Relative radiation correction coefficient updating method, correction method, system and device

Abstract

The present invention provides an updating method, a correction method, a system and a device for a relative radiation correction coefficient, and relates to the field of satellite remote sensing technology. The updating method comprises: classifying and labeling a hyperspectral remote sensing image to obtain a classified image; performing quality analysis on the classified image corrected based on an original relative radiation correction coefficient to obtain a first quality analysis result; in response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, determining an image of a target category from the classified image, and determining an updated relative radiation correction coefficient based on the image of the target category; re-performing quality analysis on the hyperspectral remote sensing image whose first quality analysis result does not satisfy the preset condition based on the updated relative radiation correction coefficient to obtain a second quality analysis result; in response to the second quality analysis result satisfying the preset condition, storing the updated relative radiation correction coefficient in a database.

Description

Technical Field

[0001] The present invention relates to the field of satellite remote sensing technology, and in particular to an updating method, a correction method, a system and a device for a relative radiation correction coefficient of a hyperspectral payload. Background Art

[0002] At present, the optimization and improvement of the radiation quality of hyperspectral payload data is a research hotspot that has received continuous and extensive attention. Carrying out continuous relative radiation correction for hyperspectral payload images is an extremely important way to improve image quality. Relative radiation calibration in remote sensing satellite processing systems currently mostly uses calibration methods, that is, directly extracting correction coefficients from images through analysis and statistics to correct images. Due to the need to accumulate images, the correction effect cannot be guaranteed during this period, and the timeliness is very low. At the same time, due to the uncertainty of the timing of initiating radiation correction and the lack of continuous monitoring of the data quality produced by the daily operation system, it cannot meet the current multi-spectral and refined relative radiation calibration needs of hyperspectral cameras. Summary of the invention

[0003] In view of this, the present invention provides an updating method, a correction method, a system and a device for a relative radiation correction coefficient for a hyperspectral load, which are used to at least partially solve the above technical problems.

[0004] One aspect of the present invention provides a method for updating relative radiation correction coefficients for hyperspectral payloads, comprising: classifying and labeling hyperspectral remote sensing images to obtain classified images; performing quality analysis on the classified images corrected based on the original relative radiation correction coefficients to obtain a first quality analysis result; in response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, determining images of a target category from the classified images, and determining an updated relative radiation correction coefficient based on the images of the target category; re-performing quality analysis on the hyperspectral remote sensing images whose first quality analysis results do not satisfy the preset conditions based on the updated relative radiation correction coefficients to obtain a second quality analysis result; in response to the second quality analysis result satisfying the preset condition, storing the updated relative radiation correction coefficients in a database.

[0005] According to an embodiment of the present invention, image classification and labeling of a hyperspectral remote sensing image includes: in a satellite system cataloging process, classifying and labeling the objects in the hyperspectral remote sensing image according to relative radiation calibration requirements to obtain a classified image.

[0006] According to an embodiment of the present invention, quality analysis is performed on a classified image corrected based on an original radiation correction coefficient, including: calculating a value of at least one quality evaluation parameter of the classified image; determining a first quality analysis result based on the value of at least one quality evaluation parameter; wherein the quality evaluation parameter is configured based on image features of the classified image.

[0007] According to an embodiment of the present invention, at least one quality evaluation parameter includes at least one of the image's radiation mean, variance, signal-to-noise ratio, clarity, image power spectrum, gain adjustment distortion, information entropy, detail energy, edge energy, contrast, radiation resolution, and equivalent visual number; wherein the radiation mean is used to characterize the average brightness value of the entire image; the variance is used to characterize the average square difference of the difference between the brightness values ​​of all pixels and the brightness average value; the signal-to-noise ratio characterizes the ratio of the strength of the useful signal to the noise signal in the image; the detail energy is used to characterize the detail and edge shape features of the image described from the perspective of the high-frequency components of the image frequency domain, and the edge energy is used to characterize the shape information of the image.

