CN107316296A - A kind of method for detecting change of remote sensing image and device based on logarithmic transformation - Google Patents
A kind of method for detecting change of remote sensing image and device based on logarithmic transformation Download PDFInfo
- Publication number
- CN107316296A CN107316296A CN201710537712.0A CN201710537712A CN107316296A CN 107316296 A CN107316296 A CN 107316296A CN 201710537712 A CN201710537712 A CN 201710537712A CN 107316296 A CN107316296 A CN 107316296A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- differential image
- sensing images
- differential
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method for detecting change of remote sensing image and device based on logarithmic transformation, it is related to technical field of image processing, main purpose is that the testing result performance indications that the existing non-supervisory image change detection method of solution is changed detection to remote sensing images are still relatively low, and then causes the problem of Remote Sensing Imagery Change Detection accuracy is relatively low.Technical scheme includes:The first remote sensing images and the second remote sensing images are obtained, first remote sensing images and the second remote sensing images are that two different phases distinguish corresponding remote sensing images;Preset first function and preset second function are utilized respectively, according to first remote sensing images and second remote sensing images, the first differential image and the second differential image is calculated;According to first differential image and second differential image, final differential image is calculated, the final differential image is the region of variation image between the described two different phases of expression.It is mainly used in the detection in two phase Remote Sensing Imagery Change regions.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of Remote Sensing Imagery Change Detection based on logarithmic transformation
Method and device.
Background technology
With developing rapidly for remote sensing technology, remote sensing images are used widely in multiple fields, such as soil profit
With monitoring, forest monitoring, city monitoring and Natural Disaster Evaluation analysis etc..The change detection of remote sensing images refers to according to same
Area is not in the same time, and two width or several remote sensing images of acquisition determine and analyzed the change information of this area's earth's surface.Usual feelings
Under condition, remote sensing images are changed with the method for detection can be divided into two classes, i.e. supervisory detection method and non-supervisory detection method.
Wherein, supervisory detection method refers to need to utilize classifier training sample, then according to the pattern detection remote sensing images of training
The method of region of variation;It is non-to subtract the method that rough detection method refers to directly detect two width or several remote sensing images.But
Because supervisory detection method needs to obtain real reference data, cost is higher, so that non-supervisory detection method is in reality
It is more universal in.
At present, when carrying out Remote Sensing Imagery Change Detection using non-supervisory detection method, data fusion and mould can be passed through
The non-supervisory image change detection method of cluster is pasted, or is examined by PPB denoisings and the K-means non-supervisory image change clustered
Method of determining and calculating etc., although improve the precision of remote sensing images testing result, but the performance indications of testing result are still relatively low, and then lead
Cause Remote Sensing Imagery Change Detection accuracy relatively low.
The content of the invention
In view of the above problems, it is proposed that the present invention is to provide a kind of Remote Sensing Imagery Change Detection side based on logarithmic transformation
Method and device, main purpose are to solve the inspection that existing non-supervisory image change detection method is changed detection to remote sensing images
Survey result performance indications still relatively low, and then cause the problem of Remote Sensing Imagery Change Detection accuracy is relatively low.
A kind of method for detecting change of remote sensing image based on logarithmic transformation provided by above-mentioned technical proposal, the present invention,
Including:
Obtain the first remote sensing images and the second remote sensing images;
Preset first function and preset second function are utilized respectively, according to first remote sensing images and second remote sensing
Image, calculates the first differential image and the second differential image;
According to first differential image and second differential image, final differential image is calculated.
A kind of Remote Sensing Imagery Change Detection device based on logarithmic transformation provided by above-mentioned technical proposal, the present invention,
Including:
Acquiring unit, for obtaining the first remote sensing images and the second remote sensing images;
Computing unit, for being utilized respectively preset first function and preset second function, according to first remote sensing images
With second remote sensing images, the first differential image and the second differential image are calculated;
The computing unit, is additionally operable to according to first differential image and second differential image, calculates final poor
Different image.
