CN107316296B - A method and device for detecting changes in remote sensing images based on logarithmic transformation - Google Patents

Abstract

The invention discloses a remote sensing image change detection method and device based on logarithmic transformation, relates to the technical field of image processing, and mainly aims to solve the problem that the performance index of a detection result of the change detection of a remote sensing image by using the existing unsupervised image change detection method is still low, so that the accuracy of the change detection of the remote sensing image is low. The technical scheme comprises the following steps: acquiring a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are respectively corresponding to two different time phases; calculating a first difference image and a second difference image according to the first remote sensing image and the second remote sensing image by respectively utilizing a preset first function and a preset second function; calculating a final difference image from the first difference image and the second difference image, the final difference image being an image representing a variation area between the two different time phases. The method is mainly used for detecting the change area of the two-time phase remote sensing image.

Description

A method and device for detecting changes in remote sensing images based on logarithmic transformation

technical field

The invention relates to the technical field of image processing, in particular to a method and device for detecting changes in remote sensing images based on logarithmic transformation.

Background technique

With the rapid development of remote sensing technology, remote sensing images have been widely used in many fields, such as land use monitoring, forest monitoring, urban monitoring and natural disaster assessment and analysis. The change detection of remote sensing images refers to determining and analyzing the change information of the surface of the region based on two or more remote sensing images obtained at different times in the same region. Generally, the methods of change detection for remote sensing images can be divided into two categories, namely supervised detection methods and unsupervised detection methods. Among them, the supervised detection method refers to the method that needs to use the classifier to train the samples, and then detects the changed area of the remote sensing image according to the training sample; the non-thick detection method refers to the method of directly detecting two or more remote sensing images. However, since supervised detection methods need to obtain real reference data, the cost is high, which makes unsupervised detection methods more common in practical applications.

At present, when using unsupervised detection methods for remote sensing image change detection, the unsupervised image change detection method of data fusion and fuzzy clustering can be used, or the unsupervised image change detection algorithm of PPB denoising and K-means clustering can be used. , although the accuracy of remote sensing image detection results is improved, the performance indicators of detection results are still low, which in turn leads to low accuracy of remote sensing image change detection.

SUMMARY OF THE INVENTION

In view of the above problems, the present invention is proposed to provide a method and device for detecting changes in remote sensing images based on logarithmic transformation. low, which in turn leads to the problem of low accuracy of remote sensing image change detection.

By the above-mentioned technical scheme, a kind of remote sensing image change detection method based on logarithmic transformation provided by the present invention comprises:

acquiring a first remote sensing image and a second remote sensing image;

Using the preset first function and the preset second function respectively, according to the first remote sensing image and the second remote sensing image, calculate the first difference image and the second difference image;

A final difference image is calculated from the first difference image and the second difference image.

By the above-mentioned technical scheme, a kind of remote sensing image change detection device based on logarithmic transformation provided by the present invention comprises:

an acquisition unit for acquiring the first remote sensing image and the second remote sensing image;

a computing unit, configured to calculate a first difference image and a second difference image according to the first remote sensing image and the second remote sensing image by using the preset first function and the preset second function respectively;

The calculating unit is further configured to calculate a final difference image according to the first difference image and the second difference image.

The method and device for detecting changes in remote sensing images based on logarithmic transformation provided by the embodiments of the present invention, compared with the existing methods for detecting changes in remote sensing images through unsupervised image changes, the embodiments of the present invention obtain two two remote sensing images corresponding to different time phases, and according to the obtained two remote sensing images, use two preset functions to calculate two different difference images respectively, and then calculate the final difference image according to the two obtained difference images, The performance index of the detection result is improved, thereby improving the accuracy of remote sensing image change detection.

