CN112465714A - Multi-temporal remote sensing image processing method, device and equipment - Google Patents

Multi-temporal remote sensing image processing method, device and equipment Download PDF

Info

Publication number
CN112465714A
CN112465714A CN202011330787.XA CN202011330787A CN112465714A CN 112465714 A CN112465714 A CN 112465714A CN 202011330787 A CN202011330787 A CN 202011330787A CN 112465714 A CN112465714 A CN 112465714A
Authority
CN
China
Prior art keywords
image
grid
remote sensing
detected
reference image
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
Application number
CN202011330787.XA
Other languages
Chinese (zh)
Other versions
CN112465714B (en
Inventor
李磊
谭靖
王战举
张哲�
任伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Aerospace Titan Technology Co ltd
Original Assignee
Beijing Aerospace Titan Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Aerospace Titan Technology Co ltd filed Critical Beijing Aerospace Titan Technology Co ltd
Priority to CN202011330787.XA priority Critical patent/CN112465714B/en
Priority claimed from CN202011330787.XA external-priority patent/CN112465714B/en
Publication of CN112465714A publication Critical patent/CN112465714A/en
Application granted granted Critical
Publication of CN112465714B publication Critical patent/CN112465714B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G06T5/80—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • 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

Abstract

The application relates to a multi-temporal remote sensing image processing method, which comprises the following steps: selecting one time phase of remote sensing image data from two different time phases of remote sensing image data as a reference image, and taking the other time phase of remote sensing image data as an image to be detected; determining an overlapping area of a reference image and an image to be detected, calculating a circumscribed rectangle of the overlapping area, taking the circumscribed rectangle as an uppermost layer grid, and gradually dividing the circumscribed rectangle to construct a multi-level grid; resampling the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an normalized image to be detected, and respectively performing feature description operator calculation on the normalized reference image and the normalized image to be detected pixel by pixel to obtain a feature description operator of each pixel; and determining the confidence coefficient of each layer of grid in the multi-level grid according to the obtained feature description operator, and obtaining the change probability of the remote sensing image according to the confidence coefficient. The method can effectively improve the accuracy of the change detection result of the remote sensing image.