A kind of method for detecting change of remote sensing image and device based on logarithmic transformation provided in an embodiment of the present invention, it is and existing
Detection be changed to remote sensing images by non-supervisory image change detection method compared, the embodiment of the present invention is same by obtaining
The different phases in one two, area distinguish corresponding remote sensing images, and according to the two width remote sensing images got, it is preset using two
Function is calculated respectively obtains two different differential images, and final disparity map is calculated further according to two obtained differential images
Picture, improves the performance indications of testing result, and then improves the accuracy of Remote Sensing Imagery Change Detection.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings:
Fig. 1 shows a kind of flow for method for detecting change of remote sensing image based on logarithmic transformation that inventive embodiments are provided
Figure;
Fig. 2 shows the stream for another method for detecting change of remote sensing image based on logarithmic transformation that inventive embodiments are provided
Cheng Tu;
Fig. 3 shows a kind of square frame for Remote Sensing Imagery Change Detection device based on logarithmic transformation that inventive embodiments are provided
Figure;
Fig. 4 shows the side for another Remote Sensing Imagery Change Detection device based on logarithmic transformation that inventive embodiments are provided
Block diagram.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
The embodiment of the present invention provides a kind of method for detecting change of remote sensing image based on logarithmic transformation, as shown in figure 1, described
Method includes:
101st, the first remote sensing images and the second remote sensing images are obtained.
Wherein, first remote sensing images and the second remote sensing images are that the different phase difference in areal two are corresponding distant
Feel image, and the remote sensing images can be SAR (Synthetic Aperture Radar, synthetic aperture radar) image.
For example, it is that SAR images of the regional A in phase 1 is X to get the first remote sensing images1, X1={ X1(i, j), 1 < i
< m, 1 < j < n }, it is that SAR images of the regional A in phase 2 is X to get the second remote sensing images2, X2={ X2(i, j), 1 < i
< m, 1 < j < n }, X1And X2It is the SAR image of m pixels × n-pixel.
102nd, preset first function and preset second function are utilized respectively, according to first remote sensing images and described second
Remote sensing images, calculate the first differential image and the second differential image.
Wherein, the preset first function can be difference functions, and second preset function can be log ratio letter
Number, for example, the first remote sensing images X got as described in step 1011With the second remote sensing images X2, then difference is specifically utilized
Function and log ratio function calculate differential image can be with as follows:
First differential image is F1(i, j)=| X1(i, j)-X2(i, j) |, the second differential image is
It should be noted that
In formula, G is used1(i, j)+1 replaces G1(i, j), uses G2(i, j)+1 replaces G2(i, j) is to avoid the occurrence of Gi(i=1,2) pixel value is 0
Situation.
103rd, according to first differential image and second differential image, final differential image is calculated.
Wherein, the final differential image is the region of variation image between the described two different phases of expression.
Specifically, the step 103 can be to distribute weight, then to the first differential image and the second differential image respectively
According to two width differential images and the corresponding final differential image of weight calculation of difference.
For the embodiment of the present invention, by obtaining the remote sensing images of two phases in areal, and during according to two obtained
The operations such as phase remote sensing images are handled, qualitative analysis, calculating, finally give the change between difference remote sensing images, i.e. two phases
Change the image in region, complete the change to remote sensing images and detect.
A kind of method for detecting change of remote sensing image based on logarithmic transformation provided in an embodiment of the present invention, passes through with existing
Non-supervisory image change detection method is changed detection to remote sensing images and compared, and the embodiment of the present invention is by obtaining areal
Two different phases distinguish corresponding remote sensing images, and according to the two width remote sensing images got, utilize two preset functions point
Two different differential images Ji Suan not be obtained, final differential image is calculated further according to two obtained differential images, are improved
The performance indications of testing result, and then improve the accuracy of Remote Sensing Imagery Change Detection.
The embodiment of the present invention additionally provides another method for detecting change of remote sensing image based on logarithmic transformation, such as Fig. 2 institutes
Show, methods described includes:
201st, the first remote sensing images and the second remote sensing images are obtained.
Wherein, first remote sensing images and the second remote sensing images are that the different phase difference in areal two are corresponding distant
Feel image.
This step is identical with step 101 method shown in Fig. 1, will not be repeated here.
202nd, Logarithm conversion is carried out respectively to first remote sensing images and second remote sensing images.
Further, obtain it is corresponding with first remote sensing images based on the image of log-domain first and with it is described second distant
Feel image corresponding based on the image of log-domain second.Wherein, the Logarithm conversion can be with 2 logarithm operations for the truth of a matter.
Specifically, the step 202 can be with as follows:
U1(i, j)=lb (X1(i, j)+1), U2(i, j)=lb (X2(i, j)+1), wherein, X1And X2Respectively two differences
The remote sensing images of phase, U1And U2Represent respectively to being obtained after remote sensing images progress Logarithm conversion based on logarithm area image.Need
Illustrate, in formula, use X1(i, j)+1 replaces X1(i, j), X2(i, j)+1 replaces X2(i, j), to avoid the occurrence of Xi(i=1,2)
Pixel value is 0 situation.
For the embodiment of the present invention, by carrying out Logarithm conversion to the remote sensing images got so that remote sensing images are changed
For logarithm area image, while so as to which the gray value of remote sensing images is compressed between [0,8], by making an uproar in remote sensing images
Sound is compressed, and then is realized to remote sensing images progress denoising, improves the precision of Remote Sensing Imagery Change Detection.
203rd, to described based on the image of log-domain first and described based on the progress denoising of the image of log-domain second.
Further, the second image after the first image and denoising is respectively obtained after denoising.Specifically, the step 203 can
Think and denoising is carried out to the image based on log-domain obtained by Logarithm conversion by Frost wave filters.
For the embodiment of the present invention, denoising, Ke Yi are carried out to the image based on log-domain by using Frost wave filters
Retain image edge information while smooth noise so that the remote sensing images after denoising are more accurate, so as to improve remote sensing figure
As the accuracy rate of change detection.
204th, preset first function and preset second function are utilized respectively, according to the first image after the denoising and described is gone
Second image after making an uproar, calculates the first differential image and the second differential image.
Wherein, the preset first function can be difference functions, and second preset function can be log ratio letter
Number, specific concept explanation may be referred to accordingly describe in step 102, will not be repeated here.
It should be noted that by being carried out the image based on log-domain after denoising and using difference operation, can be one
The influence of elimination coherent speckle noise in degree is determined, by carrying out the image based on log-domain to grasp after denoising and using log ratio
Make, the identification of region of variation can be improved, suppress the background information in non-changing region, because so that image has stronger robust
Property, improve the accuracy of Remote Sensing Imagery Change Detection.
205th, processing is filtered respectively to first differential image and second differential image.
Further, the first differential image and the second differential image after filtering after being filtered.Wherein, the filtering process
Can be mean filter processing, or median filter processing, can be with to the first differential image and the second differential image
For identical filter processing method, or different filter processing methods, the embodiment of the present invention is not specifically limited.
206th, according to the second differential image after the first differential image after the filtering and the filtering, final disparity map is calculated
Picture.
Specifically, for the embodiment of the present invention, the step 206 can specifically include:By the first difference after the filtering
The first weight coefficient and the second weight coefficient is respectively configured in the second differential image after image and the filtering;Described is calculated respectively
The product of one weight coefficient and first differential image, and second weight coefficient and the second difference remote sensing images
Product, obtain first the second product of sum of products;By the second product addition described in first sum of products and value, be defined as most
Whole difference remote sensing images.It should be noted that in order to ensure the gray value of final differential image is still placed between 0 to 8, described
One weight coefficient and the second weight coefficient sum are 1.
