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

A siamese convolutional network-based method for detecting changes in urban features in remote sensing images

A change detection and convolutional network technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of not being able to increase the diversity of samples, and the difficulty in changing the detection field, so as to overcome the spatial information of lost images , avoid cumbersome steps, improve the effect of accuracy and reliability

Active Publication Date: 2021-05-04
WUHAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to apply this technology to the field of change detection.
The reason is that two or more remote sensing images acquired at different time points in the same geographical area have great differences due to different shooting times, climate conditions, light conditions, and shooting angles. Simply using grayscale transformation, rotation, arbitrary cropping, and color Operations such as dithering cannot increase sample diversity

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
  • A siamese convolutional network-based method for detecting changes in urban features in remote sensing images
  • A siamese convolutional network-based method for detecting changes in urban features in remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0034] see figure 1 and figure 2 , a Siamese convolutional network-based remote sensing image urban feature change detection technology provided by an embodiment of the present invention includes the following steps:

[0035] Step 1: Select an initial sample set in the registered two-temporal urban image;

[0036] The specific implementation of the selection of the initial sample set in the embodiment of the present invention includes the following sub-steps:

[0037] Step 1.1: Input images of two temporal phases. In the present invention, the research is...

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 present invention provides a method for detecting changes in urban features in remote sensing images based on Siamese convolutional networks. Select the initial sample set, set the twin convolutional neural network SCNN, train the twin convolutional neural network SCNN based on the initial sample set, and use data enhancement technology to expand the initial sample set; The network SCNN is trained to obtain the trained SCNN model to realize the change detection of urban features. The invention realizes the expansion of samples through data enhancement technology, and designs a Siamese convolutional neural network, which avoids the cumbersome steps of manually designing features in the traditional change detection method, and realizes "end-to-end" operation; fully consider The spatial properties of imagery improve the accuracy and reliability of change detection.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image change detection, in particular to a change detection method of urban ground objects. Background technique [0002] Change detection is the process of using two or more remote sensing images acquired at different time points in the same geographical area to discover the changes that have occurred on the earth's surface. Change detection is an important means to maintain the current situation of geographic information data, and it is an important research direction in the field of remote sensing applications. In recent years, my country's urbanization process has been accelerating, and urban features are changing with each passing day. The change detection of urban ground features plays an important role in grasping the law of urban change, updating urban maps, assisting urban planning and design, and government decision-making. [0003] Traditional change detection methods need to m...

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): G06K9/00G06K9/34G06N3/04G06N3/08
CPCG06N3/08G06V20/39G06V10/267G06N3/045
Inventor 刘异闫利庄姊琪呙维庞超
Owner WUHAN UNIV
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