CN116416146A - Image processing method and system for parameter adjustment based on direct feedback - Google Patents
Image processing method and system for parameter adjustment based on direct feedback Download PDFInfo
- Publication number
- CN116416146A CN116416146A CN202111658047.3A CN202111658047A CN116416146A CN 116416146 A CN116416146 A CN 116416146A CN 202111658047 A CN202111658047 A CN 202111658047A CN 116416146 A CN116416146 A CN 116416146A
- Authority
- CN
- China
- Prior art keywords
- image
- width
- bit
- signal processor
- image signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 230000008447 perception Effects 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000013507 mapping Methods 0.000 claims description 66
- 238000012937 correction Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 7
- 230000000903 blocking effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 206010034960 Photophobia Diseases 0.000 description 1
- 206010070834 Sensitisation Diseases 0.000 description 1
- 238000003705 background correction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 208000013469 light sensitivity Diseases 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008313 sensitization Effects 0.000 description 1
Images
Classifications
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses an image processing method for parameter adjustment based on direct feedback, and belongs to the field of image processing. The method comprises the steps of receiving and identifying a low-bit-width RGB image by a perception model, determining an interested image area, and generating image signal processor parameter adjustment feedback information which is fed back to an image signal processor and contains relevant information of the interested image area; the image signal processor adjusts the parameters of the image signal processor according to the image signal processor parameters and feeds back information, so that the image region of interest corresponding to the obtained low-bit-width RGB image after the processing of the image signal processor has the characteristics required by the perception model; and identifying the low-bit-width RGB image by a perception model. The perception model can directly perceive the information in the image, and feed back corresponding parameters configured on the processing flow of the image signal processor by the corresponding information, so that the processed image meets the requirements of the perception model.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to an image processing method and system for parameter adjustment based on direct feedback.
Background
Since the dynamic range of the bit width of the image output from the image sensor in the in-vehicle camera is relatively high in the automatic driving, ISP (image signal processor) compresses a part of the dynamic range, and thus, a loss of a part of the dynamic range, that is, a loss of contrast, is unavoidable.
For the problem of dynamic range loss, the focus of different perception models may be different, some may focus on brighter objects in the image, and some may focus on darker objects in the image. After all images are processed by the same image signal processor, there is no way to satisfy that various perception models achieve ideal image states for their respective targets of interest. In the case that the performance of the target itself in the image is not very ideal, the effect of the recognition of the perception model is also affected.
Disclosure of Invention
Aiming at the problem that the corresponding image processing flow cannot be selected to adapt to different requirements of a perception model in the prior art, the application mainly provides an image processing method and an image processing system for parameter adjustment based on direct feedback.
The application adopts a technical scheme that: there is provided an image processing method for parameter adjustment based on direct feedback, comprising:
the bit width mapping logic maps the high bit width image acquired by the image sensor into a medium bit width image required to be input by the image signal processor;
processing the medium-width image by an image signal processor, and converting the medium-width image into a low-width RGB image;
receiving and identifying a low-bit-width RGB image by a perception model, determining an image region of interest, and generating image signal processor parameter adjustment feedback information which is fed back to an image signal processor and contains information related to the image region of interest;
the image signal processor adjusts the parameters of the image signal processor according to the image signal processor parameters and feeds back information, so that the image region of interest corresponding to the obtained low-bit-width RGB image after the processing of the image signal processor has the characteristics required by the perception model; and
and identifying the low-bit-width RGB image by a perception model.
The other technical scheme adopted by the application is as follows: there is provided an image processing system for parameter adjustment based on direct feedback, comprising bit width mapping logic, an image signal processor, and a perceptual model, wherein:
the bit width mapping logic maps the high bit width image acquired by the image sensor into a medium bit width image required to be input by the image signal processor;
processing the medium-width image by an image signal processor, and converting the medium-width image into a low-width RGB image;
receiving and identifying a low-bit-width RGB image by a perception model, determining an image region of interest, and generating image signal processor parameter adjustment feedback information which is fed back to an image signal processor and contains information related to the image region of interest;
the image signal processor adjusts the parameters of the image signal processor according to the image signal processor parameters and feeds back information, so that the image region of interest corresponding to the obtained low-bit-width RGB image after the processing of the image signal processor has the characteristics required by the perception model; and
and identifying the low-bit-width RGB image by a perception model.
The other technical scheme adopted by the application is as follows: a computer readable storage medium is provided that stores computer instructions operable to perform the image processing method of scheme one that performs parameter adjustment based on direct feedback.
The other technical scheme adopted by the application is as follows: there is provided a computer device comprising a processor and a memory storing computer instructions operable to perform the method of image processing of parameter adjustment based on direct feedback in scheme one.
The beneficial effect that this application's technical scheme can reach is: the application designs an image processing method and system for parameter adjustment based on direct feedback. The perception model in the application reversely configures corresponding parameters for the processing flow of the image signal processor by directly perceiving the information in the original image, and processes the image by the configured parameters, so that the perception model can better identify the target in the processed image.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings that are needed in the embodiments or the prior art descriptions, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic diagram of one embodiment of an image processing method for parameter adjustment based on direct feedback in accordance with the present application;
FIG. 2 is a schematic diagram of one embodiment of an image processing system for parameter adjustment based on direct feedback.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
The preferred embodiments of the present application will be described in detail below with reference to the drawings so that the advantages and features of the present application can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present application.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 shows a specific embodiment of an image processing method for parameter adjustment based on direct feedback according to the present application. In the embodiment shown in fig. 1, the image processing method for parameter adjustment based on direct feedback includes:
in step S101, the bit width mapping logic maps the high bit width image acquired by the image sensor to the medium bit width image required to be input by the image signal processor.
In this embodiment, the original image output from the image sensor in the in-vehicle camera has a high bit width dynamic range, and although the algorithm recognition is facilitated, the bit width is too high to cause the data amount to be too large to be handled, so that the dynamic range of the original image bit width having the bit width high dynamic range needs to be compressed according to the bit width mapping logic.
The method can also directly input the original image acquired by the image sensor in the vehicle-mounted camera into the perception model. The original image obtained is input into a perception model without the processing flow of the image signal processor, and the perception model perceives the original image and finally feeds back perception information to decide to modify specific parameters in the image signal processor.
In one embodiment of the present application, the bit width of the original image is determined by the image signal processor, and if the bit width of the original image is not greater than the ISP allowable bit width, the original image is directly input into the perception model; if the bit width of the original image is larger than the allowable bit width, the original image is a high-bit-width dynamic image, and the image signal processor is utilized to carry out bit width mapping on the high-bit-width dynamic image. The perceptual model is ensured to bear a certain range of data quantity, and an image signal processor is required to judge the bit width of an original image. If the bit width of the original image is not larger than the ISP allowed bit width, the original image is directly input into a perception model, and the perception model perceives the original image and is used as a basis for controlling specific parameters in an image signal processor.
In the specific embodiment shown in fig. 1, the image processing method for performing parameter adjustment based on direct feedback further includes:
step S102, the image signal processor processes the middle-width image and converts the middle-width image into a low-width RGB image.
In this embodiment, in the image signal processor, the middle-width image is processed by each parameter, and the middle-width image is converted into the low-width RGB image, so that the perception model can better perceive the target in the image.
In an alternative embodiment of the present application, processing, by an image signal processor, a medium-width image includes: the method comprises the steps of sequentially performing white balance processing, tone mapping processing, demosaicing processing and gamma correction processing on a bit-width image, wherein parameters of an image signal processor comprise white balance parameters, tone mapping parameters, demosaicing parameters and/or gamma correction parameters.