For the embodiment of the present invention, specific application scenarios can be with as follows, but not limited to this, including:
Obtain the first remote sensing images X1With the second remote sensing images X2, to remote sensing images X1And X2Logarithm conversion is carried out, base is obtained
In the image U of log-domain1And U2, then to image U1And U2Denoising is carried out, the image G after denoising is obtained1And G2, according to image G1
Calculated using differential technique and obtain the first differential image for F1, according to image G2Calculated using log ratio method and obtain the second disparity map
As being F2, then by mean filter to the first differential image F1Processing is filtered, the first differential image after being filtered
D1, by median filter to the second differential image F2Be filtered processing, after being filtered and differential image D2, in order to flat
Weigh smoothed image and reservation image detail, the first weight coefficient and the second weight coefficient can be set into equal numerical value, i.e.,
It is 0.5, can now calculates and obtain final difference remote sensing images R (i, j) and be:
R (i, j)=0.5D1(i, j)+0.5D2(i, j).
207th, the final difference remote sensing images are clustered using preset clustering algorithm.
Wherein, the preset clustering algorithm can be FCM (Flow Cytometry/financal capacity
Model, flow cytometry) clustering algorithm.
Specifically, the step 207 can be by minimizing object function JmThe fuzzy clustering of data-oriented is found, most
Smallization object function JmFor:
Y=(y in formula1, y2..., yn) it is one group of n dimension data sample
This, Z=(z1, z2..., zn) be ambiguity group I cluster centre, U=[uij]c×nIt is Y subordinated-degree matrix, uij∈ [0,1] is
yiBelong to the degree of membership of the i-th class, | | yj-zi| | for Euclidean distance between ith cluster center and j-th of data point, and m
∈ (1, ∞] it is a Weighted Index, J then can be obtained by Lagrange multipliermReach necessary condition during minimum value
WithIt is iterated, obtains optimal cluster result.
Another method for detecting change of remote sensing image based on logarithmic transformation provided in an embodiment of the present invention, leads to existing
Cross non-supervisory image change detection method detection be changed to remote sensing images and compare, the embodiment of the present invention by obtaining samely
After the remote sensing images of the different phases in two, area, Logarithm conversion is carried out to two width remote sensing images, and carries out denoising, it is then sharp
Differential image is calculated respectively with the image after difference functions and the width denoising of log ratio function pair two, and differential image is filtered
After ripple processing, final difference remote sensing images are calculated according to the weight coefficient of configuration, the performance indications of testing result is improved, enters
And improve the accuracy of Remote Sensing Imagery Change Detection.
Further, implementing as method shown in Fig. 1, the embodiment of the present invention provides a kind of based on logarithmic transformation
Remote Sensing Imagery Change Detection device, as shown in figure 3, described device can include:Acquiring unit 31, computing unit 32.
Acquiring unit 31, for obtaining the first remote sensing images and the second remote sensing images;The acquiring unit 31 is a kind of base
The functional module for obtaining the first remote sensing images and the second remote sensing images is performed in the Remote Sensing Imagery Change Detection device of logarithmic transformation.
Computing unit 32, for being utilized respectively preset first function and preset second function, according to the first remote sensing figure
Picture and second remote sensing images, calculate the first differential image and the second differential image;The computing unit 32 is based on for one kind
The Remote Sensing Imagery Change Detection device of logarithmic transformation performs the functional module for calculating the first differential image and the second differential image.
The computing unit 32, can be also used for, according to first differential image and second differential image, calculating
Final differential image;The computing unit 32 is performed for a kind of Remote Sensing Imagery Change Detection device based on logarithmic transformation and calculated most
The functional module of whole differential image.
The device embodiment is corresponding with preceding method embodiment, and for ease of reading, present apparatus embodiment is no longer to foregoing side
Detail content in method embodiment is repeated one by one, it should be understood that the device in the present embodiment can correspond to realize it is foregoing
Full content in embodiment of the method.
A kind of Remote Sensing Imagery Change Detection device based on logarithmic transformation provided in an embodiment of the present invention, passes through with existing
Non-supervisory image change detection method is changed detection to remote sensing images and compared, and the embodiment of the present invention is by obtaining areal
Two different phases distinguish corresponding remote sensing images, and according to the two width remote sensing images got, utilize two preset functions point
Two different differential images Ji Suan not be obtained, final differential image is calculated further according to two obtained differential images, are improved
The performance indications of testing result, and then improve the accuracy of Remote Sensing Imagery Change Detection.
Further, implementing as method shown in Fig. 2, the embodiment of the present invention provides another based on logarithmic transformation
Remote Sensing Imagery Change Detection device, as shown in figure 4, described device can include:Acquiring unit 41, computing unit 42.
Acquiring unit 41, for obtaining the first remote sensing images and the second remote sensing images;
Computing unit 42, for being utilized respectively preset first function and preset second function, according to the first remote sensing figure
Picture and second remote sensing images, calculate the first differential image and the second differential image;
The computing unit 42, is additionally operable to according to first differential image and second differential image, calculates final
Differential image.
Further, described device also includes:Converting unit 43, denoising unit 44.
The converting unit 43, turns for first remote sensing images and second remote sensing images to be carried out with logarithm respectively
Change.
The denoising unit 44, for described being entered to described based on the image of log-domain first and based on the image of log-domain second
Row denoising.
Further, the computing unit 42, specifically for being utilized respectively preset first function and preset second function, root
According to the second image after the first image after the denoising and the denoising, the first differential image and the second differential image are calculated.
Further, described device also includes:Filter unit 45.
The filter unit 45, for being filtered place respectively to first differential image and second differential image
Reason.
Further, the computing unit 42, is specifically additionally operable to according to the first differential image after the filtering and the filter
Second differential image after ripple, calculates final differential image.
Specifically, in order to improve the accuracy of Remote Sensing Imagery Change Detection, the computing unit 42 includes:
Configuration module 4201, for the second differential image after the first differential image after the filtering and the filtering to be distinguished
Configure the first weight coefficient and the second weight coefficient;
Computing module 4202, the product for calculating first weight coefficient and first differential image respectively, with
And the product of second weight coefficient and the second difference remote sensing images, obtain first the second product of sum of products;
Determining module 4203, for by the second product addition described in first sum of products and value, it is final poor to be defined as
Different remote sensing images.
Further, described device also includes:Cluster cell 46.
The cluster cell 46, for being clustered using preset clustering algorithm to the final difference remote sensing images.
The device embodiment is corresponding with preceding method embodiment, and for ease of reading, present apparatus embodiment is no longer to foregoing side
Detail content in method embodiment is repeated one by one, it should be understood that the device in the present embodiment can correspond to realize it is foregoing
Full content in embodiment of the method.
Another Remote Sensing Imagery Change Detection device based on logarithmic transformation provided in an embodiment of the present invention, leads to existing
Cross non-supervisory image change detection method detection be changed to remote sensing images and compare, the embodiment of the present invention by obtaining samely
After the remote sensing images of the different phases in two, area, Logarithm conversion is carried out to two width remote sensing images, and carries out denoising, it is then sharp
Differential image is calculated respectively with the image after difference functions and the width denoising of log ratio function pair two, and differential image is filtered
After ripple processing, final difference remote sensing images are calculated according to the weight coefficient of configuration, the performance indications of testing result is improved, enters
And improve the accuracy of Remote Sensing Imagery Change Detection.
The Remote Sensing Imagery Change Detection device based on logarithmic transformation includes processor and memory, above-mentioned acquisition list
Member, computing unit etc. are stored in memory as program unit, by the above-mentioned journey of computing device storage in memory
Sequence unit realizes corresponding function.
Kernel is included in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can set one
Or more, existing non-supervisory image change detection method is solved by adjusting kernel parameter remote sensing images are changed with inspection
The testing result performance indications of survey are still relatively low, and then cause the problem of Remote Sensing Imagery Change Detection accuracy is relatively low.
Memory potentially includes the volatile memory in computer-readable medium, random access memory (RAM) and/
Or the form, such as read-only storage (ROM) or flash memory (flash RAM) such as Nonvolatile memory, memory is deposited including at least one
Store up chip.
