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

A high-resolution visible light image target change detection method

A high-resolution and change detection technology, applied in the field of high-resolution visible light image target change detection, can solve the problem of high target false detection rate and achieve the effect of reducing target false detection rate

Inactive Publication Date: 2017-07-07
ZHONGBEI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of high target false detection rate caused by direct global detection in the existing method, the present invention proposes a new method of target change detection based on region selection

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 high-resolution visible light image target change detection method
  • A high-resolution visible light image target change detection method
  • A high-resolution visible light image target change detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] refer to figure 1 The flow chart of the experiment is carried out by taking a set of high-resolution visible light images as an example. The angle is about 70 degrees, the size of each image is 800×600, and the resolution is 50cm. After strict registration, there is an obvious changing target and shadow changes caused by light intensity and angle. The specific implementation steps are as follows:

[0040] (1): Input the image I before the change obtained in the same area and at different times 1 and the changed image I 2 , figure 2 is the pre-change image I of an input image instance 1 and the changed image I 2 ;

[0041] (2): For image I 1 , I 2 The image is processed by the overall variational algorithm to obtain the structural image I′ that filters out the noise and fine texture of the image 1 , I' 2 , the overall variational algorithm model adopted is as formula (3):

[0042]

[0043] Among them, E represents the energy functional, I is the input imag...

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 belongs to the technical field of image variation detection, particularly relates to a high-resolution visible light image target change detection method, and mainly solves the problem of high target false detection rate caused by direct global detection in an existing method. The high-resolution visible light image target change detection method comprises the following steps of: (1): inputting an image I1 and an image I2; (2): processing the images I1 and I2 to obtain structural images I'1 and I'2; (3): dividing the images I1, I2, I'1 and I'2 into square blocks; (4): calculating the entropy difference between the same positions of the divided images I'1 and I'2; (5): calculating the structural similarity between the same positions of the divided I1 and I2; (6): judging the entropy difference and the structural similarity according to respective judgment conditions respectively, and determining image blocks with change targets; (7): calculating a log-ratio difference chart and a mean-ratio difference chart of the image blocks, and fusing the two images to obtain a fusion difference chart; (8): processing the fusion difference chart to obtain a final change target image; and (9): storing and outputting the final change target image.

Description

technical field [0001] The invention belongs to the technical field of image change detection, and in particular relates to a high-resolution visible light image target change detection method. Background technique [0002] Generally speaking, the target change refers to the appearance or disappearance of the whole or part of the target object in a specific scene. High-resolution visible light images have become an important object because of their advantages in reflecting the details of the surface on a small spatial scale. Sources of earth observation information. Using change detection technology to extract target change information from images is an important part of processing high-resolution visible light images, and has been widely used in target detection, situational awareness, damage assessment, etc. During change detection, the change of shadow in the image will lead to regional changes in the gray value of each pixel. Traditional change detection methods directl...

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): G06T7/00G06T7/11G06T7/136G06T7/155
CPCG06T7/0002G06T2207/20021G06T2207/20221
Inventor 杨风暴张雷刘冰清李大威王肖霞董安然蔺素珍
Owner ZHONGBEI 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

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