and step 3, analyzing the difference image generated in the step 2 by using a threshold analysis algorithm to obtain a changed image. By adopting the method, the change area in the heterogeneous remote sensing image can be accurately detected.

Description

technical field [0001] The invention belongs to the field of heterogeneous remote sensing image change detection, and relates to a heterogeneous remote sensing image change detection method based on multi-scale self-encoding. Background technique [0002] Change detection is an increasingly important technique that identifies changing and unchanged regions by analyzing a set of images acquired at different times in the same geographic location. Before detection, image preprocessing such as denoising and co-registration is required. Denoising is to reduce the interference of noise and co-register the image so that pixels with the same index correspond to the same geographic location. Using these preprocessed images, the change information is obtained through the process of comparison and hypothesis testing, which is the focus of the analysis. [0003] Currently, different satellite platforms can provide various types of remote sensing images, including synthetic aperture ra...

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): G06T7/00G06T7/33G06V20/13G06V10/40G06V10/82G06N3/08
CPCG06T7/0002G06T7/33G06N3/08G06T2207/10032G06T2207/10044G06T2207/20081G06T2207/20084
Inventor 贾萌张诚高宇轩张亚文赵秦
Owner XIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com