Present invention also provides a kind of computer program product, when being performed on data processing equipment, it is adapted for carrying out just
The program code of beginningization there are as below methods step:Obtain the first remote sensing images and the second remote sensing images, first remote sensing images
It is that two different phases distinguish corresponding remote sensing images with the second remote sensing images;It is utilized respectively preset first function and preset second
Function, according to first remote sensing images and second remote sensing images, calculates the first differential image and the second differential image;Root
According to first differential image and second differential image, final differential image is calculated, the final differential image is expression
Region of variation image between described two different phases.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, the application can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the application can be used in one or more computers for wherein including computer usable program code
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is the flow with reference to method, equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and internal memory.
Memory potentially includes the volatile memory in computer-readable medium, random access memory (RAM) and/
Or the form, such as read-only storage (ROM) or flash memory (flash RAM) such as Nonvolatile memory.Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
Embodiments herein is these are only, the application is not limited to.To those skilled in the art,
The application can have various modifications and variations.All any modifications made within spirit herein and principle, equivalent substitution,
Improve etc., it should be included within the scope of claims hereof.
Claims (10)
1. a kind of method for detecting change of remote sensing image based on logarithmic transformation, it is characterised in that including:
The first remote sensing images and the second remote sensing images are obtained, first remote sensing images and the second remote sensing images are areal two
Individual different phases distinguish corresponding remote sensing images;
Preset first function and preset second function are utilized respectively, according to first remote sensing images and the second remote sensing figure
Picture, calculates the first differential image and the second differential image;
According to first differential image and second differential image, final differential image, the final differential image are calculated
To represent the region of variation image between described two different phases.
2. according to the method described in claim 1, it is characterised in that the first remote sensing images of the acquisition and the second remote sensing images it
Afterwards, methods described also includes:
Logarithm conversion is carried out respectively to first remote sensing images and second remote sensing images, obtained and the first remote sensing figure
As corresponding based on the image of log-domain first and corresponding with second remote sensing images based on the image of log-domain second;
To described based on the image of log-domain first and described based on the progress denoising of the image of log-domain second, denoising is respectively obtained
Second image after first image and denoising afterwards;
It is described to be utilized respectively preset first function and preset second function, according to first remote sensing images and second remote sensing
Image, calculating the first differential image and the second differential image includes:
Preset first function and preset second function are utilized respectively, according to after the first image after the denoising and the denoising second
Image, calculates the first differential image and the second differential image.
3. method according to claim 1 or 2, it is characterised in that described according to first differential image and described
Two differential images, are calculated before final differential image, methods described also includes:
Processing is filtered respectively to first differential image and second differential image, the first disparity map after being filtered
Second differential image after picture and filtering;
It is described according to first differential image and second differential image, calculating final differential image includes:
According to the second differential image after the first differential image after the filtering and the filtering, final differential image is calculated.
4. method according to claim 3, it is characterised in that described according to the first differential image after the filtering and described
Second differential image after filtering, calculating final differential image includes:
The first weight coefficient and is respectively configured in second differential image after first differential image after the filtering and the filtering
Two weight coefficients;
The product of first weight coefficient and first differential image, and second weight coefficient and institute are calculated respectively
The product of the second difference remote sensing images is stated, first the second product of sum of products is obtained;
By the second product addition described in first sum of products and value, be defined as final difference remote sensing images.
5. the method according to claim 1 or 4, it is characterised in that methods described also includes:
The final difference remote sensing images are clustered using preset clustering algorithm.
6. a kind of Remote Sensing Imagery Change Detection device based on logarithmic transformation, it is characterised in that including:
Acquiring unit, for obtaining the first remote sensing images and the second remote sensing images, first remote sensing images and the second remote sensing figure
As distinguishing corresponding remote sensing images for the different phases in areal two;
Computing unit, for being utilized respectively preset first function and preset second function, according to first remote sensing images and institute
The second remote sensing images are stated, the first differential image and the second differential image is calculated;
The computing unit, is additionally operable to, according to first differential image and second differential image, calculate final disparity map
Picture, the final differential image is the region of variation image between the described two different phases of expression.
7. device according to claim 6, it is characterised in that described device also includes:
Converting unit, for carrying out Logarithm conversion respectively to first remote sensing images and second remote sensing images, obtain with
First remote sensing images are corresponding based on the image of log-domain first and corresponding with second remote sensing images based on log-domain
Second image;
Denoising unit, for being carried out to described based on the image of log-domain first with the image of log-domain second that is based at denoising
Reason, respectively obtains after denoising the second image after the first image and denoising;
The computing unit, is additionally operable to described go based on the image of log-domain first and based on the image of log-domain second to described
Make an uproar processing, respectively obtain after denoising the second image after the first image and denoising.
8. the device according to claim 6 or 7, it is characterised in that described device also includes:
Filter unit, for being filtered processing respectively to first differential image and second differential image, is filtered
First differential image and the second differential image after filtering after ripple;
The computing unit, is additionally operable to according to the second differential image after the first differential image after the filtering and the filtering, meter
Calculate final differential image.
9. device according to claim 8, it is characterised in that the computing unit includes:Configuration module, computing module,
Determining module,
The configuration module, for the second differential image after the first differential image after the filtering and the filtering to be respectively configured
First weight coefficient and the second weight coefficient;
The computing module, the product for calculating first weight coefficient and first differential image respectively, Yi Jisuo
The product of the second weight coefficient and the second difference remote sensing images is stated, first the second product of sum of products is obtained;
The determining module, for by the second product addition described in first sum of products and value, be defined as final difference distant
Feel image.
10. the device according to claim 6 or 9, it is characterised in that described device also includes:
Cluster cell, for being clustered using preset clustering algorithm to the final difference remote sensing images.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710537712.0A CN107316296B (en) | 2017-06-29 | 2017-06-29 | Remote sensing image change detection method and device based on logarithmic transformation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710537712.0A CN107316296B (en) | 2017-06-29 | 2017-06-29 | Remote sensing image change detection method and device based on logarithmic transformation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107316296A true CN107316296A (en) | 2017-11-03 |
CN107316296B CN107316296B (en) | 2020-11-10 |
Family
ID=60181125
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710537712.0A Active CN107316296B (en) | 2017-06-29 | 2017-06-29 | Remote sensing image change detection method and device based on logarithmic transformation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107316296B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108830828A (en) * | 2018-04-28 | 2018-11-16 | 新疆大学 | A kind of method for detecting change of remote sensing image and device |
CN109583487A (en) * | 2018-11-21 | 2019-04-05 | 新疆大学 | A kind of SAR image change detection and device |
CN109886959A (en) * | 2019-03-19 | 2019-06-14 | 新疆大学 | The method and device of detection image variation |
CN111383216A (en) * | 2020-03-10 | 2020-07-07 | 新疆大学 | Method and device for detecting change between images |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103456020A (en) * | 2013-09-08 | 2013-12-18 | 西安电子科技大学 | Remote sensing image change detection method based on treelet feature fusion |
CN103456018A (en) * | 2013-09-08 | 2013-12-18 | 西安电子科技大学 | Remote sensing image change detection method based on fusion and PCA kernel fuzzy clustering |
CN103955894A (en) * | 2014-04-14 | 2014-07-30 | 武汉科技大学 | Medical ultrasound image speckle removing method through quantum inspiration |
CN104200471A (en) * | 2014-08-30 | 2014-12-10 | 西安电子科技大学 | SAR image change detection method based on adaptive weight image fusion |
CN104778717A (en) * | 2015-05-05 | 2015-07-15 | 西安电子科技大学 | SAR image change detection method based on oriented difference chart |
CN106296655A (en) * | 2016-07-27 | 2017-01-04 | 西安电子科技大学 | Based on adaptive weight and the SAR image change detection of high frequency threshold value |
-
2017
- 2017-06-29 CN CN201710537712.0A patent/CN107316296B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103456020A (en) * | 2013-09-08 | 2013-12-18 | 西安电子科技大学 | Remote sensing image change detection method based on treelet feature fusion |
CN103456018A (en) * | 2013-09-08 | 2013-12-18 | 西安电子科技大学 | Remote sensing image change detection method based on fusion and PCA kernel fuzzy clustering |
CN103955894A (en) * | 2014-04-14 | 2014-07-30 | 武汉科技大学 | Medical ultrasound image speckle removing method through quantum inspiration |
CN104200471A (en) * | 2014-08-30 | 2014-12-10 | 西安电子科技大学 | SAR image change detection method based on adaptive weight image fusion |
CN104778717A (en) * | 2015-05-05 | 2015-07-15 | 西安电子科技大学 | SAR image change detection method based on oriented difference chart |
CN106296655A (en) * | 2016-07-27 | 2017-01-04 | 西安电子科技大学 | Based on adaptive weight and the SAR image change detection of high frequency threshold value |
Non-Patent Citations (2)
Title |
---|
YAOGUO ZHENG ET AL: "Using Combined Difference Image and k-Means Clustering for SAR Image Change Detection", 《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》 * |
王雪国 等: "基于PM扩散方程的SAR图像变化检测", 《激光杂志》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108830828A (en) * | 2018-04-28 | 2018-11-16 | 新疆大学 | A kind of method for detecting change of remote sensing image and device |
CN108830828B (en) * | 2018-04-28 | 2022-02-18 | 新疆大学 | Method and device for detecting change of remote sensing image |
CN109583487A (en) * | 2018-11-21 | 2019-04-05 | 新疆大学 | A kind of SAR image change detection and device |
CN109886959A (en) * | 2019-03-19 | 2019-06-14 | 新疆大学 | The method and device of detection image variation |
CN111383216A (en) * | 2020-03-10 | 2020-07-07 | 新疆大学 | Method and device for detecting change between images |
CN111383216B (en) * | 2020-03-10 | 2022-04-05 | 新疆大学 | Method and device for detecting change between images |
Also Published As
Publication number | Publication date |
---|---|
CN107316296B (en) | 2020-11-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110287932B (en) | Road blocking information extraction method based on deep learning image semantic segmentation | |
CN110929607B (en) | Remote sensing identification method and system for urban building construction progress | |
CN106355188A (en) | Image detection method and device | |
CA2840436C (en) | System for mapping and identification of plants using digital image processing and route generation | |
CN110781885A (en) | Text detection method, device, medium and electronic equipment based on image processing | |
CN107316296A (en) | A kind of method for detecting change of remote sensing image and device based on logarithmic transformation | |
CN111666900B (en) | Land cover classification map obtaining method and device based on multi-source remote sensing image | |
Chawan et al. | Automatic detection of flood using remote sensing images | |
CN108256527A (en) | A kind of cutaneous lesions multiclass semantic segmentation method based on end-to-end full convolutional network | |
CN112906816B (en) | Target detection method and device based on optical differential and two-channel neural network | |
CN112288758B (en) | Infrared and visible light image registration method for power equipment | |
CN108564083A (en) | A kind of method for detecting change of remote sensing image and device | |
CN106295498A (en) | Remote sensing image target area detection apparatus and method | |
CN111259808A (en) | Detection and identification method of traffic identification based on improved SSD algorithm | |
CN113283419A (en) | Convolutional neural network pointer instrument image reading identification method based on attention | |
CN113160183A (en) | Hyperspectral data processing method, device and medium | |
CN111582387A (en) | Rock spectral feature fusion classification method and system | |
CN108830828A (en) | A kind of method for detecting change of remote sensing image and device | |
Yuan et al. | Image feature based GPS trace filtering for road network generation and road segmentation | |
CN105205807B (en) | Method for detecting change of remote sensing image based on sparse automatic coding machine | |
CN115439654A (en) | Method and system for finely dividing weakly supervised farmland plots under dynamic constraint | |
Zeybek | Inlier point preservation in outlier points removed from the ALS point cloud | |
Oga et al. | River state classification combining patch-based processing and CNN | |
CN116309612B (en) | Semiconductor silicon wafer detection method, device and medium based on frequency decoupling supervision | |
CN116503677B (en) | Wetland classification information extraction method, system, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |