Infrared image stripe correction method and device, electronic equipment and storage medium

Abstract

The invention relates to an infrared image stripe correction method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-corrected image; performing edge detection on the to-be-corrected image to obtain an edge part and a non-edge part of the to-be-corrected image; respectively calculating updated error values of the edge part and the non-edge part according to different error calculation rules; updating a preset stripe correction model based on a least mean square algorithm and the update error value to obtain a target stripe correction model; and processing the to-be-corrected image according to the target stripe correction model to obtain a target image. The correction algorithm provided by the invention is low in complexity and good in real-time performance, does not need to cache multiple rows of data, and is more favorable for being realized through hardware. According to the method, the edge part and the non-edge part of the image are divided, so that the edge structure of the image can be fully protected, and the transverse and vertical stripes of the infrared image can be corrected more quickly and accurately.

Description

Technical Field

[0001] The present invention relates to the field of infrared monitoring technology, and in particular to an infrared image stripe correction method, device, electronic equipment and storage medium. Background Art

[0002] Infrared detectors generally share one amplifier in a row or a column. However, due to the non-uniformity of the response of the detection elements in the focal plane array, horizontal or vertical stripe noise often appears in the infrared images collected by the infrared detector, resulting in poor imaging quality of the infrared system. The traditional two-point non-uniformity correction method cannot completely eliminate these stripe noises. Summary of the invention

[0003] In order to solve the above technical problems, the embodiments of the present application provide an infrared image stripe correction method, device and image processing system that can completely eliminate horizontal stripes and vertical stripes in infrared images. The specific scheme is as follows: In a first aspect, an embodiment of the present application provides an infrared image fringe correction method, comprising: Acquire an image to be corrected; Performing edge detection on the image to be corrected to obtain an edge portion and a non-edge portion of the image to be corrected; Calculate the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; The preset fringe correction model is updated based on the least mean square algorithm and the updated error value to obtain a target fringe correction model; The image to be corrected is processed according to the target fringe correction model to obtain a target image.

[0004] According to a specific implementation of the embodiment of the present application, the preset fringe correction model includes a correction gain value and a bias coefficient; the updating of the preset fringe correction model based on the least mean square algorithm and the updated error value includes: The correction gain value and the bias coefficient are updated based on a least mean square algorithm and the updated error value.

[0005] According to a specific implementation of the embodiment of the present application, performing edge detection on the image to be corrected to obtain the edge part and the non-edge part of the image to be corrected includes: Traversing the pixel points of the image to be corrected based on a window of preset specifications; When the absolute value of the difference between the grayscale value of any target pixel in the window and the grayscale value of the central pixel of the window is greater than or equal to a preset difference threshold, the target pixel is determined to be an edge pixel; All edge pixel points are determined as the edge part, and non-edge pixel points are determined as the non-edge part.

[0006] According to a specific implementation of the embodiment of the present application, the method further includes: The preset difference threshold is determined according to the distribution of the absolute value of the horizontal gradient of the image to be corrected.

[0007] According to a specific implementation of the embodiment of the present application, determining the preset difference threshold according to the distribution of the absolute value of the horizontal gradient of the image to be corrected includes: The horizontal gradient absolute value whose number of pixel points is greater than a preset number threshold is selected as the preset difference threshold.

[0008] According to a specific implementation of the embodiment of the present application, respectively calculating the updated error values ​​of the edge part and the non-edge part according to different error calculation rules includes: Calculating the expected value and the predicted value respectively according to the pixel value of each pixel point of the image to be corrected; Calculate an updated error value of the edge portion according to the pixel value and the predicted value; An updated error value of the non-edge portion is calculated according to the expected value and the predicted value.

[0009] According to a specific implementation of the embodiment of the present application, the calculating of the expected value and the predicted value according to the pixel value of each pixel point of the image to be corrected includes: Processing the pixel value with a one-dimensional horizontal mean filter to obtain the expected value; The pixel value is processed using the correction gain value and the bias coefficient corresponding to the pixel point located in the previous row of the current pixel point to obtain the predicted value.

[0010] In a second aspect, an embodiment of the present application provides an infrared image fringe correction device, comprising: An image acquisition module, used for acquiring an image to be corrected; An edge detection module is used to perform edge detection on the image to be corrected to obtain an edge portion and a non-edge portion of the image to be corrected; An error calculation module, used to calculate the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; A model updating module, used for updating a preset fringe correction model based on a least mean square algorithm and the updated error value to obtain a target fringe correction model; The model processing module is used to process the image to be corrected according to the target fringe correction model to obtain a target image.

[0011] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the infrared image fringe correction method described in the first aspect.

[0012] In a fourth aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the infrared image fringe correction method described in the first aspect.

[0013] In summary, the present embodiment provides a method, device, electronic device and storage medium for infrared image stripe correction, including: acquiring an image to be corrected; performing edge detection on the image to be corrected to obtain the edge part and the non-edge part of the image to be corrected; calculating the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; updating the preset stripe correction model based on the minimum mean square algorithm and the updated error value to obtain the target stripe correction model; processing the image to be corrected according to the target stripe correction model to obtain the target image. The correction algorithm provided by the present invention has low complexity and good real-time performance, does not need to cache multiple lines of data, and is more conducive to hardware implementation. Moreover, by dividing the edge part and the non-edge part of the image, the present invention can fully protect the edge structure of the image, and can more quickly and accurately complete the correction processing of the horizontal and vertical stripes of the infrared image. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A schematic diagram of a flow chart of an infrared image fringe correction method provided in an embodiment of the present application; Figure 2 A schematic diagram of the steps for obtaining the edge portion and the non-edge portion of the image to be corrected provided in an embodiment of the present application; Figure 3 A schematic diagram of the effect of calculating and updating the error value provided in an embodiment of the present application; Figure 4 A schematic diagram of the steps for calculating the predicted value provided in the embodiment of the present application; Figure 5 A schematic diagram of a device module of an infrared image fringe correction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0017] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0018] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0019] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0020] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, one skilled in the art will appreciate that aspects may be practiced without these specific details.

[0021] refer to Figure 1 The present invention provides an infrared image fringe correction method, comprising the following steps: S101, obtaining an image to be corrected.

[0022] In this embodiment, the infrared image fringe correction method performs fringe correction processing on the infrared image collected by the infrared detector based on a preset fringe correction model. The expression of the preset fringe correction model is: in, To correct the gain value, is the bias coefficient, is the pixel value.

[0023] In this embodiment, the image to be corrected is an infrared image collected by an infrared detector. The infrared detector may be an infrared camera, an infrared sensor, or other infrared signal acquisition equipment and circuits. This embodiment does not specifically limit the method for acquiring the image to be corrected. The scene for acquiring the image to be corrected may be an infrared image collected in real time by the infrared detector, or an infrared image called from a memory. The method for acquiring the image to be corrected may be determined according to the needs of the actual application scenario.

[0024] S102, performing edge detection on the image to be corrected to obtain edge parts and non-edge parts of the image to be corrected.

[0025] In this embodiment, edge detection is performed on the image to be corrected according to a preset edge detection algorithm, wherein the preset edge detection algorithm may be a sliding window detection method or other operator detection method, and the setting of the preset edge detection algorithm may be adaptively configured according to the needs of the actual application scenario.

[0026] In this embodiment, during the infrared image fringe correction process, different error calculation rules are used to update the error values ​​for the edge portion and non-edge portion of the image to be corrected, which can enhance the protection of the edge portion of the image to be corrected.

[0027] S103, respectively calculating updated error values ​​of the edge part and the non-edge part according to different error calculation rules.

[0028] In this embodiment, the minimum error value of the infrared image is calculated based on the steepest descent method, and then the preset fringe correction model is updated according to the minimum error value.

[0029] The Steepest Descent Method, also known as the Gradient Descent Method, can find the local minimum point of a function through iterative search. Specifically, at the current point, move a certain step in the opposite direction of the function gradient (i.e. the direction of fastest descent) to reach the local minimum.

[0030] S104, updating the preset fringe correction model based on the least mean square algorithm and the updated error value to obtain a target fringe correction model.

[0031] In this embodiment, the preset fringe correction model includes a correction gain value and a bias coefficient. The preset fringe correction model is updated based on the least mean square algorithm and the updated error value, that is, the correction gain value and the bias coefficient are updated based on the least mean square algorithm and the updated error value.

[0032] In this embodiment, the specific formula for updating the preset fringe correction model based on the least mean square (LMS) algorithm and the update error value is as follows: in, is the correction gain value of the preset fringe correction model, is the bias coefficient of the preset fringe correction model, Pixel The corresponding correction gain value, Pixel The corresponding bias coefficient is, To update the error value, is the pixel value of the current pixel, is the descending step length.

[0033] In this embodiment, when the error value is updated When it is the minimum value, it is determined that the updating step of the preset fringe correction model meets the convergence condition.

[0034] S105, processing the image to be corrected according to the target fringe correction model to obtain a target image.

[0035] In this embodiment, the target stripe correction model is a stripe correction model that updates the correction gain value and the bias coefficient, which can effectively remove the stripes in the target direction in the image to be corrected. The target direction includes vertical, horizontal and other directions. It should be noted that the target stripe correction model provided in this embodiment can effectively remove the vertical stripes and horizontal stripes in the image to be corrected. For stripes in other directions, the aforementioned filtering process or the calculation method of some intermediate values ​​can be adaptively modified to achieve effective removal.

[0036] To sum up, this embodiment provides an infrared image stripe correction method with low algorithm complexity and no need to cache multiple lines of data. It is easy to implement in hardware and can effectively remove vertical and horizontal stripes. It can be applied to more complex infrared image stripe removal scenarios and maximize the protection of information on the edge and non-edge parts of the infrared image, and has stronger applicability.

[0037] According to a specific implementation of the embodiment of the present application, Figure 2 As shown, edge detection is performed on the image to be corrected to obtain edge parts and non-edge parts of the image to be corrected, including: S201, traversing the pixels of the image to be corrected based on a window of preset specifications.

[0038] S202: When the absolute value of the difference between the grayscale value of any target pixel in the window and the grayscale value of the central pixel in the window is greater than or equal to a preset difference threshold, determine that the target pixel is an edge pixel.

[0039] S203: determine all edge pixels as edge parts, and determine non-edge pixels as non-edge parts.

[0040] In this embodiment, the window may be a filtering window or a window configured solely for the edge detection process, and the specification of the window may be set according to the scale of the image to be corrected in the actual application scenario.

[0041] In the process of traversing the image using the window, if there is a pixel in the window, and the absolute value of the difference between the grayscale value of the pixel in the center of the window is greater than or equal to the preset difference threshold TH, then the pixel can be determined as an edge pixel. By counting all edge pixels, the edge part of the image to be corrected can be determined. The other areas of the image to be corrected except the edge part are non-edge parts.

[0042] According to a specific implementation of the embodiment of the present application, the method further includes: The preset difference threshold is determined according to the distribution of the absolute value of the horizontal gradient of the image to be corrected.

[0043] In this embodiment, due to the different characteristics of different images, the use of a fixed preset difference threshold may not be suitable for application scenarios where stripes need to be removed from all images. Therefore, the preset difference threshold in this embodiment needs to be adaptively selected according to the image content.

[0044] According to a specific implementation of the embodiment of the present application, determining a preset difference threshold according to the distribution of the absolute value of the horizontal gradient of the image to be corrected includes: The horizontal gradient absolute value whose number of pixel points is greater than a preset number threshold is selected as the preset difference threshold.

[0045] This embodiment selects the threshold value according to the distribution of the absolute value of the horizontal gradient of different images. After obtaining the image to be corrected, the absolute value of the gradient of the image to be corrected in the horizontal direction is calculated to obtain the statistical histogram Hist of the absolute value of the gradient. Starting from the maximum gradient value of the statistical histogram Hist, the number of pixels corresponding to the gradient value is accumulated one by one until the accumulated number of pixels is greater than p*M pixels. The gradient value at this time is used as the threshold TH, where M is the number of pixels participating in the statistics and p is 0.99.

[0046] It should be noted that the value of p can be any value between 0 and 1, and can be configured according to the specific application scenario. A value of 0.99 for p represents 99% of the pixels.

[0047] According to a specific implementation of the embodiment of the present application, Figure 3 As shown, the updated error values ​​of the edge part and the non-edge part are calculated respectively according to different error calculation rules, including: S301, calculating expected values ​​and predicted values ​​according to the pixel values ​​of each pixel point of the image to be corrected.

[0048] S302, calculating an updated error value of the edge portion according to the pixel value and the prediction value.

[0049] S303, calculating the updated error value of the non-edge part according to the expected value and the predicted value.

[0050] In this embodiment, for the updated error value of the edge part, considering the slight difference in gain coefficient and offset between column directions, the original pixel value is used as the estimated value to calculate the updated error value, which can ensure that the updated error value finally calculated is the minimum error value.

[0051] It should be noted that the calculation method of the update error value that distinguishes the edge part and the non-edge part can effectively protect the image information of the edge part of the image to be corrected.

[0052] According to a specific implementation of the embodiment of the present application, Figure 4 As shown, the expected value and the predicted value are calculated according to the pixel value of each pixel point of the image to be corrected, including: S401, using a one-dimensional horizontal mean filter to process pixel values ​​to obtain expected values; S402, processing the pixel value using the correction gain value and the bias coefficient corresponding to the pixel point located in the previous row of the current pixel point to obtain a predicted value.

[0053] In this embodiment, a one-dimensional horizontal mean filter can be used to perform sliding mean filtering on the image to be corrected to obtain an expected value. In this embodiment, the expected value of the current pixel is obtained by low-pass filtering. When the pixel value of the image to be corrected is corrected according to the preset stripe correction model, the difference between the corrected value and the expected value is minimized, which can effectively ensure the protection of information in the image to be corrected and effectively remove stripes.

[0054] The predicted value is calculated using the correction gain value and bias coefficient corresponding to the pixel point located in the previous row of the current pixel point, which can make full use of the correlation between the detector pixels, eliminate the need to cache multiple rows of data, and facilitate hardware implementation.

[0055] In summary, this embodiment provides an infrared image stripe correction method, which can obtain the expected value of the current pixel point through low-pass filtering, and then iteratively calculate the correction parameter corresponding to the current pixel point through the steepest descent method, so that the difference between the corrected value and the expected value is minimized, and edge detection is added in the estimation process, and no filtering is performed in the edge area. The threshold of edge detection is determined in an adaptive manner, which can effectively protect the edge information from being destroyed.

[0056] In a more detailed embodiment, the complete execution process of the infrared image fringe correction method provided in this embodiment is shown in the following steps: Step 1: Obtain infrared image data collected by the infrared detector After collecting infrared signals, the infrared detector can pre-process the infrared signals to obtain infrared image data. .in, It can be used to represent the pixel value in infrared images.

[0057] Step 2: Use a one-dimensional horizontal mean filter to process the infrared image data and estimate the expected value Among them, the mean filter can be configured with the filter window specification. Assume that the filter window radius is , the processing formula of the mean filter can be expressed as: in, is the expected value, is the pixel value, is the standard filter window radius.

[0058] Step 3: Get the correction gain value corresponding to the pixel point in the same column and the previous row of the current pixel point and bias coefficient , according to the correction gain value and bias coefficient Calculate the predicted value of the current pixel. The calculation formula of the predicted value is as follows: in, is the predicted value, The pixel value of the current pixel.

[0059] Step 4: Detect infrared image data based on the preset edge detection algorithm For the edge part, the formula of the preset edge detection algorithm is as follows: in, Indicates the difference in grayscale value between the current pixel and the center pixel of the window. , It means to find the absolute value. Represents infrared image data Is it an edge point? is the preset difference threshold.

[0060] Step 5: Calculate the error values ​​of the infrared image data of the edge part and the non-edge part respectively. The specific calculation formula is as follows: in, is the error value, is the pixel value of the current pixel, is the predicted value, is the expected value, Indicates that the current pixel is an edge point. Indicates that the current pixel is a non-edge point.

[0061] In this embodiment, the steepest descent method is used to make the error value Get the minimum value to update the correction gain coefficient and bias coefficient.

[0062] Step 6: Correct the preset stripe correction model according to the updated correction gain value and bias coefficient to eliminate the horizontal and vertical stripes in the infrared image. The formula of the preset correction model is: in, To correct the gain value, is the bias coefficient, is the pixel value.

[0063] Based on the same inventive concept, the embodiment of the present application also provides an infrared image streak correction device for implementing the infrared image streak correction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more infrared image streak correction device embodiments provided below can refer to the limitations of the infrared image streak correction method above, and will not be repeated here.

[0064] In one embodiment, reference Figure 5 This embodiment also provides an infrared image fringe correction device 500, including: an image acquisition module 510, an edge detection module 520, an error calculation module 530, a model updating module 540 and a model processing module 550, wherein: An image acquisition module 510 is used to acquire an image to be corrected; An edge detection module 520 is used to perform edge detection on the image to be corrected to obtain edge parts and non-edge parts of the image to be corrected; An error calculation module 530 is used to calculate the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; A model updating module 540 is used to update the preset fringe correction model based on the least mean square algorithm and the updated error value to obtain a target fringe correction model; The model processing module 550 is used to process the image to be corrected according to the target fringe correction model to obtain a target image.

[0065] In one embodiment, the model updating module 540 is specifically configured to update the correction gain value and the bias coefficient based on a least mean square algorithm and the updated error value.

[0066] In one of the embodiments, the edge detection module 520 is specifically used to traverse the pixel points of the image to be corrected based on a window of preset specifications; when the absolute value of the difference between the grayscale value of any target pixel point in the window and the grayscale value of the center pixel point of the window is greater than or equal to a preset difference threshold, the target pixel point is determined to be an edge pixel point; the target pixel point is determined to be the edge part, and the other pixel points except the target pixel point are determined to be the non-edge part.

[0067] In one embodiment, the edge detection module 520 is specifically configured to select the horizontal gradient absolute value whose number of pixel points is greater than a preset number threshold as the preset difference threshold.

[0068] In one embodiment, the error calculation module 530 is specifically used to calculate the expected value and the predicted value according to the pixel value of each pixel point of the image to be corrected; calculate the updated error value of the edge part according to the pixel value and the predicted value; calculate the updated error value of the non-edge part according to the expected value and the predicted value.

[0069] In one embodiment, the error calculation module 530 is specifically used to process the pixel value using a one-dimensional horizontal mean filter to obtain the expected value; and process the pixel value using the correction gain value and bias coefficient corresponding to the pixel point located in the previous row of the current pixel point to obtain the predicted value.

[0070] Figure 5 The specific implementation of the device shown can refer to the specific implementation of the aforementioned method embodiment, which will not be repeated here.

[0071] In summary, this embodiment provides an infrared image fringe correction device, which makes full use of the correlation between detector pixels, updates the correction gain value and bias coefficient in an estimated manner, increases the protection of edge structures, and uses different error calculation methods for edge and non-edge parts. During edge detection, the threshold is no longer selected based on empirical values, but is selected in an adaptive manner. It has stronger applicability, lower algorithm complexity, higher real-time performance, and no need to cache multiple lines of data, which is conducive to hardware implementation.

[0072] In addition, an embodiment of the present application further provides an electronic device, the electronic device comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the infrared image stripe correction method in the aforementioned method embodiment.

[0073] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the infrared image stripe correction method in the aforementioned method embodiment.

[0074] The electronic devices in the embodiments of the present application may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0075] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Examples of computer-readable storage media may be, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0076] In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0077] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0078] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the image to be corrected; performs edge detection on the image to be corrected to obtain the edge part and the non-edge part of the image to be corrected; calculates the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; updates the preset stripe correction model based on the minimum mean square algorithm and the updated error value to obtain the target stripe correction model; processes the image to be corrected according to the target stripe correction model to obtain the target image. Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] The units involved in the embodiments described in this application can be implemented by software or hardware. It should be understood that each part of the present disclosure can be implemented by hardware, software, firmware or a combination thereof.

[0081] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for correcting infrared image fringes, characterized in that: include: Acquire an image to be corrected; Performing edge detection on the image to be corrected to obtain an edge portion and a non-edge portion of the image to be corrected; Calculate the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; The preset fringe correction model is updated based on the least mean square algorithm and the updated error value to obtain a target fringe correction model; The image to be corrected is processed according to the target fringe correction model to obtain a target image.

2. The method according to claim 1, characterized in that The preset fringe correction model includes a correction gain value and a bias coefficient; the updating of the preset fringe correction model based on the least mean square algorithm and the updated error value includes: The correction gain value and the bias coefficient are updated based on a least mean square algorithm and the updated error value.

3. The method according to claim 1, characterized in that The performing edge detection on the image to be corrected to obtain the edge part and the non-edge part of the image to be corrected comprises: Traversing the pixel points of the image to be corrected based on a window of preset specifications; When the absolute value of the difference between the grayscale value of any target pixel in the window and the grayscale value of the central pixel of the window is greater than or equal to a preset difference threshold, the target pixel is determined to be an edge pixel; All edge pixel points are determined as the edge part, and non-edge pixel points are determined as the non-edge part.

4. The method according to claim 3, characterized in that The method further comprises: The preset difference threshold is determined according to the distribution of the absolute value of the horizontal gradient of the image to be corrected.

5. The method according to claim 4, characterized in that The step of determining the preset difference threshold according to the distribution of the absolute value of the horizontal gradient of the image to be corrected comprises: The horizontal gradient absolute value whose number of pixel points is greater than a preset number threshold is selected as the preset difference threshold.

6. The method according to claim 1, characterized in that The step of respectively calculating the updated error values ​​of the edge portion and the non-edge portion according to different error calculation rules includes: Calculating the expected value and the predicted value respectively according to the pixel value of each pixel point of the image to be corrected; Calculate an updated error value of the edge portion according to the pixel value and the predicted value; An updated error value of the non-edge portion is calculated according to the expected value and the predicted value.

7. The method according to claim 6, characterized in that The calculating the expected value and the predicted value respectively according to the pixel value of each pixel point of the image to be corrected includes: Processing the pixel value with a one-dimensional horizontal mean filter to obtain the expected value; The pixel value is processed using the correction gain value and the bias coefficient corresponding to the pixel point located in the previous row of the current pixel point to obtain the predicted value.

8. An infrared image fringe correction device, characterized in that: include: An image acquisition module, used for acquiring an image to be corrected; An edge detection module is used to perform edge detection on the image to be corrected to obtain an edge portion and a non-edge portion of the image to be corrected; An error calculation module, used to calculate the updated error values ​​of the edge part and the non-edge part respectively according to different error calculation rules; A model updating module, used for updating a preset fringe correction model based on a least mean square algorithm and the updated error value to obtain a target fringe correction model; The model processing module is used to process the image to be corrected according to the target fringe correction model to obtain a target image.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the infrared image stripe correction method described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, which are used to enable the computer to execute the infrared image fringe correction method described in any one of claims 1-7.

Images