[0008] According to an embodiment of the present invention, an image of a target category is determined from the classified images, and an updated relative radiation correction coefficient is determined based on the image of the target category, including: performing dark current noise removal on the image of the target category and radiation calibration on the target object image to generate an updated relative radiation correction coefficient.

[0009] According to an embodiment of the present invention, the method also includes: in response to the second quality analysis result not satisfying the preset condition, based on a new hyperspectral remote sensing image taken by the hyperspectral camera, repeatedly performing image classification and labeling on the hyperspectral remote sensing image to obtain the classified image, and determining the updated relative radiation correction coefficient based on the image of the target category, until the second quality analysis result satisfies the preset condition.

[0010] Another aspect of the present invention provides a relative radiation correction method for hyperspectral payloads, including: obtaining the relative radiation correction coefficient of the hyperspectral remote sensing image closest to the imaging time; performing radiation correction on the hyperspectral remote sensing image based on the relative radiation correction coefficient, wherein the relative radiation correction coefficient is updated using the above-mentioned method for updating the relative radiation correction coefficient for hyperspectral payloads.

[0011] Another aspect of the present invention provides an updating system for relative radiation correction coefficients of hyperspectral payloads, comprising: an image classification subsystem, configured to perform image classification and annotation on hyperspectral remote sensing images to obtain classified images; a quality analysis subsystem, configured to perform quality analysis on the classified images corrected based on the original relative radiation correction coefficients to obtain a first quality analysis result; a radiation analysis subsystem, configured to determine images of target categories from the classified images in response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, and determine an updated relative radiation correction coefficient based on the image of the target category; the quality analysis subsystem is further configured to re-perform quality analysis on the hyperspectral remote sensing images whose first quality analysis results do not satisfy the preset conditions based on the updated relative radiation correction coefficients to obtain a second quality analysis result; and a radiation coefficient management subsystem, configured to store the updated relative radiation correction coefficients in a database in response to the second quality analysis result satisfying the preset conditions.

[0012] Another aspect of the present invention provides a relative radiation correction system for hyperspectral payloads, including: a radiation correction subsystem, configured to obtain the relative radiation correction coefficient of the hyperspectral remote sensing image as close to the imaging time as possible; and perform radiation correction on the hyperspectral remote sensing image based on the relative radiation correction coefficient, wherein the relative radiation correction coefficient is updated using the above-mentioned update system for the relative radiation correction coefficient for hyperspectral payloads.

[0013] Another aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps according to the above method.

[0014] The updating method, correction method, system and device of the relative radiation correction coefficient for hyperspectral load according to the embodiments of the present invention have at least the following beneficial effects:

[0015] The satellite system classifies data during the daily cataloging of hyperspectral payload image data, and selects high-quality image data for continuous data quality evaluation and storage. The relative radiation coefficient automatic update process is triggered by comparing the evaluation results with the quality standards, and the relative radiation coefficient is calculated and updated. The calculation and update can also be performed through scheduled tasks, which solves the problem that the relative radiation of the hyperspectral payload changes frequently and the ground processing process cannot adapt to the radiation changes, resulting in poor radiation effects. The hyperspectral data has been automated from cataloging image classification, image quality analysis, radiation analysis, test confirmation, automatic update, and intelligent matching. The automatic update of the relative radiation correction coefficient is formed with a fast update frequency, which improves the processing efficiency of the satellite processing system.

[0016] During the calculation process, dark current noise removal and target object image radiation calibration are performed successively to complete the calculation of relative radiation calibration coefficients. Image quality evaluation is performed on the calculated relative radiation coefficient. If it meets the standard or is better than the historical radiation coefficient processing result, the coefficient update management is performed, otherwise the data is waited for subsequent optimization. Subsequent image legends use time matching to select the latest relative radiation correction coefficient before the imaging time for radiation correction to improve the data dynamic range and data imaging quality.

