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

A SAR image change detection method based on complex neural network

A technology of image change detection and neural network, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problem of low detection accuracy of SAR image change detection

Inactive Publication Date: 2018-12-28
XIDIAN UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a SAR image change detection method based on a complex neural network to solve the problem of low detection accuracy in SAR image change detection and the problem of two original images in change detection. Combination problem, constructing two image data as complex data to improve the quality of change detection in SAR images

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 SAR image change detection method based on complex neural network
  • A SAR image change detection method based on complex neural network
  • A SAR image change detection method based on complex neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] The invention provides a SAR image change detection method based on a complex neural network. Two original SAR gray images are input, and a preliminary difference map is obtained by a traditional method as a preliminary label; according to the preliminary label, two original SAR images are screened out through confidence detection. Part of the pixel blocks in the image are used as candidate training samples; a complex network including 3 layers of complex fully connected layers and 2 layers of complex batch normalization layers is constructed; part of the candidate training samples is selected according to a random ratio method to construct complex training samples, In this way, the complex number network is trained; the test complex number samples directly constructed from two original SAR images are tested by using the trained complex number network, and the final change detection result is obtained. The invention has the advantages of accurately distinguishing changed...

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 SAR image change detection method based on a complex neural network, which inputs two original SAR gray-scale images and uses a preliminary difference map obtained by a traditional method as a preliminary label. According to the preliminary tags, some pixel blocks in the two original images are selected as candidate training samples by confidence detection. A complex network is constructed, which consists of three layers of all connection layers and two layers of multiple batches of normalized layers. The complex training samples are selected from the candidate training samples according to the stochastic proportional method to train the complex network. The training complex network is used to test the test complex samples constructed directly from two original SAR images, and the final change detection results are obtained. The invention not only makes full use of the advantages of the traditional change detection result, but also displays the characteristicsof the original data, so that the neural network can better learn the relationship between the two images, thereby obtaining a better change detection result.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a SAR image change detection method based on a complex neural network. Background technique [0002] Change detection is an important technique to detect regional surface changes by analyzing two images taken at the same location at different times. It has been widely used in land cover change, environmental monitoring and urban sprawl assessment. Change detection is therefore gaining more and more attention in the remote sensing community. Since SAR sensors are independent of sunlight, cloud cover and weather conditions, SAR images are an ideal source for change detection tasks. However, change detection in SAR images is often more difficult than in optical images due to the presence of speckle noise. [0003] With Hinton's layer-by-layer unsupervised pre-training method proposed in 2006, deep learning has gradually attracted people's attention. In the I...

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
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/23G06F18/214
Inventor 刘红英王钟书尚凡华公茂果杨淑媛侯彪
Owner XIDIAN 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