Description

Multi-temporal remote sensing image processing method, device and equipment
Technical Field
The present application relates to the field of remote sensing image processing technologies, and in particular, to a method, an apparatus, and a device for processing a multi-temporal remote sensing image.
Background
The multi-temporal remote sensing image is an important data source in the ground feature change monitoring. In the multi-temporal remote sensing data processing and analyzing process, geometric registration among remote sensing images in different periods is generally carried out firstly, and then change detection among the remote sensing images is carried out. Thereby discovering the change of the ground features. However, under the influence of factors such as landform, satellite observation angle and the like, the existing remote sensing image registration result still has a certain geometric residual error. Meanwhile, in the related art, when the remote sensing image is processed, image registration and change detection of the remote sensing image are usually performed separately in two stages, and the factor of surface feature change is not considered in geometric registration, so that registration geometric errors are increased, and the accuracy of the result of change detection is low.
Disclosure of Invention
In view of this, the application provides a multi-temporal remote sensing image processing method, which can effectively improve the accuracy of a remote sensing image change detection result.
According to an aspect of the application, a multi-temporal remote sensing image processing method is provided, and includes:
selecting one time phase of remote sensing image data from two different time phases of remote sensing image data as a reference image, and taking the other time phase of remote sensing image data as an image to be detected;
determining an overlapping area of the reference image and the image to be detected, calculating an external rectangle of the overlapping area, and gradually dividing the external rectangle by taking the external rectangle as an uppermost grid to construct a multi-level grid;
resampling the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an normalized image to be detected, and performing feature description operator calculation on the normalized reference image and the normalized image to be detected pixel by pixel to obtain feature description operators of pixels in the reference image and the image to be detected;
and determining the confidence coefficient of each layer of grid in the multi-level grids according to the obtained feature description operator, and obtaining the change probability of the remote sensing image according to the confidence coefficient.
In a possible implementation manner, before determining an overlapping region between the reference image and the image to be detected, the method further includes:
and performing geometric correction on the image to be detected by adopting an image registration method and taking the reference image as a reference.
In a possible implementation manner, with the external rectangle as the uppermost layer mesh, it is right that the external rectangle is segmented step by step, and the construction obtains a multi-level mesh, including:
dividing the external rectangle into two sub-rectangles by taking the perpendicular bisector of the longer side of the external rectangle as a dividing line to obtain a next-level grid of the grid on the uppermost layer;
respectively segmenting each sub-rectangle step by taking the perpendicular bisector of the longer side of each sub-rectangle as a segmentation line until the longer side of the rectangle obtained by segmentation is smaller than the pixel size of the reference image;
and taking the circumscribed rectangle as the uppermost grid, and arranging the segmentation results as a hierarchy from top to bottom according to a generation sequence to generate the corresponding multilevel grid.
In a possible implementation manner, when the reference image and the image to be detected are resampled based on the multi-level grid, a bilinear interpolation method is adopted.
In a possible implementation manner, when feature description operator calculation is performed on the normalized reference image and the normalized image to be detected pixel by pixel to obtain feature description operators of pixels in the reference image and the image to be detected, according to a formula:
Figure BDA0002795757590000021
Figure BDA0002795757590000022
calculating to obtain;
wherein i is an integer from 0 to 3, j is an integer from 0 to 31, σ is a gaussian distribution probability density function with variance of 1, and Fr (i, j) is a characteristic operator of the pixel P (x0, y 0).
In a possible implementation manner, determining a confidence level of each layer of the multi-level mesh according to the obtained feature description operator includes:
determining the confidence coefficient of the uppermost grid as a first preset value, and taking the uppermost grid as the current grid;
and searching the next layer of grid of the current grid step by step according to the corresponding relation in the multi-stage grids, and calculating the confidence coefficient of the next layer of grid according to the confidence coefficient of the current grid until the lowest grid is searched.
In a possible implementation manner, a value of the first preset value is 1;
and when the confidence coefficient of the next layer of grid is obtained by calculation according to the confidence coefficient of the current grid, according to a formula:
Figure BDA0002795757590000031
calculating to obtain;
wherein the content of the first and second substances,
Figure BDA0002795757590000032
representing all resampled pixel positions, Fr, corresponding to the lower layerrCharacteristic operator, Fr, representing a reference imagetCharacteristic operator, k, representing the image to be registeredpRepresenting the confidence of the current mesh.
In a possible implementation manner, obtaining the remote sensing image change probability according to the confidence coefficient includes:
and performing logic calculation on the confidence coefficient of each pixel, and determining the change probability of the remote sensing image according to the calculation result.
According to another aspect of the application, a multi-temporal remote sensing image processing device is further provided, and comprises an image selecting module, a grid constructing module, a feature description operator calculating module and a change probability determining module;
the image selecting module is configured to select one time phase of remote sensing image data from two different time phases of remote sensing image data as a reference image, and the other time phase of remote sensing image data as an image to be detected;
the grid construction module is configured to determine an overlapping region of the reference image and the image to be detected, calculate an external rectangle of the overlapping region, divide the external rectangle step by taking the external rectangle as an uppermost grid, and construct a multi-level grid;
the feature description operator calculation module is configured to resample the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an image to be detected, and perform feature description operator calculation on the normalized reference image and the image to be detected pixel by pixel to obtain feature description operators of pixels in the reference image and the image to be detected;
and the change probability determination module is configured to determine the confidence of each layer of the multi-level grids according to the obtained feature description operator, and obtain the change probability of the remote sensing image according to the confidence.
According to another aspect of the present application, there is also provided a multi-temporal remote sensing image processing apparatus including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute the executable instructions to implement any of the methods described above.
