Image processing method, system and device, electronic equipment and storage medium

Abstract

The invention provides an image processing method, system and device, electronic equipment and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: collecting original image data of a target object; obtaining first image information of the original image data, performing initial correction on the original image data based on the first image information, and converting the original image data subjected to initial correction into RGB image data; acquiring second image information of the RGB image data, performing color correction on the RGB image data based on the second image information, and converting the RGB image data subjected to color correction into YUV image data; acquiring third image information of the YUV image data, and performing image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; and converting the target image data into a target format, and outputting the target image data of the target object in the target format. The detail features of the image are reserved, and the quality and definition of the image are improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image processing method, system, device, electronic device and storage medium. Background Art

[0002] Image sensors are functional devices that use the photoelectric conversion function of photoelectric devices to convert the light image on the photosensitive surface into an electrical signal that is proportional to the light image. Due to its small size, light weight, high integration, long life, and low price, it is widely used in security monitoring, intelligent transportation, medical and other fields.

[0003] However, in low-light environments, such as at night, at dusk, or in low-light indoors, the image captured by the image sensor is often not bright enough overall due to insufficient light, which makes it difficult to distinguish the details of the captured image, and more noise is generated when capturing the image, affecting the image quality. In addition, due to the reduced contrast between light and dark areas in the image, the outline and texture information of the object in the image will also become blurred. The above problems will cause the images taken in low-light environments to be difficult to meet the needs of actual applications. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure propose an image processing method, system, device, electronic device and storage medium to solve the problem in the related art that images taken by image sensors in low-light environments are difficult to meet actual application requirements.

[0005] According to a first aspect of the present disclosure, there is provided an image processing method, comprising: acquiring original image data of a target object; acquiring first image information of the original image data, performing initial correction on the original image data based on the first image information, and converting the original image data after the initial correction into RGB image data; acquiring second image information of the RGB image data, performing color correction on the RGB image data based on the second image information, and converting the color-corrected RGB image data into YUV image data; acquiring third image information of the YUV image data, performing image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; converting the target image data into a target format, and outputting the target image data of the target object in the target format.

[0006] According to a second aspect of the present disclosure, an image processing system is provided, the image processing system comprising an image acquisition module, a signal conversion module, an image processing module and an image output module; wherein: the image acquisition module is used to receive the optical signal through a head plate; convert the optical signal into an electrical signal and output it as raw image data; transmit the raw image data to the image processing module; the signal conversion module is used to receive the optical signal through a head plate; convert the optical signal into an electrical signal and transmit the electrical signal to the image processing module; the image processing module is used to perform image processing on the electrical signal of the raw image data based on FPGA; wherein the image processing comprises: obtaining first image information of the raw image data, The original image data is initially calibrated based on the first image information, and the original image data after the initial calibration is converted into RGB image data; second image information of the RGB image data is obtained, color correction is performed on the RGB image data based on the second image information, and the RGB image data after the color correction is converted into YUV image data; third image information of the YUV image data is obtained, and image enhancement processing is performed on the YUV image data based on the third image information to obtain target image data of the target object; the image output module is used to convert the target image data into a target format through an interface board, and output the target image data of the target object in the target format.

[0007] According to a third aspect of the present disclosure, an image processing device is provided, comprising: an image acquisition module, for acquiring original image data of a target object; an image processing module, for acquiring first image information of the original image data, performing initial correction on the original image data based on the first image information, and converting the original image data after the initial correction into RGB image data; the image processing module is also used to acquire second image information of the RGB image data, perform color correction on the RGB image data based on the second image information, and convert the RGB image data after the color correction into YUV image data; the image processing module is also used to acquire third image information of the YUV image data, perform image enhancement processing on the YUV image data based on the third image information, and obtain target image data of the target object; an image output module, for converting the target image data into a target format, and outputting the target image data of the target object in the target format.

[0008] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to perform the above-mentioned image processing method.

[0009] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned image processing method.

[0010] The exemplary embodiments of the present disclosure may have some or all of the following beneficial effects: In the image processing method provided in the exemplary embodiment of the present disclosure, the original image data of the target object is collected; the first image information of the original image data is obtained, the original image data is initially corrected based on the first image information, and the original image data after initial calibration is converted into RGB image data; the second image information of the RGB image data is obtained, the RGB image data is color corrected based on the second image information, and the color-corrected RGB image data is converted into YUV image data; the third image information of the YUV image data is obtained, and the YUV image data is image enhanced based on the third image information to obtain the target image data of the target object; the target image data is converted into a target format, and the target image data of the target object is output in the target format. The embodiment of the present disclosure performs an initial correction on the image based on the first image information of the original image data, and converts the corrected image into RGB image data, so that the color of the image can be corrected in the RGB domain, ensuring the naturalness and accuracy of the image color. In addition, after color correction, the embodiment of the present application converts the color-corrected RGB image data into YUV image data, so that the image can be enhanced in the YUV domain, improving the quality and clarity of the image. The disclosed embodiments make full use of the feature information of the image in different domains to process the collected image, retain the detailed features of the image, improve the effect of image processing, and solve the problem that the image quality collected in low-light environments is poor and difficult to meet the needs of actual applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of an image processing method according to an exemplary embodiment of the present disclosure is shown; Figure 2 A schematic diagram of an image processing system according to an exemplary embodiment of the present disclosure is shown; Figure 3 A functional structure diagram of a head board in an image processing system according to an exemplary embodiment of the present disclosure is shown; Figure 4 A functional structure diagram of an FPGA in an image processing system according to an exemplary embodiment of the present disclosure is shown; Figure 5 A schematic block diagram of an image processing apparatus according to an exemplary embodiment of the present disclosure is shown; Figure 6 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0012] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0013] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0014] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0015] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0016] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0017] The embodiments of the present disclosure provide an image processing method, system, device, electronic device and storage medium. The embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0018] The present disclosure first provides an image processing method. Figure 1 As shown, the image processing method specifically includes the following steps: S110: collecting original image data of the target object; S120: Acquire first image information of the original image data, perform initial correction on the original image data based on the first image information, and convert the initially calibrated original image data into RGB image data; S130: Acquire second image information of the RGB image data, perform color correction on the RGB image data based on the second image information, and convert the color-corrected RGB image data into YUV image data; S140: Acquire third image information of the YUV image data, and perform image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; S150: Convert the target image data into a target format, and output the target image data of the target object in the target format.

[0019] The disclosed embodiment performs an initial correction on the image based on the first image information of the original image data, and converts the corrected image into RGB image data, so that the color of the image can be corrected in the RGB domain, ensuring the naturalness and accuracy of the image color. In addition, after color correction, the embodiment of the present application converts the color-corrected RGB image data into YUV image data, so that the image can be enhanced in the YUV domain, improving the quality and clarity of the image. The disclosed embodiment makes full use of the feature information of the image in different domains to process the collected image, retains the detailed features of the image, improves the effect of image processing, and solves the problem that the image quality collected in low-light environments is poor and difficult to meet the needs of actual applications.

[0020] Next, in another embodiment, the above steps are described in more detail.

[0021] In step S110 , original image data of the target object is acquired.

[0022] In the embodiment of the present application, the raw image data is a raw image of the target object that has not been processed and is collected by an image sensor. The image sensor is a functional device that uses the photoelectric conversion function of a photoelectric device to convert the light image on the photosensitive surface into an electrical signal that is proportional to the light image. The target object is the collection object of the image sensor.

[0023] In an embodiment of the present application, the above-mentioned acquisition of the original image data of the target object can, exemplarily, be implemented as follows: capturing the light signal on the surface of the target object, converting the captured light signal into an electrical signal through photoelectric conversion technology, and outputting it as digital image data, that is, the above-mentioned original image data.

[0024] In an embodiment of the present application, after the image sensor acquires the raw image data of the target object, the raw image data acquired in the RAW domain is transmitted to the image processing module, so that the acquired image of the target object is processed by the image processing module. Exemplarily, the above-mentioned image processing module can be implemented based on a field programmable gate array (FPGA), and then after the image sensor converts the captured light signal into an electrical signal through the photoelectric conversion technology, the output digital image data can be transmitted to the FPGA through the mobile industry processor interface (MIPI), and the MIPI interface can provide efficient and low-power data transmission.

[0025] In the embodiment of the present application, after receiving the digital image data transmitted through the MIPI interface, the image processing module can parse and process the MIPI transmitted data to obtain a processable data format. Specifically, the above parsing and processing process can be implemented as follows: decoding and formatting the MIPI transmitted data, converting it into a standard digital image data format, that is, 12-bit RAW image data; expanding the 12-bit RAW data to 16 bits, increasing the accuracy of the image data, and providing a higher dynamic range for subsequent image processing.

[0026] In step S120, first image information of the original image data is acquired, initial correction is performed on the original image data based on the first image information, and the original image data after initial correction is converted into RGB image data.

[0027] In the embodiment of the present application, the first image information is image information extracted from the original image data in the RAW domain. Exemplarily, the first image information may include texture information, brightness information and pixel information of the original image data.

[0028] In the embodiment of the present application, the above-mentioned initial correction of the original image data may exemplarily include processes such as picture cropping, fixed noise removal, black level correction and filtering noise reduction. Among them: The above-mentioned image cropping refers to cropping the original image data according to actual needs, retaining the required target area and removing the redundant parts. Exemplarily, the above-mentioned image cropping can be achieved by video stream scaling or area focus.

[0029] The fixed noise removal refers to removing the fixed image noise generated by the image sensor, which is usually caused by hardware or sensor characteristics. Exemplarily, the fixed image noise can be removed by using a double sampling noise reduction method.

[0030] The black level correction mentioned above refers to adjusting the baseline of the signal of the original image data to ensure that the pixel values ​​of the dark areas in the original image data can correctly reflect the actual brightness.

[0031] Exemplarily, the above-mentioned black level correction process can be implemented as follows: determine multiple brightness partitions, calculate the gain response and offset corresponding to each brightness partition; based on the above-mentioned brightness partitions and the gain response and offset corresponding to each brightness partition, determine the correction model corresponding to each brightness partition, and correct each pixel point in the original image data based on the correction model.

[0032] Specifically, the above process of calculating the gain response and offset corresponding to each brightness partition can be implemented as follows: for each brightness partition, calculate the first brightness mean of the high brightness points and the second brightness mean of the low brightness points in the brightness partition; determine the gain response corresponding to the brightness partition based on the first brightness mean and the second brightness mean; determine the offset corresponding to the brightness partition based on the second brightness mean and the gain response.

[0033] In a specific embodiment, the black level correction process is described in detail below: In the embodiment of the present application, the black level correction is implemented by a multi-segment correction method. The core idea of ​​the multi-segment correction is to divide the response characteristics of the image sensor into multiple brightness intervals and calculate the correction parameters K (i.e., the gain response) and B (i.e., the offset) of each brightness partition. Specifically, the multi-segment correction method establishes the correction model by collecting multiple brightness reference points. The formula of the correction model is as follows: ; Where i represents the brightness partition to which the current pixel belongs, K[i] represents the gain coefficient of the i-th brightness partition (that is, the above-mentioned gain response), and B[i] represents the bias of the i-th brightness partition (that is, the above-mentioned offset). Indicates the current pixel value. Represents the pixel value corrected by the above correction model.

[0034] The implementation process of the above multi-stage correction method is described below. Specifically, the above multi-stage correction method includes the following steps: S1: Divide into multiple brightness partitions.

[0035] In this step, the above-mentioned division into multiple brightness partitions can be achieved by the following method: dividing the input light intensity range of the image sensor into several brightness intervals (for example, from dark field to bright field) based on linear or logarithmic distribution of light intensity (such as low, medium and high light intensity).

[0036] S2: Collect multiple reference data.

[0037] In this step, the above-mentioned collection of multiple sections of reference data can be achieved in the following manner: in each brightness interval, a reference image is captured using a uniform light source, and the brightness average Vavg and the corresponding pixel value Vin of each brightness interval are calculated.

[0038] S3: Calculate segment correction parameters.

[0039] In this step, the gain coefficient K[i] of the current brightness partition can be calculated by the following formula: ; in, is the average value of the high brightness points in the current brightness partition (that is, the first brightness average value mentioned above), is the average value of the low brightness points in the current brightness partition (that is, the second brightness average value mentioned above), is the pixel value of the highest brightness point in the current brightness partition, It is the pixel value of the lowest brightness point in the current brightness partition.

[0040] The bias B[i] of the current brightness partition can be calculated by the following formula: ; in, is the average value of the low brightness points in the current brightness partition, is the pixel value of the lowest brightness point in the current brightness partition. It is the gain coefficient of the current brightness partition.

[0041] S4: Construct a segment correction table.

[0042] In this step, a segment correction table is created. Exemplarily, the segment correction table may be a random access memory (RAM). The gain coefficient K[i] and bias B[i] of each brightness partition obtained by the above calculation are stored in the segment correction table.

[0043] S5: Correct the image pixel values ​​based on the segmented correction table and the correction model.

[0044] In this step, the brightness partition to which the pixel value Vin belongs is determined according to its size; the gain coefficient K[i] and bias B[i] corresponding to the brightness partition to which it belongs are called, and based on the formula of the above correction model Correct the pixel values.

[0045] The embodiments of the present application can solve the following problems based on the above-mentioned black level correction: (1) sensor pixel non-uniformity: due to differences in manufacturing processes, different pixels have slight differences in their ability to respond to light; (2) optical lens effect: the lens of the optical system may produce different light intensity distributions in the center and edge areas of the image (such as the dark corner phenomenon); (3) light source non-uniformity: the light irradiating the image sensor presents different brightness due to the uneven distribution of the light source or reflective surface.

[0046] The embodiment of the present application innovatively introduces a multi-segment correction method, which calculates the response curve of the sensor under different lighting conditions in segments and performs fine segmentation processing on the response curve. Compared with the method of using only two reference points, bright field and dark field, for correction in the related art, this method has higher accuracy and can adapt to complex and changeable image characteristics.

[0047] The above-mentioned filtering noise reduction refers to processing an image through a specific filtering algorithm to reduce or eliminate noise in the image and improve the quality and clarity of the image.

[0048] Exemplarily, the above-mentioned filtering and denoising can be implemented as follows: based on each pixel point in the original image data, determine the pixel texture area to be processed and the first texture replacement search area corresponding to each pixel point; divide the first texture replacement search area into multiple second texture replacement search areas, and filter the pixel texture area to be processed based on the second texture replacement search area.

[0049] Specifically, the above-mentioned determination of the pixel texture area to be processed and the first texture replacement search area corresponding to each pixel point in the original image data can be implemented as follows: traverse each pixel point in the original image data; for each pixel point, determine the pixel texture area to be processed and the first texture replacement search area with the pixel point as the center; wherein the first texture replacement search area is larger than the pixel texture area to be processed.

[0050] The filtering process of the pixel texture area to be processed based on the second texture replacement search area can be implemented as follows: for each second texture replacement search area, a weight coefficient between the second texture replacement search area and the pixel texture area to be processed is calculated; and the pixel value of the pixel texture area to be processed is updated based on the weight coefficient.

[0051] In a specific embodiment, the above filtering and noise reduction process is described in detail below: The embodiment of the present application utilizes the information of similar pixel blocks in the image to remove random noise of the image. The core idea is: for each pixel i, the denoising result is determined based on the weighted mean of its similar pixels. The similar pixels are measured by the image blocks. Specifically, the pixel value Iout(i) after denoising can be calculated by the following formula: ; Where i is the current pixel position, Ω is the pixel set of the entire image, w(i,j) is the weight of pixels i and j, and I(j) is the intensity value of pixel j.

[0052] The weights of the above pixels i and j can be determined by measuring the similarity between pixels i and j. Specifically, they can be calculated by the following formula: ; Wherein, P(i) is an image block determined with pixel i as the center (that is, the pixel texture area to be processed mentioned above); P(j) is an image block determined with pixel j as the center (that is, the second texture replacement search area mentioned above); is the Euclidean distance between two image blocks P(i) and P(j); h is the filtering parameter (smoothing coefficient), which is used to adjust the decreasing speed of the weight. The larger h is, the higher the denoising level is.

[0053] The implementation process of the above filtering and noise reduction is described below. Specifically, the above filtering and noise reduction includes the following steps: S1: Image patch extraction.

[0054] In this step, each pixel i in the original image data is traversed, and an image block P(i) is extracted with the pixel as the center. The size of the image block may be KxK. For example, the size of the image block may be 3×3 or 5×5.

[0055] S2: Define the search window.

[0056] In this step, a search window (i.e., the first texture replacement search area) is defined, and the size of the search window may be generally SxS, and S>K. For example, when the size of the image block P(i) is 3×3 or 5×5, the size of the search window may be 21×21; an image block P(j) similar to the current image block P(i) is searched in the search window.

[0057] S3: Calculate the weights of image block P(i) and image block P(j).

[0058] In this step, the weight w(i, j) between the current image block P(i) and all image blocks P(j) in the search window is calculated.

[0059] S4: Calculate the weighted mean.

[0060] In this step, the weight w(i, j) is used to perform weighted averaging on the pixel values ​​I(j) in the search window to obtain the denoised pixel value Iout(i).

[0061] The embodiment of the present application executes the above steps S1 to S4 on all pixel points in the original image data, uses the information of similar pixel blocks in the image to perform denoising, and ultimately obtains a denoised image while retaining the detailed structure of the image, which is suitable for image processing in low-light environments.

[0062] In an embodiment of the present application, after performing processing such as image cropping, fixed noise removal, black level correction, and filtering noise reduction on the above-mentioned original image data in the RAW domain, the processed image can also be converted into RGB image data so that the image can be subsequently color corrected in the RGB domain.

[0063] In step S130, second image information of the RGB image data is acquired, color correction is performed on the RGB image data based on the second image information, and the color-corrected RGB image data is converted into YUV image data.

[0064] In the embodiment of the present application, the second image information is image information extracted from the RGB image data. Exemplarily, the second image information may include color information.

[0065] In the embodiment of the present application, the image processing in the RGB domain may include processes such as de-mosaicing, automatic white balance and color correction. Among them: The above-mentioned demosaicing algorithm is also called the Bayer interpolation algorithm, which is an algorithm used to process the color information in the RAW format image output by the image sensor. The image sensor usually uses a Bayer filter array to collect color information, and the array is arranged according to the three color channels of red, green and blue. Therefore, each pixel in the RAW format image only contains information of one color channel. Through the demosaicing algorithm, these monochrome pixels can be interpolated to obtain a complete color image.

[0066] The above-mentioned automatic white balance refers to adjusting the color channels of the image so that white objects can accurately restore white under different lighting conditions to ensure the natural and accurate colors of the image.

[0067] The above-mentioned color correction refers to correcting the colors captured by the image sensor using matrix transformation so that they conform to the real colors perceived by the human eye.

[0068] Exemplarily, the above color correction process can be implemented as follows: obtain color information of RGB image data, and determine deviation information between the color information and the standard color; determine a color correction matrix based on the deviation information, and perform color correction on the RGB image data based on the color correction matrix.

[0069] In a specific embodiment, the color correction process is described in detail below: S1: Building a color correction model.

[0070] In this step, a color correction model is established, which is used to describe the relationship between the colors in the RGB image data and the real colors. Specifically, the input color space of the color correction model is the original RGB value captured by the image sensor, which usually has color deviation, and the output color space is the ideal RGB value, which is usually determined based on a standard color space (such as sRGB or Adobe RGB). The core of the above color correction model is a set of linear transformation relationships: ; Among them, the above M is a 3×3 color correction matrix used to represent the linear transformation between color channels; C is a bias vector used to fine-tune the color.

[0071] S2: Construct a color pairing dataset.

[0072] In this step, reference data is obtained to provide an accurate reference for the color correction model based on the reference data so as to derive the correct color correction matrix. Specifically, the process of obtaining reference data can be implemented as follows: using a standard color card (such as X-Rite ColorChecker) to obtain known ideal RGB values; taking an image of the standard color card and extracting the RGB values ​​captured by the image sensor; matching the measured values ​​with the standard values ​​one by one to form a color pairing data set: (Rin, Gin, Bin) → (Rref, Gref, Bref).

[0073] S3: Determine a color correction matrix.

[0074] In this step, the correction matrix M and the bias vector C are derived using the reference data. This can be achieved as follows: The relationship between the measured value and the standard value is modeled as a linear transformation: Y = X∙M+C, where Y is a matrix constructed based on the standard color value and X is a matrix constructed based on the image sensor measurement value.

[0075] S4: Perform color correction on the RGB image data based on the color correction matrix.

[0076] In this step, color correction is performed on each pixel in the RGB image data based on the color correction matrix M and the offset vector C calculated above. Specifically, the color correction of each pixel can be implemented based on the following transformation: ; After color correction, the adjusted color values ​​are clipped to the valid range: Rout, Gout, Bout∈ [0,255].

[0077] In the embodiment of the present application, after color correction is performed on the RGB image data based on the color correction model, tone mapping and gamma correction may be further performed on the RGB image data. The tone mapping refers to adjusting the brightness range of the RGB image data to make the details of the highlight and shadow areas clearer; the gamma correction refers to applying nonlinear transformation to improve the contrast and brightness of the image to optimize the display effect.

[0078] Furthermore, after the above-mentioned image processing of the RGB image data is completed, the embodiment of the present application can also convert the processed RGB image data into YUV image data, so as to further process the image in the YUV domain. Specifically, the above-mentioned process of converting the processed RGB image data into YUV image data can be implemented as follows: using the color space transformation formula to convert the RGB format image into the YUV format; downsampling the chrominance component of the YUV data from a 4:4:4 format (each pixel has independent Y, U, and V values) to a 4:2:2 format (the chrominance component is downsampled at a ratio of 2:1).

[0079] In an embodiment of the present application, by using a color space transformation formula to convert an RGB format image into a YUV format, the storage requirements of the chromaticity data can be reduced, facilitating subsequent compression; by downsampling the chromaticity component of the YUV data, most of the visual quality of the image can be retained while reducing the amount of data.

[0080] In step S140, third image information of the YUV image data is acquired, and image enhancement processing is performed on the YUV image data based on the third image information to obtain target image data of the target object.

[0081] In the embodiment of the present application, the third image information is image information extracted from the YUV image data. Exemplarily, the third image information may include information such as pixel information, brightness information, and histogram parameters.

[0082] In the embodiment of the present application, the image processing in the YUV domain may include processes such as automatic exposure statistics, automatic histogram statistics, automatic focus statistics, brightness contrast and saturation adjustment, and edge enhancement. Among them: The automatic exposure statistics mentioned above refer to analyzing brightness information and adjusting exposure parameters based on the brightness information.

[0083] The automatic histogram statistics refers to optimizing the brightness and contrast of the YUV image data by statistical histograms. Exemplarily, the automatic histogram statistics can be implemented by the following process: obtaining histogram parameters of the YUV image data and correcting the histogram parameters; and fusing the histogram parameters of the corrected YUV image data with the histogram parameters of the historical image frame.

[0084] Specifically, the above automatic histogram statistics can be achieved by the following steps: S1: Process the YUV image data in blocks.

[0085] In this step, the above YUV image data is divided into several regional sub-blocks, and each regional sub-block can be customized according to the needs of the actual scene. Exemplarily, the regional sub-block can select a rectangular area with a size of MxN. By processing the YUV image data in blocks, more accurate grayscale distribution information can be calculated in the local area without being affected by the global characteristics.

[0086] S2: Calculate the local histogram.

[0087] In this step, a histogram is calculated for each of the above-mentioned regional sub-blocks separately, that is, the number of pixels of each gray level in each regional sub-block is counted; a cumulative distribution function is determined based on the calculated local histogram, and the cumulative distribution function is used to map the gray value.

[0088] S3: Histogram equalization.

[0089] In this step, for the pixel value in each regional sub-block, the gray level of the pixel is adjusted according to the mapping of its gray value in the cumulative distribution function. Specifically, the gray level of each pixel value adjusted according to the cumulative distribution function can be implemented as follows: Iout(x,y)=CDF[Iin(x,y)]·(L-1); Among them, Iin(x,y) is the original pixel value of the YUV image data; Iout(x,y) is the pixel value after histogram equalization; L is the grayscale level of the image, usually 256; CDF is the above-mentioned cumulative distribution function.

[0090] S4: interpolation smoothing processing.

[0091] In this step, the equalization results between the adjacent regional sub-blocks are interpolated. For example, the interpolation method can be bilinear interpolation. The interpolation smoothing process can alleviate the block effect of the image boundary caused by the independent equalization of each regional sub-block, effectively smooth the change of the histogram parameters, and thus eliminate the image flickering caused by scene switching or sudden change of illumination.

[0092] The above-mentioned automatic focusing statistics refer to adjusting the clarity of the above-mentioned YUV image data based on the focusing information.

[0093] The brightness contrast and saturation adjustment process is used to adjust the overall hue and visual effect of the YUV image data. Exemplarily, the process can be implemented as follows: obtaining the Y component of the YUV image data, and enhancing the contrast of the YUV image data based on the Y component. Specifically, the processing of the Y component can be implemented based on the following formula: ; in, , used to adjust the contrast; , used to adjust the brightness, is the bit depth of the image. is the threshold, which is the statistical average of the image brightness.

[0094] The edge enhancement process is used to enhance the clarity of the edge of the YUV image data. Exemplarily, the edge clarity enhancement process can be implemented as follows: determining a target template, and determining an active window based on the target template; wherein the target template is a convolution kernel; traversing the YUV image data based on the active window, and updating the pixel values ​​of the pixels in the active window based on the target template.

[0095] In a specific embodiment, the above-mentioned edge enhancement process is described in detail below: In the embodiment of the present application, the implementation principle of the above edge enhancement is as follows: using the target template to traverse the entire YUV image data starting from the upper left corner of the above YUV image data, and updating the pixel value of the target pixel in the YUV image data. Specifically, the process can be implemented by the following steps: S1: Create an active window of the same size as the target template; S2: Multiply the active window image and the target template pixel correspondingly and then add them, and use the calculation result to replace the pixel value of the window center; S3: traverse the YUV image data from left to right and from top to bottom based on the active window, and repeat step S2 to update the above YUV image data.

[0096] For example, the target template is also called an operator, a correlation kernel, or a convolution kernel. The matrix of Generally equal to 3, 5, 7, 9. The relevant operation symbol is " , the convolution operator symbol is “*”.

[0097] The relevant kernel is expressed as: ; The formula for sharpness enhancement can be expressed as follows: ; ; ; in, is the original image to be processed, is the blurred image after spatial filtering, For the texture map, This is the enhanced image after processing. is the threshold value, is the enhancement factor.

[0098] Specifically, the relevant kernels used in the above process can be as follows: ; In the embodiment of the present application, through the image processing of steps S120 to S140, a significant improvement in image quality and optimization of details are achieved, and finally 8-bit YUV image data is output.

[0099] In step S150 , the target image data is converted into a target format, and the target image data of the target object is output in the target format.

[0100] In the embodiment of the present application, the target image data is image data obtained after performing image processing from step S120 to step S140 on the original image data.

[0101] In an embodiment of the present application, the target format is the output format of the target image data, which can be determined based on actual needs. Exemplarily, the target format can be a CML format code stream. Exemplarily, converting the 8-bit YUV image data into a CML format code stream can be achieved as follows: restoring the downsampled 4:2:2 data to a 4:4:4 format; integrating a CML encoder to compress the image data and generate a 16-bit CML format code stream.

[0102] The disclosed embodiment performs an initial correction on the image based on the first image information of the original image data, and converts the corrected image into RGB image data, so that the color of the image can be corrected in the RGB domain, ensuring the naturalness and accuracy of the image color. In addition, after color correction, the embodiment of the present application converts the color-corrected RGB image data into YUV image data, so that the image can be enhanced in the YUV domain, improving the quality and clarity of the image. The disclosed embodiment makes full use of the feature information of the image in different domains to process the collected image, retains the detailed features of the image, improves the effect of image processing, and solves the problem that the image quality collected in low-light environments is poor and difficult to meet the needs of actual applications.

[0103] The above mainly introduces the solution provided by the embodiment of the present invention from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0104] The embodiment of the present invention can divide the image processing device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0105] Furthermore, the present application also provides an image processing system. Figure 2 As shown, the image processing system includes an image acquisition module, a signal conversion module, an image processing module and an image output module; wherein: The image acquisition module is used to acquire the optical signal of the original image data of the target object and transmit the optical signal to the signal conversion module; The signal conversion module is used to receive the optical signal through the head plate; convert the optical signal into an electrical signal and output it as raw image data; and transmit the raw image data to the image processing module; The image processing module is used to perform image processing on the electrical signal of the original image data based on the FPGA; wherein the image processing includes: obtaining first image information of the original image data, performing initial correction on the original image data based on the first image information, and converting the initially calibrated original image data into RGB image data; obtaining second image information of the RGB image data, performing color correction on the RGB image data based on the second image information, and converting the color-corrected RGB image data into YUV image data; obtaining third image information of the YUV image data, performing image enhancement processing on the YUV image data based on the third image information, and obtaining target image data of the target object; The above-mentioned image output module is used to convert the target image data into a target format through the interface board, and output the target image data of the target object in the target format.

[0106] The specific implementation details of each module of the above-mentioned image processing system have been described in detail in the corresponding position of the above-mentioned image processing method, so they will not be repeated here.

[0107] The head board, FPGA and interface board used in the above image processing system are described in detail below: like Figure 3 As shown, the head board (Sensor board) includes a power module, an image detector and an inter-board connector. The power module is used to supply power to the head board.

[0108] The above-mentioned image detector is used to transmit the light radiation on the surface of the target object through the atmosphere to the lens of the imaging component system. After the lens converges the light radiation and projects it onto the image detector, the image detector converts the received light signal into an analog electrical signal through the image sensor.

[0109] The above-mentioned inter-board connector is used to transmit the original image data output after photoelectric conversion to FPGA through the MIPI interface.

[0110] like Figure 4 As shown, the FPGA includes a core processing unit, a JTAG debugging and downloading interface, a reset control module, a high-precision crystal oscillator module, a FLASH storage unit, a power management module, a sensor board connector, and an interface board multifunctional connector. The core processing unit is the core platform for running digital image processing algorithms, which has a high degree of programmability and powerful parallel processing capabilities, and can support the efficient implementation of complex image processing algorithms. Specifically, the processing of image data in the above-mentioned image processing method can be implemented based on the programmability and parallel processing capabilities of the core processing unit.

[0111] The JTAG debugging and downloading interface is used to provide convenient FPGA program debugging and downloading functions, support high-speed data transmission and real-time online debugging, and ensure rapid iteration and optimization of algorithm development. Specifically, the FPGA program in the embodiment of the present application is a programming implementation of the image processing algorithm involved in the image processing method.

[0112] The reset control module is an integrated system reset signal generator, which is used to enable the FPGA to quickly return to the initial state in abnormal or restart situations to ensure stable operation of the system.

[0113] The above-mentioned high-precision crystal oscillator module is used to provide a stable 50MHz system clock for the FPGA, ensuring the precise synchronization of internal logic operations and improving the system processing speed.

[0114] The FLASH storage unit is used to store FPGA programs and configuration parameters, supports automatic loading upon power-on, and improves system startup efficiency and reliability.

[0115] The above power management module is used to provide stable power supply for FPGA and its peripheral components, ensuring that the system can work normally under various working conditions and enhancing system stability.

[0116] The above-mentioned sensor inter-board connector is used to receive the original image signal and transmit the detector configuration instruction. It has the characteristics of high speed and low noise to ensure the accurate transmission of the image signal.

[0117] The multifunctional connector between the above interface boards supports the output of digital image signals and the reception of external synchronization signals and serial communications, and provides a variety of interface types to meet the flexible connection requirements with external devices or systems.

[0118] The image processing system provided in the embodiment of the present application significantly improves the speed and accuracy of digital image processing by optimizing the coordination between the FPGA core processing unit and the high-precision crystal oscillator module; through the integration of the reset control module and the efficient power management module, the stable operation and exception handling capabilities of the system are ensured, and the stability of the system is improved; through the design of the JTAG debugging and downloading interface and the multi-function connector, great flexibility is provided for algorithm development and external device connection; by introducing the FLASH storage unit, the system startup process is simplified and the convenience of operation is improved. In addition, the image processing system provided in the embodiment of the present application realizes image processing by adopting an FPGA module, abandoning high-power consumption components such as DDR, SRAM, DSP and high-performance MCU in the related technology, while ensuring system performance, significantly reducing the overall cost and power consumption, and opening up a new path for the development of image signal processing systems.

[0119] The above interface board is responsible for the input of external video signals and the output of internal signals. The interface board can receive external video signals such as PAL and convert them into a format recognizable within the system for processing. At the same time, it can also convert the processed signals into CML and other formats for output to meet the needs of different devices.

[0120] Accordingly, the present disclosure also provides an image processing device. Figure 5 As shown, the image processing device 500 may include an image acquisition module 510, an image processing module 520 and an image output module 530, wherein: An image acquisition module 510 may be used to acquire raw image data of a target object; The image processing module 520 may acquire first image information of the original image data, perform initial correction on the original image data based on the first image information, and convert the initially calibrated original image data into RGB image data; The image processing module 520 is further used to obtain second image information of the RGB image data, perform color correction on the RGB image data based on the second image information, and convert the color-corrected RGB image data into YUV image data; The image processing module 520 is further used to obtain third image information of the YUV image data, and perform image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; The image output module 530 is used to convert the target image data into a target format and output the target image data of the target object in the target format.

[0121] In an embodiment of the present application, the above-mentioned image processing module is specifically used to: determine multiple brightness partitions, calculate the gain response and offset corresponding to each brightness partition; determine the correction model corresponding to each brightness partition based on the brightness partition and the gain response and offset corresponding to each brightness partition, and correct each pixel point in the original image data based on the correction model; based on each pixel point in the original image data, determine the pixel texture area to be processed and the first texture replacement search area corresponding to each pixel point; divide the first texture replacement search area into multiple second texture replacement search areas, and filter the pixel texture area to be processed based on the second texture replacement search area.

[0122] In an embodiment of the present application, the above-mentioned image processing module is specifically used to: calculate, for each brightness partition, a first brightness mean of the high brightness points and a second brightness mean of the low brightness points in the brightness partition; determine a gain response corresponding to the brightness partition based on the first brightness mean and the second brightness mean of the low brightness points; determine an offset corresponding to the brightness partition based on the second brightness mean and the gain response.

[0123] In an embodiment of the present application, the above-mentioned image processing module is specifically used to: traverse each pixel point in the original image data; for each pixel point, determine the pixel texture area to be processed and the first texture replacement search area with the pixel point as the center; wherein the first texture replacement search area is larger than the pixel texture area to be processed; for each second texture replacement search area, calculate the weight coefficient of the second texture replacement search area and the pixel texture area to be processed; and update the pixel value of the pixel texture area to be processed based on the weight coefficient.

[0124] In an embodiment of the present application, the above-mentioned image processing module is specifically used to: obtain color information of RGB image data, and determine the deviation information between the color information and the standard color; determine a color correction matrix based on the deviation information, and perform color correction on the RGB image data based on the color correction matrix.

[0125] In an embodiment of the present application, the above-mentioned image processing module is specifically used to: obtain histogram parameters of YUV image data and correct the histogram parameters; perform fusion processing based on the histogram parameters of the corrected YUV image data and the histogram parameters of the historical image frame; obtain the Y component of the YUV image data, and enhance the contrast of the YUV image data based on the Y component; determine the target template, and determine the active window based on the target template; wherein the target template is a convolution kernel; traverse the YUV image data based on the active window, and update the pixel values ​​of the pixels in the active window based on the target template.

[0126] In addition, the specific implementation details of the above-mentioned image processing device have been described in detail in the corresponding position of the image processing method, so they will not be repeated here.

[0127] Figure 6 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 6 , which shows a structural schematic diagram of an electronic device 600 suitable for implementing the embodiments of the present disclosure. Figure 6 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 disclosure.

[0128] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603 to implement the image processing method of the embodiment described in the present disclosure. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0129] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0130] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the image processing method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0131] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present 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, device 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. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0132] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0133] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0134] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: Collecting raw image data of the target object; Acquire first image information of the original image data, perform initial correction on the original image data based on the first image information, and convert the initially calibrated original image data into RGB image data; Acquire second image information of the RGB image data, perform color correction on the RGB image data based on the second image information, and convert the color-corrected RGB image data into YUV image data; Acquire third image information of the YUV image data, and perform image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; The target image data is converted into a target format, and the target image data of the target object is output in the target format.

[0135] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0136] 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, but not limited to, 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).

[0137] 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.

[0138] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0139] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0140] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0142] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0143] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An image processing method, characterized in that: include: Collecting raw image data of the target object; Acquire first image information of the original image data, perform initial correction on the original image data based on the first image information, and convert the original image data after the initial correction into RGB image data; Acquire second image information of the RGB image data, perform color correction on the RGB image data based on the second image information, and convert the color-corrected RGB image data into YUV image data; Acquire third image information of the YUV image data, and perform image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; The target image data is converted into a target format, and the target image data of the target object is output in the target format.

2. The image processing method according to claim 1, characterized in that: The acquiring first image information of the original image data and performing initial correction on the original image data based on the first image information includes: Determine a plurality of brightness partitions, and calculate a gain response and an offset corresponding to each of the brightness partitions; Determine a correction model corresponding to each brightness partition based on the brightness partitions and the gain response and the offset corresponding to each brightness partition, and correct each pixel in the original image data based on the correction model; Based on each pixel point in the original image data, determining a pixel texture area to be processed and a first texture replacement search area corresponding to each pixel point; The first texture replacement search area is divided into a plurality of second texture replacement search areas, and filtering is performed on the pixel texture area to be processed based on the second texture replacement search areas.

3. The image processing method according to claim 2, characterized in that: The calculating the gain response and the offset corresponding to each brightness partition includes: For each brightness partition, calculating a first brightness average of brightness high points and a second brightness average of brightness low points in the brightness partition; Determine the gain response corresponding to the brightness partition based on the first brightness mean value and the second brightness low point mean value; The offset corresponding to the brightness partition is determined based on the second brightness low point average and the gain response.

4. The image processing method according to claim 2, characterized in that: The step of determining, based on each pixel point in the original image data, a pixel texture region to be processed and a first texture replacement search region corresponding to each pixel point includes: Traversing each pixel point in the original image data; For each of the pixel points, the pixel texture area to be processed and the first texture replacement search area are determined with the pixel point as the center; wherein the first texture replacement search area is larger than the pixel texture area to be processed; The filtering process of the pixel texture area to be processed based on the second texture replacement search area includes: For each of the second texture replacement search areas, calculating a weight coefficient between the second texture replacement search area and the pixel texture area to be processed; The pixel values ​​of the pixel texture area to be processed are updated based on the weight coefficient.

5. The image processing method according to claim 2, characterized in that: The step of acquiring second image information of the RGB image data and performing color correction on the RGB image data based on the second image information includes: Acquire color information of the RGB image data, and determine deviation information between the color information and a standard color; A color correction matrix is ​​determined based on the deviation information, and color correction is performed on the RGB image data based on the color correction matrix.

6. The image processing method according to claim 5, characterized in that: The step of acquiring the third image information of the YUV image data and performing image enhancement processing on the YUV image data based on the third image information includes: Acquire histogram parameters of the YUV image data, and correct the histogram parameters; Performing fusion processing based on the corrected histogram parameters of the YUV image data and the histogram parameters of the historical image frame; Acquire a Y component of the YUV image data, and enhance the contrast of the YUV image data based on the Y component; Determine a target template, and determine an active window based on the target template; wherein the target template is a convolution kernel; The YUV image data is traversed based on the active window, and the pixel values ​​of the pixels in the active window are updated based on the target template.

7. An image processing system, characterized in that: The image processing system includes an image acquisition module, a signal conversion module, an image processing module and an image output module; wherein: The image acquisition module is used to acquire the optical signal of the original image data of the target object and transmit the optical signal to the signal conversion module; The signal conversion module is used to receive the optical signal through the head plate; convert the optical signal into an electrical signal and output it as raw image data; and transmit the raw image data to the image processing module; The image processing module is used to perform image processing on the electrical signal of the original image data based on the FPGA; wherein the image processing includes: acquiring first image information of the original image data, performing initial correction on the original image data based on the first image information, and converting the original image data after the initial correction into RGB image data; acquiring second image information of the RGB image data, performing color correction on the RGB image data based on the second image information, and converting the RGB image data after the color correction into YUV image data; acquiring third image information of the YUV image data, performing image enhancement processing on the YUV image data based on the third image information, and obtaining target image data of the target object; The image output module is used to convert the target image data into a target format through an interface board, and output the target image data of the target object in the target format.

8. An image processing device, characterized in that: include: An image acquisition module, used to acquire original image data of a target object; An image processing module, used for acquiring first image information of the original image data, performing initial correction on the original image data based on the first image information, and converting the original image data after the initial correction into RGB image data; The image processing module is further used to obtain second image information of the RGB image data, perform color correction on the RGB image data based on the second image information, and convert the color-corrected RGB image data into YUV image data; The image processing module is further used to obtain third image information of the YUV image data, and perform image enhancement processing on the YUV image data based on the third image information to obtain target image data of the target object; The image output module is used to convert the target image data into a target format and output the target image data of the target object in the target format.

9. An electronic device, comprising: processor; and a memory storing a program, wherein the program comprises instructions, and the instructions are used to cause the processor to execute the method according to any one of claims 1-6.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images