Image processing method and system for bit width mapping adjustment based on feedback

Abstract

The application discloses an image processing method based on feedback for bit width mapping adjustment, and belongs to the field of image processing. The method comprises the following steps: an image signal processor determines the gray scale precision required by the brightness of different regions of a medium bit width image according to the image region of interest fed back by a perception model and the corresponding brightness level of the image region of interest in the medium bit width image, and generates bit width mapping feedback information for the bit width mapping logic feedback according to the gray scale precision required by the brightness of different regions of the medium bit width image; and the bit width mapping logic adjusts the mapping relationship between a high bit width image and the medium bit width image according to the bit width mapping feedback information, so that the brightness of the image region of interest has high gray scale precision. According to the bit width mapping feedback information fed back by the image signal processor, the bit width mapping is configured for the image processing procedure, so that the perception model can better identify the target in the processed image.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an image processing method and system for adjusting bit width mapping based on feedback. Background Technology

[0002] Because the dynamic range of the images output by the image sensors in the onboard cameras of autonomous vehicles is relatively high, the ISP (Image Signal Processor) will compress part of the dynamic range, inevitably resulting in a loss of dynamic range, which is also a loss of contrast.

[0003] To address the issue of dynamic range loss, different perceptual models may focus on different aspects. Some models might focus on brighter targets in the image, while others might focus on darker targets. Even after all images are processed by the same image signal processor, it's impossible to achieve the ideal image state for each perceptual model's specific target. Furthermore, if the target itself in the image doesn't appear ideal, it will also affect the recognition performance of the perceptual model. Summary of the Invention

[0004] To address the problem that existing technologies cannot select appropriate image processing flows to adapt to different needs of perception models, this application mainly provides an image processing method based on feedback for bit-width mapping adjustment.

[0005] One technical solution adopted in this application is: providing an image processing method and system for bit-width mapping adjustment based on feedback, which includes:

[0006] The bit-width mapping logic maps the high bit-width image acquired by the image sensor to the medium bit-width image required by the image signal processor.

[0007] The image signal processor calculates the brightness level of the mid-width image in blocks and transforms the mid-width image into a low-width RGB image.

[0008] The perception model is used to identify low-bit-width RGB images and determine the region of interest.

[0009] The image signal processor, based on the region of interest (ROI) fed back from the perceptual model and the corresponding brightness level of the ROI in the median-width image, determines the required grayscale accuracy for the brightness of different regions in the median-width image.

[0010] Based on the required grayscale accuracy for brightness in different regions of the mid-width image, bit-width mapping feedback information is generated for the bit-width mapping logic feedback; and

[0011] The bit-width mapping logic adjusts the mapping relationship between the high-bit-width image and the medium-bit-width image based on the bit-width mapping feedback information, so that the brightness of the region of interest has high grayscale accuracy.

[0012] Another technical solution adopted in this application is: providing an image processing system for bit-width mapping adjustment based on feedback, which includes bit-width mapping logic, an image signal processor, and a perceptual model, wherein:

[0013] The bit-width mapping logic maps the high bit-width image acquired by the image sensor to the medium bit-width image required by the image signal processor.

[0014] The image signal processor calculates the brightness level of the mid-width image in blocks and transforms the mid-width image into a low-width RGB image.

[0015] The perception model is used to identify low-bit-width RGB images and determine the region of interest.

[0016] The image signal processor, based on the region of interest (ROI) fed back from the perceptual model and the corresponding brightness level of the ROI in the median-width image, determines the required grayscale accuracy for the brightness of different regions in the median-width image.

[0017] Based on the required grayscale accuracy for brightness in different regions of the mid-width image, bit-width mapping feedback information is generated for the bit-width mapping logic feedback; and

[0018] The bit-width mapping logic adjusts the mapping relationship between the high-bit-width image and the medium-bit-width image based on the bit-width mapping feedback information, so that the brightness of the region of interest has high grayscale accuracy.

[0019] Another technical solution adopted in this application is to provide a computer-readable storage medium storing computer instructions that are operated to execute the image processing method for bit-width mapping adjustment based on feedback in Solution 1.

[0020] Another technical solution adopted in this application is: providing a computer device, which includes a processor and a memory, the memory storing computer instructions, which are operated to execute the image processing method based on feedback for bit-width mapping adjustment in Solution 1.

[0021] The beneficial effects of the technical solution of this application are as follows: This application designs an image processing method and system based on feedback for bit-width mapping adjustment. Based on the bit-width mapping feedback information from the image signal processor, this application configures a bit-width mapping function for the image processing flow of the image signal processor, preprocesses the image, and enables the perception model to better identify targets in the preprocessed image. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of a specific implementation of an image processing method for bit-width mapping adjustment based on feedback, as described in this application.

[0024] Figure 2 This is a schematic diagram of a specific implementation of an image processing system based on feedback for bit-width mapping adjustment according to this application.

[0025] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0026] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0027] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0028] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0029] Figure 1 This illustration shows a specific implementation of an image processing method based on feedback for bit-width mapping adjustment, as proposed in this application. Figure 1 In the specific implementation shown, the image processing method for adjusting bit width mapping based on feedback includes:

[0030] Step S101: The high bit-width image acquired by the image sensor is mapped to the medium bit-width image required by the image signal processor by the bit-width mapping logic.

[0031] In this embodiment, the original image output from the image sensor in the vehicle camera has a high bit width dynamic range, which is beneficial for algorithm recognition. However, the high bit width results in an excessive amount of data that cannot be processed. Therefore, it is necessary to compress the dynamic range of the bit width of the original image with a high bit width dynamic range according to the bit width mapping logic.

[0032] In a specific example of this application, the image sensor in the automotive camera is a photoelectric conversion device. Each pixel senses light, and after sensing, the images are stitched together to form a high-bit-width image. However, the bit width differs somewhat from that of images generated by general positive and negative electrons because automotive image sensors require high dynamic range scenes and simultaneous exposure as much as possible; otherwise, there will be some moving images, which must be avoided as much as possible in automotive applications. After different exposures, the images are first stitched together to form a high dynamic range (HDR) image. The pixels of the image are represented by 24 bits, resulting in a relatively wide bit width.

[0033] It's important to note that High Dynamic Range (HDR) images, compared to ordinary images, offer greater dynamic range and image detail. They are synthesized by combining LDR (Low Dynamic Range) images with varying exposure times, utilizing the LDR images with the best detail corresponding to each exposure time. This results in a more accurate representation of the visual effects in the real-world environment.

[0034] exist Figure 1 In the specific implementation shown, the image processing method for adjusting bit width mapping based on feedback further includes:

[0035] In step S102, the image signal processor calculates the brightness level of the mid-width image in blocks and converts the mid-width image into a low-width RGB image.

[0036] In this embodiment, the image signal processor divides the median-width image into a preset number of blocks, calculates and obtains the brightness value of each block, and thus obtains the brightness level of the median-width image, identifying the current brightness scene. By statistically analyzing the brightness values ​​of each block in the median-width image, the current brightness scene can be identified, which is beneficial for accurately adjusting the median-width image by block division.

[0037] In an optional embodiment of this application, the image signal processor calculates the brightness level of the mid-bit-width image in blocks, including: dividing the high-bit-width image into a preset number of blocks, calculating the weighted average brightness of the pixels in each block, and obtaining the brightness level of each block.

[0038] In this embodiment, the image signal processor divides the median-width image into a preset number of blocks, calculates and obtains the brightness value of each block, i.e., the weighted average of the brightness of the pixels, and then obtains the brightness level of the median-width image.

[0039] In one optional embodiment of this application, the image signal processor calculates the brightness level of the medium bit-width image in blocks, including: determining the brightness scene corresponding to the high bit-width image based on the brightness level of each block.

[0040] In this embodiment, by statistically analyzing the brightness values ​​of each patch in the median-width image, the current brightness scene of the median-width image can be identified, thus determining whether the current brightness scene of the median-width image is a daytime scene or a nighttime scene. This allows for a comprehensive grasp of the macroscopic information of the image.

[0041] In a specific example of this application, the median-width image is divided into a preset number of blocks. The weighted average brightness of each block is calculated to obtain its brightness value. The brightness values ​​corresponding to each block in the median-width image are statistically analyzed to obtain brightness statistics. Based on the relationship between the brightness statistics and a first brightness threshold and a second brightness threshold, the current brightness scene in the median-width image is identified. According to the relationship between the brightness statistics and the first and second brightness thresholds, the image signal processor performs mode adjustment on the median-width image to identify the current brightness scene. The image signal processor has a daytime mode and a nighttime mode, switching between modes on the acquired median-width image to make the brightness scene in the median-width image easier to identify.

[0042] For example, when the luminance statistics value is greater than or equal to a first luminance threshold, the Image Signal Processor (ISP) adjusts the median-width image using daytime mode, identifying the current luminance scene as a high-luminance scene. When the luminance statistics value is less than or equal to a second luminance threshold, the ISP adjusts the median-width image using nighttime mode, identifying the current luminance scene as a low-luminance scene. Distinguishing luminance scenes in the median-width image based on daytime and nighttime mode adjustments in the ISP helps the perception model identify the luminance scene of the original image.

[0043] In a specific example of this application, the image signal processor (ISP) has a day mode and a night mode. When switching between day mode and night mode, there are two switching points: one is the switching point from low brightness to high brightness, and the other is the switching point from high brightness to low brightness, forming a Schmitt trigger to prevent the image from jumping back and forth between these two modes. For example, when the brightness is approximately 200 lux, it switches to day mode; when it is below 50 lux, it switches to night mode.

[0044] It should be noted that the first and second brightness thresholds are determined based on the vehicle's requirements during autonomous driving. The brightness thresholds are fine-tuned during debugging and are not fixed; their range depends on the vehicle's driving needs.

[0045] exist Figure 1 In the specific implementation shown, the image processing method for adjusting bit width mapping based on feedback further includes:

[0046] Step S103: The perception model identifies the low-bit-width RGB image and determines the region of interest.

[0047] In this embodiment, the perception model can detect and identify targets in the low-bit-width RGB image from the image signal processor, determine the region of interest in the low-bit-width RGB image, and facilitate the perception model to feed back to the image signal processor.

[0048] exist Figure 1 In the specific implementation shown, the image processing method for adjusting bit width mapping based on feedback further includes:

[0049] In step S104, the image signal processor determines the required grayscale accuracy for the brightness of different regions of the medium-width image based on the region of interest fed back by the perception model and the brightness level of the region of interest in the medium-width image. Based on the required grayscale accuracy for the brightness of different regions of the medium-width image, it generates bit-width mapping feedback information for the bit-width mapping logic feedback.

[0050] In this embodiment, the bit-width mapping feedback information includes the grayscale precision of each patch in the mid-bit-width image. Based on the brightness level of the region of interest in the image signal processor corresponding to the mid-bit-width image in the image signal processor, the grayscale precision is determined and bit-width mapping feedback information is generated. The image signal processor then generates a mapping function based on the generated bit-width mapping feedback information, which can both preserve the details of the dark areas in the original image and ensure that the entire image is not overexposed.

[0051] In a specific example of this application, in a relatively dark scene, there is no streetlight illumination on the left side of the image, but streetlight illumination on the right side. This is equivalent to the original image being darker on the left and brighter on the right. To see the image details of the darker scene on the left, it's desirable to preserve the lower bit width. The brighter part on the right might contain objects like car lights, streetlights, or traffic lights, ensuring that the lights themselves are not overexposed. When a traffic light is overexposed, its color information will be somewhat lost; for example, a red light will turn yellow, and a yellow light will turn white. At this time, the darker information on the left may also be lost due to overexposure.

[0052] In a specific example of this application, this scheme can adjust the grayscale precision of the brightness of each patch in a medium-width image according to the region of interest through a mapping function, thereby obtaining a compressed RGB image with a low bit width. This RGB image is then input into a perceptual model for subsequent perceptual processing. Grayscale precision refers to the precision represented by brightness. A low-bit-width RGB image refers to an 8-bit image for each of the R, G, and B pixels.

[0053] It should be noted that, depending on the mapping function, the precision of the retained brightness positions will be different, and the retained bit width will also be different.

[0054] In an optional embodiment of this application, the image signal processor determines the required grayscale accuracy for the brightness of different regions of the median-width image based on the region of interest fed back by the perception model and the brightness level corresponding to the region of interest in the median-width image. This includes determining the grayscale accuracy based on the region of interest, the brightness level corresponding to the region of interest in the median-width image, and the brightness scene.

[0055] In this embodiment, based on the correspondence between the brightness level and brightness scene in the region of interest and the brightness level and brightness scene in the median bit-width image, the grayscale precision of each patch in the median bit-width image is adjusted. In the median bit-width image, the grayscale precision of the patch corresponding to the region of interest is increased, while the grayscale precision of other patches is decreased. Overall, the amount of data contained in the original image is reduced, resulting in a smaller bit width, thereby achieving the purpose of bit-width mapping.

[0056] In one optional embodiment of this application, bit-width mapping feedback information is generated based on the grayscale accuracy required for the brightness of different regions of the mid-width image, including: generating bit-width mapping feedback information based on grayscale accuracy and brightness scene.

[0057] In this embodiment, the grayscale accuracy of the brightness is determined based on the current brightness scene.

[0058] exist Figure 1 In the specific implementation shown, the image processing method for adjusting bit width mapping based on feedback further includes:

[0059] Step S105: The bit-width mapping logic adjusts the mapping relationship between the high bit-width image and the medium bit-width image based on the bit-width mapping feedback information, so that the brightness of the region of interest has high grayscale accuracy.

[0060] In this embodiment, the mapping relationship between the high bit-width image and the medium bit-width image is adjusted based on the bit-width mapping feedback information, making it easier for the perception model to identify the region of interest in the image.

[0061] In one optional embodiment of this application, the bit-width mapping logic adjusts the mapping relationship between the high-bit-width image and the mid-bit-width image based on the bit-width mapping feedback information. This includes: when the brightness of the region of interest is low, the bit-width mapping feedback information instructs the bit-width mapping logic to cut off one or more consecutive bits starting from the highest bit of the high-bit-width image to obtain the mid-bit-width image; or when the brightness of the region of interest is high, the bit-width mapping feedback information instructs the bit-width mapping logic to cut off one or more consecutive bits starting from the lowest bit of the high-bit-width image to obtain the mid-bit-width image.

[0062] In this embodiment, based on the bit-width mapping feedback information, a medium bit-width image is obtained by directly cutting bits from a high bit-width image. Bit cutting can only cut low bits or high bits. Bit cutting is used to perform bit-width mapping to preserve the details of targets with relatively low pixel values ​​in the high bit-width image as much as possible.

[0063] In an optional embodiment of this application, the bit-width mapping logic adjusts the mapping relationship between the high bit-width image and the medium bit-width image based on the bit-width mapping feedback information. This includes: when the brightness of the region of interest contains multiple brightness levels, the bit-width mapping feedback information instructs the bit-width mapping logic to obtain the medium bit-width image using all bits of the high bit-width image according to the bit-width mapping function specified by the image signal processor.

[0064] In this embodiment, according to the mapping relationship in the bit-width mapping function specified by the image signal processor, the high bit-width image is used as the input of the bit-width mapping function to obtain the input of the bit-width mapping function, namely the medium bit-width image.

[0065] In a specific example of this application, the image signal processor uses a mapping function to adjust the grayscale accuracy of the brightness of the patch corresponding to the region of interest in the median-width image to a high-precision range; and adjusts the grayscale accuracy of the brightness of other patches in the median-width image to a low-precision range, wherein the high-precision range is greater than the low-precision range.

[0066] Figure 2 This illustration shows a specific implementation of an image processing system based on feedback for bit-width mapping adjustment, as described in this application. Figure 2 In the specific implementation shown, the image processing system for bit-width mapping adjustment based on feedback mainly includes:

[0067] Module 201 is a bit-wide mapping logic, module 202 is an image signal processor, and module 203 is a perception model, wherein:

[0068] The high-bit-width image acquired by the image sensor is mapped to the medium-bit-width image required by the image signal processor by the bit-width mapping logic of module 201.

[0069] The image signal processor module 202 calculates the brightness level of the mid-width image in blocks and converts the mid-width image into a low-width RGB image.

[0070] The perception model of module 203 identifies the low bit-width RGB image and determines the region of interest.

[0071] The image signal processor in module 202 determines the required grayscale accuracy for different regions of the mid-width image based on the region of interest fed back from the perception model and the corresponding brightness level of the region of interest in the mid-width image. Furthermore, based on the required grayscale accuracy for different regions of the mid-width image, it generates bit-width mapping feedback information for the bit-width mapping logic feedback.

[0072] The bit-width mapping logic of module 201 adjusts the mapping relationship between the high bit-width image and the medium bit-width image based on the bit-width mapping feedback information, so that the brightness of the region of interest has high grayscale accuracy.

[0073] In this embodiment, based on the feedback mechanism, the bit width mapping feedback information provided by the image signal processor is made more suitable for the brightness scene of the current frame image. The grayscale accuracy of different regions of the image is adjusted in blocks by the bit width mapping feedback information, so that the output image has a better effect and is easier for the perception model to perform image perception.

[0074] In an optional embodiment of this application, the image signal processor calculates the brightness level of the mid-bit-width image in blocks, including: dividing the high-bit-width image into a preset number of blocks, calculating the weighted average brightness of the pixels in each block, and obtaining the brightness level of each block.

[0075] In this embodiment, the image signal processor divides the median-width image into a preset number of blocks, calculates and obtains the brightness value of each block, i.e., the weighted average of the brightness of the pixels, and then obtains the brightness level of the median-width image.

[0076] In one optional embodiment of this application, the image signal processor calculates the brightness level of the medium bit-width image in blocks, including: determining the brightness scene corresponding to the high bit-width image based on the brightness level of each block.

[0077] In this embodiment, by statistically analyzing the brightness values ​​of each patch in the median-width image, the current brightness scene of the median-width image can be identified, thus determining whether the current brightness scene of the median-width image is a daytime scene or a nighttime scene. This allows for a comprehensive grasp of the macroscopic information of the image.

[0078] In an optional embodiment of this application, the image signal processor determines the required grayscale accuracy for the brightness of different regions of the median-width image based on the region of interest fed back by the perception model and the brightness level corresponding to the region of interest in the median-width image. This includes determining the grayscale accuracy based on the region of interest, the brightness level corresponding to the region of interest in the median-width image, and the brightness scene.

[0079] In this embodiment, based on the correspondence between the brightness level and brightness scene in the region of interest and the brightness level and brightness scene in the median bit-width image, the grayscale precision of each patch in the median bit-width image is adjusted. In the median bit-width image, the grayscale precision of the patch corresponding to the region of interest is increased, while the grayscale precision of other patches is decreased. Overall, the amount of data contained in the original image is reduced, resulting in a smaller bit width, thereby achieving the purpose of bit-width mapping.

[0080] In one optional embodiment of this application, bit-width mapping feedback information is generated based on the grayscale accuracy required for the brightness of different regions of the mid-width image, including: generating bit-width mapping feedback information based on grayscale accuracy and brightness scene.

[0081] In this embodiment, the grayscale accuracy of the brightness is determined based on the current brightness scene.

[0082] In one optional embodiment of this application, the bit-width mapping logic adjusts the mapping relationship between the high-bit-width image and the mid-bit-width image based on the bit-width mapping feedback information. This includes: when the brightness of the region of interest is low, the bit-width mapping feedback information instructs the bit-width mapping logic to cut off one or more consecutive bits starting from the highest bit of the high-bit-width image to obtain the mid-bit-width image; or when the brightness of the region of interest is high, the bit-width mapping feedback information instructs the bit-width mapping logic to cut off one or more consecutive bits starting from the lowest bit of the high-bit-width image to obtain the mid-bit-width image.

[0083] In this embodiment, based on the bit-width mapping feedback information, a medium bit-width image is obtained by directly cutting bits from a high bit-width image. Bit cutting can only cut low bits or high bits. Bit cutting is used to perform bit-width mapping to preserve the details of targets with relatively low pixel values ​​in the high bit-width image as much as possible.

[0084] In an optional embodiment of this application, the bit-width mapping logic adjusts the mapping relationship between the high bit-width image and the medium bit-width image based on the bit-width mapping feedback information. This includes: when the brightness of the region of interest contains multiple brightness levels, the bit-width mapping feedback information instructs the bit-width mapping logic to obtain the medium bit-width image using all bits of the high bit-width image according to the bit-width mapping function specified by the image signal processor.

[0085] In this embodiment, according to the mapping relationship in the bit-width mapping function specified by the image signal processor, the high bit-width image is used as the input of the bit-width mapping function to obtain the output of the bit-width mapping function, namely the medium bit-width image.

[0086] The image processing system for bit-width mapping adjustment based on feedback provided in this application can be used to execute the image processing method for bit-width mapping adjustment based on feedback described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0087] In one specific embodiment of this application, each functional module in the image processing system for bit-width mapping adjustment based on feedback can be directly in hardware, in a software module executed by a processor, or in a combination of both.

[0088] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0089] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0090] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores computer instructions that are operated to perform the image processing method for bit-width mapping adjustment based on feedback in any embodiment.

[0091] In another specific embodiment of this application, a computer device includes a processor and a memory, the memory storing computer instructions that are operated to perform the image processing method for bit-width mapping adjustment based on feedback in any embodiment.

[0092] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An image processing method for bit-width mapping adjustment based on feedback, characterized in that, include: The bit-width mapping logic maps the high bit-width image acquired by the image sensor to the medium bit-width image required by the image signal processor. The image signal processor calculates the brightness level of the median-width image in blocks and converts the median-width image into a low-width RGB image. The perceptual model is used to identify the low-bit-width RGB image and determine the region of interest. The image signal processor, based on the region of interest fed back by the perception model and the corresponding brightness level of the region of interest in the median width image, determines the required grayscale accuracy for the brightness of different regions of the median width image, and... Based on the grayscale accuracy required for the brightness of different regions of the mid-width image, bit-width mapping feedback information is generated for the bit-width mapping logic feedback. as well as The bit-width mapping logic adjusts the mapping relationship between the high-bit-width image and the mid-bit-width image based on the bit-width mapping feedback information, so that the brightness of the region of interest has high grayscale accuracy. The adjustment of the mapping relationship between the high-bit-width image and the mid-bit-width image by the bit-width mapping logic based on the bit-width mapping feedback information includes: When the brightness of the regions of interest is all at low levels, the bit-width mapping feedback information instructs the bit-width mapping logic to remove one or more consecutive bits starting from the highest bit of the high-bit-width image to obtain the medium-bit-width image; or When the brightness of the regions of interest is all at a high brightness level, the bit width mapping feedback information instructs the bit width mapping logic to cut off one or more consecutive bits starting from the least significant bit of the high bit width image to obtain the medium bit width image.

2. The image processing method for bit-width mapping adjustment based on feedback as described in claim 1, characterized in that, The step of adjusting the mapping relationship between the high-bit-width image and the mid-bit-width image by the bit-width mapping logic based on the bit-width mapping feedback information includes: When the brightness of the region of interest contains multiple brightness levels, the bit-width mapping feedback information instructs the bit-width mapping logic to obtain the medium bit-width image using all bits of the high bit-width image, according to the bit-width mapping function specified by the image signal processor.

3. The image processing method for bit-width mapping adjustment based on feedback as described in claim 1, characterized in that, The step of calculating the brightness level of the median-width image in blocks by the image signal processor includes: The median-width image is divided into a preset number of blocks, and the weighted average brightness of the pixels in each block is calculated to obtain the brightness level of each block.

4. The image processing method for bit-width mapping adjustment based on feedback as described in claim 3, characterized in that, The step of calculating the brightness level of the median-width image in blocks by the image signal processor includes: The brightness scene corresponding to the median width image is determined based on the brightness level of each of the image blocks.

5. The image processing method for bit-width mapping adjustment based on feedback as described in claim 4, characterized in that, The image signal processor determines the required grayscale accuracy for the brightness of different regions of the median-width image based on the region of interest fed back by the perceptual model and the brightness level corresponding to the region of interest in the median-width image, including: The grayscale accuracy is determined based on the region of interest, the brightness level corresponding to the region of interest in the median width image, and the brightness scene.

6. The image processing method for bit-width mapping adjustment based on feedback as described in claim 4, characterized in that, The step of generating bit-width mapping feedback information for the bit-width mapping logic feedback based on the required grayscale accuracy of different regions of the mid-width image includes: The bit-width mapping feedback information is generated based on the grayscale accuracy and the brightness scene.

7. An image processing system for bit-width mapping adjustment based on feedback, comprising bit-width mapping logic, an image signal processor, and a perceptual model, characterized in that: The bit-width mapping logic maps the high bit-width image acquired by the image sensor to the medium bit-width image required by the image signal processor. The image signal processor calculates the brightness level of the median-width image in blocks and converts the median-width image into a low-width RGB image. The perception model is used to identify the low-bit-width RGB image and determine the region of interest. The image signal processor, based on the region of interest fed back by the perception model and the corresponding brightness level of the region of interest in the median width image, determines the required grayscale accuracy for the brightness of different regions of the median width image, and... Based on the grayscale accuracy required for the brightness of different regions of the mid-width image, bit-width mapping feedback information is generated for the bit-width mapping logic feedback. as well as The bit-width mapping logic adjusts the mapping relationship between the high-bit-width image and the medium-bit-width image based on the bit-width mapping feedback information, so that the brightness of the region of interest has high grayscale accuracy. The adjustment includes: when the brightness of the region of interest is at a low level, the bit-width mapping feedback information instructs the bit-width mapping logic to remove one or more consecutive bits from the highest bit of the high-bit-width image to obtain the medium-bit-width image; or when the brightness of the region of interest is at a high level, the bit-width mapping feedback information instructs the bit-width mapping logic to remove one or more consecutive bits from the lowest bit of the high-bit-width image to obtain the medium-bit-width image.

8. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are operated to perform the image processing method for bit-width mapping adjustment based on feedback, as described in any one of claims 1-6.

9. A computer device comprising a processor and a memory storing computer instructions, wherein the processor operates the computer instructions to perform the image processing method for feedback-based bit-width mapping adjustment as described in any one of claims 1-6.

Images