The above description is only an overview of the technical solutions of the present invention, in order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand , the following specific embodiments of the present invention are given.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the invention. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

1 shows a flowchart of a method for detecting changes in remote sensing images based on logarithmic transformation provided by an embodiment of the invention;

2 shows a flowchart of another method for detecting changes in remote sensing images based on logarithmic transformation provided by an embodiment of the invention;

3 shows a block diagram of a logarithmic transformation-based remote sensing image change detection device provided by an embodiment of the invention;

FIG. 4 shows a block diagram of another remote sensing image change detection device based on logarithmic transformation provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

An embodiment of the present invention provides a method for detecting changes in remote sensing images based on logarithmic transformation. As shown in FIG. 1 , the method includes:

101. Acquire a first remote sensing image and a second remote sensing image.

The first remote sensing image and the second remote sensing image are remote sensing images corresponding to two different time phases in the same area, and the remote sensing image may be a SAR (Synthetic Aperture Radar, synthetic aperture radar) image.

For example, the obtained first remote sensing image is that the SAR image of region A at time phase 1 is X ₁ , X ₁ ={X ₁ (i,j), 1<i<m, 1<j<n}, and the obtained The second remote sensing image is the SAR image of region A at time phase 2, X ₂ , X ₂ ={X ₂ (i, j), 1<i<m, 1<j<n}, X ₁ and X ₂ are both is an m pixel × n pixel SAR image.

102. Calculate a first difference image and a second difference image according to the first remote sensing image and the second remote sensing image by using a preset first function and a preset second function, respectively.

Wherein, the preset first function may be a difference function, and the second preset function may be a logarithmic ratio function, for example, the first remote sensing image X ₁ and the second remote sensing image obtained in step 101 Image X ₂ , then the specific difference image calculated by the difference function and the logarithmic ratio function can be as follows:

需要说明的是，式中，用G₁(i，j)+1代替G₁(i，j)，用G₂(i，j)+1代替G₂(i，j)以避免出现G_i(i＝1，2)像素值为0的情况。The first difference image is F ₁ (i, j)=|X ₁ (i, j)-X ₂ (i, j)|, and the second difference image is

It should be noted that, in the formula, G ₁ (i, j)+1 is used to replace G ₁ (i, j), and G ₂ (i, j)+1 is used to replace G ₂ (i, j) to avoid the occurrence of G _i (i=1, 2) The case where the pixel value is 0.

103. Calculate a final difference image according to the first difference image and the second difference image.

Wherein, the final difference image is an image representing the change area between the two different time phases.

Specifically, the step 103 may be to assign weights to the first difference image and the second difference image respectively, and then calculate the final difference image according to the two difference images and their corresponding weights.

For the embodiment of the present invention, by acquiring remote sensing images of two temporal phases in the same area, and performing operations such as processing, qualitative analysis, and calculation according to the obtained remote sensing images of two temporal phases, a difference remote sensing image is finally obtained, that is, the difference between the two temporal phases. The image of the changed area is completed to detect the change of the remote sensing image.

A method for detecting changes in remote sensing images based on logarithmic transformation provided by an embodiment of the present invention, compared with the existing method for detecting changes in remote sensing images through unsupervised image change detection, the embodiment of the present invention obtains two different changes in the same area by acquiring At the same time, the corresponding remote sensing images are compared, and two different difference images are calculated by using two preset functions according to the two obtained remote sensing images, and then the final difference image is calculated according to the obtained two difference images, which improves the The performance indicators of the detection results, thereby improving the accuracy of remote sensing image change detection.

The embodiment of the present invention also provides another method for detecting changes in remote sensing images based on logarithmic transformation, as shown in FIG. 2 , the method includes:

201. Acquire a first remote sensing image and a second remote sensing image.

Wherein, the first remote sensing image and the second remote sensing image are remote sensing images corresponding to two different time phases in the same area.

This step is the same as the method of step 101 shown in FIG. 1 , and will not be repeated here.

202. Perform logarithmic transformation on the first remote sensing image and the second remote sensing image respectively.

Further, a first image based on logarithmic domain corresponding to the first remote sensing image and a second image based on logarithmic domain corresponding to the second remote sensing image are obtained. Wherein, the logarithmic conversion may be a logarithmic operation with a base of 2.

Specifically, the step 202 may be as follows:

U ₁ (i, j)=lb(X ₁ (i, j)+1), U ₂ (i, j)=lb(X ₂ (i, j)+1), where X ₁ and X ₂ are respectively are two remote sensing images of different time phases, U ₁ and U ₂ respectively represent images based on logarithmic domain obtained by logarithmic transformation of remote sensing images. It should be noted that, in the formula, X ₁ (i, j)+1 is used to replace X ₁ (i, j), and X ₂ (i, j)+1 is used to replace X ₂ (i, j) to avoid the occurrence of X _i (i=1, 2) The case where the pixel value is 0.

For the embodiment of the present invention, by performing logarithmic conversion on the obtained remote sensing image, the remote sensing image is converted into a logarithmic domain image, so that the gray value of the remote sensing image can be compressed to be between [0, 8], and the The noise in the remote sensing image is compressed, which realizes the denoising of the remote sensing image and improves the accuracy of the change detection of the remote sensing image.

203. Perform denoising processing on the first image based on the logarithmic domain and the second image based on the logarithmic domain.

Further, the first image after denoising and the second image after denoising are obtained respectively. Specifically, the step 203 may be to perform denoising on the logarithmic domain-based image obtained by logarithmic transformation through a Frost filter.

For the embodiment of the present invention, by using the Frost filter to denoise the image based on the logarithmic domain, the edge information of the image can be preserved while the noise is smoothed, so that the denoised remote sensing image is more accurate, thereby improving the detection of changes in the remote sensing image. 's accuracy.

204. Calculate a first difference image and a second difference image according to the first image after denoising and the second image after denoising by using the preset first function and the preset second function respectively.

The preset first function may be a difference function, and the second preset function may be a logarithmic ratio function. For specific concept explanations, refer to the corresponding description in step 102, which will not be repeated here.

It should be noted that the influence of speckle noise can be eliminated to a certain extent by denoising the image based on the logarithmic domain and using the difference operation. The numerical ratio operation can improve the identification of the changed area and suppress the background information of the non-changed area, because it makes the image more robust and improves the accuracy of remote sensing image change detection.

205. Perform filtering processing on the first difference image and the second difference image respectively.

Further, the filtered first difference image and the filtered second difference image are obtained. Wherein, the filtering processing may be mean value filtering processing or median filtering processing, and may be the same filtering processing method or different filtering processing methods for the first difference image and the second difference image. The embodiments of the invention are not specifically limited.

206. Calculate a final difference image according to the filtered first difference image and the filtered second difference image.

Specifically, for the embodiment of the present invention, the step 206 may specifically include: configuring the first weight coefficient and the second weight coefficient for the filtered first difference image and the filtered second difference image respectively; The product of the first weight coefficient and the first difference image, and the product of the second weight coefficient and the second difference remote sensing image, to obtain the first product and the second product; The sum of the above-mentioned second products is determined as the final difference remote sensing image. It should be noted that, in order to ensure that the gray value of the final difference image is still between 0 and 8, the sum of the first weight coefficient and the second weight coefficient is 1.

For this embodiment of the present invention, specific application scenarios may be as follows, but are not limited thereto, including:

Obtain the first remote sensing image X ₁ and the second remote sensing image X ₂ , perform logarithmic transformation on the remote sensing images X ₁ and X ₂ to obtain images U ₁ and U ₂ based on the logarithmic domain, and then perform a logarithmic transformation on the images U ₁ and U ₂ Denoising to obtain denoised images G ₁ and G ₂ , the first difference image is F ₁ calculated by the difference method according to the image G ₁ , and the second difference image F is calculated by the logarithmic ratio method according to the image G _{2 2} , and then filter the _first difference image F1 through the mean filter to obtain the filtered _first difference image D1, and filter the _second difference image F2 through the median filter to obtain the first difference after filtering. In the image D ₂ , in order to balance the smooth image and preserve the image details, the first weight coefficient and the second weight coefficient can be set to the same value, that is, both are 0.5, at this time, the final difference remote sensing image R(i, j can be calculated )for:

R(i,j)= _0.5D1 (i,j)+ _0.5D2 (i,j).

207. Use a preset clustering algorithm to cluster the final difference remote sensing image.

The preset clustering algorithm may be an FCM (Flow Cytometry/financal capacity model, flow cytometry) clustering algorithm.

Specifically, the step 207 may be to find the fuzzy clustering of the given data by minimizing the objective function _Jm , and the minimizing objective function _Jm is:

式中Y＝(y₁，y₂，...，y_n)是一组n维数据样本，Z＝(z₁，z₂，...，z_n)是模糊组I的聚类中心，U＝[u_ij]_c×n是Y的隶属度矩阵，u_ij∈[0，1]是y_i属于第i类的隶属度，||y_j-z_i||为第i个聚类中心与第j个数据点间的欧几里德距离，且m∈(1，∞]是一个加权指数，而后通过拉格朗日乘子可以得到J_m达到最小值时的必要条件

where Y=(y ₁ , y ₂ ,..., y _n ) is a group of n-dimensional data samples, Z=(z ₁ , z ₂ ,..., z _n ) is the cluster center of fuzzy group I , U=[u _ij ] _c×n is the membership degree matrix of Y, u _ij ∈[0, 1] is the membership degree of _yi belonging to the ith class, ||y _j -z _i || is the ith cluster The Euclidean distance between the class center and the jth data point, and m∈(1, ∞] is a weighted exponent, and then the necessary condition for J _m to reach the minimum value can be obtained through the Lagrange multiplier

进行迭代，得到最优的聚类结果。and

Iterate to get the best clustering result.

Another method for detecting changes in remote sensing images based on logarithmic transformation provided by the embodiment of the present invention, compared with the existing method for detecting changes in remote sensing images through unsupervised image change detection, the embodiment of the present invention obtains two After remote sensing images of different time phases, logarithmically transform the two remote sensing images and perform denoising processing, and then use the difference function and the logarithm ratio function to calculate the difference images respectively for the two denoised images, and compare the differences. After the image is filtered, the final difference remote sensing image is calculated according to the configured weight coefficient, which improves the performance index of the detection result, and further improves the accuracy of remote sensing image change detection.

Further, as a specific implementation of the method shown in FIG. 1 , an embodiment of the present invention provides a remote sensing image change detection device based on logarithmic transformation. As shown in FIG. 3 , the device may include: an acquisition unit 31 and a calculation unit 32 .

The acquiring unit 31 is used for acquiring the first remote sensing image and the second remote sensing image; the acquiring unit 31 is a functional module for acquiring the first remote sensing image and the second remote sensing image by a logarithmic transformation-based remote sensing image change detection device.

The calculation unit 32 is used to calculate the first difference image and the second difference image according to the first remote sensing image and the second remote sensing image by using the preset first function and the preset second function respectively; the calculation unit 32 is a functional module for calculating a first difference image and a second difference image for a remote sensing image change detection device based on logarithmic transformation.

The calculation unit 32 can also be used to calculate the final difference image according to the first difference image and the second difference image; the calculation unit 32 performs calculation for a remote sensing image change detection device based on logarithmic transformation. A functional module for the final difference image.

This apparatus embodiment corresponds to the foregoing method embodiments. For ease of reading, this apparatus embodiment will not repeat the details in the foregoing method embodiments one by one, but it should be clear that the apparatus in this embodiment can correspondingly implement the foregoing method embodiments. the entire contents of the example.

A method for detecting changes in remote sensing images based on logarithmic transformation provided by the embodiment of the present invention, compared with the existing method for detecting changes in remote sensing images through unsupervised image change detection, the embodiment of the present invention obtains two different images in the same area by acquiring At the same time, the corresponding remote sensing images are compared, and two different difference images are calculated by using two preset functions according to the two obtained remote sensing images, and then the final difference image is calculated according to the obtained two difference images, which improves the The performance indicators of the detection results, thereby improving the accuracy of remote sensing image change detection.

Further, as a specific implementation of the method shown in FIG. 2 , an embodiment of the present invention provides another remote sensing image change detection device based on logarithmic transformation. As shown in FIG. 4 , the device may include: an acquisition unit 41 , a calculation unit 42.

an acquisition unit 41, for acquiring the first remote sensing image and the second remote sensing image;

The calculation unit 42 is used to calculate the first difference image and the second difference image according to the first remote sensing image and the second remote sensing image by using the preset first function and the preset second function respectively;

The calculating unit 42 is further configured to calculate a final difference image according to the first difference image and the second difference image.

Further, the apparatus further includes: a converting unit 43 and a denoising unit 44 .

The conversion unit 43 is configured to perform logarithmic conversion on the first remote sensing image and the second remote sensing image respectively.

The denoising unit 44 is configured to perform denoising processing on the first image based on the logarithmic domain and the second image based on the logarithmic domain.

Further, the calculation unit 42 is specifically configured to calculate the first difference image according to the first image after denoising and the second image after denoising by using a preset first function and a preset second function respectively. and the second difference image.

Further, the apparatus further includes: a filtering unit 45 .

The filtering unit 45 is configured to perform filtering processing on the first difference image and the second difference image respectively.

Further, the calculating unit 42 is further configured to calculate the final difference image according to the filtered first difference image and the filtered second difference image.

Specifically, in order to improve the accuracy of remote sensing image change detection, the computing unit 42 includes:

A configuration module 4201, configured to configure a first weight coefficient and a second weight coefficient respectively for the filtered first difference image and the filtered second difference image;

A calculation module 4202, configured to calculate the product of the first weight coefficient and the first difference image, and the product of the second weight coefficient and the second difference remote sensing image, respectively, to obtain the first product and the second product ;

The determining module 4203 is configured to determine the sum of the first product and the second product as the final difference remote sensing image.

Further, the apparatus further includes: a clustering unit 46 .

The clustering unit 46 is configured to use a preset clustering algorithm to cluster the final difference remote sensing images.

This apparatus embodiment corresponds to the foregoing method embodiments. For ease of reading, this apparatus embodiment will not repeat the details in the foregoing method embodiments one by one, but it should be clear that the apparatus in this embodiment can correspondingly implement the foregoing method embodiments. the entire contents of the example.

Another method for detecting changes in remote sensing images based on logarithmic transformation provided by the embodiment of the present invention, compared with the existing method for detecting changes in remote sensing images through unsupervised image change detection, the embodiment of the present invention obtains two After remote sensing images of different time phases, logarithmically transform the two remote sensing images and perform denoising processing, and then use the difference function and the logarithm ratio function to calculate the difference images respectively for the two denoised images, and compare the differences. After the image is filtered, the final difference remote sensing image is calculated according to the configured weight coefficient, which improves the performance index of the detection result, and further improves the accuracy of remote sensing image change detection.

The remote sensing image change detection device based on logarithmic transformation includes a processor and a memory, and the above-mentioned acquisition unit, calculation unit, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding. Function.

The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set. By adjusting the kernel parameters, the existing unsupervised image change detection methods for remote sensing image change detection still have low performance indicators, which leads to the problem of low accuracy of remote sensing image change detection.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one memory chip.

The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program code initialized with the following method steps: acquiring a first remote sensing image and a second remote sensing image, the first remote sensing image and the The second remote sensing image is two remote sensing images corresponding to different time phases respectively; the first difference image is calculated according to the first remote sensing image and the second remote sensing image by using the preset first function and the preset second function respectively. and a second difference image; according to the first difference image and the second difference image, a final difference image is calculated, and the final difference image is an image representing a change area between the two different phases.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, excludes transitory computer-readable media, such as modulated data signals and carrier waves.

The above are merely examples of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims (6)

1. A remote sensing image change detection method based on logarithmic transformation is characterized by comprising the following steps:

acquiring a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are remote sensing images respectively corresponding to two different time phases in the same area;

respectively carrying out logarithmic transformation on the first remote sensing image and the second remote sensing image to obtain a log domain-based first image corresponding to the first remote sensing image and a log domain-based second image corresponding to the second remote sensing image, and compressing the gray values of the first remote sensing image and the second remote sensing image to be between [0,8 ];

denoising the first image based on the logarithmic domain and the second image based on the logarithmic domain through a Frost filter to respectively obtain a denoised first image and a denoised second image;

calculating a first difference image and a second difference image according to the first remote sensing image and the second remote sensing image by respectively utilizing a preset first function and a preset second function;

respectively performing filtering processing on the first difference image and the second difference image, wherein the filtering processing is mean filter processing or median filter processing to obtain a filtered first difference image and a filtered second difference image;

calculating a final difference image according to the filtered first difference image and the filtered second difference image, wherein the final difference image is a change area image representing the two different time phases;

the calculating the first difference image and the second difference image according to the first remote sensing image and the second remote sensing image by respectively utilizing a preset first function and a preset second function comprises the following steps:

and calculating a first difference image and a second difference image according to the denoised first image and the denoised second image by respectively utilizing a preset first function and a preset second function.

2. The method of claim 1, wherein computing a final difference image from the filtered first difference image and the filtered second difference image comprises:

configuring a first weight coefficient and a second weight coefficient for the filtered first difference image and the filtered second difference image respectively;

respectively calculating a product of the first weight coefficient and the filtered first difference image and a product of the second weight coefficient and the filtered second difference image to obtain a first product and a second product;

and determining a sum value of the first product and the second product as a final difference image.

3. The method according to claim 1 or 2, characterized in that the method further comprises:

and clustering the final difference images by using a preset clustering algorithm.

4. A remote sensing image change detection device based on logarithmic transformation is characterized by comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first remote sensing image and a second remote sensing image, and the first remote sensing image and the second remote sensing image are respectively corresponding remote sensing images in two different time phases in the same area;

the conversion unit is used for respectively carrying out logarithmic conversion on the first remote sensing image and the second remote sensing image to obtain a first image based on a logarithmic domain corresponding to the first remote sensing image and a second image based on the logarithmic domain corresponding to the second remote sensing image, and compressing the gray values of the first remote sensing image and the second remote sensing image to be between [0,8 ];

the denoising unit is used for denoising the first image based on the logarithmic domain and the second image based on the logarithmic domain through a Frost filter to respectively obtain a denoised first image and a denoised second image;

the calculation unit is used for calculating a first difference image and a second difference image according to the first remote sensing image and the second remote sensing image by respectively utilizing a preset first function and a preset second function;

the filtering unit is used for respectively performing filtering processing on the first difference image and the second difference image, wherein the filtering processing is mean filter processing or median filter processing to obtain a first difference image after filtering and a second difference image after filtering;

the calculating unit is further configured to calculate a final difference image according to the filtered first difference image and the filtered second difference image, where the final difference image is a change area image representing the two different time phases;

the calculating unit is specifically configured to calculate a first difference image and a second difference image according to the denoised first image and the denoised second image by using a preset first function and a preset second function, respectively.

5. The apparatus of claim 4, wherein the computing unit comprises: a configuration module, a calculation module, a determination module,

the configuration module is configured to configure a first weight coefficient and a second weight coefficient for the filtered first difference image and the filtered second difference image respectively;

the calculating module is configured to calculate a product of the first weight coefficient and the filtered first difference image, and a product of the second weight coefficient and the filtered second difference image, respectively, to obtain a first product and a second product;

the determining module is configured to determine a sum of the first product and the second product as a final difference image.

6. The apparatus of claim 4 or 5, further comprising:

and the clustering unit is used for clustering the final difference image by utilizing a preset clustering algorithm.

Images