Remote sensing image registration method and device, equipment and medium

Abstract

The remote sensing image registration method is suitable for the technical field of remote sensing image processing. The method comprises the following steps: acquiring a remote sensing image to be registered and a reference image; obtaining homonymy point pair coordinates of the to-be-registered remote sensing image and the reference image based on image matching; performing height layering augmentation on the homonymy point pair coordinates to obtain augmented point pair coordinates; performing normalization processing on the augmented point pair coordinates to obtain a normalized coordinate pair; calculating hyper-parameters of the geometric transformation model based on the normalized coordinate pair; and on the basis of the hyper-parameters, calculating to obtain a coordinate transformation value of the remote sensing image to be registered by utilizing the geometric transformation model, and completing remote sensing image registration. An augmented homonymy point pair is constructed through a height layering technology, so that the problem of local geometric deformation caused by terrain height change in a remote sensing image is solved; and a geometric transformation model expressed by hyper-parameters is adopted, so that the registration speed and the adaptability of the model are improved. The invention also provides a remote sensing image registration device, equipment and a medium.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image processing, and in particular to a remote sensing image registration method, device, equipment and medium. Background Art

[0002] In remote sensing image applications, it is often necessary to fuse or detect changes in image data acquired by different types of remote sensors or the same remote sensor at different times, which requires remote sensing image registration processing. Remote sensing image registration is the process of aligning remote sensing images from different sources in space, which mainly involves image matching and image geometric transformation. Its essence is to obtain the coordinate transformation relationship between the images based on the similarity measurement criteria when there is a certain grayscale transformation and geometric transformation between the two remote sensing images, and transform the two remote sensing images of the same scene into the same coordinate system. Image matching is mainly to extract the same-name points on the two images, and image geometric transformation is to achieve coordinate alignment of the two images.

[0003] The geometric transformation in remote sensing images is to fit the geometric changes between images using mathematical models based on the geometric distortion between two remote sensing images. It can generally be divided into global image geometric transformation and local image geometric transformation. Global geometric transformation usually uses parameter matrices to describe the global geometric transformation of the image, such as translation transformation model, rotation transformation model, rigid body transformation model, affine transformation model and projection transformation model. However, due to the use of global transformation models, it is difficult to eliminate the local geometric deformation in the image, so the image registration accuracy is relatively limited, and it is difficult to achieve high-precision registration.

[0004] The local geometric transformation model uses a local deformation model according to the local geometric deformation of the remote sensing image at different locations, such as the commonly used affine transformation model, to achieve local high-precision registration. The most common technology is to construct a precise registration method of small image facets based on matching same-name point pairs, such as constructing triangular facets based on triangulated networks, to achieve high-precision local registration. However, this type of method requires constructing small facets one by one based on a large number of same-name point pairs, which is time-consuming.

[0005] With the development of remote sensing image processing, higher requirements are placed on the accuracy and speed of remote sensing image registration. These traditional global geometric transformation and local geometric transformation methods are difficult to achieve efficient and high-precision geometric transformation effects. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In order to solve at least one of the above-mentioned technical problems in remote sensing image registration in the prior art, the embodiments of the present invention provide a remote sensing image registration method, device, equipment and medium, which solves the local geometric deformation problem caused by the change of terrain height in the remote sensing image by constructing augmented same-name point pairs through height layering technology; in addition, a geometric transformation model expressed by hyperparameters is used to describe the geometric transformation relationship between the two remote sensing images, and a large number of augmented same-name point pairs are used to solve the fitting parameters of the geometric transformation model between the two remote sensing images, thereby improving the registration speed. At the same time, the universal model of hyperparameters has extremely strong adaptability and can adapt to remote sensing images of various imaging geometries. Therefore, the method of the embodiment of the present invention has good registration accuracy for the geometric transformation of remote sensing images from different sources.

[0008] (II) Technical solution

[0009] In view of the above problems, embodiments of the present invention provide a remote sensing image registration method, apparatus, device and medium.

[0010] According to a first aspect of the present invention, a remote sensing image registration method is provided, comprising: obtaining a remote sensing image to be registered and a reference image; obtaining the coordinates of the same-name point pairs of the remote sensing image to be registered and the reference image based on image matching; performing highly layered augmentation on the coordinates of the same-name point pairs to obtain augmented point pair coordinates; normalizing the augmented point pair coordinates to obtain normalized coordinate pairs; calculating hyperparameters of a geometric transformation model based on the normalized coordinate pairs; and, based on the hyperparameters, using the geometric transformation model, calculating the coordinate transformation values ​​of the remote sensing image to be registered, thereby completing remote sensing image registration.

[0011] In some exemplary embodiments, performing highly layered augmentation on the coordinates of the same-name point pairs includes performing N layers of height augmentation on the coordinates of the same-name point pairs in the height direction, and placing the augmented height values ​​at the middle positions of the coordinates of the same-name point pairs, respectively, to obtain augmented point pair coordinates; wherein N is a positive integer greater than or equal to 2; and the number of augmented point pair coordinates is N times the number of the coordinates of the same-name point pairs.

[0012] In some exemplary embodiments, normalizing the augmented point pair coordinates includes constructing a normalization equation based on a data centering parameter and a scale parameter of the augmented point pair coordinates to calculate and obtain a normalized coordinate pair.

[0013] In some exemplary embodiments, the normalized coordinate pair includes a first normalized coordinate consisting of an augmented height coordinate and a normalized coordinate of a reference image and a second normalized coordinate of the remote sensing image to be registered.

[0014] In some exemplary embodiments, the hyperparameters include a first hyperparameter and a second hyperparameter associated with the horizontal coordinate in the second normalized coordinate and the first normalized coordinate; and a third hyperparameter and a fourth hyperparameter associated with the vertical coordinate in the second normalized coordinate and the first normalized coordinate.

[0015] In some exemplary embodiments, the number of first hyperparameters is 20; the number of second hyperparameters is 19; the number of third hyperparameters is 20; and the number of fourth hyperparameters is 19.

[0016] In some exemplary embodiments, based on the hyperparameters, using the geometric transformation model, calculating the coordinate transformation value of the remote sensing image to be registered includes: multiplying the first hyperparameter, the second hyperparameter, the third hyperparameter and the third hyperparameter respectively with the polynomial composed of the second normalized coordinates and summing them to obtain the corresponding first calculation factor, the second calculation factor, the third calculation factor and the fourth calculation factor. Dividing the first calculation factor by the second calculation factor to obtain the first coefficient; dividing the third calculation factor by the fourth calculation factor to obtain the second coefficient; calculating the horizontal coordinate of the registration based on the first coefficient, the scale parameter of the horizontal coordinate of the reference image and the centering parameter of the horizontal coordinate of the reference image; and calculating the vertical coordinate of the registration based on the second coefficient, the scale parameter of the vertical coordinate of the reference image and the centering parameter of the vertical coordinate of the reference image.

[0017] The second aspect of the present invention provides a remote sensing image registration device, including: an acquisition module, used to obtain a remote sensing image to be registered and a reference image; a first processing module, used to obtain the coordinates of the same-name point pairs of the remote sensing image to be registered and the reference image based on image matching; a second processing module, used to perform highly hierarchical augmentation on the coordinates of the same-name point pairs to obtain augmented point pair coordinates; a third processing module, used to perform normalization processing on the augmented point pair coordinates to obtain normalized coordinates; a calculation module, used to calculate the hyperparameters of a geometric transformation model based on the normalized coordinates; and a registration module, used to calculate the coordinate transformation values ​​of the remote sensing image to be registered based on the hyperparameters and using the geometric transformation model to complete the remote sensing image registration.

[0018] A third aspect of the present invention provides an electronic device, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0019] The fourth aspect of the present invention also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above method.

[0020] (III) Beneficial effects

[0021] It can be seen from the above technical solutions that the remote sensing image registration method, device, equipment and medium provided by the embodiments of the present invention have at least one of the following beneficial effects:

[0022] (1) A universal geometric transformation expressed by hyperparameters is used to describe the geometric correspondence of remote sensing image registration. This model can adapt to the geometric transformation of images acquired by various types of remote sensors. Whether it is the angular imaging geometry of optical remote sensing images or the range imaging geometry model of synthetic aperture radar (SAR), it can be accurately fitted by the universal geometric transformation model, making the geometric transformation model highly applicable.

[0023] (2) The extracted pairs of same-name points are expanded by three layers in height using data augmentation technology. The augmented data are used to fit the local geometric deformation of the image caused by terrain changes. This allows the geometric transformation model fitted by hyperparameters to adapt well to the local geometric deformation between the two images, thus achieving high-precision registration of the two images. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0025] Figure 1 A schematic diagram of a process flow of a remote sensing image registration method according to an embodiment of the present invention is schematically shown;

[0026] Figure 2 A schematic structural block diagram of a remote sensing image registration device 800 according to an embodiment of the present invention is shown; and

[0027] Figure 3 A block diagram of an electronic device for a remote sensing image registration method according to an embodiment of the present invention is schematically shown.

[0028] Illustration Description:

[0029] 600-electronic device; 601-processor; 602-read only memory (ROM); 603-random access memory (RAM); 604-bus; 605-input / output (I / O) interface; 606-input part; 607-output part; 608-storage part; 609-communication part; 610-drive; 611-removable medium. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Figure 1 The flowchart of a remote sensing image registration method according to an embodiment of the present invention is schematically shown.

[0032] like Figure 1 As shown, a remote sensing image registration method according to an embodiment of the present invention includes steps S110-S160.

[0033] In step S110 , a remote sensing image to be registered and a reference image are obtained.

[0034] In step S120, the coordinates of the same-name point pairs of the remote sensing image to be registered and the reference image are obtained based on image matching.

[0035] For example, a total of m pairs of coordinates of points with the same name are extracted through remote sensing image matching methods: (x1, y1, u1, v1), (x2, y2, u2, v2)… (x m ,y m ,u m ,v m ), where x i is the i-th point (x i ,y i ), y i is the i-th point (x i ,y i )’s ordinate, u i is the i-th point on the remote sensing image to be registered (u i ,v i ), v i is the i-th point on the remote sensing image to be registered (u i ,v i )’s vertical coordinate.

[0036] In step S130, the coordinates of the point pairs with the same name are highly layered augmented to obtain augmented point pair coordinates.

[0037] In some exemplary embodiments, performing highly layered augmentation on the coordinates of the same-name point pairs includes performing N layers of height augmentation on the coordinates of the same-name point pairs in the height direction, and placing the augmented height values ​​at the middle positions of the coordinates of the same-name point pairs, respectively, to obtain augmented point pair coordinates; wherein N is a positive integer greater than or equal to 2; and the number of augmented point pair coordinates is N times the number of the coordinates of the same-name point pairs.

[0038] For example, the m pairs of coordinates of the same-name point pairs obtained in step S120 are augmented with three levels of height (the heights are set to 0, 50, and 100 respectively) to obtain 3m pairs of point pair data, namely: (x1, y1, 0, u1, v1), (x1, y1, 50, u1, v1) (x1, y1, 100, u1, v1) (x2, y2, 0, u2, v2) (x2, y2, 50, u2, v2) (x2, y2, 100, u2, v2), …, (x1, y1, 0, u1, v1) m ,y m ,0,u m ,v m )(x m ,y m ,50,u m ,v m )(x m ,y m ,100,u m ,v m ).

[0039] In step S140, the augmented point pair coordinates are normalized to obtain normalized coordinate pairs.

[0040] In some exemplary embodiments, normalizing the augmented point pair coordinates includes constructing a normalization equation based on data centering parameters and scale parameters of the augmented point pair coordinates, and calculating a normalized coordinate pair, the normalized coordinate pair including a first normalized coordinate consisting of an augmented height coordinate and a normalized coordinate of a reference image and a second normalized coordinate of the remote sensing image to be registered.

[0041] For example, the 3m-pair point pair data obtained in step S130 is normalized to obtain a normalized 3m-pair normalized coordinate pair. The normalization formula is as follows:

[0042] (1)

[0043] (2)

[0044] (3)

[0045] (4)

[0046] (5)

[0047] Among them, (x0, y0, h0, u0, v0) is the centralization parameter of each data, and the centralization parameter is the average value of each data. s ,y s ,h s ,u s , v s ) is the scale parameter, which is the difference between the maximum and minimum values ​​of each data, x i represents the horizontal coordinate of the i-th point on the reference image, y i represents the ordinate of the i-th point on the reference image, h i represents the height of the i-th point, u i represents the horizontal coordinate of the i-th point on the remote sensing image to be registered, v i represents the ordinate of the i-th point on the remote sensing image to be registered, and then, ( , ) represents the normalized image coordinates of the i-th point on the remote sensing image and ( , , ) represents the normalized image coordinates of the i-th point on the reference image, and the subscript i represents the sequence number of the point pair from 1 to 3m.

[0048] In step S150 , hyperparameters of the geometric transformation model are calculated based on the normalized coordinate pairs.

[0049] In some exemplary embodiments, the hyperparameters include a first hyperparameter and a second hyperparameter associated with the abscissa in the second normalized coordinate and the first normalized coordinate; and a third hyperparameter and a fourth hyperparameter associated with the ordinate in the second normalized coordinate and the first normalized coordinate. Optionally, the number of the first hyperparameter is 20; the number of the second hyperparameter is 19; the number of the third hyperparameter is 20; and the number of the fourth hyperparameter is 19.

[0050] For example, the hyperparameters of the geometric transformation model are calculated based on the augmented normalized coordinates. The specific calculation formulas are:

[0051] (6)

[0052] (7)

[0053] in, is the first hyperparameter; is the second hyperparameter; is the third hyperparameter; is the fourth hyperparameter. The number of the first hyperparameter is 20; the number of the second hyperparameter is 19; the number of the third hyperparameter is 20; and the number of the fourth hyperparameter is 19, and the four types of parameters are 78 in total.

[0054] A represents a matrix with k (k=3m) rows and 39 columns. A can be expressed as:

[0055] (8)

[0056] Among them, R in each row i (i=1 to 3m) has 39 columns of elements, as follows (each element is separated by a comma):

[0057] (9)

[0058] L represents a matrix with k (k=3m) rows and 1 column, and its specific form is:

[0059] (10)

[0060] A T Represents the transpose operation of matrix A. (A) -1 Indicates the inverse calculation of matrix A.

[0061] B is a matrix with k (k=3m) rows and 39 columns, that is:

[0062] (11)

[0063] Each row has 39 columns of elements, as follows (each element is separated by a comma):

[0064] (12)

[0065] M is a matrix with k (k=3m) rows and 1 column, and its specific form is:

[0066] (13)

[0067] B T represents the transpose operation of matrix B, (B) -1 Indicates the inverse calculation of matrix B.

[0068] In step S160, based on the hyperparameters and using the geometric transformation model, the coordinate transformation value of the remote sensing image to be registered is calculated to complete the remote sensing image registration.

[0069] In some exemplary embodiments, calculating the coordinate transformation value of the remote sensing image to be registered includes: multiplying the first hyperparameter, the second hyperparameter, the third hyperparameter and the third hyperparameter respectively with the polynomial composed of the second normalized coordinates and summing them to obtain the corresponding first calculation factor, the second calculation factor, the third calculation factor and the fourth calculation factor. Dividing the first calculation factor by the second calculation factor to obtain the first coefficient; dividing the third calculation factor by the fourth calculation factor to obtain the second coefficient; calculating the horizontal coordinate of the registration based on the first coefficient, the scale parameter of the horizontal coordinate of the reference image and the centering parameter of the horizontal coordinate of the reference image; and calculating the vertical coordinate of the registration based on the second coefficient, the scale parameter of the vertical coordinate of the reference image and the centering parameter of the vertical coordinate of the reference image.

[0070] For example, the formula for calculating the transformation value of the image coordinates to be registered according to the hyperparameters of the geometric transformation model is:

[0071] (14)

[0072] (15)

[0073] Among them, (u, v) is the calculated registration coordinates, (X n , Y n , Z n ) is the normalized image coordinate of the image to be registered, u0, v0 are the centering parameters of the coordinates, u s , v s is the scale parameter, which is calculated in step S130. The first calculation factor, the second calculation factor, the third calculation factor and the fourth calculation factor are respectively , , , Four polynomials, the specific calculation formula is as follows:

[0074] (16)

[0075] (17)

[0076] (18)

[0077] (19)

[0078] in, are the 78 hyperparameters calculated in step S150,

[0079] (X n , Y n , Z n) is calculated as follows:

[0080] (20)

[0081] (twenty one)

[0082] (twenty two)

[0083] Among them, (x, y) is the image coordinate of a pixel of the image to be registered, and h is the height value, which can be directly set to 50. x0, y0, h0 are the corresponding centering parameters, x s ,y s ,h s is a scale parameter, which is calculated in step S130.

[0084] Figure 2 The structural block diagram of a remote sensing image registration device 800 according to an embodiment of the present invention is schematically shown.

[0085] like Figure 2 As shown, a remote sensing image registration device 800 according to an embodiment of the present invention includes an acquisition module 810 , a first processing module 820 , a second processing module 830 , a third processing module 840 , a calculation module 850 and a registration module 860 .

[0086] The acquisition module 810 is used to obtain the remote sensing image and the reference image to be registered.

[0087] The first processing module 820 is used to obtain the coordinates of the same-name point pairs of the remote sensing image to be registered and the reference image based on image matching.

[0088] The second processing module 830 is used to perform highly hierarchical augmentation on the coordinates of the same-name point pairs to obtain augmented point pair coordinates.

[0089] The third processing module 840 is used to normalize the augmented point pair coordinates to obtain normalized coordinates.

[0090] The calculation module 850 is used to calculate the hyperparameters of the geometric transformation model based on the normalized coordinates.

[0091] The registration module 860 is used to calculate the coordinate transformation value of the remote sensing image to be registered based on the hyperparameters and the geometric transformation model to complete the remote sensing image registration.

[0092] In some specific embodiments, any multiple modules among the acquisition module 810, the first processing module 820, the second processing module 830, the third processing module 840, the calculation module 850 and the registration module 860 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0093] In some specific embodiments, at least one of the acquisition module 810, the first processing module 820, the second processing module 830, the third processing module 840, the calculation module 850 and the registration module 860 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the acquisition module 810, the first processing module 820, the second processing module 830, the third processing module 840, the calculation module 850 and the registration module 860 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0094] Figure 3 A block diagram of an electronic device for a remote sensing image registration method according to an embodiment of the present invention is schematically shown.

[0095] like Figure 3 As shown, the electronic device 600 according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an on-board memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0096] In RAM603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM602 and RAM603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to an embodiment of the present invention by executing the program in ROM602 and / or RAM603. It should be noted that the program can also be stored in one or more memories other than ROM602 and RAM603. Processor 601 can also perform various operations of the method flow according to an embodiment of the present invention by executing the program stored in one or more memories.

[0097] In some specific embodiments, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0098] An embodiment of the present invention shows a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0099] In some specific embodiments, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM602 and / or RAM603 described above and / or one or more memories other than ROM602 and RAM603.

[0100] An embodiment of the present invention shows a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present invention.

[0101] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when it is executed by the processor 601. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0102] In some specific embodiments, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0103] In some specific embodiments, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0104] In some specific embodiments, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages, specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, such as Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0105] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present invention may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention may be combined and / or combined in various ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0107] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A remote sensing image registration method, characterized in that: include: Obtaining a remote sensing image to be registered and a reference image; Obtaining coordinates of pairs of points of the same name between the remote sensing image to be registered and the reference image based on image matching; Performing highly hierarchical augmentation on the coordinates of the same-name point pairs to obtain augmented point pair coordinates; Normalizing the augmented point pair coordinates to obtain normalized coordinate pairs; Calculating hyperparameters of a geometric transformation model based on the normalized coordinate pair; as well as Based on the hyperparameters, the coordinate transformation value of the remote sensing image to be registered is calculated using a geometric transformation model to complete the remote sensing image registration.

2. The method according to claim 1, characterized in that The performing height layered augmentation on the coordinates of the same-name point pairs includes performing N-layer height augmentation on the coordinates of the same-name point pairs in the height direction, and placing the augmented height values ​​at the middle positions of the coordinates of the same-name point pairs, respectively, to obtain augmented point pair coordinates; Wherein, N is a positive integer greater than or equal to 2; and The number of the augmented point pair coordinates is N times the number of the same-name point pair coordinates.

3. The method according to claim 1, characterized in that The normalizing the augmented point pair coordinates includes constructing a normalization equation based on a data centering parameter and a scale parameter of the augmented point pair coordinates, and calculating to obtain a normalized coordinate pair.

4. The method according to claim 3, characterized in that The normalized coordinate pair includes a first normalized coordinate consisting of an augmented height coordinate and a normalized coordinate of a reference image and a second normalized coordinate of the remote sensing image to be registered.

5. The method according to claim 4, characterized in that The hyperparameters include a first hyperparameter and a second hyperparameter associated with the abscissa in the second normalized coordinate and the first normalized coordinate; as well as A third hyperparameter and a fourth hyperparameter related to the ordinate in the second normalized coordinate and the first normalized coordinate.

6. The method according to claim 5, characterized in that The number of the first hyperparameters is 20; The number of the second hyperparameters is 19; The number of the third hyperparameters is 20; and The number of the fourth hyperparameters is 19.

7. The method according to claim 5, characterized in that The step of calculating the coordinate transformation value of the remote sensing image to be registered based on the hyperparameters and using the geometric transformation model includes: Multiplying the first hyperparameter, the second hyperparameter, the third hyperparameter and the third hyperparameter respectively with the polynomial composed of the second normalized coordinates and summing them to obtain the corresponding first calculation factor, second calculation factor, third calculation factor and fourth calculation factor; Dividing the first calculation factor by the second calculation factor to obtain a first coefficient; Dividing the third calculation factor by the fourth calculation factor to obtain a second coefficient; Calculating a registered abscissa based on the first coefficient, a scale parameter of the abscissa of the reference image, and a centering parameter of the abscissa of the reference image; and The registered ordinate is calculated based on the second coefficient, the scale parameter of the ordinate of the reference image, and the centering parameter of the ordinate of the reference image.

8. A remote sensing image registration device, characterized in that: The device comprises: An acquisition module, used for obtaining a remote sensing image to be registered and a reference image; A first processing module, used for obtaining the coordinates of the same-name point pairs of the remote sensing image to be registered and the reference image based on image matching; A second processing module is used to perform highly hierarchical augmentation on the coordinates of the same-name point pairs to obtain augmented point pair coordinates; A third processing module, used for normalizing the coordinates of the augmented point pair to obtain normalized coordinates; A calculation module, configured to calculate hyperparameters of a geometric transformation model based on the normalized coordinates; and The registration module is used to calculate the coordinate transformation value of the remote sensing image to be registered based on the hyperparameters and use the geometric transformation model to complete the remote sensing image registration.

9. An electronic device, wherein: include: one or more processors; as well as a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 7.

Images