CN114998755A - Method and device for matching landmarks in remote sensing image - Google Patents
Method and device for matching landmarks in remote sensing image Download PDFInfo
- Publication number
- CN114998755A CN114998755A CN202210534424.0A CN202210534424A CN114998755A CN 114998755 A CN114998755 A CN 114998755A CN 202210534424 A CN202210534424 A CN 202210534424A CN 114998755 A CN114998755 A CN 114998755A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- landmark
- image
- matching
- coastline
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 239000002245 particle Substances 0.000 claims abstract description 136
- 238000011524 similarity measure Methods 0.000 claims abstract description 62
- 230000009466 transformation Effects 0.000 claims abstract description 58
- 238000005457 optimization Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 38
- 238000012952 Resampling Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 136
- 230000003044 adaptive effect Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 10
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000001308 synthesis method Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/759—Region-based matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a device for matching landmarks in remote sensing images. The method comprises the following steps: determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite; determining a similarity measure function value based on a preset geometric transformation function, cloud mask data, a landmark region in a coastline grid image and the image gradient of a remote sensing image of a matching region; taking the target parameter of the preset geometric transformation function as the space position of the particle in a target particle swarm optimization algorithm, taking a similarity measure function as a fitness function of the particle, and determining the parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value; and resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
Description
Technical Field
The application relates to the technical field of satellites, in particular to a method and a device for matching landmarks in remote sensing images.
Background
A new generation of stationary orbit remote sensing satellite images the ground in a triaxial stable mode, and due to the influence of external factors such as orbit, attitude, thermal deformation and the like and geometric distortion factors inside a remote sensor, the ground pointing direction of an optical axis can change greatly within one day under the influence of no control, so that the geographic positioning of a remote sensing image acquired by the stationary orbit remote sensing satellite has a large positioning error. To better eliminate pointing errors and systematic differences caused by the above effects, it is common practice to locate landmarks in remote sensing images.
The existing landmark matching method is mainly used for positioning landmarks in remote sensing images based on gray scale or features. The gray level-based landmark matching method mainly utilizes a one-dimensional or two-dimensional sliding template of a spatial domain to carry out image matching, but has large calculation amount and low matching speed, and because the sea-land image with landmarks and the remote sensing image belong to two types of data with different attributes, the accuracy and the reliability of the landmarks positioned in the remote sensing image are not high; the landmark matching method based on the features is to perform feature matching by extracting significant features from an original image as matching elements, such as corner features, high curvature point features and the like, but due to shielding influence of various factors, good matching cannot be realized for some special areas, such as islands, rivers and the like, and the accuracy and reliability are low.
Disclosure of Invention
The embodiment of the application aims to provide a method and a device for matching landmarks in a remote sensing image, which are used for improving the accuracy and reliability of matching landmarks in the remote sensing image.
In order to achieve the above purpose, the following technical solutions are adopted in the embodiments of the present application:
in a first aspect, an embodiment of the present application provides a method for landmark matching in a remote sensing image, including:
determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
determining a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image and an image gradient of a remote sensing image, wherein the preset geometric transformation function is used for representing a coordinate position corresponding relation between the coastline raster image data of the landmark region and remote sensing image data of a matching region corresponding to the landmark region in the remote sensing image, and the similarity measure function value is used for representing the similarity between the remote sensing image data of the matching region and the coastline raster image data of the landmark region;
taking the target parameter of the preset geometric transformation function as the space position of the particle in a target particle swarm optimization algorithm, taking a similarity measure function as a fitness function of the particle, and determining the parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
In a second aspect, an embodiment of the present application provides an apparatus for landmark matching in a remote sensing image, including:
the first determination module is used for determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
a second determining module, configured to determine a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image, and an image gradient of a remote sensing image, where the preset geometric transformation function is used to represent a coordinate position correspondence between the coastline raster image data of the landmark region and remote sensing image data of a matching region of the landmark region in the remote sensing image, and the similarity measure function value is used to represent a similarity between remote sensing image data of the matching region and the coastline raster image data of the landmark region;
a third determining module, configured to use a target parameter of the preset geometric transformation function as a spatial position of a particle in a target particle swarm optimization algorithm, use a similarity measure function as a fitness function of the particle, and determine a parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and the landmark matching module is used for resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where instructions, when executed by a processor of an electronic device, enable the electronic device to perform the method according to the first aspect.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
considering that the remote sensing image and the coastline grid image belong to two types of data with different attributes, determining that a certain deviation exists between the corresponding relation between the image of the matching area in the remote sensing image and the coastline grid image of the area based on the existing gray correlation matching method, the characteristic matching method and the like, and further influencing the matching precision and reliability of the landmark, for this reason, representing the corresponding relation between the coordinate position of the landmark area in the coastline grid image and the coordinate position of the corresponding matching position of the landmark area in the remote sensing image by adopting a preset geometric transformation function, and representing the similarity between the coastline grid image of the landmark area and the image of the corresponding actual area in the remote sensing image by adopting a similarity measure function, so that the aim of landmark matching can be regarded as that when the similarity between the image of the landmark area in the coastline grid image and the image of the corresponding matching area in the remote sensing image is maximum, presetting a value of a target parameter of a geometric transformation function so as to obtain a corresponding relation between a coordinate position of a landmark region in a coastline grid image and a coordinate position of a corresponding matching position of the landmark region in a remote sensing image, and then positioning the landmark region in the remote sensing image by utilizing the corresponding relation and the coordinate position of the landmark region in the coastline grid image so as to realize landmark matching; further, considering that the similarity measure function is a non-convex function and may have a plurality of extreme values, a heuristic group optimization algorithm, specifically a target particle swarm optimization algorithm, can be adopted, the similarity measure function is used as a fitness function by taking the target parameter of the preset geometric transformation function as the spatial position of the particles in the target particle swarm optimization algorithm, and the parameter value of the target parameter of the preset geometric transformation function can be quickly and accurately determined based on the target particle swarm optimization algorithm and the similarity measure function, so that the accuracy and reliability of landmark matching of candidates in the remote sensing image can be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flowchart of a method for matching landmarks in a remote sensing image according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for matching landmarks in a remote sensing image according to another embodiment of the present application;
fig. 3 is a schematic flowchart of a method for determining a parameter value of a target parameter according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for matching landmarks in remote sensing images according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or described herein. In addition, "and/or" in the specification and claims means at least one of connected objects, and a character "/" generally means that the former and latter related objects are in an "or" relationship.
It should be understood that the training method and the speech synthesis method of the acoustic model provided in the embodiments of the present application may be executed by an electronic device or software installed in the electronic device, and specifically may be executed by a terminal device or a server device.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a method for matching landmarks in remote sensing images according to an embodiment of the present application is provided, which may include the following steps:
s102, determining landmark areas in the coastline grid images, image gradients of remote sensing images obtained by remote sensing satellites and cloud mask data.
Because the gray scale change of pixels of the remote sensing image is obvious and the gradient value is large at the boundary between the land and the water area, the landmark can be positioned in the remote sensing image based on the landmark region in the coastline grid image and the image gradient of the remote sensing image, so as to realize the landmark matching.
In an alternative implementation, determining landmark regions in the coastline raster image includes: and determining a landmark area in the coastline grid image based on the preset nominal grid data and the coordinate position of the matching area in the remote sensing image. More specifically, the coastline image data of the matching area may be determined based on the coordinate position of the matching area in the remote sensing image and preset nominal grid data, and the coastline image data of the matching area may be determined as the landmark area.
In order to ensure the accuracy of the landmark region in the coastline grid image and thus improve the accuracy and reliability of landmark positioning on the remote sensing image, in another alternative implementation, as shown in fig. 2, the determining the landmark region in the coastline grid image may be specifically implemented as: determining rasterized sea-land boundary mask data based on the coastline raster image and preset nominal grid data; further, landmark regions in the coastline raster image are determined based on the rasterized sea-land boundary mask data.
For example, each grid cell in the nominal grid data may be taken as a whole, a spatial index is established according to four corner coordinates of each grid cell, a vector node corresponding to the coastline grid image is determined, a grid cell where the vector node is located is determined through the spatial index, and then a pixel corresponding to the grid cell where the vector node is located is set to be 1, thereby obtaining rasterized sea and land boundary mask data. Of course, it should be understood that the sea-land boundary mask data may also be obtained according to other ways in the art, and this is not limited in the embodiments of the present application.
After obtaining the rasterized sea-land boundary mask data, optionally, the coastline image data of the matching area may be determined based on the landmark area and the size of the matching area of the coastline raster image, and the coastline image data of the matching area may be determined as the landmark area. In the embodiment of the present application, the image gradient of the remote sensing image may be calculated according to a preset gradient operator, for example, a Sobel gradient operator, which is not limited in the embodiment of the present application.
In another embodiment of the present application, to enhance the contrast of the remote sensing image and enhance the interpretation and recognition capabilities of the remote sensing image, thereby facilitating the accuracy and reliability of landmark matching, as shown in fig. 2, before S102, the method implemented by the present application further includes: and carrying out enhancement processing on the remote sensing image. In practical application, the enhancement processing on the remote sensing image can be realized by adopting various image enhancement methods in the field, and the embodiment of the application is not limited to this.
In practical application, the coastline grid image and the remote sensing image related to the embodiment of the application can be generated based on preset nominal grid data.
And S104, determining a similarity measure function value based on a preset geometric transformation function, cloud mask data of the remote sensing image, a landmark region in a coastline grid image and an image gradient of the remote sensing image.
In the embodiment of the application, the preset geometric transformation function is used for representing the coordinate position corresponding relationship between the landmark region and the corresponding matching region in the remote sensing image, or in other words, the preset geometric transformation function is used for representing the coordinate position corresponding relationship between the coastline raster image data of the landmark region and the remote sensing image data of the corresponding matching region in the remote sensing image of the landmark region. Optionally, to accurately represent the correspondence between the coordinate position of the landmark region in the coastline grid image and the coordinate position of the matching region corresponding to the landmark region in the remote sensing image, the preset geometric transformation function may include an affine transformation function, which is specifically shown in the following formula (1):
wherein, (i ', j') represents the coordinate position of the landmark region in the coastline grid image; (i, j) representing the coordinate position of the corresponding matching area of the landmark area in the remote sensing image; a is a 0 And b 0 Representing parameters for controlling translation of a region of landmarks, a 1 、a 2 、b 1 And b 2 Representing parameters for controlling the rotation of the landmark region.
In the embodiment of the application, the similarity measure function is used for representing the similarity between a matching area corresponding to the landmark area in the remote sensing image and an actual area, or the similarity measure function value is used for representing the similarity between the remote sensing image data of the matching area corresponding to the landmark area in the remote sensing image and the coastline raster image data of the landmark area.
In an optional implementation manner, considering that the gray scale change of the pixel at the boundary between the land and the water of the remote sensing image is obvious and the gradient value is large, and also considering that the deformation, cloud and other factors of the remote sensing image may affect the accuracy and reliability of landmark positioning in the remote sensing image, for this reason, as shown in fig. 1 and fig. 2, in S102, determining cloud mask data of the remote sensing image acquired by the stationary orbit remote sensing satellite includes: and carrying out cloud detection on the remote sensing image, and obtaining cloud mask data of the remote sensing image based on a cloud detection result. Accordingly, the above S104 may be specifically implemented as: and determining the convolution sum of the image gradient corresponding to the matching region in the remote sensing image, the cloud mask data of the matching region in the remote sensing image and the coastline raster image data of the landmark region as a similarity measure function value between the remote sensing image data of the matching region and the coastline raster image collection of the landmark region.
Illustratively, the similarity measure function is shown in equation (2) below:
wherein R represents a similarity measure function value; d (i, j) represents a landmark region; (i, j) representing the coordinate position of the landmark region in the coastline raster image; f represents a preset geometric transformation function; (i ', j') represents the coordinate position of the corresponding matching region of the landmark region in the remote sensing image; m (F (i, j)) represents cloud mask data for the corresponding coordinate location (i ', j') in the remote sensing image; int (g) denotes a rounding operation; grad (i ', j') represents the image gradient of the matching region of the corresponding landmark region in the remote sensing image; x denotes the convolution operation.
The cloud mask data of the remote sensing image represents mask image data generated after cloud detection is performed on the remote sensing image, and images shielded by clouds can be shielded in landmark matching. In practical application, various detection technologies in the field can be adopted to perform cloud detection on the remote sensing image, such as a single-channel cloud detection algorithm with a minimum cross entropy criterion, and the like, which is not limited in the embodiment of the present application.
S106, taking the target parameters of the preset geometric transformation function as the space positions of the particles in the target particle swarm optimization algorithm, taking the similarity measure function as the fitness function of the particles, and determining the parameter values of the target parameters based on the target particle swarm optimization algorithm and the similarity measure function values.
Considering that the remote sensing image and the coastline raster image belong to two types of data with different attributes, determining an image of a matching area in the remote sensing image and the coastline raster image of the area based on the existing gray-scale correlation matching method, feature matching method and the likeThe preset geometric transformation function can represent the corresponding relation between the coordinate position of the landmark region in the coastline grid image and the coordinate position of the corresponding matching position of the landmark region in the remote sensing image, and the similarity measure function can represent the similarity between the coastline grid image of the landmark region and the image of the corresponding actual region in the remote sensing image, so as to reflect the precision of the landmark region located in the remote sensing image, therefore, the goal of landmark matching is to actually determine that when the similarity between the matching region and the actual region of the landmark region in the coastline grid image is the maximum, the parameter of the preset geometric transformation function (such as the parameter a in the formula (1)) is preset 0 ～a 2 And b 0 ～b 2 ) To obtain a corresponding relationship between the coordinate position of the landmark region in the coastline grid image and the coordinate position of the corresponding matching position of the landmark region in the remote sensing image. Further, considering that the similarity measure function is a non-convex function and may have a plurality of extreme values, a heuristic population optimization algorithm, specifically a target particle swarm optimization algorithm, may be adopted, and by taking a target parameter of a preset geometric transformation function as a particle space position in the target particle swarm optimization algorithm, the similarity between a matching area corresponding to the maximum landmark area in the coastline grid image in the remote sensing image and an actual area is taken as a target, and based on the target particle swarm optimization algorithm and the similarity measure function, a parameter value of the target parameter is determined. The target parameter of the predetermined geometric transformation function refers to an unknown parameter in the predetermined geometric transformation function, for example, the target parameter of the predetermined geometric transformation function shown in the above formula (1) includes a parameter a 0 ～a 2 And b 0 ～b 2 。
In an alternative implementation manner, to ensure the accuracy of the obtained parameter value of the target parameter, so as to subsequently improve the accuracy and reliability of landmark matching in the remote sensing image, as shown in fig. 3, S106 includes:
s161, randomly generating a specified number of particle groups and initializing the spatial position and velocity of each particle in the particle groups.
Specifically, the number of particles in the particle group and the initial values of the spatial position and the velocity of each particle may be set according to actual needs, which is not limited in the embodiments of the present application. In practice, to prevent the particles from exceeding the search space, the velocity of the particles needs to be limited, i.e. v i,j ∈[-V max ，V max ]Wherein v is i,j Representing the velocity of the particles.
Next, the similarity measure function may be used as a fitness function of the particle, and the following steps S162 to S164 are repeatedly performed until the preset optimization stop condition is satisfied. The preset optimization stop condition may be set according to actual needs, for example, the preset optimization stop condition may include that the iteration number reaches a preset number threshold, or a difference between an optimal adaptation value after the last iteration and an optimal adaptation value after the current iteration is smaller than a preset difference value.
And S162, determining a first spatial position corresponding to the optimal adaptive value searched by each particle in the particle group and a second spatial position corresponding to the optimal adaptive value searched by the particle group based on the current spatial position and the current speed of each particle in the particle group.
The adaptive value (Fitness Values) refers to a similarity measure function value, that is, a similarity between a coastline grid image of a landmark region and an image of a corresponding actual region in a remote sensing image. In the embodiment of the application, the first spatial position corresponding to the optimal adaptive value searched by the particle is the spatial position of the particle when the similarity between the corresponding matching region and the actual region of the landmark region in the coastline raster image searched by the particle is the maximum; the second spatial position corresponding to the optimal adaptive value searched by the particle population refers to the spatial position of the particles in the particle population when the similarity between the corresponding matching region and the actual region of the landmark region in the coastline grid image searched by the particle population is the maximum in the remote sensing image.
It should be noted that searching for the optimal adaptive value for each particle in the particle group and searching for the optimal adaptive value for the particle group may be implemented in various ways, and the embodiments of the present application are not described in detail herein.
S163, the velocity of each particle in the population of particles is updated based on the current velocity, the first spatial position, and the second spatial position of the particle.
For example, the velocity of each particle in the population of particles can be determined by the following equation (3):
wherein i represents the number of the particle, i ═ 1, 2.., n; j represents a space dimension number, and j is 1,2, wherein D is equal to the number of target parameters;
representing the velocity of the ith particle in the jth spatial dimension at time t + 1;
representing the velocity of the ith particle in the jth spatial dimension prior to time t;
the method comprises the steps that a first space position of an ith particle corresponding to an optimal adaptive value searched in a jth space dimension at a tth moment is shown;
representing a second spatial position corresponding to the optimal adaptive value searched by the particle group before the t-th time;
representing the spatial position of the ith particle in the jth spatial dimension at time instant t; c1 and c2 represent acceleration factors; w represents an inertial weight that determines the effect of the historical velocity of the particle on the current velocity; r1 and r2 are random numbers within (0, 1).
And S164, updating the spatial position of each particle in the particle group based on the current spatial position and the updated speed of each particle in the particle group.
For example, the spatial position of each particle in the population of particles can be determined by the following equation (4):
wherein,
representing the spatial position of the ith particle in the jth spatial dimension at time t + 1;
representing the spatial position of the ith particle in the jth spatial dimension at time instant t;
representing the velocity of the ith particle in the jth spatial dimension at time t + 1.
The embodiment of the present application shows a specific implementation manner of the step S106. Of course, it should be understood that step S106 may also be implemented in other ways, and this is not limited by this embodiment of the application.
And S108, resampling the coastline raster image data of the landmark area based on the calculated parameter value of the target parameter, and realizing landmark matching.
Exemplarily, based on a preset geometric transformation function and a parameter value of a target parameter, a corresponding relation between a coordinate position of a landmark region in a coastline grid image and a coordinate position of a corresponding matching region of the landmark region in a remote sensing image can be determined; further, based on the coordinate position of the landmark region in the coastline grid image and the corresponding relation, the coordinate position of the corresponding matching region of the landmark region in the remote sensing image can be obtained, and therefore landmark matching is achieved.
In another embodiment of the present application, to improve landmark matching efficiency, after determining the landmark region in the coastline raster image based on the rasterized sea-land boundary mask data through the above S102, before the above S108, the method of the embodiment of the present application may further include: determining rasterized sea-land boundary mask data based on the coastline raster image and preset nominal grid data; and carrying out integral pre-matching on the basis of the image gradient of the remote sensing image and the rasterized sea-land boundary mask data to obtain a candidate matching region corresponding to the landmark region in the remote sensing image, and determining a search region in the remote sensing image on the basis of the candidate matching region. Accordingly, the above S108 may be specifically implemented as: and positioning the landmark region in the search region based on the coordinate position of the landmark region, the preset geometric transformation function and the parameter value of the target parameter.
Illustratively, the remote sensing image and the coastline raster image of the matching area range can be obtained by roughly aligning the remote sensing image with rasterized sea-land boundary mask data under the projection of a preset nominal grid. However, the obtained remote sensing image of the candidate matching area and the coastline grid image still have deviation, and in order to realize better registration of the two images, an overall landmark matching algorithm based on particle swarm optimization can be used for solving specified parameter values and resampling the coastline grid image, so that registration of the two data is realized.
In the method for matching the landmark in the remote sensing image provided by the embodiment of the application, considering that the remote sensing image and the coastline raster image belong to two types of data with different attributes, based on the existing gray scale correlation matching method, the feature matching method and the like, the corresponding relationship between the image of the matching area in the remote sensing image and the coastline raster image of the area is determined to have a certain deviation, so that the positioning precision and the reliability are influenced, for this reason, the corresponding relationship between the coordinate position of the landmark area in the coastline raster image and the coordinate position of the matching position of the landmark area in the remote sensing image is represented by adopting a preset geometric transformation function, and the similarity between the coastline raster image of the landmark area and the image of the corresponding actual area in the remote sensing image is represented by adopting a similarity measure function, so that the purpose of matching the landmark can be regarded as that the similarity between the coastline raster image in the landmark area and the remote sensing image in the matching area is maximum, presetting a value of a target parameter of a geometric transformation function so as to obtain a corresponding relation between a coordinate position of a landmark region in a coastline grid image and a coordinate position of a corresponding matching position of the landmark region in a remote sensing image, realizing landmark matching, and then positioning the landmark region in the remote sensing image by utilizing the corresponding relation and the coordinate position of the landmark region in the coastline grid image; further, considering that the similarity measure function is a non-convex function and may have a plurality of extreme values, a heuristic group optimization algorithm, specifically a target particle swarm optimization algorithm, may be adopted, and the target parameter of the preset geometric transformation function is taken as the spatial position of the particle in the target particle swarm optimization algorithm, and the similarity measure function is taken as the fitness function of the particle swarm, based on the target particle swarm optimization algorithm and the similarity measure function, the parameter value of the target parameter of the preset geometric transformation function may be determined quickly and accurately, thereby facilitating to improve the accuracy and reliability of the candidate for locating the landmark in the remote sensing image.
In addition, corresponding to the method for matching landmarks in the remote sensing image shown in fig. 1, the embodiment of the application also provides a device for matching landmarks in the remote sensing image. Referring to fig. 4, a schematic structural diagram of an apparatus 400 for matching landmarks in remote sensing images according to an embodiment of the present application is provided, where the apparatus 400 includes:
the first determining module 410 is configured to determine a landmark area in a coastline grid image, and image gradients and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
a second determining module 420, configured to determine a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image, and an image gradient of the remote sensing image, where the preset geometric transformation function is used to represent a coordinate position correspondence between the coastline raster image data of the landmark region and remote sensing image data of a matching region of the landmark region in the remote sensing image, and the similarity measure function value is used to represent a similarity between remote sensing image data of the matching region and the coastline raster image data of the landmark region;
a third determining module 430, configured to use a target parameter of the preset geometric transformation function as a spatial position of a particle in a target particle swarm optimization algorithm, use a similarity measure function as a fitness function of the particle, and determine a parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and the landmark matching module 440 is configured to resample the coastline raster image data of the landmark area based on the parameter value of the target parameter, so as to implement landmark matching.
In the device for matching the landmark in the remote sensing image, given that the remote sensing image and the coastline raster image belong to two types of data with different attributes, based on the existing gray scale correlation matching method, the feature matching method and the like, it is determined that a certain deviation exists between the image of the matching area in the remote sensing image and the coastline raster image of the area, and then positioning accuracy and reliability are affected, and accordingly, a preset geometric transformation function is adopted to represent the corresponding relationship between the coordinate position of the landmark area in the coastline raster image and the coordinate position of the matching position corresponding to the landmark area in the remote sensing image, and a similarity measure function is adopted to represent the similarity between the coastline raster image of the landmark area and the image of the corresponding actual area in the remote sensing image, so that the purpose of matching the landmark can be regarded as determining the similarity between the matching area corresponding to the landmark area in the remote sensing image and the actual area of the landmark area in the coastline raster image When the similarity is maximum, presetting the value of a target parameter of a geometric transformation function so as to obtain the corresponding relation between the coordinate position of the landmark region in the coastline grid image and the coordinate position of the corresponding matching position of the landmark region in the remote sensing image, and then positioning the landmark region in the remote sensing image by utilizing the corresponding relation and the coordinate position of the landmark region in the coastline grid image so as to realize landmark matching; further, considering that the similarity measure function is a non-convex function and may have a plurality of extreme values, a heuristic group optimization algorithm, specifically a target particle swarm optimization algorithm, can be adopted, and by taking a target parameter of a preset geometric transformation function as a particle space position in the target particle swarm optimization algorithm, the similarity between a matching area corresponding to a landmark area in a coastline grid image and an actual area is maximized as a target, and based on the target particle swarm optimization algorithm and the similarity measure function, a parameter value of the target parameter of the preset geometric transformation function can be quickly and accurately determined, so that the accuracy and reliability of candidate landmark positioning in the remote sensing image are improved.
Optionally, the third determining module includes:
the initialization submodule is used for randomly generating a specified number of particle groups and initializing the spatial position and speed of each particle in the particle groups;
and the optimization submodule is used for taking the similarity measure function as a fitness function of the particles, and repeatedly executing the following iterative operations until a preset optimization stop condition is met:
determining a first spatial position corresponding to the optimal adaptive value searched by each particle in the particle group and a second spatial position corresponding to the optimal adaptive value searched by the particle group based on the current spatial position and the current speed of each particle in the particle group;
updating the velocity of each particle in the population of particles based on the current velocity of the particle, the first spatial location, and the second spatial location;
and updating the spatial position of each particle in the particle group based on the current spatial position and the updated speed of each particle in the particle group.
Optionally, the determining, by the first determining module, cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite includes:
carrying out cloud detection on the remote sensing image, and obtaining cloud mask data of the remote sensing image based on a cloud detection result;
the third determining module is configured to determine a convolution sum between an image gradient corresponding to the matching region in the remote sensing image, cloud mask data of the matching region in the remote sensing image, and coastline raster image data of the landmark region as a similarity measure function value between the remote sensing image data of the matching region and the coastline raster image data of the landmark region.
Optionally, the first determining module determines landmark regions in a coastline raster image, including:
and determining a landmark area in the coastline grid image based on preset nominal grid data and the coordinate position of the matching area in the remote sensing image.
Optionally, the determining, by the first determining module, a landmark region in the coastline raster image based on preset nominal grid data and a coordinate position of the matching region in the remote sensing image includes:
determining coastline image data of the matching area based on the coordinate location of the matching area in the remote sensing image and the nominal grid data;
and determining the coastline image data of the matching area as the landmark area.
Optionally, the apparatus further comprises:
the pre-matching module is used for performing overall pre-matching based on the image gradient of the remote sensing image and the rasterized sea-land boundary mask data to obtain a corresponding candidate matching area of the landmark area in the remote sensing image before the landmark matching module resamples the coastline raster image based on the parameter value of the target parameter;
the searching region determining module is used for determining a searching region in the remote sensing image based on the candidate matching region;
the landmark matching module is used for positioning the landmark region in the search region based on the coordinate position of the landmark region, the preset geometric transformation function and the parameter value of the target parameter.
Optionally, the preset geometric transformation function comprises an affine transformation function.
Obviously, the device for matching a landmark in a remote sensing image provided in the embodiment of the present application can be used as an execution subject of the method for matching a landmark in a remote sensing image shown in fig. 1, and therefore, the function of the device for matching a landmark in a remote sensing image in fig. 1 can be realized. Since the principle is the same, the description will not be repeated here.
The foregoing description of specific embodiments has been presented for purposes of illustration and description. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 5, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other by an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form a landmark matching device in the remote sensing image on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
determining a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image and an image gradient of the remote sensing image, wherein the preset geometric transformation function is used for representing a coordinate position corresponding relation between the coastline raster image data of the landmark region and remote sensing image data of a matching region corresponding to the landmark region in the remote sensing image, and the similarity measure function value is used for representing the similarity between the remote sensing image data of the matching region and the coastline raster image data of the landmark region;
taking the target parameter of the preset geometric transformation function as the space position of the particle in a target particle swarm optimization algorithm, taking a similarity measure function as a fitness function of the particle, and determining the parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
The method executed by the device for matching landmarks in remote sensing images disclosed in the embodiment of fig. 1 of the present application can be applied to or realized by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method of fig. 1, and implement the functions of the embodiment shown in fig. 1 of the apparatus for matching landmarks in remote sensing images, which are not described herein again in this embodiment of the application.
Of course, besides the software implementation, the electronic device of the present application does not exclude other implementations, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or a logic device.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to perform the method of the embodiment shown in fig. 1, and are specifically configured to:
determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
determining a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark area in the coastline grid image and an image gradient of the remote sensing image, wherein the preset geometric transformation function is used for representing a coordinate position corresponding relation between the coastline grid image data of the landmark area and remote sensing image data of a corresponding matching area of the landmark area in the remote sensing image, and the similarity measure function value is used for representing the similarity between the remote sensing image data of the matching area and the coastline grid image data of the landmark area;
taking the target parameter of the preset geometric transformation function as the space position of the particle in a target particle swarm optimization algorithm, taking a similarity measure function as a fitness function of the particle, and determining the parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
In short, the above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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 Discs (DVD) or other optical storage, magnetic cassettes, 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. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for relevant points.
Claims (10)
1. A method of landmark matching in remotely sensed images, comprising:
determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
determining a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image and an image gradient of a remote sensing image, wherein the preset geometric transformation function is used for representing a coordinate position corresponding relation between the coastline raster image data of the landmark region and remote sensing image data of a matching region corresponding to the landmark region in the remote sensing image, and the similarity measure function value is used for representing the similarity between the remote sensing image data of the matching region and the coastline raster image data of the landmark region;
taking the target parameter of the preset geometric transformation function as the space position of the particle in a target particle swarm optimization algorithm, taking a similarity measure function as a fitness function of the particle, and determining the parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
2. The method of claim 1, wherein determining the parameter value of the target parameter using the target parameter of the predetermined geometric transformation function as the spatial position of the particle in the target particle swarm optimization algorithm, using the similarity measure function as the fitness function of the particle, based on the target particle swarm optimization algorithm and the similarity measure function value, comprises:
randomly generating a specified number of particle groups and initializing the spatial position and speed of each particle in the particle groups;
and taking the similarity measure function as a fitness function of the particles, and repeatedly executing the following iterative operations until a preset optimization stop condition is met:
determining a first spatial position corresponding to the optimal adaptive value searched by each particle in the particle group and a second spatial position corresponding to the optimal adaptive value searched by the particle group based on the current spatial position and the current speed of each particle in the particle group;
updating the velocity of each particle in the population of particles based on the current velocity of the particle, the first spatial location, and the second spatial location;
and updating the spatial position of each particle in the particle group based on the current spatial position and the updated velocity of each particle in the particle group.
3. The method of claim 1, wherein determining cloud mask data for remote sensing images acquired by the geostationary orbit remote sensing satellite comprises:
carrying out cloud detection on the remote sensing image, and obtaining cloud mask data of the remote sensing image based on a cloud detection result;
the determining a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image and an image gradient of the remote sensing image comprises:
and determining the convolution sum of the image gradient corresponding to the matching region in the remote sensing image, the cloud mask data of the matching region in the remote sensing image and the coastline raster image data of the landmark region as a similarity measure function value between the remote sensing image data of the matching region and the coastline raster image data of the landmark region.
4. The method of claim 1, wherein determining landmark regions in a coastline raster image comprises:
and determining a landmark area in the coastline grid image based on preset nominal grid data and the coordinate position of the matching area in the remote sensing image.
5. The method of claim 4, wherein determining a landmark region in the coastline raster image based on preset nominal grid data and a coordinate location of the matching region in the remote sensing image comprises:
determining coastline image data of the matching area based on the coordinate position of the matching area in the remote sensing image and the nominal grid data;
and determining the coastline image data of the matching area as the landmark area.
6. The method of claim 1, wherein prior to resampling the shoreline raster image based on parameter values of the target parameters, the method further comprises:
performing overall pre-matching based on the image gradient of the remote sensing image and the rasterized sea-land boundary mask data to obtain a corresponding candidate matching region of the landmark region in the remote sensing image;
determining a search area in the remote sensing image based on the candidate matching area;
the resampling the coastline grid image based on the parameter value of the target parameter to realize landmark matching comprises the following steps:
and positioning the landmark area in the search area based on the coordinate position of the landmark area, the preset geometric transformation function and the parameter value of the target parameter.
7. The method according to any one of claims 1 to 6, wherein the preset geometric transformation function comprises an affine transformation function.
8. A remote sensing image landmark matching device, comprising:
the first determination module is used for determining a landmark area in a coastline grid image, and image gradient and cloud mask data of a remote sensing image acquired by a stationary orbit remote sensing satellite;
a second determining module, configured to determine a similarity measure function value based on a preset geometric transformation function, the cloud mask data, a landmark region in the coastline raster image, and an image gradient of a remote sensing image, where the preset geometric transformation function is used to represent a coordinate position correspondence between the coastline raster image data of the landmark region and remote sensing image data of a matching region of the landmark region in the remote sensing image, and the similarity measure function value is used to represent a similarity between remote sensing image data of the matching region and the coastline raster image data of the landmark region;
a third determining module, configured to use a target parameter of the preset geometric transformation function as a spatial position of a particle in a target particle swarm optimization algorithm, use a similarity measure function as a fitness function of the particle, and determine a parameter value of the target parameter based on the target particle swarm optimization algorithm and the similarity measure function value;
and the landmark matching module is used for resampling the coastline raster image data of the landmark area based on the parameter value of the target parameter to realize landmark matching.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 7.
10. A computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210534424.0A CN114998755A (en) | 2022-05-17 | 2022-05-17 | Method and device for matching landmarks in remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210534424.0A CN114998755A (en) | 2022-05-17 | 2022-05-17 | Method and device for matching landmarks in remote sensing image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114998755A true CN114998755A (en) | 2022-09-02 |
Family
ID=83027071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210534424.0A Pending CN114998755A (en) | 2022-05-17 | 2022-05-17 | Method and device for matching landmarks in remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114998755A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661286A (en) * | 2022-10-27 | 2023-01-31 | 北京星天科技有限公司 | Vectorization chart drawing method and device and electronic equipment |
-
2022
- 2022-05-17 CN CN202210534424.0A patent/CN114998755A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661286A (en) * | 2022-10-27 | 2023-01-31 | 北京星天科技有限公司 | Vectorization chart drawing method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348454B (en) | Matching local image feature descriptors | |
| US11250291B2 (en) | Information detection method, apparatus, and device | |
| CN113256712B (en) | Positioning method, positioning device, electronic equipment and storage medium | |
| CN106952338B (en) | Three-dimensional reconstruction method and system based on deep learning and readable storage medium | |
| CN110287831B (en) | Method and device for acquiring control point based on landmark and electronic equipment | |
| CN111612834B (en) | Method, device and equipment for generating target image | |
| CN109711486A (en) | Based on the relevant high degree of overlapping remote sensing image full scale tie point matching process of phase | |
| CN113793370B (en) | Three-dimensional point cloud registration method and device, electronic equipment and readable medium | |
| CN112284394A (en) | Map construction and visual positioning method and device | |
| CN112991441A (en) | Camera positioning method and device, electronic equipment and storage medium | |
| CN115409896A (en) | Pose prediction method, pose prediction device, electronic device and medium | |
| CN114998755A (en) | Method and device for matching landmarks in remote sensing image | |
| Yamni et al. | Accurate 2D and 3D images classification using translation and scale invariants of Meixner moments | |
| CN111552751B (en) | Three-dimensional landmark control point generation and application method, generation and application device | |
| CN114565953A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN111967365A (en) | Method and device for extracting image connection points | |
| CN114065868B (en) | Training method of text detection model, text detection method and device | |
| CN112257686B (en) | Training method and device for human body posture recognition model and storage medium | |
| CN113670253B (en) | Space target attitude inversion method and device, computing equipment and storage medium | |
| JP2020041950A (en) | Surveying device, surveying method, and program | |
| Hou et al. | Navigation landmark recognition and matching algorithm based on the improved SURF | |
| CN114241313A (en) | Method, apparatus, medium, and program product for extracting road boundary | |
| CN117975044B (en) | Image processing method and device based on feature space | |
| CN112037258B (en) | Target tracking method, device, equipment and storage medium | |
| CN117953019A (en) | Point cloud registration method and device for adding weight information |
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 |