[0017] The entire satellite system uses an automated process to update the relative radiation coefficient without human intervention, greatly improving the system's automated operation and maintenance capabilities while ensuring that the image relative radiation correction accuracy is at the optimal state. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0019] Figure 1 The overall flow chart of the method for updating the relative radiation correction coefficient for the hyperspectral load according to the embodiment of the present invention is schematically shown;

[0020] Figure 2 Schematically showing a flow chart of a method for updating a relative radiation correction coefficient for a hyperspectral load according to another embodiment of the present invention;

[0021] Figure 3 A flowchart of relative radiation correction coefficient calculation according to an embodiment of the present invention is schematically shown;

[0022] Figure 4 A schematic diagram showing a composition diagram of a system for updating relative radiation correction coefficients for hyperspectral loads according to an embodiment of the present invention;

[0023] Figure 5 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0024] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0025] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0026] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0027] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0028] In the process of realizing the present disclosure, the applicant found that after the hyperspectral camera is in orbit, the dark current and other sensor parameters of the camera will change due to factors such as solar radiation and operating temperature changes. Therefore, the relative radiation of the hyperspectral payload changes quickly, and the ground processing process cannot adapt to the radiation changes, resulting in a problem of poor radiation effect. In addition, the current satellite processing system uses image accumulation and regular processing and updating to calibrate the relative radiation parameters. It is necessary to manually process the received valid image data to complete the calculation of the relative radiation coefficient, which has low time efficiency, poor data timeliness, and poor radiation quality of some images.

[0029] In view of this, the embodiments of the present disclosure provide an update method, correction method, system and device for relative radiation correction coefficients for hyperspectral payloads. The method is based on the relative radiation correction coefficient processing logic. First, in the daily cataloging process of the satellite processing system, the image classification and labeling of the data product is completed, and the image quality analysis is performed. When the image data quality analysis does not meet the requirements, the relative radiation analysis is performed based on the classified images and dark current data within a certain period of time to obtain the latest relative radiation correction coefficient, and the radiation coefficient is automatically updated. The image that does not meet the radiation analysis requirements is re-analyzed. If it meets the requirements, the relative radiation correction coefficient is set to be available for subsequent image processing. In addition, the system can also periodically update the relative radiation coefficient correction. When the update time is reached, a new relative radiation correction coefficient is automatically calculated and compared with the image quality evaluation result of the old radiation coefficient. If the evaluation analysis result is better than the old radiation coefficient, the new relative radiation correction coefficient is set to be available. In the selection of relative radiation correction coefficients, the time forward method is selected, and the relative radiation correction coefficient closest to the image imaging time is selected for product processing. This method solves the problem of rapid changes in relative radiation resulting in poor radiation effects during the processing process, while removing dark current noise, greatly improving the accuracy of image relative radiation correction. At the same time, this system uses an automated process to calculate and test the relative radiation correction coefficient based on changes in image quality and complete automatic updates.

[0030] The following is a detailed description with reference to specific embodiments.

[0031] Figure 1 The overall flow chart of the method for updating the relative radiation correction coefficient for hyperspectral load according to an embodiment of the present invention is schematically shown.

[0032] like Figure 1 As shown, the method for updating the relative radiation correction coefficient for the hyperspectral load may include operations S110 to S150.

[0033] In operation S110 , image classification and annotation are performed on the hyperspectral remote sensing image to obtain a classified image.

[0034] In operation S120, quality analysis is performed on the classified image corrected based on the original relative radiation correction coefficient to obtain a first quality analysis result.

[0035] In operation S130, in response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, an image of a target category is determined from the classified images, and an updated relative radiation correction coefficient is determined based on the image of the target category.

[0036] In operation S140, quality analysis is performed again on the hyperspectral remote sensing image whose first quality analysis result does not meet the preset condition based on the updated relative radiation correction coefficient to obtain a second quality analysis result.

[0037] In operation S150, in response to the second mass analysis result satisfying a preset condition, the updated relative radiation correction coefficient is stored in a library.

[0038] In the embodiments of the present disclosure, the first quality analysis result and the second quality analysis result can be used to characterize the image quality level division, and the preset condition can be understood as the image quality requirement standard. The image quality level division is compared with the image quality requirement standard to determine whether the first quality analysis result or the second quality analysis result meets the preset condition.

[0039] In the embodiment of the present disclosure, the fact that the update time is greater than the preset time threshold can be understood as a timed update mode being preset, and updates are performed at certain time intervals.

[0040] Figure 2 The flowchart of a method for updating relative radiation correction coefficients for hyperspectral loads according to another embodiment of the present invention is schematically shown.

[0041] like Figure 2 As shown, based on the above embodiment, the hyperspectral remote sensing image is classified and labeled, including: in the cataloging process of the satellite system, the hyperspectral remote sensing image is classified and labeled according to the relative radiation calibration requirements to obtain a classified image.

[0042] For example, the classification method of hyperspectral catalog image data can be: according to the land classification data, the area used for statistical relative radiation quality data can be marked as a data set to be stored in the database, and the data level will be used for subsequent image classification. In daily tasks, the coordinate position of the catalog data is extracted and the data set image is automatically classified, that is, the image can be classified and marked according to the features such as deserts, water bodies, mountains, villages, and cities, and the classification and labeling of the catalog image can be completed. In addition, by processing the image data as dark current data, the DN value response (i.e., dark current level) of the satellite payload in a state close to 0 input can be obtained for subsequent removal of dark current noise.

[0043] In an embodiment of the present disclosure, a method for performing radiation correction quality analysis and evaluation on classified hyperspectral images may be as follows: high-quality classified images may be selected for image quality analysis according to the type of land object, cloud cover, and regional location.

[0044] In one possible implementation, quality analysis is performed on a classified image that has been corrected based on an original radiation correction coefficient, including: calculating a value of at least one quality evaluation parameter of the classified image; determining a first quality analysis result based on the value of at least one quality evaluation parameter; wherein the quality evaluation parameter is configured based on image features of the classified image.

[0045] Furthermore, quality evaluation parameters configured based on image features include, but are not limited to, image radiation mean, variance, signal-to-noise ratio, clarity, image power spectrum, gain adjustment distortion, information entropy, detail energy, edge energy, contrast, radiation resolution, equivalent visual number, etc. During the quality evaluation process, one or more combinations thereof may be selected for quality evaluation.

[0046] In some possible implementations, some main quality evaluation parameters may be determined in the following manner:

[0047] Radiation mean M: It is used to characterize the average brightness of the entire image. The specific calculation method can be:

[0048]

[0049] Where S is the image area, is the gray value corresponding to the position (x, y).

[0050] Variance Yar: It is used to characterize the average square difference between the brightness values ​​of all pixels and the average brightness value:

[0051]

[0052] in, is the weight corresponding to the point, where the weight is equal .

[0053] Signal-to-noise ratio (SNR): It is used to characterize the ratio of the useful signal to the noise signal strength in an image, and is calculated using the local mean and local standard deviation.

[0054]

[0055] Where M is the mean radiation value, is the local standard deviation of the image, is the sum of the local standard deviations that satisfy the maximum majority condition, and max(n) is the number of local standard deviations that satisfy the maximum majority condition.

[0056] Detail Energy: Describes the details and edge shape features of an image from the perspective of the high-frequency components of the image frequency domain. Detail energy evaluates the quality of an image from a local perspective.

[0057]

[0058] in Regional variance, expressed as

[0059]

[0060] represents the average gray value of the region.

[0061]

[0062] Detail energy is the average value of the sum of variances of all (2M+1)×(2M+1) regions in the image, reflecting the richness of detail information in the image. The larger the value, the finer the texture of the image, the richer the information provided, and the clearer the image. Where mean is the image mean.

[0063] Edge energy: It is important information about the shape features of the image. The edge is the high-frequency information of the image, but unlike the noise signal, it has directionality and can be extracted through anisotropic filters. Use two normalized edge operators E1 and E2 of 45 degrees and 135 degrees to perform convolution calculations on the image to eliminate the block effect. After adding them, the edge e(x, y) of the image is obtained, that is:

[0064]

[0065]

[0066] The edge energy is defined as

[0067]

[0068] The edge energy of an image describes the richness and clarity of the edges in the image. The larger the edge energy value, the higher the image quality. Mean is the image mean.