In this embodiment, the parameter processing of the Image Signal Processor (ISP) includes, but is not limited to, black level correction (black level compensation), lens correction (lens shading correction), bad pixel correction (bad pixel correction), color interpolation (demosaic), bayer noise removal (Bayer noise) white balance (AWB) correction, color correction (color correction), and gamma (gamma) correction. This results in a better image effect.
In one embodiment of the present application, each pixel within the image sensor is a photodiode, which in a fully dark condition has its output which is actually turned out at the time of analog to digital conversion. Instead of the value of the actual photodiode output, the perception model only needs the data of the linear relation of the brightness corresponding to the photodiode. And correcting (bad pixel correction) bad pixels, wherein the bad pixels are white points in the output image in a full black environment, and are black points in the output image in a high bright environment. Gamma correction is a nonlinear operation performed on the gray values of an input image, so that the gray values of the output image and the gray values of the input image are in an exponential relationship, and human eyes do not have a linear relationship with the light sensitivity of an external light source and the input light intensity, but have an exponential relationship. Under low illumination, the human eyes can more easily distinguish the change of the brightness, and with the increase of the illumination, the human eyes cannot easily distinguish the change of the brightness. The sensitization of the camera and the input light intensity are in linear relation, and in order to facilitate human eyes to identify images, gamma correction is required to be carried out on the images acquired by the camera.
In one specific example of the application, an Image Signal Processor (ISP) performs white balance on a median width image, and reduces the pixel value of the median width image belonging to white by adjusting the proportion of RGB pixels, so as to obtain a median width image subjected to white balance; an Image Signal Processor (ISP) performs tone mapping on the white-balanced middle-width image to obtain a gray image; an Image Signal Processor (ISP) demosaices the gray-scale image to obtain a color image; an Image Signal Processor (ISP) gamma-corrects the color image and finally outputs a low-bit-width RGB image.
In the specific embodiment shown in fig. 1, the image processing method for performing parameter adjustment based on direct feedback further includes:
step S103, receiving and identifying the low-bit-width RGB image by the perception model, determining the interested image area, and generating image signal processor parameter adjustment feedback information which is fed back to the image signal processor and contains the interested image area related information.
In this embodiment, the perception model detects a target in the input low-bandwidth RGB image, and obtains perceived image signal processor parameter adjustment feedback information. The perception model may perceive objects that itself may need attention. The perception model perceives the low-bit-width RGB image processed by the image signal processor, and obtains some image signal processor parameters according to the intensity of perceived effect to adjust feedback information.
In one embodiment of the present application, if the image input into the perceptual model is an original image, i.e. its bit-width is not greater than the ISP allowed bit-width. The perception model directly detects an interested target in the original image; and identifying the interest region of the original image according to the interest target to obtain the perception information related to the interest target in the original image. The perception model perceives the interested target in the original image according to the self function, thereby delineating the interested region in the original image, and determining and modifying the parameters of the corresponding image signal processor according to the obtained value of the interested region.
In a specific example of the application, when the original image is a high-bit-width dynamic image, the image needs to be processed by an image signal processor, and the perception model can acquire a corresponding target of the low-bit-width RGB image in the perception model according to the low-bit-width RGB image output by the image signal processor, so that the target of interest is acquired, and a basis is provided for subsequent processing.
In a specific example of the application, the sensing model detects the image, and obtains sensing information including relevant parameters in the image, namely parameter adjustment feedback information of the image signal processor, according to the overall detection effect of the image. The sensing information obtained from the sensing model is not necessarily an interested target of the sensing model, but can be an integral scene, and the sensing model obtains related sensing information for the integral detection effect of the sensing model on the image aiming at the integral scene of the image so as to control the specific modification mode of the parameters of the image signal processor. Adjusting feedback information according to parameters of the image signal processor fed back by the perception model, wherein the image signal processor adjusts the parameters of the image signal processor, and the image signal processor identifies the parameter adjustment feedback information of the image signal processor by using an ISP algorithm to obtain identified adjustment information; and correspondingly adjusting parameters of the image signal processor according to the identified adjustment information.
In an alternative embodiment of the present application, the adjusting, by the image signal processor, the parameter of the image signal processor according to the image signal processor parameter adjustment feedback information includes: and adjusting at least one of white balance parameters, tone mapping parameters, demosaicing parameters and/or gamma correction parameters according to the image signal processor parameter adjustment feedback information, so that the obtained image region of interest has the characteristics required by a perception model after the medium-width image is processed by the image signal processor.
In this embodiment, the feedback information is adjusted according to the parameters of the image signal processor generated by the image region of interest, and at least one parameter of the image signal processor is adjusted. The specific adjustment is performed according to the actual feedback result.
In an alternative embodiment of the present application, computing, by an image signal processor, a luminance level of a bit-width image in blocks includes: and dividing the high-bit-width image into a preset number of image blocks, and respectively calculating the weighted average value of the brightness of pixels in each image block to obtain the brightness level of each image block.
In this embodiment, in the image signal processor, the median width image is segmented into a predetermined number of tiles, and the luminance value of each tile, that is, the weighted average of the luminance of the pixels, is calculated and obtained, so as to obtain the luminance level of the median width image.
In an optional embodiment of the present application, the image signal processor calculates the brightness level of the middle-width image in a blocking manner, determines the gray scale precision required by the brightness of different areas of the middle-width image according to the interested image area fed back by the perception model and the corresponding brightness level of the interested image area in the middle-width image, and generates the bit-width mapping feedback information fed back by the middle-width mapping logic according to the gray scale precision required by the brightness of different areas of the middle-width image; and adjusting the mapping relation between the high-bit-width image and the medium-bit-width image by the bit-width mapping logic according to the bit-width mapping feedback information, so that the brightness of the image region of interest has high gray scale precision.
In this embodiment, the bit width mapping feedback information includes the gray scale precision of each tile in the bit width image. The gray scale precision is determined and bit width mapping feedback information is generated based on the brightness level corresponding to the middle bit width image of the interested image area fed back by the perception model in the image signal processor, and the image signal processor generates a mapping function according to the generated bit width mapping feedback information, so that the details of dark parts in an original image can be reserved, and the whole image can be ensured not to be overexposed. And according to the bit width mapping feedback information, the mapping relation between the high bit width image and the medium bit width image is adjusted, so that the perception model can be more easily identified to the interested image area.
In an alternative embodiment of the present application, the adjusting, by the bit width mapping logic, the mapping relationship between the high bit width image and the medium bit width image according to the bit width mapping feedback information includes: under the condition that the brightness of the interested image area is low in brightness level, the bit width mapping feedback information indicates bit width mapping logic, one bit or a plurality of continuous bits are cut off from the highest bit of the high-bit width image, and a medium-bit width image is obtained; or in the case that the brightness of the interested image area is at a high brightness level, the bit width mapping feedback information indicates the bit width mapping logic to chop one bit or continuous multiple bits from the lowest bit of the high bit width image to obtain the medium bit width image.
In the embodiment, according to the bit width mapping feedback information, the bit width image is obtained by directly cutting bits of the high bit width image; the cut bits can only cut low bits or cut high bits, and the cut bits are used for mapping the bit width, so that the details of the target with lower pixel values are reserved in the image with the highest bit width as possible.
In an alternative embodiment of the present application, the adjusting, by the bit width mapping logic, the mapping relationship between the high bit width image and the medium bit width image according to the bit width mapping feedback information includes: in the case where the luminance of the image region of interest contains a plurality of luminance levels, the bit-width mapping feedback information indicates bit-width mapping logic that obtains a 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.
In this embodiment, according to the mapping relation 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, so as to obtain the output of the bit width mapping function, that is, the bit width image.
In the specific embodiment shown in fig. 1, the image processing method for performing parameter adjustment based on direct feedback further includes:
step S104, the image signal processor adjusts the parameters of the image signal processor according to the image signal processor parameter adjustment feedback information, so that the corresponding interested image area in the obtained low-bit-width RGB image has the characteristics required by the perception model after the processing of the medium-bit-width image by the image signal processor.
In this embodiment, the sensing model feeds back the parameter adjustment feedback information of the image signal processor to the image signal processor, and the image signal processor adjusts according to the parameter of the image signal processor, so that the image processing effect is better, and the sensing model has the characteristics required by the sensing model.
In one embodiment of the present application, the corresponding image processing flows are selected according to different requirements of different classes of perception models on the image, wherein the image processing flows include various pipelines in the image signal processor and processing flows without the image signal processor. According to the feedback mechanism, the parameters corresponding to different pipelines in the image signal processor are modified, so that the image processed by the image signal processor can better meet the perceived requirements of different categories.
In the specific embodiment shown in fig. 1, the image processing method for performing parameter adjustment based on direct feedback further includes:
step S105, the low-bit-width RGB image is identified by the perception model.
In this embodiment, the image signal processor processes the input high-bandwidth dynamic image according to the adjusted parameters, and outputs the processed result low-bandwidth RGB image to the perception model, and the adjusted parameters have better processing effect on the input high-bandwidth dynamic image, so that the perception model can better perceive the target in the image.
Fig. 2 shows a specific embodiment of an image processing system for parameter adjustment based on direct feedback according to the present application. In the embodiment shown in fig. 2, the image processing system for parameter adjustment based on direct feedback mainly includes a module 201 bit width mapping logic, a module 202 image signal processor, and a module 203 perception model, wherein:
the module 201 bit width mapping logic maps the high bit width image acquired by the image sensor into a medium bit width image required to be input by the image signal processor;
processing the mid-width image by a module 202 image signal processor and converting the mid-width image into a low-bit-width RGB image;
receiving and identifying the low-bit-width RGB image by the module 203 perception model, determining an image region of interest, and generating image signal processor parameter adjustment feedback information containing information related to the image region of interest for feedback to the image signal processor;
the image signal processor of the module 202 adjusts the parameters of the image signal processor according to the parameter adjustment feedback information of the image signal processor, so that the corresponding interested image area in the low-bit-width RGB image obtained after the processing of the middle-bit-width image by the image signal processor has the characteristic of sensing model requirements; and
the model is perceived by module 203 to identify the low-bit-width RGB image.
In this embodiment, the perception model receives the low-bit-width RGB image processed by the image signal processor or the raw image which meets the bit-width requirement and is unprocessed, the perception model can perceive the bayer array in the received image, the perceived information is fed back to the image signal processor, and the image signal processor correspondingly adjusts the parameters of the bayer array, so that the image processing effect is better, and the perception model can identify the attention target of the perception model more easily.
The image processing system for performing parameter adjustment based on direct feedback provided by the application can be used for executing the image processing method for performing parameter adjustment based on direct feedback described in any embodiment, and the implementation principle and technical effects are similar, and are not repeated here.
In a specific embodiment of the present application, the functional modules of an image processing system for parameter adjustment based on direct feedback of the present application may be directly in hardware, in a software module executed by a processor, or in a combination of both.
A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium.
The processor may be a central processing unit (English: central Processing Unit; CPU; for short), or other general purpose processor, digital signal processor (English: digital Signal Processor; for short DSP), application specific integrated circuit (English: application Specific Integrated Circuit; ASIC; for short), field programmable gate array (English: field Programmable Gate Array; FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, etc. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.
In another embodiment of the present application, a computer readable storage medium stores computer instructions operable to perform the method of image processing of parameter adjustment based on direct feedback in any of the embodiments.
In another embodiment of the present application, a computer device includes a processor and a memory storing computer instructions that are operable to perform the method of image processing of any of the embodiments based on direct feedback for parameter adjustment.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the partitioning of elements is merely a logical functional partitioning, and there may be additional partitioning in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not implemented. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is only examples of the present application, and is not intended to limit the scope of the patent application, and all equivalent structural changes made by the specification and drawings of the present application, or direct or indirect application in other related technical fields, are included in the scope of the patent protection of the present application.
Claims (10)
1. An image processing method for parameter adjustment based on direct feedback, comprising:
the bit width mapping logic maps the high bit width image acquired by the image sensor into a medium bit width image required to be input by the image signal processor;
processing, by the image signal processor, the mid-width image and converting the mid-width image into a low-bit-width RGB image;
receiving and identifying the low-bit-width RGB image by a perception model, determining an image region of interest, and generating image signal processor parameter adjustment feedback information which is fed back to an image signal processor and contains information related to the image region of interest;
the image signal processor adjusts the parameters of the image signal processor according to the image signal processor parameter adjustment feedback information, so that the middle-width image has the characteristics required by the perception model after the processing of the image signal processor, and the corresponding image region of interest in the obtained low-width RGB image has the characteristics required by the perception model; and
and identifying the low-bit-width RGB image by the perception model.
2. The image processing method for parameter adjustment based on direct feedback as claimed in claim 1, wherein said processing of said medium width image by said image signal processor comprises:
sequentially performing white balance processing, tone mapping processing, demosaicing processing and gamma correction processing on the medium-width image,
wherein the parameters of the image signal processor include white balance parameters, tone mapping parameters, demosaicing parameters, and/or gamma correction parameters.
3. The image processing method of claim 2, wherein the adjusting, by the image signal processor, the parameter of the image signal processor according to the image signal processor parameter adjustment feedback information comprises:
and adjusting at least one of the white balance parameter, the tone mapping parameter, the demosaicing parameter and/or the gamma correction parameter according to the image signal processor parameter adjustment feedback information, so that the obtained image region of interest of the medium-width image after the processing performed by the image signal processor has the characteristics required by the perception model.
4. The image processing method for parameter adjustment based on direct feedback as claimed in claim 1, further comprising:
by means of the image signal processor,
calculating the brightness level of the medium-width image in a blocking mode, determining the gray scale precision required by the brightness of different areas of the medium-width image according to the interested image area fed back by the perception model and the corresponding brightness level of the interested image area in the medium-width image, and
generating bit width mapping feedback information fed back to the bit width mapping logic according to gray scale precision required to be possessed by brightness of different areas of the bit width image; and
and adjusting the mapping relation between the high-bit-width image and the medium-bit-width image by the bit-width mapping logic according to the bit-width mapping feedback information, so that the brightness of the image region of interest has high gray scale precision.
5. The method of claim 4, wherein said adjusting, by said bit-width mapping logic, a mapping relationship between said high bit-width image and said medium bit-width image according to said bit-width mapping feedback information comprises:
in the case that the brightness of the image region of interest is at a low brightness level, the bit width mapping feedback information indicates the bit width mapping logic to chop one or more bits from the highest bit of the high bit width image to obtain the medium bit width image; or alternatively
In the case that the brightness of the image region of interest is at a high brightness level, the bit-width mapping feedback information indicates the bit-width mapping logic to chop one or more bits from the lowest bit of the high-bit-width image to obtain the medium-bit-width image.
6. The method of claim 4, wherein said adjusting, by said bit-width mapping logic, a mapping relationship between said high bit-width image and said medium bit-width image according to said bit-width mapping feedback information comprises:
and in the case that the brightness of the image region of interest comprises a plurality of brightness levels, the bit width mapping feedback information indicates the bit width mapping logic to obtain the bit width image by utilizing all bits of the high bit width image according to the bit width mapping function specified by the image signal processor.
7. The image processing method of parameter adjustment based on direct feedback as claimed in claim 4, wherein said calculating, by said image signal processor, a luminance level of said medium width image in blocks includes:
and dividing the high-bit wide image into a preset number of image blocks, and respectively calculating the weighted average value of the brightness of pixels in each image block to obtain the brightness level of each image block.
8. An image processing system for parameter adjustment based on direct 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 into a medium bit width image required to be input by the image signal processor;
processing, by the image signal processor, the mid-width image and converting the mid-width image into a low-bit-width RGB image;
receiving and identifying the low-bit-width RGB image by a perception model, determining an image region of interest, and generating image signal processor parameter adjustment feedback information which is fed back to an image signal processor and contains information related to the image region of interest;
the image signal processor adjusts the parameters of the image signal processor according to the image signal processor parameter adjustment feedback information, so that the middle-width image has the characteristics required by the perception model after the processing of the image signal processor, and the corresponding image region of interest in the obtained low-width RGB image has the characteristics required by the perception model; and
and identifying the low-bit-width RGB image by the perception model.
9. A computer readable storage medium storing computer instructions operable to perform the method of image processing for parameter adjustment based on direct feedback of any one of claims 1-7.
10. A computer device comprising a processor and a memory, the memory storing computer instructions, wherein the processor operates the computer instructions to perform the method of image processing of parameter adjustment based on direct feedback of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111658047.3A CN116416146A (en) | 2021-12-30 | 2021-12-30 | Image processing method and system for parameter adjustment based on direct feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111658047.3A CN116416146A (en) | 2021-12-30 | 2021-12-30 | Image processing method and system for parameter adjustment based on direct feedback |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116416146A true CN116416146A (en) | 2023-07-11 |
Family
ID=87058274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111658047.3A Pending CN116416146A (en) | 2021-12-30 | 2021-12-30 | Image processing method and system for parameter adjustment based on direct feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116416146A (en) |
-
2021
- 2021-12-30 CN CN202111658047.3A patent/CN116416146A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109361910B (en) | Self-adaptive white balance correction method and device | |
| KR100983037B1 (en) | Method for controlling auto white balance | |
| CN109785240B (en) | Low-illumination image enhancement method and device and image processing equipment | |
| US8760538B2 (en) | Adaptive gain control image processing system and method | |
| CN112752023B (en) | Image adjusting method and device, electronic equipment and storage medium | |
| CN112118388B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| US20070041636A1 (en) | Apparatus and method for image contrast enhancement using RGB value | |
| US9355327B2 (en) | Image processing apparatus and imaging apparatus with noise correction function and signal level correction function | |
| US9307162B2 (en) | Local enhancement apparatus and method to generate high dynamic range images by blending brightness-preserved and brightness-adjusted blocks | |
| US7421121B2 (en) | Spectral normalization using illuminant exposure estimation | |
| CN110047060B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN105578067A (en) | Image generation method and device, terminal equipment | |
| JP4595569B2 (en) | Imaging device | |
| CN105338214A (en) | Image processing method and image processing device | |
| US11323632B2 (en) | Electronic device and method for increasing exposure control performance of a camera by adjusting exposure parameter of the camera | |
| KR101113483B1 (en) | Apparatus for enhancing visibility of color image | |
| CN112634148B (en) | Image correction method, device and storage medium | |
| GB2569593A (en) | Exposure ratio control | |
| CN116416146A (en) | Image processing method and system for parameter adjustment based on direct feedback | |
| JP7454704B2 (en) | Image dynamic range processing method and device | |
| CN116416144A (en) | Image processing method and system for parameter adjustment based on feedback | |
| US8953063B2 (en) | Method for white balance adjustment | |
| CN113408380A (en) | Video image adjusting method, device and storage medium | |
| CN116416145A (en) | Image processing method and system for carrying out bit width mapping adjustment based on feedback | |
| JP2019040382A (en) | Image processing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |