WO2023088487A1 - Orthographic rectification method and apparatus for hyperspectral image, and storage medium - Google Patents

Orthographic rectification method and apparatus for hyperspectral image, and storage medium Download PDF

Info

Publication number
WO2023088487A1
WO2023088487A1 PCT/CN2022/133512 CN2022133512W WO2023088487A1 WO 2023088487 A1 WO2023088487 A1 WO 2023088487A1 CN 2022133512 W CN2022133512 W CN 2022133512W WO 2023088487 A1 WO2023088487 A1 WO 2023088487A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
grid
panchromatic
panchromatic image
outer orientation
Prior art date
Application number
PCT/CN2022/133512
Other languages
French (fr)
Chinese (zh)
Inventor
周剑
黄佳伟
李松
何虎
Original Assignee
中移(成都)信息通信科技有限公司
***通信集团有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中移(成都)信息通信科技有限公司, ***通信集团有限公司 filed Critical 中移(成都)信息通信科技有限公司
Publication of WO2023088487A1 publication Critical patent/WO2023088487A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/64—Circuits for processing colour signals
    • H04N9/646—Circuits for processing colour signals for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
    • G01C11/04—Interpretation of pictures
    • G01C11/30—Interpretation of pictures by triangulation
    • G01C11/34—Aerial triangulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/64—Circuits for processing colour signals
    • 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
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture

Definitions

  • the present application relates to the technical field of remote sensing image processing, in particular to a hyperspectral image orthographic correction method and device, and a storage medium.
  • the existing orthophoto correction method for recording hyperspectral remote sensing images is to extract and match feature points for airborne hyperspectral images.
  • the first is to directly adopt the conventional visible light remote sensing image orthophoto correction method, and directly perform feature extraction, feature matching, block adjustment, regular grid generation and orthophoto correction on the airborne hyperspectral image.
  • the hyperspectral image has a higher spectral
  • the resolution limits the improvement of the spatial resolution, and the diversity of its spectrum also makes it possible that the image features of the same ground object in different wave bands are quite different, which leads to the fact that the orthophoto correction process will be affected by the observation area. Influence of terrain type.
  • the second is to fuse and preprocess the hyperspectral image with the panchromatic image that is higher than its spatial resolution and is expected to be geometrically registered to obtain a fused image with both higher spatial and spectral resolutions, and then perform subsequent
  • the processing flow of conventional orthophoto correction will increase the workload, and the processing result is essentially the orthographic image of the fused image, which changes the spectral characteristics of the original image to a certain extent, which is not conducive to the subsequent orthographic image. Quantitative analysis and other applications.
  • the third is to add auxiliary operations of hyperspectral image feature point extraction and inspection based on manual visual interpretation to the routine orthophoto correction process to ensure that the number of points with the same name and the accuracy of their image coordinates meet the operational requirements.
  • the process of assisting the feature extraction and matching of hyperspectral images based on manual visual interpretation increases the workload on the basis of conventional processing, greatly increases labor costs, and introduces errors in manual interpretation. possibility.
  • Embodiments of the present application provide a hyperspectral image orthophoto correction method, device, and storage medium, which can avoid the influence of the type of objects in the observation area on the orthophoto correction, and improve the accuracy of the orthophoto correction.
  • the embodiment of the present application proposes a hyperspectral image orthorectification method, the method comprising:
  • Orthorectification is performed on the hyperspectral image data according to the outer orientation element of the target and the regular grid to obtain an orthoimage corresponding to the hyperspectral image.
  • the embodiment of the present application proposes a hyperspectral image orthorectification device, which includes:
  • An acquisition unit configured to acquire panchromatic image data corresponding to the hyperspectral image data to be corrected
  • the feature extraction and feature matching unit is used to obtain the target outer orientation element corresponding to the panchromatic image data by performing feature extraction and feature matching on the panchromatic image data;
  • a grid generating unit configured to perform spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid
  • the orthographic correction unit is configured to perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
  • the embodiment of the present application proposes a hyperspectral image orthorectification device, the device includes: a processor, a memory, and a communication bus; when the processor executes the running program stored in the memory, the hyperspectral image as described above is realized Orthophoto correction method.
  • the embodiment of the present application provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the hyperspectral image orthophoto correction method as described above is implemented.
  • An embodiment of the present application provides a hyperspectral image orthophoto correction method and device, and a storage medium.
  • the method includes: acquiring panchromatic image data corresponding to hyperspectral image data to be corrected; performing feature extraction sequentially on the panchromatic image data Match the features to obtain the target outer orientation elements corresponding to the panchromatic image data; carry out spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid; according to the target outer orientation elements and regular grids, hyperspectral image The data is orthorectified to obtain the orthophoto corresponding to the hyperspectral image.
  • the panchromatic image data corresponding to the hyperspectral image data is used for feature extraction and feature matching, and then the obtained target outer orientation elements are used as the outer orientation elements of the hyperspectral image orthophoto correction, and then the subsequent orthophoto correction is performed.
  • the process of using the high-resolution characteristics of panchromatic images more points with the same name can be matched, and more target external orientation elements can be obtained, which can not be affected by the type of objects in the observation area;
  • the spectral characteristics of hyperspectral are also retained, which can improve the accuracy of orthophoto correction.
  • FIG. 1 is a flow chart of a hyperspectral image orthographic correction method provided in an embodiment of the present application
  • Fig. 2 is an exemplary airborne hyperspectral image orthophoto correction method provided by the embodiment of the present application
  • Fig. 3 is a structural schematic diagram 1 of a hyperspectral image orthographic correction device provided by an embodiment of the present application;
  • FIG. 4 is a second structural schematic diagram of a hyperspectral image orthophoto correction device provided by an embodiment of the present application.
  • the embodiment of the present application provides a hyperspectral image orthophoto correction method, as shown in Figure 1, the method may include:
  • a hyperspectral image orthographic correction method proposed in an embodiment of the present application is applicable to a scene where fully automatic orthographic correction is performed on an airborne hyperspectral remote sensing image.
  • the hyperspectral image data to be corrected can be stored in the airborne hyperspectral image data set. In the embodiment of the present application, it is determined whether each hyperspectral image data in the airborne hyperspectral image data set has a corresponding panchromatic image data.
  • each piece of hyperspectral image data to be corrected needs to have corresponding panchromatic image data.
  • the number of hyperspectral image data is two or more, which can be selected according to the actual situation, and is not specifically limited in the embodiment of the present application.
  • feature extraction is first performed on the panchromatic image data to obtain feature data corresponding to the panchromatic image data.
  • a scale invariant feature transform Scale Invariant Feature Transform, SIFT
  • SIFT Scale Invariant Feature Transform
  • GPU Graphics Processing Unit
  • the feature extraction process includes scale space extremum detection, key point positioning, main direction determination, and key point feature vectors to describe four steps; and if the SIFT-GPU algorithm is used to extract features from each panchromatic image data, on the basis of the SIFT-GPU algorithm, the GPU parallel algorithm is used to construct a Gaussian pyramid image for each panchromatic image data, The steps of key point positioning and main direction determination can improve the speed of feature extraction.
  • the embodiment of the present application performs feature extraction on panchromatic image data, which can make the number of obtained feature points larger and more uniform in distribution, and can effectively overcome the problem of low radiance values on single-band images of hyperspectral images. Insufficiency of missing feature points caused by shaded areas.
  • the feature extraction function corresponding to the above-mentioned SIFT-CPU algorithm or SIFT-GPU algorithm can be stored in a third-party open source library such as OpenCV (cross-platform computer vision and machine learning software), and can be accessed by calling the third-party open source library The feature extraction function to call the above SIFT-CPU algorithm or SIFT-GPU algorithm.
  • a third-party open source library such as OpenCV (cross-platform computer vision and machine learning software)
  • feature matching is performed on the panchromatic image data based on the feature data to obtain the panchromatic image data. Matching relationships in image data.
  • the statistical feature data may include statistical data such as average value and/or standard deviation, which may be selected according to actual conditions, and is not specifically limited in the embodiment of the present application.
  • panchromatic image data whose difference between the image center distance and the average value is greater than 3 times the standard deviation, it is considered that there is no matching relationship between these panchromatic image data.
  • the Fast Approximate Nearest Neighbor Search Library (FLANN) matching method can be used to perform feature matching on panchromatic image data with a matching relationship, and obtain the same-name points in the panchromatic image data. matching relationship.
  • FLANN Fast Approximate Nearest Neighbor Search Library
  • the feature matching function corresponding to the FLANN matching algorithm can also be stored in a third-party open source library such as OpenCV.
  • the basic matrix corresponding to the matching relationship can also be determined; based on the basic matrix, the error matching relationship in the matching relationship is determined; the error matching relationship is deleted from the matching relationship , to get the updated matching relationship.
  • the basic matrix for transforming the left and right image data of the panchromatic image data pair corresponding to the matching relationship can be calculated according to the 7-point method in the field of computer vision; after that, random sampling consistency (Random Sample Consensus, RANSAC) method to determine the error matching relationship.
  • random sampling consistency Random Sample Consensus, RANSAC
  • formula (1) can be used to calculate the epipolar line equation corresponding to the feature point coordinates of the left and right image data, and further calculate the epipolar line error corresponding to the feature point coordinates, and according to the epipolar line error and the kernel line Line errors are eliminated.
  • x L , y L , x R , y R are the feature point coordinates on the left image data and right image data of the matching pair respectively
  • f 1 , f 2 ,..., f 9 are the transformation equation formula (2) The coefficients of the fundamental matrix in .
  • the initial outer orientation element of the panchromatic image data and the undetermined ground point coordinates is used to determine the target outer orientation element corresponding to the panchromatic image data.
  • the POS auxiliary data provided by the project can be used to determine the initial outer orientation elements corresponding to each panchromatic image data and the initial values of the undetermined ground point coordinates corresponding to each feature point of the panchromatic image data.
  • the initial outer orientation element of the panchromatic image data and the corresponding The initial value of the ground point coordinates is to be determined, and the target outer orientation element corresponding to the panchromatic image data is determined.
  • the target outer orientation element corresponding to the panchromatic image data is determined based on the updated matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data.
  • the spatial front intersection calculation is performed on the outer orientation elements of the target to obtain the undetermined ground point coordinates, and the undetermined ground point coordinates are determined as a sparse point cloud.
  • the sparse point cloud adaptive filtering is performed to obtain the sparse ground point cloud, and then the irregular triangulation network is constructed for the sparse ground point cloud, and finally the regular grid is obtained by interpolating the irregular triangulation network.
  • multi-scale morphological filtering and progressive triangulation encryption can be used for adaptive filtering of sparse point clouds.
  • Delaunay triangulation network can be constructed on the sparse ground point cloud.
  • Linear interpolation is used when performing regular grid interpolation, that is, interpolation is performed on the spatial plane determined by the three points of the triangle.
  • the process of determining the target outer orientation element corresponding to the panchromatic image data and the target constitutes the process of beam block adjustment.
  • S104 Perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
  • the interpolation grid of the hyperspectral image is determined according to the preset interpolation interval; and the first pixel coordinates of each grid point in the interpolation grid are obtained; the interpolation value is calculated according to the target outer orientation element and the regular grid The second image point coordinates of each grid point in the grid; based on the first image point coordinates and the second image point coordinates, perform orthophoto correction on the hyperspectral image data to obtain an orthophoto image.
  • the process of calculating the second pixel coordinates of each grid point in the interpolation grid according to the outer orientation element of the target and the regular grid specifically includes: according to the preset orthographic image scale parameter, calculating the corresponding ground of each grid point The X-axis coordinates and Y-axis coordinates of the point; according to the X-axis coordinates, Y-axis coordinates and the regular grid, determine the Z-axis coordinates of each grid point corresponding to the undetermined ground point; calculate the interpolation grid according to the target outer orientation element and the Z-axis coordinates The second pixel coordinates of each grid point in the grid.
  • first pixel coordinates are the corrected coordinates corresponding to the grid points in the interpolation grid
  • second pixel coordinates are the uncorrected coordinates corresponding to the grid points in the difference grid.
  • the coordinates of the second image point can be obtained through calculation according to formula (3).
  • ⁇ is the variable that can be eliminated
  • f is the main distance
  • m′ 1 , m′ 1 , n′ 1 , n′ 2 are the internal orientation transformation coefficients
  • a 1 , a 2 ,...,c 3 are the outer orientation of the target
  • I 0 , J 0 are the coordinates of the first image point
  • X S , Y S , Z S are the three-dimensional coordinates of the photography center
  • I, J are the image square coordinates corresponding to the grid points
  • X, Y, Z is the three-dimensional coordinate corresponding to the grid point.
  • I, J, X, Y, Z can be used as the second image point coordinates.
  • a bilinear difference is performed on the coordinates of the first image point and the coordinates of the second image point to obtain corrections corresponding to other points in the hyperspectral image
  • the image point coordinates before correction and then the image point assignment is performed on the image point coordinates before correction, and finally the orthographic image corresponding to the hyperspectral image is obtained.
  • the process of calculating the second pixel coordinates of each grid point in the interpolation grid according to the target outer orientation element and the regular grid may specifically include: obtaining the ground range data corresponding to the hyperspectral image; according to the ground range data and a regular grid to construct a regular grid in memory; calculate the second image point coordinates of each grid point in the interpolation grid according to the orientation elements outside the target and the regular grid in memory. That is, before calculating the second image point coordinates of each grid point in the interpolation grid according to the outer orientation elements of the target and the Z-axis coordinates, first construct a memory regular grid based on the ground range and the regular grid to reduce memory requirements.
  • shared memory parallel programming Open Multi-Processing, Open MP
  • Open MP Open Multi-Processing, Open MP
  • a block correction strategy can be used.
  • panchromatic image data corresponding to the hyperspectral image data is used for feature extraction and feature matching, and then the obtained outer orientation elements of the target are used as the outer orientation elements of the hyperspectral image for orthophoto correction, and then subsequent orthophoto correction is performed.
  • the spectral characteristics of hyperspectral are also retained, which can improve the accuracy of orthophoto correction.
  • the embodiment of the present application proposes an airborne hyperspectral image orthographic correction method, as shown in Figure 2, the method may include:
  • step 3 includes the following 3.1-3.5,
  • step 5 includes the following 5.1-5.3,
  • step 7 includes the following 7.1-7.3,
  • an embodiment of the present application provides a hyperspectral image orthorectification device.
  • the hyperspectral image orthorectification device 1 includes:
  • An acquisition unit 10 configured to acquire panchromatic image data corresponding to the hyperspectral image data to be corrected
  • the feature extraction and feature matching unit 11 is used to obtain the target outer orientation element corresponding to the panchromatic image data by performing feature extraction and feature matching on the panchromatic image data;
  • a grid generating unit 12 configured to perform spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid
  • the orthophoto correction unit 13 is configured to perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
  • the hyperspectral image orthorectification device 1 further includes: a feature extraction unit, a feature matching unit, and a determination unit;
  • the feature extraction unit is configured to perform feature extraction on the panchromatic image data to obtain feature data corresponding to the panchromatic image data;
  • the feature matching unit is configured to perform feature matching on the panchromatic image data based on the feature data, to obtain a matching relationship of the same-named points of the panchromatic image data in the panchromatic image data;
  • the determining unit is configured to determine, based on the matching relationship, the initial outer orientation element of the panchromatic image data, and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, that the panchromatic image data corresponds to The out-of-target orientation element of .
  • the hyperspectral image orthorectification device 1 further includes: a calculation unit and a screening unit;
  • the acquiring unit 10 is further configured to acquire an initial outer orientation element of the panchromatic image data
  • the calculation unit is used to calculate the image center distance between the panchromatic images according to the initial outer orientation element; calculate the statistical feature data between the center distances of the target images;
  • the screening unit is configured to screen the target image center distances smaller than the image distance threshold from the image center distances;
  • the determining unit is configured to determine a matching relationship of the same-named points in the panchromatic image data based on the statistical feature data.
  • the determining unit is further configured to determine the interpolation grid of the hyperspectral image according to a preset interpolation interval;
  • the acquiring unit 10 is further configured to acquire the first pixel coordinates of each grid point in the interpolation grid;
  • the calculation unit is further configured to calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the regular grid;
  • the orthophoto correction unit 13 is further configured to perform orthophoto correction on the hyperspectral image data based on the first image point coordinates and the second image point coordinates to obtain the orthophoto image.
  • the calculation unit is also used to calculate the X-axis coordinates and Y-axis coordinates of each grid point corresponding to the undetermined ground point according to the preset orthographic image scale parameter; according to the target outer orientation element and the Z Axis coordinates, calculating the second image point coordinates of each grid point in the interpolation grid;
  • the determining unit is further configured to determine, according to the X-axis coordinates, the Y-axis coordinates and the regular grid, the Z-axis coordinates of each grid point corresponding to the undetermined ground point.
  • the hyperspectral image orthorectification device 1 further includes: a deletion unit;
  • the determining unit is further configured to determine a basic matrix corresponding to the matching relationship; based on the basic matrix, determine an error matching relationship in the matching relationship; based on the updated matching relationship, the panchromatic image data The initial value of the initial outer orientation element and the undetermined ground point coordinates corresponding to the panchromatic image data, and determine the target outer orientation element corresponding to the panchromatic image data;
  • the deleting unit is configured to delete the error matching relationship from the matching relationship to obtain an updated matching relationship.
  • the hyperspectral image orthorectification device 1 further includes: a construction unit;
  • the acquiring unit 10 is further configured to acquire ground range data corresponding to the hyperspectral image
  • the construction unit is configured to construct a memory regular grid according to the ground range data and the regular grid;
  • the calculation unit is further configured to calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the internal regular grid.
  • a hyperspectral image orthorectification device obtained in an embodiment of the present application obtains panchromatic image data corresponding to hyperspectral image data to be corrected; panchromatic image data is obtained by sequentially performing feature extraction and feature matching on the panchromatic image data Corresponding target external orientation elements; carry out space forward intersection calculation and grid construction on the target external orientation elements to obtain regular grids; according to target external orientation elements and regular grids, perform orthorectification on hyperspectral image data to obtain hyperspectral The orthophoto corresponding to the image.
  • the hyperspectral image orthorectification device proposed in this embodiment uses the panchromatic image data corresponding to the hyperspectral image data to perform feature extraction and feature matching, and then uses the obtained target outer orientation elements as hyperspectral image orthophoto correction
  • the outer azimuth elements of the target and then carry out the subsequent orthophoto correction process, using the high-resolution characteristics of the panchromatic image to match more points with the same name, and then get more outer azimuth elements of the target, which can not be affected by the observation area.
  • the influence of the type when the hyperspectral image data is orthographically corrected by using the external azimuth elements of the target, the spectral characteristics of the hyperspectral spectrum are also retained, which can improve the accuracy of the orthographic correction.
  • Fig. 4 is a schematic diagram of the composition and structure of a hyperspectral image orthorectification device 1 provided by the embodiment of the present application.
  • the hyperspectral image orthorectification device 1 includes: a processor 14 , a memory 15 and a communication bus 16 .
  • the above-mentioned acquisition unit 10, feature extraction and feature matching unit 11, grid generation unit 12, orthophoto correction unit 13, feature extraction unit, feature matching unit, determination unit, calculation unit, screening unit can be realized by a processor 14 located on the hyperspectral image orthorectification device 1, and the above-mentioned processor 14 can be an application-specific integrated circuit (ASIC, Application Specific Integrated Circuit), a digital signal processor (DSP, Digital Signal Processor), digital signal processing image processing device (DSPD, Digital Signal Processing Device), programmable logic image processing device (PLD, Programmable Logic Device), field programmable gate array (FPGA, Field Programmable Gate Array), CPU, control At least one of controllers, microcontrollers, and microprocessors. It can be understood that, for different devices, the electronic device used to implement the above processor function may also be other, which is not specifically limited in this embodiment.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • DSPD digital signal processing image processing device
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate
  • the above-mentioned communication bus 16 is used to realize connection and communication between the processor 14 and the memory 15; when the above-mentioned processor 14 executes the running program stored in the memory 15, the following hyperspectral image orthorectification method is realized:
  • the panchromatic image data corresponding to the hyperspectral image data Acquiring the panchromatic image data corresponding to the hyperspectral image data to be corrected; by sequentially performing feature extraction and feature matching on the panchromatic image data, obtaining the target external orientation element corresponding to the panchromatic image data;
  • the azimuth element performs spatial forward intersection calculation and grid construction to obtain a regular grid; according to the target outer azimuth element and the regular grid, the hyperspectral image data is orthorectified to obtain the hyperspectral image corresponding to shooting images.
  • the above-mentioned processor 14 is further configured to perform feature extraction on the panchromatic image data to obtain feature data corresponding to the panchromatic image data; perform feature matching on the panchromatic image data based on the feature data, Obtain the matching relationship of the same-named point of the panchromatic image data in the panchromatic image data; The initial value of the point coordinate determines the target outer orientation element corresponding to the panchromatic image data.
  • the above-mentioned processor 14 is also used to acquire the initial outer orientation element of the panchromatic image data; calculate the image center distance between the panchromatic images according to the initial outer orientation element; Selecting the target image center distance smaller than the image distance threshold from the distance; calculating the statistical feature data between the target image center distances; based on the statistical feature data, determining the matching of the same name point in the panchromatic image data relation.
  • the above-mentioned processor 14 is also configured to determine the interpolation grid of the hyperspectral image according to the preset interpolation interval; and obtain the first pixel coordinates of each grid point in the interpolation grid; according to the Calculate the second image point coordinates of each grid point in the interpolation grid based on the outer orientation element of the target and the regular grid; based on the first image point coordinates and the second image point coordinates, the height Orthophoto correction is performed on the spectral image data to obtain the orthophoto image.
  • the above-mentioned processor 14 is also used to calculate the X-axis coordinates and Y-axis coordinates of each grid point corresponding to the undetermined ground point according to the preset orthographic image scale parameters; according to the X-axis coordinates, the Y-axis coordinates and the regular grid, determine the Z-axis coordinates of each grid point corresponding to the undetermined ground point; according to the target outer orientation element and the Z-axis coordinates, calculate the first grid point of each grid point in the interpolation grid Two pixel coordinates.
  • the above-mentioned processor 14 is also configured to determine the basic matrix corresponding to the matching relationship; determine the error matching relationship in the matching relationship based on the basic matrix; delete the error matching relationship from the matching relationship , to obtain the updated matching relationship; based on the updated matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, determine the full The target outer orientation element corresponding to the color image data.
  • the above-mentioned processor 14 is also used to obtain ground range data corresponding to the hyperspectral image; construct a memory regular grid according to the ground range data and the regular grid; The internal regular grid calculates the second image point coordinates of each grid point in the interpolation grid.
  • An embodiment of the present application provides a storage medium on which a computer program is stored.
  • the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors.
  • the computer program implements the above hyperspectral image orthorectification method.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present disclosure can be embodied in the form of a software product in essence or the part that contributes to the related technology, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk, etc.) ) includes several instructions to make an image display device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in various embodiments of the present disclosure.
  • an image display device which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Health & Medical Sciences (AREA)
  • Image Processing (AREA)

Abstract

Provided in the present application are an orthographic rectification method and apparatus for a hyperspectral image, and a storage medium. The method comprises: acquiring panchromatic image data corresponding to hyperspectral image data to be rectified (S101); sequentially performing feature extraction and feature matching on the panchromatic image data, so as to obtain target exterior orientation elements corresponding to the panchromatic image data (S102); performing spatial front intersection calculation and grid construction on the target exterior orientation elements, so as to obtain a regular grid (S103); and performing orthographic rectification on the hyperspectral image data according to the target exterior orientation elements and the regular grid, so as to obtain an orthographic image corresponding to a hyperspectral image (S104). The effect of a land feature type of an observation area on orthographic rectification can be avoided, thereby improving the accuracy of orthographic rectification.

Description

一种高光谱影像正摄校正方法及装置、存储介质A hyperspectral image orthographic correction method, device, and storage medium
相关申请的交叉引用Cross References to Related Applications
本申请基于申请号为202111389002.0、申请日为2021年11月22日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本申请。This application is based on a Chinese patent application with application number 202111389002.0 and a filing date of November 22, 2021, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated into this application by reference.
技术领域technical field
本申请涉及遥感影像处理技术领域，尤其涉及一种高光谱影像正摄校正方法及装置、存储介质。The present application relates to the technical field of remote sensing image processing, in particular to a hyperspectral image orthographic correction method and device, and a storage medium.
背景技术Background technique
目前的可见光遥感影像正摄校正方法，特征点提取与匹配的过程需要结合影像来实现，特征点提取与匹配所得的同名点数量及其图像坐标的精确度会影响后续的正摄校正的精度。现有的记载高光谱遥感影像的正摄校正方法是针对机载高光谱影像进行特征点提取和匹配的。In the current orthophoto correction method for visible light remote sensing images, the process of feature point extraction and matching needs to be combined with images. The number of points with the same name and the accuracy of the image coordinates obtained by feature point extraction and matching will affect the accuracy of subsequent orthophoto correction. The existing orthophoto correction method for recording hyperspectral remote sensing images is to extract and match feature points for airborne hyperspectral images.
具体的，可以通过三种方法进行机载高光谱遥感影像的全自动正摄校正方法。Specifically, there are three methods for fully automatic orthographic correction of airborne hyperspectral remote sensing images.
一是直接采用常规可见光遥感影像正摄校正方法，直接对机载高光谱影像进行特征提取、特征匹配、区域网平差、规则网格生成和正摄校正。然而，一方面，在单波段的高光谱影像图像存在弱纹理区域的特点，导致特征点匹配的结果不全面，进而降低了正摄校正的精确度；另一方面，高光谱影像较高的光谱分辨率限制了空间分辨率的提高，且其光谱的多样性也使得了存在同一地物在其不同波段上呈现的影像特征具有较大差异的可能性，导致了正摄校正过程会受观测区域地物类型的影响。The first is to directly adopt the conventional visible light remote sensing image orthophoto correction method, and directly perform feature extraction, feature matching, block adjustment, regular grid generation and orthophoto correction on the airborne hyperspectral image. However, on the one hand, there are weak texture areas in the single-band hyperspectral image, which leads to incomplete feature point matching results, which reduces the accuracy of orthographic correction; on the other hand, the hyperspectral image has a higher spectral The resolution limits the improvement of the spatial resolution, and the diversity of its spectrum also makes it possible that the image features of the same ground object in different wave bands are quite different, which leads to the fact that the orthophoto correction process will be affected by the observation area. Influence of terrain type.
二是将高光谱影像与高于其空间分辨率且预期进行几何配准后的全色影像进行融合预处理，以获得同时具有较高空间分辨率和光谱分辨率的融合影像，再进行后续的常规正摄校正的处理流程。然而新增的数据准备工作及预处理工作，会导致工作量变大，且处理结果实质为融合后影像的正摄影像，在一定程度上改变了原影像的光谱特征，不利于正摄影像后续的定量分析等应用。The second is to fuse and preprocess the hyperspectral image with the panchromatic image that is higher than its spatial resolution and is expected to be geometrically registered to obtain a fused image with both higher spatial and spectral resolutions, and then perform subsequent The processing flow of conventional orthophoto correction. However, the newly added data preparation and preprocessing work will increase the workload, and the processing result is essentially the orthographic image of the fused image, which changes the spectral characteristics of the original image to a certain extent, which is not conducive to the subsequent orthographic image. Quantitative analysis and other applications.
三是在常规正摄校正的处理流程中增加基于人工目视判读的高光谱影像特征点提取及检查的辅助作业，来保证同名点的数量及其图像坐标的精度满足作业要求。然而，基于人工目视判读来辅助进行高光谱影像的特征提取与匹配的流程，在常规处理流程的基础上增加了较多的工作量，极大 提高了人工成本，并且存在引入人工判读误差的可能性。The third is to add auxiliary operations of hyperspectral image feature point extraction and inspection based on manual visual interpretation to the routine orthophoto correction process to ensure that the number of points with the same name and the accuracy of their image coordinates meet the operational requirements. However, the process of assisting the feature extraction and matching of hyperspectral images based on manual visual interpretation increases the workload on the basis of conventional processing, greatly increases labor costs, and introduces errors in manual interpretation. possibility.
发明内容Contents of the invention
本申请实施例提供一种高光谱影像正摄校正方法及装置、存储介质，能够避免观测区域地物类型对正摄校正的影响，提高正摄校正的精确度。Embodiments of the present application provide a hyperspectral image orthophoto correction method, device, and storage medium, which can avoid the influence of the type of objects in the observation area on the orthophoto correction, and improve the accuracy of the orthophoto correction.
本申请的技术方案是这样实现的：The technical scheme of the present application is realized like this:
第一方面，本申请实施例提出一种高光谱影像正射校正方法，所述方法包括：In the first aspect, the embodiment of the present application proposes a hyperspectral image orthorectification method, the method comprising:
获取待校正的高光谱影像数据对应的全色影像数据；Obtain panchromatic image data corresponding to the hyperspectral image data to be corrected;
通过对所述全色影像数据依次进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素；Obtaining target outer orientation elements corresponding to the panchromatic image data by sequentially performing feature extraction and feature matching on the panchromatic image data;
对所述目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；Carrying out spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid;
根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。Orthorectification is performed on the hyperspectral image data according to the outer orientation element of the target and the regular grid to obtain an orthoimage corresponding to the hyperspectral image.
第二方面，本申请实施例提出一种高光谱影像正射校正装置，所述装置包括：In the second aspect, the embodiment of the present application proposes a hyperspectral image orthorectification device, which includes:
获取单元，用于获取待校正的高光谱影像数据对应的全色影像数据；An acquisition unit, configured to acquire panchromatic image data corresponding to the hyperspectral image data to be corrected;
特征提取和特征匹配单元，用于通过对所述全色影像数据进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素；The feature extraction and feature matching unit is used to obtain the target outer orientation element corresponding to the panchromatic image data by performing feature extraction and feature matching on the panchromatic image data;
格网生成单元，用于对所述目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；A grid generating unit, configured to perform spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid;
正摄校正单元，用于根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。The orthographic correction unit is configured to perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
第三方面，本申请实施例提出一种高光谱影像正射校正装置，所述装置包括：处理器、存储器及通信总线；所述处理器执行存储器存储的运行程序时实现如上述的高光谱影像正摄校正方法。In the third aspect, the embodiment of the present application proposes a hyperspectral image orthorectification device, the device includes: a processor, a memory, and a communication bus; when the processor executes the running program stored in the memory, the hyperspectral image as described above is realized Orthophoto correction method.
第四方面，本申请实施例提出一种存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述的高光谱影像正摄校正方法。In a fourth aspect, the embodiment of the present application provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the hyperspectral image orthophoto correction method as described above is implemented.
本申请实施例提供了一种高光谱影像正摄校正方法及装置、存储介质，该方法包括：获取待校正的高光谱影像数据对应的全色影像数据；通过对全色影像数据依次进行特征提取和特征匹配，得到全色影像数据对应的目标外方位元素；对目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；根据目标外方位元素和规则格网，对高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。采用上述实现方案，采用高光谱影像数据对应的全色影像数据进行特征提取和特征匹配，然后将得到的目标外方位元素作为高光谱影像正摄校正的外方位元素，进而进行后续的 正摄校正的过程，利用全色影像高分辨率的特性能够匹配到更多的同名点，进而得到更多的目标外方位元素，能够不受观察区域地物类型的影响；后续再利用目标外方位元素对高光谱影像数据进行正摄校正时，同时还保留了高光谱的光谱特征，能够提高正摄校正的精确度。An embodiment of the present application provides a hyperspectral image orthophoto correction method and device, and a storage medium. The method includes: acquiring panchromatic image data corresponding to hyperspectral image data to be corrected; performing feature extraction sequentially on the panchromatic image data Match the features to obtain the target outer orientation elements corresponding to the panchromatic image data; carry out spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid; according to the target outer orientation elements and regular grids, hyperspectral image The data is orthorectified to obtain the orthophoto corresponding to the hyperspectral image. Using the above implementation scheme, the panchromatic image data corresponding to the hyperspectral image data is used for feature extraction and feature matching, and then the obtained target outer orientation elements are used as the outer orientation elements of the hyperspectral image orthophoto correction, and then the subsequent orthophoto correction is performed. In the process of using the high-resolution characteristics of panchromatic images, more points with the same name can be matched, and more target external orientation elements can be obtained, which can not be affected by the type of objects in the observation area; When performing orthophoto correction on hyperspectral image data, the spectral characteristics of hyperspectral are also retained, which can improve the accuracy of orthophoto correction.
附图说明Description of drawings
图1为本申请实施例提供的一种高光谱影像正摄校正方法的流程图；FIG. 1 is a flow chart of a hyperspectral image orthographic correction method provided in an embodiment of the present application;
图2为本申请实施例提供的一种示例性的机载高光谱影像正摄校正方法；Fig. 2 is an exemplary airborne hyperspectral image orthophoto correction method provided by the embodiment of the present application;
图3为本申请实施例提供的一种高光谱影像正摄校正装置的结构示意图一；Fig. 3 is a structural schematic diagram 1 of a hyperspectral image orthographic correction device provided by an embodiment of the present application;
图4为本申请实施例提供的一种高光谱影像正摄校正装置的结构示意图二。FIG. 4 is a second structural schematic diagram of a hyperspectral image orthophoto correction device provided by an embodiment of the present application.
具体实施方式Detailed ways
应当理解，此处描述的具体实施例仅仅用以解释本申请。并不用于限定本申请。It should be understood that the specific embodiments described here are only used to explain the present application. It is not intended to limit the application.
本申请实施例提供一种高光谱影像正摄校正方法，如图1所示，该方法可以包括：The embodiment of the present application provides a hyperspectral image orthophoto correction method, as shown in Figure 1, the method may include:
S101、获取待校正的高光谱影像数据对应的全色影像数据。S101. Acquire panchromatic image data corresponding to hyperspectral image data to be corrected.
本申请实施例提出的一种高光谱影像正摄校正方法适用于对机载高光谱遥感影像进行全自动正摄校正的场景中。A hyperspectral image orthographic correction method proposed in an embodiment of the present application is applicable to a scene where fully automatic orthographic correction is performed on an airborne hyperspectral remote sensing image.
本申请实施例中，待校正的高光谱影像数据可以存储在机载高光谱影像数据集中，在本申请实施例中，确定机载高光谱影像数据集中是否每一幅高光谱影像数据均存在对应的全色影像数据。In the embodiment of the present application, the hyperspectral image data to be corrected can be stored in the airborne hyperspectral image data set. In the embodiment of the present application, it is determined whether each hyperspectral image data in the airborne hyperspectral image data set has a corresponding panchromatic image data.
需要说明的是，在本申请实施例中，每一幅待校正的高光谱影像数据均需存在对应的全色影像数据。It should be noted that, in the embodiment of the present application, each piece of hyperspectral image data to be corrected needs to have corresponding panchromatic image data.
本申请实施例中，高光谱影像数据的数量为两幅或者多幅，具体的可以根据实际情况进行选择，本申请实施例不做具体的限定。In the embodiment of the present application, the number of hyperspectral image data is two or more, which can be selected according to the actual situation, and is not specifically limited in the embodiment of the present application.
S102、通过对全色影像数据依次进行特征提取和特征匹配，得到全色影像数据对应的目标外方位元素。S102. Obtain the target outer orientation element corresponding to the panchromatic image data by performing feature extraction and feature matching sequentially on the panchromatic image data.
在本申请实施例中，先对全色影像数据进行特征提取，得到全色影像数据对应的特征数据。In the embodiment of the present application, feature extraction is first performed on the panchromatic image data to obtain feature data corresponding to the panchromatic image data.
本申请实施例中，可以采用尺度不变特征变换(Scale Invariant Feature Transform，SIFT)-CPU或SIFT-图形处理单元(Graphics Processing Unit，GPU)算法对每一幅全色影像数据进行特征提取，具体的可以根据实际情况进行选择，本申请实施例不做具体的限定。In the embodiment of the present application, a scale invariant feature transform (Scale Invariant Feature Transform, SIFT)-CPU or SIFT-graphics processing unit (Graphics Processing Unit, GPU) algorithm can be used to extract features from each piece of panchromatic image data, specifically can be selected according to the actual situation, and is not specifically limited in this embodiment of the application.
需要说明的是，若采用SIFT-CPU算法对每一幅全色影像数据进行特征提取，则特征提取过程包括尺度空间极值检测、关键点定位、主方向确定和关键点特征向量描述着四个步骤；而若采用SIFT-GPU算法对每一幅全色影像数据进行特征提取，则会在SIFT-GPU算法的基础上、采用GPU并行算法对每一幅全色影像数据进行高斯金字塔影像构建、关键点定位和主方向确定的步骤，进而提高特征提取速度。It should be noted that if the SIFT-CPU algorithm is used to extract features from each piece of panchromatic image data, the feature extraction process includes scale space extremum detection, key point positioning, main direction determination, and key point feature vectors to describe four steps; and if the SIFT-GPU algorithm is used to extract features from each panchromatic image data, on the basis of the SIFT-GPU algorithm, the GPU parallel algorithm is used to construct a Gaussian pyramid image for each panchromatic image data, The steps of key point positioning and main direction determination can improve the speed of feature extraction.
可以理解的是，本申请实施例对全色影像数据进行特征提取，可以使得获得的特征点数量更大，且分布更加均匀，可以有效克服高光谱影像单波段图像上的辐射亮度值较低的阴影区造成的特征点缺失的不足。It can be understood that the embodiment of the present application performs feature extraction on panchromatic image data, which can make the number of obtained feature points larger and more uniform in distribution, and can effectively overcome the problem of low radiance values on single-band images of hyperspectral images. Insufficiency of missing feature points caused by shaded areas.
需要说明的是，上述SIFT-CPU算法或SIFT-GPU算法对应的特征提取函数可以存储在如OpenCV(跨平台计算机视觉和机器学习软件)的第三方开源库中，可以通过调用第三方开源库中的特征提取函数来调用上述SIFT-CPU算法或SIFT-GPU算法。It should be noted that the feature extraction function corresponding to the above-mentioned SIFT-CPU algorithm or SIFT-GPU algorithm can be stored in a third-party open source library such as OpenCV (cross-platform computer vision and machine learning software), and can be accessed by calling the third-party open source library The feature extraction function to call the above SIFT-CPU algorithm or SIFT-GPU algorithm.
本申请实施例中，在对全色影像数据进行特征提取，得到全色影像数据对应的特征数据之后，基于特征数据对全色影像数据进行特征匹配，得到全色影像数据的同名点在全色影像数据中的匹配关系。In the embodiment of the present application, after feature extraction is performed on the panchromatic image data to obtain the feature data corresponding to the panchromatic image data, feature matching is performed on the panchromatic image data based on the feature data to obtain the panchromatic image data. Matching relationships in image data.
具体的，首先获取全色影像数据的初始外方位元素；之后根据初始外方位元素，计算全色影像之间的影像中心距离；再从影像中心距离中筛选出小于影像距离阈值的目标影像中心距离；之后计算目标影像中心距离之间的统计特征数据；并基于统计特征数据，确定同名点在全色影像数据中的匹配关系。Specifically, first obtain the initial outer orientation element of the panchromatic image data; then calculate the image center distance between the panchromatic images according to the initial outer orientation element; then filter out the target image center distance smaller than the image distance threshold from the image center distance ; Then calculate the statistical feature data between the center distances of the target images; and based on the statistical feature data, determine the matching relationship of the points with the same name in the panchromatic image data.
本申请实施例中，统计特征数据可以包括平均值和/或标准差等统计数据，具体的可以根据实际情况进行选择，本申请实施例不做具体的限定。In the embodiment of the present application, the statistical feature data may include statistical data such as average value and/or standard deviation, which may be selected according to actual conditions, and is not specifically limited in the embodiment of the present application.
示例性的，针对影像中心距离与平均值的差值大于3倍标准差的全色影像数据，则认为这几个全色影像数据之间不存在匹配关系。Exemplarily, for the panchromatic image data whose difference between the image center distance and the average value is greater than 3 times the standard deviation, it is considered that there is no matching relationship between these panchromatic image data.
本申请实施例中，可以采用快速最近邻逼近搜索函数库(Fast Approximate Nearest Neighbor Search Library，FLANN)匹配方法对存在匹配关系的全色影像数据进行特征匹配，得到同名点在全色影像数据中的匹配关系。In the embodiment of the present application, the Fast Approximate Nearest Neighbor Search Library (FLANN) matching method can be used to perform feature matching on panchromatic image data with a matching relationship, and obtain the same-name points in the panchromatic image data. matching relationship.
需要说明的是，FLANN匹配算法对应的特征匹配函数也可以存储在如OpenCV的第三方开源库中。It should be noted that the feature matching function corresponding to the FLANN matching algorithm can also be stored in a third-party open source library such as OpenCV.
进一步地，在确定出同名点在全色影像数据中的匹配关系之后；还可以确定匹配关系对应的基础矩阵；基于基础矩阵，确定匹配关系中的误差匹配关系；从匹配关系中删除误差匹配关系，得到更新后的匹配关系。Further, after determining the matching relationship of the same-name point in the panchromatic image data; the basic matrix corresponding to the matching relationship can also be determined; based on the basic matrix, the error matching relationship in the matching relationship is determined; the error matching relationship is deleted from the matching relationship , to get the updated matching relationship.
在本申请实施例中，可以根据计算机视觉领域的7-点法计算得到匹配关系对应的全色影像数据对的左右影像数据进行变换的基础矩阵；之后，采用随机抽样一致性(Random Sample Consensus，RANSAC)方法确定误差匹配关系。In the embodiment of the present application, the basic matrix for transforming the left and right image data of the panchromatic image data pair corresponding to the matching relationship can be calculated according to the 7-point method in the field of computer vision; after that, random sampling consistency (Random Sample Consensus, RANSAC) method to determine the error matching relationship.
具体的，在得到基础矩阵后，可以利用公式(1)计算得到左右影像数据的特征点坐标对应的核线方程，进一步计算特征点坐标对应的核线误差，并根据核线误差，并根据核线误差进行误差剔除。Specifically, after obtaining the basic matrix, formula (1) can be used to calculate the epipolar line equation corresponding to the feature point coordinates of the left and right image data, and further calculate the epipolar line error corresponding to the feature point coordinates, and according to the epipolar line error and the kernel line Line errors are eliminated.
l R:(x Lf 1+y Lf 2+f 3)x+(x Lf 4+y Lf 5+f 6)y+(x Lf 7+y Lf 8+f 9)＝0 l R :(x L f 1 +y L f 2 +f 3 )x+(x L f 4 +y L f 5 +f 6 )y+(x L f 7 +y L f 8 +f 9 )＝0
l L:(x Rf 1+y Rf 2+f 3)x+(x Rf 4+y Rf 5+f 6)y+(x Rf 7+y Rf 8+f 9)＝0    (1) l L :(x R f 1 +y R f 2 +f 3 )x+(x R f 4 +y R f 5 +f 6 )y+(x R f 7 +y R f 8 +f 9 )＝0 ( 1)
其中，x L,y L,x R,y R分别为匹配对的左影像数据、右影像数据上的特征点坐标，f 1,f 2,...,f 9为变换方程公式(2)中基础矩阵的系数。 Among them, x L , y L , x R , y R are the feature point coordinates on the left image data and right image data of the matching pair respectively, and f 1 , f 2 ,..., f 9 are the transformation equation formula (2) The coefficients of the fundamental matrix in .
Figure PCTCN2022133512-appb-000001
Figure PCTCN2022133512-appb-000001
本申请实施例中，在得到全色影像数据的同名点在全色影像数据中的匹配关系之后；基于匹配关系、全色影像数据的初始外方位元素和全色影像数据对应的待定地面点坐标的初始值，确定出全色影像数据对应的目标外方位元素。In the embodiment of the present application, after obtaining the matching relationship of the same-named point of the panchromatic image data in the panchromatic image data; based on the matching relationship, the initial outer orientation element of the panchromatic image data and the undetermined ground point coordinates The initial value of is used to determine the target outer orientation element corresponding to the panchromatic image data.
本申请实施例中，首先确定各个全色影像数据对应的初始外方位元素和全色影像数据的各个特征点对应的待定地面点坐标的初始值，之后，根据预设的共线方程建立误差方程，将匹配关系、全色影像数据的初始外方位元素和全色影像数据对应的待定地面点坐标的初始值输入误差方程中，求解方程，得到全色影像数据对应的目标外方位元素。In the embodiment of the present application, first determine the initial outer orientation elements corresponding to each panchromatic image data and the initial values of the undetermined ground point coordinates corresponding to each feature point of the panchromatic image data, and then establish the error equation according to the preset collinear equation , input the matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data into the error equation, and solve the equation to obtain the target outer orientation element corresponding to the panchromatic image data.
本申请实施例中，可以将工程提供的POS辅助数据确定各个全色影像数据对应的初始外方位元素和全色影像数据的各个特征点对应的待定地面点坐标的初始值。In this embodiment of the application, the POS auxiliary data provided by the project can be used to determine the initial outer orientation elements corresponding to each panchromatic image data and the initial values of the undetermined ground point coordinates corresponding to each feature point of the panchromatic image data.
进一步地，还计算目标外方位元素的过程中，还可以通过选权迭代法剔除误匹配的同名点，并剔除不满足区域网平差条件的全色影像数据。对于地面覆盖范围较大的高光谱影像数据集，可以进行基于位置的分块区域网平差。Furthermore, in the process of calculating the outer orientation elements of the target, it is also possible to eliminate the wrongly matched points with the same name through the weight selection iteration method, and to eliminate the panchromatic image data that does not meet the block adjustment conditions. For hyperspectral imagery datasets with large ground coverage, a location-based block block adjustment can be performed.
进一步地，在从匹配关系中删除所述误差匹配关系，得到更新后的匹配关系后，还可以基于更新后的匹配关系、全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出全色影像数据对应的目标外方位元素。需要说明的是，基于更新后的匹配关系、全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出全色影像数据对应的目标外方位元素的过程与基于更新后的匹配关系、全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出全色影像数据对应的目标外方位元素的过程一致，在此不再赘述。Further, after deleting the error matching relationship from the matching relationship and obtaining the updated matching relationship, based on the updated matching relationship, the initial outer orientation element of the panchromatic image data and the corresponding The initial value of the ground point coordinates is to be determined, and the target outer orientation element corresponding to the panchromatic image data is determined. It should be noted that based on the updated matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, the target outer orientation element corresponding to the panchromatic image data is determined The process and the process of determining the target outer orientation element corresponding to the panchromatic image data based on the updated matching relationship, the initial outer orientation element of the panchromatic image data, and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data Consistent, no more details here.
S103、对目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网。S103. Carry out spatial forward intersection calculation and grid construction on the outer orientation elements of the target to obtain a regular grid.
本申请实施例中，首先对目标外方位元素进行空间前方交汇计算，得到待定地面点坐标，并将待定地面点坐标确定为稀疏点云。之后，进行稀疏点云自适应滤波，得到稀疏地面点云，再对稀疏地面点云构建不规则三角网，最后根据不规则三角网内插得到规则格网。In the embodiment of the present application, firstly, the spatial front intersection calculation is performed on the outer orientation elements of the target to obtain the undetermined ground point coordinates, and the undetermined ground point coordinates are determined as a sparse point cloud. After that, the sparse point cloud adaptive filtering is performed to obtain the sparse ground point cloud, and then the irregular triangulation network is constructed for the sparse ground point cloud, and finally the regular grid is obtained by interpolating the irregular triangulation network.
具体的，可以采用多尺度形态学滤波以及渐进三角网加密的方法进行稀疏点云的自适应滤波。Specifically, multi-scale morphological filtering and progressive triangulation encryption can be used for adaptive filtering of sparse point clouds.
需要说明的是，考虑到稀疏地面点云平面坐标互不重叠，可以对稀疏地面点云进行二维Delaunay(德洛内)三角网构建即可。在进行规则格网内插时使用线性内插，即在三角形三点确定的空间平面上进行插值。It should be noted that, considering that the plane coordinates of the sparse ground point cloud do not overlap with each other, a two-dimensional Delaunay (Delaunay) triangulation network can be constructed on the sparse ground point cloud. Linear interpolation is used when performing regular grid interpolation, that is, interpolation is performed on the spatial plane determined by the three points of the triangle.
需要说明的是，基于匹配关系、全色影像数据的初始外方位元素和全色影像数据对应的待定地面点坐标的初始值，确定出全色影像数据对应的目标外方位元素的过程和对目标外方位元素进行空间前方交汇计算，得到待定地面点坐标，并将待定地面点坐标确定为稀疏点云的过程共同构成了光束法区域网平差过程。It should be noted that based on the matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, the process of determining the target outer orientation element corresponding to the panchromatic image data and the target The process of calculating the spatial forward intersection of the outer orientation elements to obtain the undetermined ground point coordinates, and determining the undetermined ground point coordinates as a sparse point cloud together constitutes the process of beam block adjustment.
S104、根据目标外方位元素和规则格网，对高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。S104. Perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
本申请实施例中，根据预设插值间隔，确定高光谱影像的插值格网；并获取插值格网中每个格网点的第一像点坐标；根据目标外方位元素和规则格网，计算插值格网中每个格网点的第二像点坐标；基于第一像点坐标和第二像点坐标，对高光谱影像数据进行正摄校正，得到正摄影像。In the embodiment of the present application, the interpolation grid of the hyperspectral image is determined according to the preset interpolation interval; and the first pixel coordinates of each grid point in the interpolation grid are obtained; the interpolation value is calculated according to the target outer orientation element and the regular grid The second image point coordinates of each grid point in the grid; based on the first image point coordinates and the second image point coordinates, perform orthophoto correction on the hyperspectral image data to obtain an orthophoto image.
具体的，根据目标外方位元素和规则格网，计算插值格网中每个格网点的第二像点坐标的过程具体包括：根据预设正摄影像比例尺参数，计算每个格网点对应待定地面点的X轴坐标和Y轴坐标；根据X轴坐标、Y轴坐标和规则格网，确定每个格网点对应待定地面点的Z轴坐标；根据目标外方位元素和Z轴坐标，计算插值格网中每个格网点的第二像点坐标。Specifically, the process of calculating the second pixel coordinates of each grid point in the interpolation grid according to the outer orientation element of the target and the regular grid specifically includes: according to the preset orthographic image scale parameter, calculating the corresponding ground of each grid point The X-axis coordinates and Y-axis coordinates of the point; according to the X-axis coordinates, Y-axis coordinates and the regular grid, determine the Z-axis coordinates of each grid point corresponding to the undetermined ground point; calculate the interpolation grid according to the target outer orientation element and the Z-axis coordinates The second pixel coordinates of each grid point in the grid.
需要说明的是，第一像点坐标为插值格网内的格网点对应的校正后的坐标，第二像点坐标为差值格网内的格网点对应的校正前的坐标。It should be noted that the first pixel coordinates are the corrected coordinates corresponding to the grid points in the interpolation grid, and the second pixel coordinates are the uncorrected coordinates corresponding to the grid points in the difference grid.
在本申请实施例中，可以根据公式(3)计算得到第二像点坐标。In the embodiment of the present application, the coordinates of the second image point can be obtained through calculation according to formula (3).
Figure PCTCN2022133512-appb-000002
Figure PCTCN2022133512-appb-000002
其中，λ为可消除变量，f为主距，m′ 1,m′ 1,n′ 1,n′ 2为内定向变换系数，a 1,a 2,...,c 3为目标外方位元素计算所得到的旋转矩阵，I 0,J 0为第一像点坐标，X S,Y S,Z S为摄影中心三维坐标，I,J为格网点对应的像方坐标，X,Y,Z为格网点对应的三维坐标。I,J,X,Y,Z均可作为第二像点坐标。 Among them, λ is the variable that can be eliminated, f is the main distance, m′ 1 , m′ 1 , n′ 1 , n′ 2 are the internal orientation transformation coefficients, a 1 , a 2 ,...,c 3 are the outer orientation of the target The rotation matrix obtained by element calculation, I 0 , J 0 are the coordinates of the first image point, X S , Y S , Z S are the three-dimensional coordinates of the photography center, I, J are the image square coordinates corresponding to the grid points, X, Y, Z is the three-dimensional coordinate corresponding to the grid point. I, J, X, Y, Z can be used as the second image point coordinates.
本申请实施例中，在得到第一像点坐标和第二像点坐标之后，对第一像点坐标和第二像点坐标进行双线性差值，获取高光谱影像中其他点对应 的校正前的像点坐标，再在校正前的像点坐标上进行像点赋值，最终得到高光谱影像对应的正摄影像。In the embodiment of the present application, after obtaining the coordinates of the first image point and the coordinates of the second image point, a bilinear difference is performed on the coordinates of the first image point and the coordinates of the second image point to obtain corrections corresponding to other points in the hyperspectral image The image point coordinates before correction, and then the image point assignment is performed on the image point coordinates before correction, and finally the orthographic image corresponding to the hyperspectral image is obtained.
需要说明的是，根据目标外方位元素和规则格网，计算插值格网中每个格网点的第二像点坐标的过程具体可以包括：获取高光谱影像对应的地面范围数据；根据地面范围数据和规则格网，构建内存规则格网；根据目标外方位元素和内存规则格网，计算插值格网中每个格网点的第二像点坐标。即在根据目标外方位元素和Z轴坐标，计算插值格网中每个格网点的第二像点坐标之前，首先根据地面范围与规则格网，构建内存规则格网，以减少内存需求。It should be noted that the process of calculating the second pixel coordinates of each grid point in the interpolation grid according to the target outer orientation element and the regular grid may specifically include: obtaining the ground range data corresponding to the hyperspectral image; according to the ground range data and a regular grid to construct a regular grid in memory; calculate the second image point coordinates of each grid point in the interpolation grid according to the orientation elements outside the target and the regular grid in memory. That is, before calculating the second image point coordinates of each grid point in the interpolation grid according to the outer orientation elements of the target and the Z-axis coordinates, first construct a memory regular grid based on the ground range and the regular grid to reduce memory requirements.
进一步地，计算第二像点坐标时，可以采用共享存储并行编程(Open Multi-Processing，Open MP)进行并行计算，以提高处理效率；且对超大尺度的高光谱影像数据进行正射校正时，可以采用分块校正的策略。Further, when calculating the coordinates of the second image point, shared memory parallel programming (Open Multi-Processing, Open MP) can be used for parallel computing to improve processing efficiency; and when performing orthorectification on ultra-large-scale hyperspectral image data, A block correction strategy can be used.
可以理解的是，采用高光谱影像数据对应的全色影像数据进行特征提取和特征匹配，然后将得到的目标外方位元素作为高光谱影像正摄校正的外方位元素，进而进行后续的正摄校正的过程，利用全色影像高分辨率的特性能够匹配到更多的同名点，进而得到更多的目标外方位元素，能够不受观察区域地物类型的影响；后续再利用目标外方位元素对高光谱影像数据进行正摄校正时，同时还保留了高光谱的光谱特征，能够提高正摄校正的精确度。It is understandable that the panchromatic image data corresponding to the hyperspectral image data is used for feature extraction and feature matching, and then the obtained outer orientation elements of the target are used as the outer orientation elements of the hyperspectral image for orthophoto correction, and then subsequent orthophoto correction is performed. In the process of using the high-resolution characteristics of panchromatic images, more points with the same name can be matched, and more target external orientation elements can be obtained, which can not be affected by the type of objects in the observation area; When performing orthophoto correction on hyperspectral image data, the spectral characteristics of hyperspectral are also retained, which can improve the accuracy of orthophoto correction.
基于上述实施例，本申请实施例提出一种机载高光谱影像正摄校正方法，如图2所示，该方法可以包括：Based on the above embodiments, the embodiment of the present application proposes an airborne hyperspectral image orthographic correction method, as shown in Figure 2, the method may include:
1、获取高光谱影像数据对应的全色影像数据和全色影像数据对应的初始外方位元素；1. Obtain the panchromatic image data corresponding to the hyperspectral image data and the initial outer orientation element corresponding to the panchromatic image data;
2、根据初始外方位元素，对全色影像进行特征提取，得到全色影像数据对应的特征数据；2. According to the initial outer orientation elements, feature extraction is performed on the panchromatic image to obtain the feature data corresponding to the panchromatic image data;
3、基于特征数据对全色影像数据进行特征匹配，得到全色影像数据的同名点在全色影像数据中的匹配关系；3. Perform feature matching on the panchromatic image data based on the feature data, and obtain the matching relationship of the same-named points of the panchromatic image data in the panchromatic image data;
需要说明的是，步骤3包括以下3.1-3.5，It should be noted that step 3 includes the following 3.1-3.5,
3.1、根据初始外方位元素，计算全色影像之间的影像中心距离；3.1. Calculate the image center distance between panchromatic images according to the initial outer orientation elements;
3.2、从影像中心距离中，筛选出小于影像距离阈值的目标影像中心距离；3.2. From the image center distance, select the target image center distance smaller than the image distance threshold;
3.3、计算目标影像中心距离之间的统计特征数据；3.3. Calculate the statistical feature data between the center distances of the target images;
3.4、根据统计特征数据确定同名点是否在全色影像数据存在匹配关系；3.4. According to the statistical feature data, determine whether the point with the same name has a matching relationship in the panchromatic image data;
3.5、若确定出同名点在全色影像数据存在匹配关系，则采用FLANN匹配方法对存在匹配关系的全书色影像数据进行特征匹配，得到同名点在全色影像数据中的匹配关系。3.5. If it is determined that there is a matching relationship between the same-named points in the panchromatic image data, then use the FLANN matching method to perform feature matching on the full-color image data that has a matching relationship, and obtain the matching relationship of the same-named points in the panchromatic image data.
4、获取全色影像数据的各个特征点对应的待定地面点坐标的初始值；4. Obtain the initial value of the undetermined ground point coordinates corresponding to each feature point of the panchromatic image data;
5、根据初始外方位元素和全色影像数据的各个特征点对应的待定地面 点坐标的初始值确定全色影像数据对应的目标外方位元素和稀疏点云；5. Determine the target outer orientation element and sparse point cloud corresponding to the panchromatic image data according to the initial value of the undetermined ground point coordinates corresponding to each feature point of the initial outer orientation element and the panchromatic image data;
需要说明的是，步骤5包括以下5.1-5.3，It should be noted that step 5 includes the following 5.1-5.3,
5.1、根据预设共线方程建立误差方程；5.1. Establish the error equation according to the preset collinear equation;
5.2、将匹配关系、初始外方位元素、全色影像数据的各个特征点对应的待定地面点坐标的初始值输入误差方程中，求解出目标外方位元素；5.2. Input the initial value of the matching relation, the initial outer orientation element, and the undetermined ground point coordinates corresponding to each feature point of the panchromatic image data into the error equation, and solve the target outer orientation element;
5.3、对目标外方位元素进行空间前方交汇计算，得到稀疏点云；5.3. Carry out spatial forward intersection calculations on the outer orientation elements of the target to obtain sparse point clouds;
6、根据稀疏点云，生成规则格网；6. Generate a regular grid based on the sparse point cloud;
7、根据目标外方位元素和规则格网，对高光谱影像进行正摄校正，得到高光谱影像对应的正摄影像；7. Perform orthophoto correction on the hyperspectral image according to the outer orientation elements of the target and the regular grid, and obtain the orthophoto image corresponding to the hyperspectral image;
需要说明的是，步骤7包括以下7.1-7.3，It should be noted that step 7 includes the following 7.1-7.3,
7.1、根据预设插值间隔确定高光谱影像的插值格网；并获取插值格网中每个格网点对应的校正后的像点坐标；7.1. Determine the interpolation grid of the hyperspectral image according to the preset interpolation interval; and obtain the corrected image point coordinates corresponding to each grid point in the interpolation grid;
7.2、根据目标外方位元素、规则格网和校正后的像点坐标，确定每个格网点校正前的像点坐标；7.2. Determine the image point coordinates of each grid point before correction according to the outer orientation elements of the target, the regular grid, and the corrected image point coordinates;
7.3、基于第一像点坐标和第二像点坐标，对高光谱影像数据进行正摄校正，得到正摄影像。7.3. Based on the coordinates of the first image point and the coordinates of the second image point, perform orthographic correction on the hyperspectral image data to obtain an orthographic image.
基于上述实施例，本申请实施例提供一种高光谱影像正射校正装置。如图3所示，该高光谱影像正射校正装置1包括：Based on the above-mentioned embodiments, an embodiment of the present application provides a hyperspectral image orthorectification device. As shown in Figure 3, the hyperspectral image orthorectification device 1 includes:
获取单元10，用于获取待校正的高光谱影像数据对应的全色影像数据；An acquisition unit 10, configured to acquire panchromatic image data corresponding to the hyperspectral image data to be corrected;
特征提取和特征匹配单元11，用于通过对所述全色影像数据进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素；The feature extraction and feature matching unit 11 is used to obtain the target outer orientation element corresponding to the panchromatic image data by performing feature extraction and feature matching on the panchromatic image data;
格网生成单元12，用于对所述目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；A grid generating unit 12, configured to perform spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid;
正摄校正单元13，用于根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。The orthophoto correction unit 13 is configured to perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
可选的，所述高光谱影像正射校正装置1还包括：特征提取单元、特征匹配单元和确定单元；Optionally, the hyperspectral image orthorectification device 1 further includes: a feature extraction unit, a feature matching unit, and a determination unit;
所述特征提取单元，用于对所述全色影像数据进行特征提取，得到所述全色影像数据对应的特征数据；The feature extraction unit is configured to perform feature extraction on the panchromatic image data to obtain feature data corresponding to the panchromatic image data;
所述特征匹配单元，用于基于所述特征数据对所述全色影像数据进行特征匹配，得到所述全色影像数据的同名点在所述全色影像数据中的匹配关系；The feature matching unit is configured to perform feature matching on the panchromatic image data based on the feature data, to obtain a matching relationship of the same-named points of the panchromatic image data in the panchromatic image data;
所述确定单元，用于基于所述匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素。The determining unit is configured to determine, based on the matching relationship, the initial outer orientation element of the panchromatic image data, and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, that the panchromatic image data corresponds to The out-of-target orientation element of .
可选的，所述高光谱影像正射校正装置1还包括：计算单元和筛选单元；Optionally, the hyperspectral image orthorectification device 1 further includes: a calculation unit and a screening unit;
所述获取单元10，还用于获取所述全色影像数据的初始外方位元素；The acquiring unit 10 is further configured to acquire an initial outer orientation element of the panchromatic image data;
所述计算单元，用于根据所述初始外方位元素，计算所述全色影像之间的影像中心距离；计算所述目标影像中心距离之间的统计特征数据；The calculation unit is used to calculate the image center distance between the panchromatic images according to the initial outer orientation element; calculate the statistical feature data between the center distances of the target images;
所述筛选单元，用于从所述影像中心距离中筛选出小于影像距离阈值的目标影像中心距离；The screening unit is configured to screen the target image center distances smaller than the image distance threshold from the image center distances;
所述确定单元，用于基于所述统计特征数据，确定所述同名点在所述全色影像数据中的匹配关系。The determining unit is configured to determine a matching relationship of the same-named points in the panchromatic image data based on the statistical feature data.
可选的，所述确定单元，还用于根据预设插值间隔，确定所述高光谱影像的插值格网；Optionally, the determining unit is further configured to determine the interpolation grid of the hyperspectral image according to a preset interpolation interval;
所述获取单元10，还用于获取所述插值格网中每个格网点的第一像点坐标；The acquiring unit 10 is further configured to acquire the first pixel coordinates of each grid point in the interpolation grid;
所述计算单元，还用于根据所述目标外方位元素和所述规则格网，计算所述插值格网中每个格网点的第二像点坐标；The calculation unit is further configured to calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the regular grid;
所述正摄校正单元13，还用于基于所述第一像点坐标和所述第二像点坐标，对所述高光谱影像数据进行正摄校正，得到所述正摄影像。The orthophoto correction unit 13 is further configured to perform orthophoto correction on the hyperspectral image data based on the first image point coordinates and the second image point coordinates to obtain the orthophoto image.
可选的，所述计算单元，还用于根据预设正摄影像比例尺参数，计算每个格网点对应待定地面点的X轴坐标和Y轴坐标；根据所述目标外方位元素和所述Z轴坐标，计算所述插值格网中每个格网点的所述第二像点坐标；Optionally, the calculation unit is also used to calculate the X-axis coordinates and Y-axis coordinates of each grid point corresponding to the undetermined ground point according to the preset orthographic image scale parameter; according to the target outer orientation element and the Z Axis coordinates, calculating the second image point coordinates of each grid point in the interpolation grid;
所述确定单元，还用于根据所述X轴坐标、所述Y轴坐标和所述规则格网，确定每个格网点对应待定地面点的Z轴坐标。The determining unit is further configured to determine, according to the X-axis coordinates, the Y-axis coordinates and the regular grid, the Z-axis coordinates of each grid point corresponding to the undetermined ground point.
可选的，所述高光谱影像正射校正装置1还包括：删除单元；Optionally, the hyperspectral image orthorectification device 1 further includes: a deletion unit;
所述确定单元，还用于确定所述匹配关系对应的基础矩阵；基于所述基础矩阵，确定所述匹配关系中的误差匹配关系；基于所述更新后的匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素；The determining unit is further configured to determine a basic matrix corresponding to the matching relationship; based on the basic matrix, determine an error matching relationship in the matching relationship; based on the updated matching relationship, the panchromatic image data The initial value of the initial outer orientation element and the undetermined ground point coordinates corresponding to the panchromatic image data, and determine the target outer orientation element corresponding to the panchromatic image data;
所述删除单元，用于从所述匹配关系中删除所述误差匹配关系，得到更新后的匹配关系。The deleting unit is configured to delete the error matching relationship from the matching relationship to obtain an updated matching relationship.
可选的，所述高光谱影像正射校正装置1还包括：构建单元；Optionally, the hyperspectral image orthorectification device 1 further includes: a construction unit;
所述获取单元10，还用于获取所述高光谱影像对应的地面范围数据；The acquiring unit 10 is further configured to acquire ground range data corresponding to the hyperspectral image;
所述构建单元，用于根据所述地面范围数据和所述规则格网，构建内存规则格网；The construction unit is configured to construct a memory regular grid according to the ground range data and the regular grid;
所述计算单元，还用于根据所述目标外方位元素和所述内存规则格网，计算所述插值格网中每个格网点的第二像点坐标。The calculation unit is further configured to calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the internal regular grid.
本申请实施例提供的一种高光谱影像正射校正装置，获取待校正的高光谱影像数据对应的全色影像数据；通过对全色影像数据依次进行特征提取和特征匹配，得到全色影像数据对应的目标外方位元素；对目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；根据目标外方位元素和规则格网，对高光谱影像数据进行正射校正，得到高光谱影像对应 的正射影像。由此可见，本实施例提出的高光谱影像正射校正装置，采用高光谱影像数据对应的全色影像数据进行特征提取和特征匹配，然后将得到的目标外方位元素作为高光谱影像正摄校正的外方位元素，进而进行后续的正摄校正的过程，利用全色影像高分辨率的特性能够匹配到更多的同名点，进而得到更多的目标外方位元素，能够不受观察区域地物类型的影响；后续再利用目标外方位元素对高光谱影像数据进行正摄校正时，同时还保留了高光谱的光谱特征，能够提高正摄校正的精确度。A hyperspectral image orthorectification device provided in an embodiment of the present application obtains panchromatic image data corresponding to hyperspectral image data to be corrected; panchromatic image data is obtained by sequentially performing feature extraction and feature matching on the panchromatic image data Corresponding target external orientation elements; carry out space forward intersection calculation and grid construction on the target external orientation elements to obtain regular grids; according to target external orientation elements and regular grids, perform orthorectification on hyperspectral image data to obtain hyperspectral The orthophoto corresponding to the image. It can be seen that the hyperspectral image orthorectification device proposed in this embodiment uses the panchromatic image data corresponding to the hyperspectral image data to perform feature extraction and feature matching, and then uses the obtained target outer orientation elements as hyperspectral image orthophoto correction The outer azimuth elements of the target, and then carry out the subsequent orthophoto correction process, using the high-resolution characteristics of the panchromatic image to match more points with the same name, and then get more outer azimuth elements of the target, which can not be affected by the observation area. The influence of the type; when the hyperspectral image data is orthographically corrected by using the external azimuth elements of the target, the spectral characteristics of the hyperspectral spectrum are also retained, which can improve the accuracy of the orthographic correction.
图4为本申请实施例提供的一种高光谱影像正射校正装置1的组成结构示意图二，在实际应用中，基于上述实施例的同一公开构思下，如图4所示，本实施例的高光谱影像正射校正装置1包括：处理器14、存储器15及通信总线16。Fig. 4 is a schematic diagram of the composition and structure of a hyperspectral image orthorectification device 1 provided by the embodiment of the present application. In practical applications, based on the same disclosed concept of the above embodiment, as shown in Fig. The hyperspectral image orthorectification device 1 includes: a processor 14 , a memory 15 and a communication bus 16 .
在具体的实施例的过程中，上述获取单元10、特征提取和特征匹配单元11、格网生成单元12、正摄校正单元13、特征提取单元、特征匹配单元、确定单元、计算单元、筛选单元、删除单元和构建单元可由位于高光谱影像正射校正装置1上的处理器14实现，上述处理器14可以为特定用途集成电路(ASIC，Application Specific Integrated Circuit)、数字信号处理器(DSP，Digital Signal Processor)、数字信号处理图像处理装置(DSPD，Digital Signal Processing Device)、可编程逻辑图像处理装置(PLD，Programmable Logic Device)、现场可编程门阵列(FPGA，Field Programmable Gate Array)、CPU、控制器、微控制器、微处理器中的至少一种。可以理解地，对于不同的设备，用于实现上述处理器功能的电子器件还可以为其它，本实施例不作具体限定。In the process of a specific embodiment, the above-mentioned acquisition unit 10, feature extraction and feature matching unit 11, grid generation unit 12, orthophoto correction unit 13, feature extraction unit, feature matching unit, determination unit, calculation unit, screening unit The deletion unit and the construction unit can be realized by a processor 14 located on the hyperspectral image orthorectification device 1, and the above-mentioned processor 14 can be an application-specific integrated circuit (ASIC, Application Specific Integrated Circuit), a digital signal processor (DSP, Digital Signal Processor), digital signal processing image processing device (DSPD, Digital Signal Processing Device), programmable logic image processing device (PLD, Programmable Logic Device), field programmable gate array (FPGA, Field Programmable Gate Array), CPU, control At least one of controllers, microcontrollers, and microprocessors. It can be understood that, for different devices, the electronic device used to implement the above processor function may also be other, which is not specifically limited in this embodiment.
在本申请实施例中，上述通信总线16用于实现处理器14和存储器15之间的连接通信；上述处理器14执行存储器15中存储的运行程序时实现如下的高光谱影像正射校正方法：In the embodiment of the present application, the above-mentioned communication bus 16 is used to realize connection and communication between the processor 14 and the memory 15; when the above-mentioned processor 14 executes the running program stored in the memory 15, the following hyperspectral image orthorectification method is realized:
获取待校正的高光谱影像数据对应的全色影像数据；通过对所述全色影像数据依次进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素；对所述目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。Acquiring the panchromatic image data corresponding to the hyperspectral image data to be corrected; by sequentially performing feature extraction and feature matching on the panchromatic image data, obtaining the target external orientation element corresponding to the panchromatic image data; The azimuth element performs spatial forward intersection calculation and grid construction to obtain a regular grid; according to the target outer azimuth element and the regular grid, the hyperspectral image data is orthorectified to obtain the hyperspectral image corresponding to shooting images.
进一步地，上述处理器14，还用于对所述全色影像数据进行特征提取，得到所述全色影像数据对应的特征数据；基于所述特征数据对所述全色影像数据进行特征匹配，得到所述全色影像数据的同名点在所述全色影像数据中的匹配关系；基于所述匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素。Further, the above-mentioned processor 14 is further configured to perform feature extraction on the panchromatic image data to obtain feature data corresponding to the panchromatic image data; perform feature matching on the panchromatic image data based on the feature data, Obtain the matching relationship of the same-named point of the panchromatic image data in the panchromatic image data; The initial value of the point coordinate determines the target outer orientation element corresponding to the panchromatic image data.
进一步地，上述处理器14，还用于获取所述全色影像数据的初始外方位元素；根据所述初始外方位元素，计算所述全色影像之间的影像中心距 离；从所述影像中心距离中筛选出小于影像距离阈值的目标影像中心距离；计算所述目标影像中心距离之间的统计特征数据；基于所述统计特征数据，确定所述同名点在所述全色影像数据中的匹配关系。Further, the above-mentioned processor 14 is also used to acquire the initial outer orientation element of the panchromatic image data; calculate the image center distance between the panchromatic images according to the initial outer orientation element; Selecting the target image center distance smaller than the image distance threshold from the distance; calculating the statistical feature data between the target image center distances; based on the statistical feature data, determining the matching of the same name point in the panchromatic image data relation.
进一步地，上述处理器14，还用于根据预设插值间隔，确定所述高光谱影像的插值格网；并获取所述插值格网中每个格网点的第一像点坐标；根据所述目标外方位元素和所述规则格网，计算所述插值格网中每个格网点的第二像点坐标；基于所述第一像点坐标和所述第二像点坐标，对所述高光谱影像数据进行正摄校正，得到所述正摄影像。Further, the above-mentioned processor 14 is also configured to determine the interpolation grid of the hyperspectral image according to the preset interpolation interval; and obtain the first pixel coordinates of each grid point in the interpolation grid; according to the Calculate the second image point coordinates of each grid point in the interpolation grid based on the outer orientation element of the target and the regular grid; based on the first image point coordinates and the second image point coordinates, the height Orthophoto correction is performed on the spectral image data to obtain the orthophoto image.
进一步地，上述处理器14，还用于根据预设正摄影像比例尺参数，计算每个格网点对应待定地面点的X轴坐标和Y轴坐标；根据所述X轴坐标、所述Y轴坐标和所述规则格网，确定每个格网点对应待定地面点的Z轴坐标；根据所述目标外方位元素和所述Z轴坐标，计算所述插值格网中每个格网点的所述第二像点坐标。Further, the above-mentioned processor 14 is also used to calculate the X-axis coordinates and Y-axis coordinates of each grid point corresponding to the undetermined ground point according to the preset orthographic image scale parameters; according to the X-axis coordinates, the Y-axis coordinates and the regular grid, determine the Z-axis coordinates of each grid point corresponding to the undetermined ground point; according to the target outer orientation element and the Z-axis coordinates, calculate the first grid point of each grid point in the interpolation grid Two pixel coordinates.
进一步地，上述处理器14，还用于确定所述匹配关系对应的基础矩阵；基于所述基础矩阵，确定所述匹配关系中的误差匹配关系；从所述匹配关系中删除所述误差匹配关系，得到更新后的匹配关系；基于所述更新后的匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素。Further, the above-mentioned processor 14 is also configured to determine the basic matrix corresponding to the matching relationship; determine the error matching relationship in the matching relationship based on the basic matrix; delete the error matching relationship from the matching relationship , to obtain the updated matching relationship; based on the updated matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, determine the full The target outer orientation element corresponding to the color image data.
进一步地，上述处理器14，还用于获取所述高光谱影像对应的地面范围数据；根据所述地面范围数据和所述规则格网，构建内存规则格网；根据所述目标外方位元素和所述内存规则格网，计算所述插值格网中每个格网点的第二像点坐标。Further, the above-mentioned processor 14 is also used to obtain ground range data corresponding to the hyperspectral image; construct a memory regular grid according to the ground range data and the regular grid; The internal regular grid calculates the second image point coordinates of each grid point in the interpolation grid.
本申请实施例提供一种存储介质，其上存储有计算机程序，上述计算机可读存储介质存储有一个或者多个程序，上述一个或者多个程序可被一个或者多个处理器执行，应用于高光谱影像正射校正装置中，该计算机程序实现如上述的高光谱影像正射校正方法。An embodiment of the present application provides a storage medium on which a computer program is stored. The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors. In the spectral image orthorectification device, the computer program implements the above hyperspectral image orthorectification method.
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本公开的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、 磁碟、光盘)中，包括若干指令用以使得一台图像显示设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本公开各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present disclosure can be embodied in the form of a software product in essence or the part that contributes to the related technology, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk, etc.) ) includes several instructions to make an image display device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in various embodiments of the present disclosure.
以上所述，仅为本申请的较佳实施例而已，并非用于限定本申请的保护范围。The above descriptions are only preferred embodiments of the present application, and are not intended to limit the protection scope of the present application.

Claims (10)

  1. 一种高光谱影像正射校正方法，所述方法包括：A hyperspectral image orthorectification method, the method comprising:
    获取待校正的高光谱影像数据对应的全色影像数据；Obtain panchromatic image data corresponding to the hyperspectral image data to be corrected;
    通过对所述全色影像数据依次进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素；Obtaining target outer orientation elements corresponding to the panchromatic image data by sequentially performing feature extraction and feature matching on the panchromatic image data;
    对所述目标外方位元素进行空间前方交汇计算和格网构建，得到规则格网；Carrying out spatial forward intersection calculation and grid construction on the target outer orientation elements to obtain a regular grid;
    根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。Orthorectification is performed on the hyperspectral image data according to the outer orientation element of the target and the regular grid to obtain an orthoimage corresponding to the hyperspectral image.
  2. 根据权利要求1所述的方法，其中，所述通过对所述全色影像数据依次进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素，包括：The method according to claim 1, wherein said obtaining the target outer orientation element corresponding to the panchromatic image data by sequentially performing feature extraction and feature matching on the panchromatic image data includes:
    对所述全色影像数据进行特征提取，得到所述全色影像数据对应的特征数据；performing feature extraction on the panchromatic image data to obtain feature data corresponding to the panchromatic image data;
    基于所述特征数据对所述全色影像数据进行特征匹配，得到所述全色影像数据的同名点在所述全色影像数据中的匹配关系；performing feature matching on the panchromatic image data based on the feature data to obtain a matching relationship of the same-named points of the panchromatic image data in the panchromatic image data;
    基于所述匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素。Based on the matching relationship, the initial outer orientation element of the panchromatic image data, and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, the target outer orientation element corresponding to the panchromatic image data is determined.
  3. 根据权利要求2所述的方法，其中，所述基于所述特征数据对所述全色影像数据进行特征匹配，得到所述全色影像数据的同名点在所述全色影像数据中的匹配关系，包括：The method according to claim 2, wherein the feature matching is performed on the panchromatic image data based on the feature data to obtain the matching relationship of the same-named points of the panchromatic image data in the panchromatic image data ,include:
    获取所述全色影像数据的初始外方位元素；Acquiring the initial outer orientation element of the panchromatic image data;
    根据所述初始外方位元素，计算所述全色影像之间的影像中心距离；Calculate the image center distance between the panchromatic images according to the initial outer orientation element;
    从所述影像中心距离中筛选出小于影像距离阈值的目标影像中心距离；Selecting a target image center distance smaller than the image distance threshold from the image center distance;
    计算所述目标影像中心距离之间的统计特征数据；Calculating the statistical feature data between the center distances of the target images;
    基于所述统计特征数据，确定所述同名点在所述全色影像数据中的匹配关系。Based on the statistical characteristic data, a matching relationship of the same-named points in the panchromatic image data is determined.
  4. 根据权利要求1所述的方法，其中，所述根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像，包括：The method according to claim 1, wherein, performing orthorectification on the hyperspectral image data according to the target outer orientation element and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image, including :
    根据预设插值间隔，确定所述高光谱影像的插值格网；并获取所述插值格网中每个格网点的第一像点坐标；Determine the interpolation grid of the hyperspectral image according to a preset interpolation interval; and obtain the first pixel coordinates of each grid point in the interpolation grid;
    根据所述目标外方位元素和所述规则格网，计算所述插值格网中每个格网点的第二像点坐标；Calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the regular grid;
    基于所述第一像点坐标和所述第二像点坐标，对所述高光谱影像数据进行正摄校正，得到所述正摄影像。Based on the first image point coordinates and the second image point coordinates, performing orthophoto correction on the hyperspectral image data to obtain the orthophoto image.
  5. 根据权利要求4所述的方法，其中，所述根据所述目标外方位元素和所述规则格网，计算所述插值格网中每个格网点的第二像点坐标，包括：The method according to claim 4, wherein said calculating the second pixel coordinates of each grid point in said interpolation grid according to said target outer orientation element and said regular grid comprises:
    根据预设正摄影像比例尺参数，计算每个格网点对应待定地面点的X轴坐标和Y轴坐标；Calculate the X-axis coordinates and Y-axis coordinates of each grid point corresponding to the undetermined ground point according to the preset orthographic image scale parameters;
    根据所述X轴坐标、所述Y轴坐标和所述规则格网，确定每个格网点对应待定地面点的Z轴坐标；According to the X-axis coordinates, the Y-axis coordinates and the regular grid, determine the Z-axis coordinates of each grid point corresponding to the undetermined ground point;
    根据所述目标外方位元素和所述Z轴坐标，计算所述插值格网中每个格网点的所述第二像点坐标。Calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the Z-axis coordinates.
  6. 根据权利要求2所述的方法，其中，所述基于所述特征数据对所述全色影像数据进行特征匹配，得到所述全色影像数据的同名点在所述全色影像数据中的匹配关系之后，所述基于所述匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素之前，所述方法还包括：The method according to claim 2, wherein the feature matching is performed on the panchromatic image data based on the feature data to obtain the matching relationship of the same-named points of the panchromatic image data in the panchromatic image data Afterwards, based on the matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, determine the target outer surface corresponding to the panchromatic image data. Before the orientation element, the method also includes:
    确定所述匹配关系对应的基础矩阵；determining the fundamental matrix corresponding to the matching relationship;
    基于所述基础矩阵，确定所述匹配关系中的误差匹配关系；determining an error matching relationship in the matching relationship based on the fundamental matrix;
    从所述匹配关系中删除所述误差匹配关系，得到更新后的匹配关系；Deleting the error matching relationship from the matching relationship to obtain an updated matching relationship;
    相应的，所述基于所述匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素，包括：Correspondingly, the target corresponding to the panchromatic image data is determined based on the matching relationship, the initial outer orientation element of the panchromatic image data, and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data. Outer orientation elements, including:
    基于所述更新后的匹配关系、所述全色影像数据的初始外方位元素和所述全色影像数据对应的待定地面点坐标的初始值，确定出所述全色影像数据对应的目标外方位元素。Based on the updated matching relationship, the initial outer orientation element of the panchromatic image data and the initial value of the undetermined ground point coordinates corresponding to the panchromatic image data, determine the target outer orientation corresponding to the panchromatic image data element.
  7. 根据权利要求5所述的方法，其中，所述根据所述目标外方位元素和所述规则格网，计算所述插值格网中每个格网点的第二像点坐标，包括：The method according to claim 5, wherein said calculating the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the regular grid comprises:
    获取所述高光谱影像对应的地面范围数据；Obtain ground range data corresponding to the hyperspectral image;
    根据所述地面范围数据和所述规则格网，构建内存规则格网；Constructing a regular grid in memory according to the ground range data and the regular grid;
    根据所述目标外方位元素和所述内存规则格网，计算所述插值格网中每个格网点的第二像点坐标。Calculate the second image point coordinates of each grid point in the interpolation grid according to the target outer orientation element and the internal regular grid.
  8. 一种高光谱影像正射校正装置，所述装置包括：A hyperspectral image orthorectification device, said device comprising:
    获取单元，用于获取待校正的高光谱影像数据对应的全色影像数据；An acquisition unit, configured to acquire panchromatic image data corresponding to the hyperspectral image data to be corrected;
    特征提取和特征匹配单元，用于通过对所述全色影像数据进行特征提取和特征匹配，得到所述全色影像数据对应的目标外方位元素；The feature extraction and feature matching unit is used to obtain the target outer orientation element corresponding to the panchromatic image data by performing feature extraction and feature matching on the panchromatic image data;
    格网生成单元，用于对所述目标外方位元素进行空间前方交汇计算 和格网构建，得到规则格网；A grid generation unit is used to carry out space forward intersection calculation and grid construction to the target outer orientation element to obtain a regular grid;
    正摄校正单元，用于根据所述目标外方位元素和所述规则格网，对所述高光谱影像数据进行正射校正，得到高光谱影像对应的正射影像。The orthographic correction unit is configured to perform orthorectification on the hyperspectral image data according to the outer orientation elements of the target and the regular grid, to obtain an orthoimage corresponding to the hyperspectral image.
  9. 一种高光谱影像正射校正装置，所述装置包括：处理器、存储器及通信总线；所述处理器执行存储器存储的运行程序时实现如权利要求1-7任一项所述的方法。A hyperspectral image orthorectification device, the device comprising: a processor, a memory, and a communication bus; the processor implements the method according to any one of claims 1-7 when executing a running program stored in the memory.
  10. 一种存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如权利要求1-7任一项所述的方法。A storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1-7 is implemented.
PCT/CN2022/133512 2021-11-22 2022-11-22 Orthographic rectification method and apparatus for hyperspectral image, and storage medium WO2023088487A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111389002.0A CN116170569A (en) 2021-11-22 2021-11-22 Hyperspectral image forward shooting correction method and device and storage medium
CN202111389002.0 2021-11-22

Publications (1)

Publication Number Publication Date
WO2023088487A1 true WO2023088487A1 (en) 2023-05-25

Family

ID=86396305

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/133512 WO2023088487A1 (en) 2021-11-22 2022-11-22 Orthographic rectification method and apparatus for hyperspectral image, and storage medium

Country Status (2)

Country Link
CN (1) CN116170569A (en)
WO (1) WO2023088487A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117575970A (en) * 2024-01-15 2024-02-20 航天宏图信息技术股份有限公司 Classification-based satellite image automatic processing method, device, equipment and medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6757445B1 (en) * 2000-10-04 2004-06-29 Pixxures, Inc. Method and apparatus for producing digital orthophotos using sparse stereo configurations and external models
CN103823981A (en) * 2014-02-28 2014-05-28 武汉大学 DEM (Digital Elevation Model)-assisted satellite image block adjustment method
CN111003214A (en) * 2019-11-22 2020-04-14 武汉大学 Attitude and orbit refinement method for domestic land observation satellite based on cloud control
CN112393714A (en) * 2020-11-25 2021-02-23 国网安徽省电力有限公司电力科学研究院 Image correction method based on unmanned aerial vehicle aerial photography and satellite remote sensing fusion
CN113627357A (en) * 2021-08-13 2021-11-09 哈尔滨工业大学 High-spatial-high-spectral-resolution intrinsic decomposition method and system for remote sensing image

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6757445B1 (en) * 2000-10-04 2004-06-29 Pixxures, Inc. Method and apparatus for producing digital orthophotos using sparse stereo configurations and external models
CN103823981A (en) * 2014-02-28 2014-05-28 武汉大学 DEM (Digital Elevation Model)-assisted satellite image block adjustment method
CN111003214A (en) * 2019-11-22 2020-04-14 武汉大学 Attitude and orbit refinement method for domestic land observation satellite based on cloud control
CN112393714A (en) * 2020-11-25 2021-02-23 国网安徽省电力有限公司电力科学研究院 Image correction method based on unmanned aerial vehicle aerial photography and satellite remote sensing fusion
CN113627357A (en) * 2021-08-13 2021-11-09 哈尔滨工业大学 High-spatial-high-spectral-resolution intrinsic decomposition method and system for remote sensing image

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117575970A (en) * 2024-01-15 2024-02-20 航天宏图信息技术股份有限公司 Classification-based satellite image automatic processing method, device, equipment and medium
CN117575970B (en) * 2024-01-15 2024-04-16 航天宏图信息技术股份有限公司 Classification-based satellite image automatic processing method, device, equipment and medium

Also Published As

Publication number Publication date
CN116170569A (en) 2023-05-26

Similar Documents

Publication Publication Date Title
CN110443836B (en) Point cloud data automatic registration method and device based on plane features
CN109949399B (en) Scene three-dimensional reconstruction method based on unmanned aerial vehicle aerial image
WO2018127007A1 (en) Depth image acquisition method and system
WO2019042232A1 (en) Fast and robust multimodal remote sensing image matching method and system
US10553020B1 (en) Shadow mask generation using elevation data
CN105354841B (en) A kind of rapid remote sensing image matching method and system
CN108759788B (en) Unmanned aerial vehicle image positioning and attitude determining method and unmanned aerial vehicle
CN106887016B (en) Automatic relative registration method for GF-4 satellite sequence images
WO2023088487A1 (en) Orthographic rectification method and apparatus for hyperspectral image, and storage medium
CN111768337B (en) Image processing method and device and electronic equipment
CN115187798A (en) Multi-unmanned aerial vehicle high-precision matching positioning method
CN108230375A (en) Visible images and SAR image registration method based on structural similarity fast robust
CN112946679B (en) Unmanned aerial vehicle mapping jelly effect detection method and system based on artificial intelligence
Cao et al. Nonlinear bias compensation of ZiYuan-3 satellite imagery with cubic splines
Zhang et al. Lidar-guided stereo matching with a spatial consistency constraint
CN112767461A (en) Automatic registration method for laser point cloud and sequence panoramic image
CN114529681A (en) Hand-held double-camera building temperature field three-dimensional model construction method and system
CN114519681A (en) Automatic calibration method and device, computer readable storage medium and terminal
CN111126418A (en) Oblique image matching method based on planar perspective projection
CN116977671A (en) Target tracking method, device, equipment and storage medium based on image space positioning
Hu et al. Planetary3D: A photogrammetric tool for 3D topographic mapping of planetary bodies
JP6761388B2 (en) Estimator and program
Qin et al. A coarse elevation map-based registration method for super-resolution of three-line scanner images
CN114529682A (en) Method and system for constructing true three-dimensional temperature field of heat-carrying infrared image building
CN107705267B (en) Optical satellite image geometric correction method based on control vector

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22895016

Country of ref document: EP

Kind code of ref document: A1