Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for detecting image changing by combining deep convolutional neural network with morphology

A neural network and deep convolution technology, which is applied in the field of deep convolutional neural network combined with morphological detection of image changes, can solve the problems of low detection accuracy, difficult processing, and large noise, and achieve high detection accuracy, simple method and high accuracy. Effects of Sex and Robustness

Active Publication Date: 2018-11-13
NANJING INST OF TECH +1
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: The purpose of the present invention is to provide a method for detecting image changes with a deep convolutional neural network combined with morphology, which solves the problems of large noise, difficult processing, low detection accuracy, and poor visual effects in existing methods for detecting image changes

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
  • Method for detecting image changing by combining deep convolutional neural network with morphology
  • Method for detecting image changing by combining deep convolutional neural network with morphology
  • Method for detecting image changing by combining deep convolutional neural network with morphology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described below in conjunction with the accompanying drawings.

[0021] Such as figure 1 As shown, the method of combining deep convolutional neural network with morphology to detect image changes includes the following steps:

[0022] (1) Segment the registered remote sensing images of 2015 and 2017. Since the input image size of the improved SegNet network is an 8-channel image of 224×224, the images of 2015 and 2017 are respectively divided into 224×224 size. In order to make reasonable use of data resources, the original image is segmented by partial overlapping sliding, which can increase the amount of training data after segmentation of small remote sensing images. For example, when splitting, the coordinates of the upper left corner of the first horizontal image are (0,0), the second is (112,0), the third is (224,0) and so on, and the vertical coordinates of the upper corner are ( 0,112), (0,224) and so on. When the sampl...

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 method for detecting image changing by combining deep convolutional neural network with morphology. The method comprises the following steps: segmenting registered remote sensing images of different time phases; rotating and mirroring the segmented images, and combining the remote sensing images at the corresponding locations of different time phases into a 8-channel image; inputting the obtained 8-channel image into a SegNet network model to train, and outputting a 2-channel image; adopting and operating the image so as to perform hole filling on the image, and thenremoving noise information by adopting a corrosion operation so as to obtain an image processing model; segmenting the to-be-detected remote sensing images and then inputting into the model of the previous step to process, and outputting the images; combining the output images into the size of the original to-be-detected remote sensing image, thereby accomplishing the image change detection. By adopting the method of combining the deep convolutional neural network with the morphology, the detection precision is high, the noise is effectively removed, the method is simple, the detection on thebuilding change has high accuracy and robustness.

Description

technical field [0001] The invention relates to an image change detection method, in particular to a method for detecting image changes using a deep convolutional neural network combined with morphology. Background technique [0002] In recent years, with the rapid development of computer technology and artificial intelligence, land supervision has also become increasingly intelligent. The supervision of land resources is beneficial to the country's rational distribution and utilization of land resources. A major problem in land supervision is that the land resources are extremely large, and it takes a lot of manpower to conduct on-the-spot inspections and investigations in real life. Using remote sensing images to compare images in different phases can effectively find out the differences in changes in buildings in different phases, thereby realizing effective supervision of land resources. However, for remote sensing images of large areas, it takes a lot of human resourc...

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): G06T7/00G06T7/10G06T7/30G06N3/04
CPCG06T7/0002G06T7/10G06T7/30G06T2207/30181G06T2207/20084G06T2207/20081G06T2207/10032G06N3/045
Inventor 徐梦溪吴晓彬朱斌王鑫石爱业陈哲韩磊
Owner NANJING INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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