The multi-temporal remote sensing image processing method of the embodiment of the application respectively uses the remote sensing images of two different temporal phases as the reference image and the image to be detected, then, the overlapped area of the reference image and the image to be detected is segmented step by step to construct a corresponding multi-stage grid, then, the reference image and the image to be detected are resampled based on the constructed multi-level grid, and then the characteristic description operators of each pixel in the reference image and the image to be detected are respectively calculated, after the confidence coefficient of each grade of grid is determined according to the feature description operator of each pixel, the change probability of the remote sensing image is finally obtained according to the determined confidence coefficient of each grade of grid, so that the multi-grade grid is designed, the aim of integrating local registration and change detection is fulfilled by multiple iterative operations on the basis of calculating an image pixel feature description operator, so that the accuracy of a remote sensing image change detection result is effectively improved.
Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the application and, together with the description, serve to explain the principles of the application.
Fig. 1 shows a flowchart of a multi-temporal remote sensing image processing method according to an embodiment of the present application;
fig. 2 is a block diagram showing a configuration of a multi-temporal remote sensing image processing apparatus according to an embodiment of the present application;
fig. 3 shows a block diagram of a multi-temporal remote sensing image processing device according to an embodiment of the present application.
Detailed Description
Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present application.
Fig. 1 shows a flowchart of a multi-temporal remote sensing image processing method according to an embodiment of the present application. As shown in fig. 1, the method includes: and S100, selecting the remote sensing image data of one time phase from the remote sensing image data of two different time phases as a reference image, and using the remote sensing image data of the other time phase as an image to be detected. Here, it should be noted that the remote sensing image data of two different time phases refers to two remote sensing images of different time phases of the same region that are acquired. Meanwhile, it should be noted that the selection of the reference image and the image to be detected can be flexibly selected according to the requirement. Namely, the front time phase remote sensing image in the same area can be used as a reference image, and the rear time phase remote sensing image can be used as an image to be detected. Or selecting a front time phase remote sensing image of the same area as an image to be detected and a rear time phase remote sensing image as a reference image.
Step S200, determining an overlapping area of the reference image and the image to be detected, calculating an external rectangle of the overlapping area, taking the external rectangle as the uppermost grid, and gradually dividing the external rectangle to construct a multi-level grid. In this step, the calculation of the overlapping area between the reference image and the image to be detected may be implemented by using conventional technical means in the art, which is not described herein again. The circumscribed rectangle of the overlap region refers to the four to four range of the overlap region, which includes all the pixels of the overlap region. The constructed multi-level grid corresponds to image areas contained in rectangles segmented by different levels.
And step S300, resampling the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an image to be detected, and calculating feature description operators pixel by pixel for the normalized reference image and the image to be detected respectively to obtain the feature description operators of each pixel in the reference image and the image to be detected.
And finally, determining the confidence of each layer of grid in the multi-level grids according to the obtained feature description operator through step S400, and obtaining the change probability of the remote sensing image according to the confidence.
Therefore, the multi-temporal remote sensing image processing method of the embodiment of the application, by respectively using the remote sensing images of two different time phases as the reference image and the image to be detected, then segmenting the overlapping region of the reference image and the image to be detected step by step, constructing the corresponding multi-level grid, then resampling the reference image and the image to be detected based on the constructed multi-level grid, then respectively calculating the feature description operators of each pixel in the reference image and the image to be detected, determining the confidence coefficient of each level of grid according to the feature description operators of each pixel, finally obtaining the change probability of the remote sensing image according to the confidence coefficient of each level of grid, achieves the purpose of integrating local registration and change detection integrated processing by designing the multi-level grid and performing multiple iterative operations on the basis of calculating the pixel feature description operators of the image, therefore, the accuracy of the change detection result of the remote sensing image is effectively improved.
It should be noted that, in the method of the embodiment of the present application, after the reference image and the image to be detected are determined, and before the overlapping region between the reference image and the image to be detected is calculated, a step of performing geometric correction on the image to be detected by using a general image registration method and using the reference image as a reference is further included, so that the geometric error between the reference image and the image to be detected is reduced as much as possible, and a foundation is laid for ensuring the accuracy of the determined overlapping region.
Here, it should be noted that, taking the reference image as a reference, the image registration method adopted for performing geometric correction on the image to be detected may be a conventional technique in the art, and details are not repeated here.
After the overlapping area between the reference image and the image to be detected is determined, the circumscribed rectangle of the overlapping area can be calculated. The circumscribed rectangle may be implemented in a manner that calculates the four to four range of the overlap region. Then, the perpendicular bisector of the longer side of the circumscribed rectangle is used as a dividing line, which is equally divided into two sub-rectangles. And then, respectively repeating the division operation on the two divided sub-rectangles, namely respectively dividing the two sub-rectangles by taking the perpendicular bisectors of the longer sides of the two sub-rectangles as the division lines to obtain four rectangles. By analogy, each rectangle obtained by current segmentation is segmented in the above manner step by step until the lengths of the two sides of the sub-rectangle after current segmentation are both smaller than the pixel size of the reference image (or the length of the longer side is smaller than the pixel size of the reference image), and then the segmentation of the multi-stage grid can be completed.
Wherein, the external rectangles of the overlapped region are used as the uppermost layer grid, and the division results are used as a hierarchy and are arranged from top to bottom according to the generation sequence, thereby constructing the multi-level grid.
Here, as can be understood by those skilled in the art, by constructing a multi-level mesh, multi-level segmentation of an overlapping region between a reference image and an image to be detected is achieved, and each layer and the mesh include a part of images in the overlapping region.
And then, resampling the reference image and the image to be detected to obtain the normalized reference image and the normalized image to be detected. When the reference image and the image to be detected are resampled, a bilinear interpolation method can be adopted to resample the image according to the lowest grid. By adopting a bilinear interpolation method based on the constructed multi-level grid, the reference image and the image to be detected are respectively resampled according to the lowest grid (namely, the lowest grid) in the multi-level grid, so that the characteristics of the structured reference image and the image to be detected are more obvious.