[0069] On the basis of the above embodiment, an image of the target category is determined from the classified images, and an updated relative radiation correction coefficient is determined based on the image of the target category, including: performing dark current noise removal on the image of the target category and radiation calibration of the target object image to generate an updated relative radiation correction coefficient.

[0070] Figure 3 The figure schematically shows a relative radiation correction coefficient calculation flow chart according to an embodiment of the present invention.

[0071] like Figure 3As shown in the figure, the relative radiation correction coefficient calculation can be divided into two modes: automatic analysis and update and timed update. Automatic analysis and update means that when the overall image quality decreases during the quality analysis process, the image with the best quality classification within the time period from the last radiation coefficient update to the present is selected for radiation analysis and calculation. The timed update mode means that at a certain time interval, the image quality effect is selected for relative radiation coefficient calculation.

[0072] The processing flow of the two modes is roughly the same. Both modes first obtain the most recent dark current data, remove dark current noise, improve the dynamic range of the camera and thus improve image quality, and then select the high-quality classified images that have been annotated within the time period to calculate and generate the latest relative radiation correction coefficient. After the relative radiation coefficient calculation is completed, the automatic analysis and update mode re-analyzes the quality of data that does not meet the image quality standard, and the scheduled update mode re-analyzes the quality of data with poor recent radiation effects.

[0073] Furthermore, the method further includes: in response to the second quality analysis result not meeting the preset condition, based on the new hyperspectral remote sensing image taken by the hyperspectral camera, repeatedly performing image classification and labeling on the hyperspectral remote sensing image to obtain the classified image, and determining the updated relative radiation correction coefficient based on the image of the target category, until the second quality analysis result meets the preset condition. That is, if the data that does not meet the image quality standard still does not meet the standard after re-quality analysis, the cataloged data is waited for to recalculate the relative radiation correction coefficient.

[0074] Furthermore, after the evaluation results meet the standards and the image quality is improved, the radiation coefficient is stored in the warehouse for use in subsequent products.

[0075] Based on this, an embodiment of the present invention also provides a relative radiation correction method for hyperspectral payloads, including: obtaining the relative radiation correction coefficient of the hyperspectral remote sensing image closest to the imaging time; performing radiation correction on the hyperspectral remote sensing image based on the relative radiation correction coefficient, wherein the relative radiation correction coefficient is updated using the above-mentioned method for updating the relative radiation correction coefficient for hyperspectral payloads.

[0076] The latest relative radiation correction coefficients that meet the standard requirements are stored in the warehouse. Based on this correction method, the time-forward method is adopted to select the relative radiation correction coefficient closest to the image imaging time to perform product radiation correction processing to improve image quality.

[0077] The updating method and correction method provided by the embodiments of the present invention can realize the automated processing flow of hyperspectral data from catalog image classification, image quality analysis, radiation analysis, test confirmation, automatic updating, and intelligent matching, forming an automated system for calculating and updating relative radiation correction coefficients, improving the processing efficiency of the satellite processing system, and optimizing the overall accuracy of hyperspectral image radiation correction.

[0078] Based on the above-mentioned method for updating relative radiation correction coefficients for hyperspectral loads, an embodiment of the present invention further provides a system for updating relative radiation correction coefficients for hyperspectral loads.

[0079] Figure 4 The component diagram of the system for updating the relative radiation correction coefficient for hyperspectral load according to an embodiment of the present invention is schematically shown.

[0080] like Figure 4 As shown, the update system for relative radiation correction coefficients of hyperspectral payloads includes four subsystems: image classification subsystem, quality analysis subsystem, radiation analysis subsystem, and radiation coefficient management subsystem.

[0081] The image classification subsystem is configured to classify and annotate the hyperspectral remote sensing image to obtain a classified image.

[0082] The mass analysis subsystem is configured to perform a mass analysis on the classified image corrected based on the original relative radiation correction coefficient to obtain a first mass analysis result.

[0083] The radiation analysis subsystem is configured to determine an image of the target category from the classified images in response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, and determine an updated relative radiation correction coefficient based on the image of the target category.

[0084] The mass analysis subsystem is further configured to re-perform mass analysis on the hyperspectral remote sensing image whose first mass analysis result does not meet the preset conditions based on the updated relative radiation correction coefficient to obtain a second mass analysis result.

[0085] The radiation coefficient management subsystem is configured to store the updated relative radiation correction coefficient in the database in response to the second mass analysis result satisfying a preset condition.

[0086] Based on the above-mentioned system and method for updating relative radiation correction coefficients for hyperspectral payloads, an embodiment of the present disclosure further provides a relative radiation correction system for hyperspectral payloads, including: a radiation correction subsystem configured to obtain the relative radiation correction coefficient of the hyperspectral remote sensing image closest to the imaging time; performing radiation correction on the hyperspectral remote sensing image based on the relative radiation correction coefficient, wherein the relative radiation correction coefficient adopts Figure 4 The updating system for the relative radiation correction coefficients for the hyperspectral loading is shown.

[0087] It should be noted that the updating system for relative radiation correction coefficients for hyperspectral loads and the relative radiation correction system for hyperspectral loads provided in the embodiments of the present invention are the same or similar to the specific implementation details and technical effects brought about by the corresponding updating method for relative radiation correction coefficients for hyperspectral loads and the relative radiation correction method for hyperspectral loads, which will not be repeated here.

[0088] Figure 5 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present invention is schematically shown. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0089] like Figure 5 As shown, the electronic device 500 according to an embodiment of the present invention includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 to a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include an onboard memory configured for cache purposes. The processor 501 may include a single processing unit or multiple processing units configured to perform different actions of the method flow according to an embodiment of the present invention.

[0090] In RAM 503, various programs and data required for the operation of electronic device 500 are stored. Processor 501, ROM 502 and RAM 503 are connected to each other via bus 504. Processor 501 performs various operations of the method flow according to the embodiment of the present invention by executing the program in ROM 502 and / or RAM 503. It should be noted that the program can also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 can also perform various operations of the method flow according to the embodiment of the present invention by executing the program stored in the one or more memories.

[0091] According to an embodiment of the present invention, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to the bus 504. The electronic device 500 may further include one or more of the following components connected to the input / output (I / O) interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that the computer program read therefrom is installed into the storage portion 508 as needed.

[0092] According to an embodiment of the present invention, the method flow according to an embodiment of the present invention can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code configured to execute the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the processor 501, the above-mentioned functions defined in the system of the embodiment of the present invention are executed. According to an embodiment of the present invention, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0093] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0094] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0095] For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 502 and / or the RAM 503 described above and / or one or more memories other than the ROM 502 and the RAM 503 .

[0096] An embodiment of the present invention also includes a computer program product, which includes a computer program, which contains program code configured to execute the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program code is configured to enable the electronic device to implement the training method and prediction method provided by the embodiment of the present invention.

[0097] When the computer program is executed by the processor 501, the above functions defined in the system / device of the embodiment of the present invention are executed. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0098] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 509, and / or installed from the removable medium 511. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0099] According to an embodiment of the present invention, the program code configured to execute the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions configured to implement the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It will be understood by those skilled in the art that the features recorded in the various embodiments of the present invention can be combined and / or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features recorded in the various embodiments of the present invention can be combined and / or combined in various ways. All these combinations and / or combinations fall within the scope of the present invention.

[0101] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for updating relative radiation correction coefficients for hyperspectral loads, characterized in that: include: Perform image classification and annotation on the hyperspectral remote sensing image to obtain the classified image; Performing quality analysis on the classified image corrected based on the original relative radiation correction coefficient to obtain a first quality analysis result; In response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, determining an image of a target category from the classified images, performing dark current noise removal and target ground object image radiation calibration on the image of the target category, and generating an updated relative radiation correction coefficient; Re-performing a quality analysis on the hyperspectral remote sensing image whose first quality analysis result does not meet the preset conditions based on the updated relative radiation correction coefficient to obtain a second quality analysis result; In response to the second mass analysis result satisfying a preset condition, the updated relative radiation correction coefficient is stored in a database.

2. The updating method according to claim 1, characterized in that: The image classification and annotation of the hyperspectral remote sensing image includes: In the cataloguing process of the satellite system, the hyperspectral remote sensing image is used to classify and label the ground objects according to the relative radiometric calibration requirements to obtain a classified image.

3. The updating method according to claim 1, characterized in that: The quality analysis of the classified image corrected based on the original radiation correction coefficient comprises: Calculating a value of at least one quality assessment parameter of the classified image; determining the first quality analysis result based on the value of the at least one quality assessment parameter; Wherein, the quality evaluation parameter is configured based on the image features of the classified image.

4. The updating method according to claim 3, characterized in that: The at least one quality evaluation parameter includes at least one of the image's radiation mean, variance, signal-to-noise ratio, clarity, image power spectrum, gain adjustment distortion, information entropy, detail energy, edge energy, contrast, radiation resolution, and equivalent visual number; wherein the radiation mean is used to characterize the average brightness of the entire image; the variance is used to characterize the average square difference of the difference between the brightness values ​​of all pixels and the brightness average; the signal-to-noise ratio characterizes the ratio of the intensity of the useful signal to the noise signal in the image; the detail energy is used to characterize the detail and edge shape features of the image described from the perspective of the high-frequency components of the image frequency domain, and the edge energy is used to characterize the shape information of the image.

5. The updating method according to claim 1, characterized in that: The method further comprises: In response to the second quality analysis result not satisfying the preset conditions, the image classification and labeling of the hyperspectral remote sensing image is repeated based on a new hyperspectral remote sensing image taken by the hyperspectral camera to obtain the classified image, and the operation of determining the updated relative radiation correction coefficient based on the image of the target category is repeated until the second quality analysis result satisfies the preset conditions.

6. A relative radiation correction method for hyperspectral payloads, characterized in that: include: Obtain the relative radiation correction coefficient of the hyperspectral remote sensing image as recently as the imaging time; The hyperspectral remote sensing image is subjected to radiation correction based on the relative radiation correction coefficient, wherein the relative radiation correction coefficient is updated using the method for updating the relative radiation correction coefficient for hyperspectral loads as described in any one of claims 1 to 5.

7. A system for updating relative radiation correction coefficients for hyperspectral loads, characterized in that: include: An image classification subsystem is configured to classify and annotate the hyperspectral remote sensing image to obtain a classified image; A quality analysis subsystem is configured to perform quality analysis on the classified image corrected based on the original relative radiation correction coefficient to obtain a first quality analysis result; The radiation analysis subsystem is configured to, in response to the first quality analysis result not satisfying a preset condition or the original radiation correction coefficient being updated for a time greater than a preset time threshold, determine an image of a target category from the classified images, perform dark current noise removal and target ground object image radiation calibration on the image of the target category, and generate an updated relative radiation correction coefficient; The mass analysis subsystem is further configured to re-perform mass analysis on the hyperspectral remote sensing image whose first mass analysis result does not meet the preset conditions based on the updated relative radiation correction coefficient to obtain a second mass analysis result; The radiation coefficient management subsystem is configured to store the updated relative radiation correction coefficient in a database in response to the second mass analysis result satisfying a preset condition.

8. A relative radiation correction system for hyperspectral payloads, characterized in that: include: A radiation correction subsystem is configured to obtain a relative radiation correction coefficient of the hyperspectral remote sensing image closest to the imaging time; The hyperspectral remote sensing image is subjected to radiation correction based on the relative radiation correction coefficient, wherein the relative radiation correction coefficient is updated using the update system for relative radiation correction coefficient for hyperspectral loads as described in claim 7.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more computer programs, The one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6.

Images