Meanwhile, respectively carrying out feature description operator calculation on the normalized reference image and the normalized image to be detected pixel by pixel, and obtaining the feature description operator of each pixel in the reference image and the image to be detected according to the following formula:
Figure BDA0002795757590000071
Figure BDA0002795757590000072
wherein i is an integer from 0 to 3, j is an integer from 0 to 31, and σ is a gaussian distribution probability density function with variance of 1. Taking Fr (i, j) as a 128-dimensional feature array, namely, taking Fr (i, j) as a pixel P (x)0,y0) The feature operator is obtained by adopting an SIFT operator calculation method.
Further, determining the confidence of each layer of grid in the multi-level grids according to the obtained feature description operator can be realized in the following manner.
That is, the topmost grid only contains one grid, the confidence of the grid is determined to be a first preset value, and the topmost grid is used as the current grid. Then, according to the corresponding relation in the multi-stage grids, the next layer of grid of the current grid is searched step by step, and according to the confidence coefficient of the current grid, the confidence coefficient of the next layer of grid is calculated until the grid at the bottommost layer is searched. Here, it should be noted that the value of the first preset value may be set to 1.
That is to say, when determining the confidence of each layer of lattice in the multi-level lattice according to the obtained feature description operator, the confidence of all the lattices in each layer of lattice may be determined layer by layer (step by step) starting from the topmost lattice of the constructed multi-level lattice.
Meanwhile, when the confidence coefficient of each layer of grid is carried out, the confidence coefficient of the uppermost layer grid is set to be 1, and the uppermost layer grid is used as the current grid. Then, according to the corresponding relationship of the multilevel grids, searching the lower-layer grid corresponding to the current grid, and respectively calculating the confidence of the lower-layer grid according to the following formula:
Figure BDA0002795757590000081
wherein the content of the first and second substances,
Figure BDA0002795757590000082
representing all resampled pixel positions, Fr, corresponding to the lower gridrCharacteristic operator, Fr, representing a reference imagetCharacteristic operator, k, representing the image to be registeredpThe confidence of the current layer lattice is characterized.
And after the confidence coefficient of the next layer of the current lattice is calculated, continuing to execute the steps, taking the currently calculated lattice as the current lattice, and continuing to calculate the confidence coefficient of the next layer of the lattice until the confidence coefficient of the lowest layer of the lattice is calculated.
After the confidence of the bottom layer grid is calculated, the bottom layer grid and the pixels are in one-to-one correspondence, and the confidence of all the pixels in the overlapping area of the reference image and the image to be detected is obtained.
And after the confidence coefficient of each pixel is obtained, calculating the corresponding grid change probability according to the following formula.
Pc＝∑i∈gridki
Wherein, PcFor the lattice change probability, grid is all pixels in the lattice, i is the ith pixel in the lattice, kiIs the confidence of the pixel.
The lattice change probability is calculated starting from the lowest mesh. Firstly, calculating the lattice change probability of all lattices in the lowest layer of the grid; when P of a certain latticecWhen the number of the pixels is more than or equal to 0.5, the grid is considered to have ground object change, and the pixels belonging to the grid do not participate in the calculation of the change probability of the corresponding upper grid; such as PcAnd if the grid change probability is less than 0.5, the grid change probability of the upper-level grid is continued. And calculating and judging the change probability of all the layers of grids until the grids which are changed are identified as the result of change detection.
Correspondingly, based on any one of the multi-temporal remote sensing image processing methods, the application also provides a multi-temporal remote sensing image processing device. Because the working principle of the multi-temporal remote sensing image processing device provided by the application is the same as or similar to that of the multi-temporal remote sensing image processing method provided by the application, repeated parts are not repeated.
Referring to fig. 2, the multi-temporal remote sensing image processing apparatus 100 provided by the present application includes an image selecting module 110, a mesh constructing module 120, a feature descriptor calculating module 130, and a change probability determining module 140. The image selecting module 110 is configured to select one time phase of remote sensing image data from two different time phases of remote sensing image data as a reference image, and select another time phase of remote sensing image data as an image to be detected. The grid constructing module 120 is configured to determine an overlapping region between the reference image and the image to be detected, calculate an external rectangle of the overlapping region, use the external rectangle as the uppermost grid, divide the external rectangle step by step, and construct a multi-level grid. The feature description operator calculation module 130 is configured to resample the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an normalized image to be detected, and perform feature description operator calculation on the normalized reference image and the normalized image to be detected pixel by pixel to obtain feature description operators of pixels in the reference image and the image to be detected. And the change probability determination module 140 is configured to determine a confidence of each layer of the multi-level grid according to the obtained feature description operator, and obtain the change probability of the remote sensing image according to the confidence.
Still further, according to another aspect of the present application, there is also provided a multi-temporal remote sensing image processing apparatus 200. Referring to fig. 3, the multi-temporal remote sensing image processing apparatus 200 according to the embodiment of the present application includes a processor 210 and a memory 220 for storing instructions executable by the processor 210. The processor 210 is configured to execute the executable instructions to implement any one of the aforementioned multi-temporal remote sensing image processing methods.
Here, it should be noted that the number of the processors 210 may be one or more. Meanwhile, the multi-temporal remote sensing image processing apparatus 200 according to the embodiment of the present application may further include an input device 230 and an output device 240. The processor 210, the memory 220, the input device 230, and the output device 240 may be connected via a bus, or may be connected via other methods, which is not limited in detail herein.
The memory 220, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and various modules, such as: the program or the module corresponding to the multi-temporal remote sensing image processing method in the embodiment of the application. The processor 210 executes various functional applications and data processing of the multi-temporal remote sensing image processing apparatus 200 by executing software programs or modules stored in the memory 220.
The input device 230 may be used to receive an input number or signal. Wherein the signal may be a key signal generated in connection with user settings and function control of the device/terminal/server. The output device 240 may include a display device such as a display screen.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (10)

1. A multi-temporal remote sensing image processing method is characterized by comprising the following steps:
selecting one time phase of remote sensing image data from two different time phases of remote sensing image data as a reference image, and taking the other time phase of remote sensing image data as an image to be detected;
determining an overlapping area of the reference image and the image to be detected, calculating an external rectangle of the overlapping area, and gradually dividing the external rectangle by taking the external rectangle as an uppermost grid to construct a multi-level grid;
resampling the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an normalized image to be detected, and performing feature description operator calculation on the normalized reference image and the normalized image to be detected pixel by pixel to obtain feature description operators of pixels in the reference image and the image to be detected;
and determining the confidence coefficient of each layer of grid in the multi-level grids according to the obtained feature description operator, and obtaining the change probability of the remote sensing image according to the confidence coefficient.
2. The method according to claim 1, wherein before determining the overlapping region between the reference image and the image to be detected, further comprising:
and performing geometric correction on the image to be detected by adopting an image registration method and taking the reference image as a reference.
3. The method according to claim 1, wherein the step-by-step dividing the bounding rectangle with the bounding rectangle as the topmost grid to construct a multi-level grid comprises:
dividing the external rectangle into two sub-rectangles by taking the perpendicular bisector of the longer side of the external rectangle as a dividing line to obtain a next-level grid of the grid on the uppermost layer;
respectively segmenting each sub-rectangle step by taking the perpendicular bisector of the longer side of each sub-rectangle as a segmentation line until the longer side of the rectangle obtained by segmentation is smaller than the pixel size of the reference image;
and taking the circumscribed rectangle as the uppermost grid, and arranging the segmentation results as a hierarchy from top to bottom according to a generation sequence to generate the corresponding multilevel grid.
4. The method according to claim 1, wherein the resampling of the reference image and the image to be detected based on the multi-level mesh is performed by using a bilinear interpolation method.
5. The method according to claim 1, wherein when the feature description operator calculation is performed on the normalized reference image and the normalized image to be detected pixel by pixel to obtain the feature description operator of each pixel in the reference image and the image to be detected, according to a formula:
Figure FDA0002795757580000021
calculating to obtain;
wherein i is an integer from 0 to 3, j is an integer from 0 to 31, σ is a gaussian distribution probability density function with variance of 1, and Fr (i, j) is a characteristic operator of the pixel P (x0, y 0).
6. The method of claim 1, wherein determining a confidence level for each of the multiple levels of meshes based on the obtained feature descriptors comprises:
determining the confidence coefficient of the uppermost grid as a first preset value, and taking the uppermost grid as the current grid;
and searching the next layer of grid of the current grid step by step according to the corresponding relation in the multi-stage grids, and calculating the confidence coefficient of the next layer of grid according to the confidence coefficient of the current grid until the lowest grid is searched.
7. The method of claim 6, wherein the first preset value takes a value of 1;
and when the confidence coefficient of the next layer of grid is obtained by calculation according to the confidence coefficient of the current grid, according to a formula:
Figure FDA0002795757580000022
calculating to obtain;
wherein the content of the first and second substances,
Figure FDA0002795757580000023
representing all resampled pixel positions, Fr, corresponding to the lower layerrCharacteristic operator, Fr, representing a reference imagetCharacteristic operator, k, representing the image to be registeredpRepresenting the confidence of the current mesh.
8. The method of claim 1, wherein obtaining the remote sensing image change probability according to the confidence level comprises:
and performing logic calculation on the confidence coefficient of each pixel, and determining the change probability of the remote sensing image according to the calculation result.
9. A multi-temporal remote sensing image processing device is characterized by comprising an image selection module, a grid construction module, a feature description operator calculation module and a change probability determination module;
the image selecting module is configured to select one time phase of remote sensing image data from two different time phases of remote sensing image data as a reference image, and the other time phase of remote sensing image data as an image to be detected;
the grid construction module is configured to determine an overlapping region of the reference image and the image to be detected, calculate an external rectangle of the overlapping region, divide the external rectangle step by taking the external rectangle as an uppermost grid, and construct a multi-level grid;
the feature description operator calculation module is configured to resample the reference image and the image to be detected based on the multi-level grid to obtain a normalized reference image and an image to be detected, and perform feature description operator calculation on the normalized reference image and the image to be detected pixel by pixel to obtain feature description operators of pixels in the reference image and the image to be detected;
and the change probability determination module is configured to determine the confidence of each layer of the multi-level grids according to the obtained feature description operator, and obtain the change probability of the remote sensing image according to the confidence.
10. A multi-temporal remote sensing image processing device is characterized by comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to carry out the executable instructions when implementing the method of any one of claims 1 to 8.
CN202011330787.XA 2020-11-24 Multi-time-phase remote sensing image processing method, device and equipment Active CN112465714B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011330787.XA CN112465714B (en) 2020-11-24 Multi-time-phase remote sensing image processing method, device and equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011330787.XA CN112465714B (en) 2020-11-24 Multi-time-phase remote sensing image processing method, device and equipment

Publications (2)

Publication Number Publication Date
CN112465714A true CN112465714A (en) 2021-03-09
CN112465714B CN112465714B (en) 2024-05-07

Family

ID=

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102073990A (en) * 2010-11-26 2011-05-25 中国科学院遥感应用研究所 System framework and method for automatic geometric correction of remote sensing images
CN103544711A (en) * 2013-11-08 2014-01-29 国家测绘地理信息局卫星测绘应用中心 Automatic registering method of remote-sensing image
US20140146996A1 (en) * 2012-11-27 2014-05-29 Deutsches Zentrum Fur Luft-Und Raumfahrt E.V. Device and Method for the Processing of Remote Sensing Data
CN105551028A (en) * 2015-12-09 2016-05-04 中山大学 Method and system for dynamically updating geographic space data based on remote sensing image
CN105913435A (en) * 2016-04-13 2016-08-31 西安航天天绘数据技术有限公司 Multidimensional remote sensing image matching method and multidirectional remote sensing image matching system suitable for large area
CN106447653A (en) * 2016-09-09 2017-02-22 河海大学 Method for detecting change of multi-temporal and multispectral image based on spatial constraint chi-squared transform
CN106780355A (en) * 2016-11-17 2017-05-31 中国科学院遥感与数字地球研究所 A kind of Enhancement Methods about Satellite Images
CN109598750A (en) * 2018-12-07 2019-04-09 中国地质大学（武汉） One kind being based on the pyramidal large scale differential image characteristic point matching method of deformation space
US10325370B1 (en) * 2016-05-31 2019-06-18 University Of New Brunswick Method and system of coregistration of remote sensing images

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102073990A (en) * 2010-11-26 2011-05-25 中国科学院遥感应用研究所 System framework and method for automatic geometric correction of remote sensing images
US20140146996A1 (en) * 2012-11-27 2014-05-29 Deutsches Zentrum Fur Luft-Und Raumfahrt E.V. Device and Method for the Processing of Remote Sensing Data
CN103544711A (en) * 2013-11-08 2014-01-29 国家测绘地理信息局卫星测绘应用中心 Automatic registering method of remote-sensing image
CN105551028A (en) * 2015-12-09 2016-05-04 中山大学 Method and system for dynamically updating geographic space data based on remote sensing image
CN105913435A (en) * 2016-04-13 2016-08-31 西安航天天绘数据技术有限公司 Multidimensional remote sensing image matching method and multidirectional remote sensing image matching system suitable for large area
US10325370B1 (en) * 2016-05-31 2019-06-18 University Of New Brunswick Method and system of coregistration of remote sensing images
CN106447653A (en) * 2016-09-09 2017-02-22 河海大学 Method for detecting change of multi-temporal and multispectral image based on spatial constraint chi-squared transform
CN106780355A (en) * 2016-11-17 2017-05-31 中国科学院遥感与数字地球研究所 A kind of Enhancement Methods about Satellite Images
CN109598750A (en) * 2018-12-07 2019-04-09 中国地质大学（武汉） One kind being based on the pyramidal large scale differential image characteristic point matching method of deformation space

Similar Documents

Publication Publication Date Title
EP2067123A1 (en) Method of deriving digital terrain models from digital surface models
CN111750864A (en) Repositioning method and device based on visual map
CN113496150B (en) Dense target detection method and device, storage medium and computer equipment
CN111091572B (en) Image processing method and device, electronic equipment and storage medium
CN115375917A (en) Target edge feature extraction method, device, terminal and storage medium
US10089764B2 (en) Variable patch shape synthesis
CN111552751B (en) Three-dimensional landmark control point generation and application method, generation and application device
CN116881515B (en) Method and electronic equipment for comparing capacitance results solved by different algorithms
CN114494775A (en) Video segmentation method, device, equipment and storage medium
CN112446951B (en) Three-dimensional reconstruction method, three-dimensional reconstruction device, electronic equipment and computer storage medium
CN112465714A (en) Multi-temporal remote sensing image processing method, device and equipment
CN111275616B (en) Low-altitude aerial image splicing method and device
CN112465714B (en) Multi-time-phase remote sensing image processing method, device and equipment
CN111027551B (en) Image processing method, apparatus and medium
US11205091B2 (en) Object information registration apparatus and object information registration method
CN116645499A (en) Determination method, determination device, determination apparatus, determination device, determination program storage medium, and determination program product
CN113344994B (en) Image registration method, device, electronic equipment and storage medium
CN114463503A (en) Fusion method and device of three-dimensional model and geographic information system
CN109242894B (en) Image alignment method and system based on mobile least square method
CN109816613B (en) Image completion method and device
WO2022063386A1 (en) Generation of a 3d point cloud of a scene
CN112927256A (en) Boundary fusion method and device for partitioned area and mobile robot
CN111754397B (en) Remote sensing image embedding method and device, electronic equipment and storage medium
KR20190086323A (en) Method and apparatus for composing images
US20220147754A1 (en) Relocation method, mobile machine using the same, and computer readable 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
CB02 Change of applicant information

Country or region after: China

Address after: 100075 room 1107, Haitai building, 229 beisihuanzhong Road, Haidian District, Beijing

Applicant after: Aerospace Science and Technology (Beijing) Space Information Application Co.,Ltd.

Address before: 100075 room 1107, Haitai building, 229 beisihuanzhong Road, Haidian District, Beijing

Applicant before: BEIJING AEROSPACE TITAN TECHNOLOGY Co.,Ltd.

Country or region before: China

GR01 Patent grant