High-precision CMOS image sensor data storage optimization method, device, medium and equipment based on adaptive compression algorithm

Abstract

The present disclosure relates to a method, apparatus, medium, and device for optimizing data storage for a high-precision CMOS image sensor based on an adaptive compression algorithm, and relates to the field of image processing technology. The method comprises: determining, with user permission, a user's personalized perception configuration of an image based on the user's behavioral data; acquiring a target image captured by a high-precision CMOS image sensor; generating a perception weight map associated with the target image based on the personalized perception configuration; segmenting the perception weight map into multiple regions and calculating the weight of each region; determining the importance level of each region based on the weight of each region; and compressing the portion of the target image associated with the region based on the importance level. In this way, the efficiency of image storage and transmission is significantly improved, while meeting the user's personalized needs for image quality.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to a method, apparatus, medium, and device for optimizing data storage of a high-precision CMOS image sensor based on an adaptive compression algorithm. Background Art

[0002] The widespread adoption of high-precision CMOS (Complementary Metal-Oxide-Semiconductor) image sensors has significantly improved the resolution and quality of image data, but this has also placed increasing pressure on data storage and transmission. Traditional image compression methods struggle to strike a balance between user needs, compression efficiency, and image quality. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a high-precision CMOS image sensor data storage optimization method, device, medium and equipment based on an adaptive compression algorithm to solve the above technical problems.

[0004] To achieve the above objectives, in a first aspect, the present disclosure provides a high-precision CMOS image sensor data storage optimization method based on an adaptive compression algorithm, comprising:

[0005] With the user's permission, determining the user's personalized perception configuration of the image based on the user's behavior data;

[0006] Acquire target images captured by high-precision CMOS image sensors;

[0007] generating a perceptual weight map associated with the target image according to the personalized perceptual configuration;

[0008] Dividing the perception weight map into multiple regions and calculating the weight of each region;

[0009] Determine the importance level of the areas according to the weights of the areas;

[0010] The portion of the target image associated with the region is compressed according to the importance level.

[0011] Optionally, determining the user's personalized perception configuration of the image based on the user's behavior data includes:

[0012] Conducting a brightness sensitivity test on the user to obtain the user's brightness sensitivity to the image;

[0013] Conducting a color sensitivity test on the user to obtain the user's color sensitivity to the image;

[0014] Performing a contrast sensitivity test on the user to obtain the user's contrast sensitivity to the image;

[0015] Conducting a texture complexity preference test on users to obtain their texture complexity preferences for images;

[0016] The personalized perception configuration includes the brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference.

[0017] Optionally, generating a perception weight map associated with the target image according to the personalized perception configuration includes:

[0018] Generating a user perception vector according to the personalized perception configuration, the user perception vector including a brightness sensitivity dimension, a color sensitivity dimension, a contrast sensitivity dimension, and a texture complexity preference dimension;

[0019] Generating a feature map of the target image, wherein each pixel in the feature map includes brightness features, color features, contrast features, and texture features;

[0020] For the feature map, each pixel in the feature map is weightedly superimposed with the user perception vector to obtain the perception weight map.

[0021] Optionally, dividing the perception weight map into a plurality of regions and calculating the weight of each region includes:

[0022] dividing the perceptual weight map into a plurality of regions;

[0023] For each region, calculating the weighted average of the pixels in the region;

[0024] The weighted average is used as the weight of the region.

[0025] Optionally, determining the importance level of each area according to the weight of each area includes:

[0026] For each region, when the weight of the region is greater than a first threshold, determining the importance level of the region as the first level;

[0027] When the weight of the area is greater than a second threshold and less than or equal to the first threshold, determining the importance level of the area to be a second level;

[0028] When the weight of the area is greater than a third threshold and less than or equal to the second threshold, determining the importance level of the area to be a third level;

[0029] The third threshold is smaller than the second threshold, the second threshold is smaller than the first threshold, and the importance of the first level, the second level, and the third level decreases in sequence.

[0030] Optionally, compressing the portion of the target image associated with the region according to the importance level includes:

[0031] When the importance level of the region is a first level, compressing a portion of the target image associated with the region to a first degree;

[0032] When the importance level of the region is the second level, compressing the portion of the target image associated with the region to a second degree;

[0033] When the importance level of the region is the third level, performing a third degree of compression on a portion of the target image associated with the region;

[0034] Among them, at the first degree, the second degree, and the third degree, the compression degree of the portion of the target image associated with the region gradually increases.

[0035] Optionally, the image is a JPEG image,

[0036] The compressing the portion of the target image associated with the region to a first degree comprises: compressing the portion of the target image associated with the region by a quality factor of 10-30;

[0037] The compressing the portion of the target image associated with the region to a second degree comprises: compressing the portion of the target image associated with the region by a quality factor of 50-70;

[0038] The compressing the portion of the target image associated with the region to a third degree includes compressing the portion of the target image associated with the region using a quality factor of 90-100.

[0039] In a second aspect, a high-precision CMOS image sensor data storage optimization device based on an adaptive compression algorithm is provided, comprising:

[0040] A first module is configured to determine, with the user's permission, a personalized perception configuration of the user for the image based on the user's behavior data;

[0041] The second module is used to obtain the target image captured by the high-precision CMOS image sensor;

[0042] A third module is configured to generate a perception weight map associated with the target image according to the personalized perception configuration;

[0043] A fourth module is used to divide the perception weight map into multiple regions and calculate the weight of each region;

[0044] The fifth module is used to determine the importance level of each area according to the weight of each area;

[0045] The sixth module is configured to compress the portion of the target image associated with the region according to the importance level.

[0046] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0047] In a fourth aspect, a device is provided, comprising:

[0048] a memory having a computer program stored thereon;

[0049] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0050] In this solution, user behavior data can be combined to generate a personalized perception weight map, reflecting the user's level of attention to different image regions. This can then be combined with an adaptive compression algorithm to differentially compress images based on the importance of each region, achieving a balance between high-fidelity storage of critical areas and efficient compression of non-critical areas. Ultimately, this significantly improves image storage and transmission efficiency while meeting users' personalized image quality needs.

[0051] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0053] Figure 1 The present invention is a flowchart of a method for optimizing data storage of a high-precision CMOS image sensor based on an adaptive compression algorithm.

[0054] Figure 2 This is a device diagram of a high-precision CMOS image sensor data storage optimization method based on an adaptive compression algorithm.

[0055] Figure 3 It is a block diagram of an electronic device. DETAILED DESCRIPTION

[0056] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0057] The widespread adoption of high-precision CMOS image sensors has significantly improved the resolution and quality of image data, but this has also led to increasing pressure on data storage and transmission. Traditional image compression methods often fail to balance compression efficiency and image quality. This is especially true when users have individualized preferences for different image regions. A uniform compression strategy can lead to loss of detail in key areas or waste of storage resources. Therefore, a solution is urgently needed that can optimize image storage based on the user's personalized perception, significantly reducing data storage requirements while maintaining quality in key areas.

[0058] In order to achieve the above objectives, the present disclosure provides a high-precision CMOS image sensor data storage optimization method based on an adaptive compression algorithm. Figure 1 This is a flowchart of a high-precision CMOS image sensor data storage optimization method based on an adaptive compression algorithm. Figure 1 , the method comprising:

[0059] S11, with the user's permission, determining the user's personalized perception configuration of the image based on the user's behavior data;

[0060] S12, acquiring a target image captured by a high-precision CMOS image sensor;

[0061] S13, generating a perception weight map associated with the target image according to the personalized perception configuration;

[0062] S14, dividing the perception weight map into multiple regions and calculating the weight of each region;

[0063] S15, determining the importance level of each area according to the weight of each area;

[0064] S16: Compress the portion of the target image associated with the region according to the importance level.

[0065] The following is an illustrative description of the implementation of each of the above steps.

[0066] In step S11 , with the user's permission, the user's personalized perception configuration of the image is determined based on the user's behavior data.

[0067] In one embodiment, determining the user's personalized perception configuration of an image based on the user's behavior data includes:

[0068] Conducting a brightness sensitivity test on the user to obtain the user's brightness sensitivity to the image;

[0069] Conducting a color sensitivity test on the user to obtain the user's color sensitivity to the image;

[0070] Performing a contrast sensitivity test on the user to obtain the user's contrast sensitivity to the image;

[0071] Conducting a texture complexity preference test on users to obtain their texture complexity preferences for images;

[0072] The personalized perception configuration includes the brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference.

[0073] For example, in a brightness sensitivity test, users can be shown a series of grayscale images with varying brightness levels, ranging from low to high (for example, grayscale values from 10 to 250). Within an image containing regions of varying brightness, users can mark the brightness range where detail is most easily discernible. Alternatively, users can select the brightness level they find most comfortable among multiple images of scenes with varying brightness levels. Different brightness levels correspond to different brightness sensitivities.

[0074] If a user can clearly discern details in low-brightness areas (e.g., grayscale values of 10-50), this indicates they are sensitive to low brightness. If a user prefers images in high-brightness areas (e.g., grayscale values of 200-250), this indicates they are more sensitive to high brightness. This allows us to determine the user's brightness sensitivity and prioritize information in the corresponding brightness areas during image compression.

[0075] When testing color sensitivity, you can show the user a set of color gradient images and test them for hue, saturation, and lightness:

[0076] Hue test: Users observe an image that gradients from red to blue and mark the areas where the color change is most easily perceived.

[0077] Saturation test: Users observe a set of images with saturation varying from low to high, and select the saturation range that is easiest for them to distinguish.

[0078] Brightness-color combination test: Users observe a set of color images at different brightness levels and choose their preferred brightness-color combination.

[0079] This allows us to record the user's choices in the hue, saturation, and brightness tests and analyze their color sensitivity. For example, if a user is more sensitive to changes in light blue areas (such as the less saturated portion of a blue gradient), this suggests they pay more attention to light blue and low-saturation areas. If a user is more sensitive to changes in highly saturated colors (such as red or green), this suggests they pay more attention to strong color contrast. Based on these test results, we can determine the user's color sensitivity.

[0080] During the contrast sensitivity test, a set of images with different contrasts can be shown to the user. The test is divided into two parts:

[0081] Edge clarity test: Users observe an image containing areas of varying contrast (e.g., edges ranging from blurry to clear) and mark the edge areas that are easiest for them to distinguish.

[0082] Contrast preference test: Users observe a set of natural scene images with contrast varying from low to high, and select their preferred contrast range.

[0083] This allows users to record their marked areas in the edge clarity test and their choices in the contrast preference test. If users can more easily distinguish high-contrast areas (such as those with sharp edges), this indicates they are more sensitive to high contrast. If they prefer low-contrast scenes, this indicates they are more interested in images with smooth transitions. Based on these test results, contrast sensitivity can be determined.

[0084] When testing texture complexity preference, users can be shown a set of images with different texture complexities. The test is divided into two parts:

[0085] Texture discrimination test: Users observe an image containing simple textures (such as regular lines) and complex textures (such as interlaced patterns or natural textures) and mark the texture areas that they can more easily distinguish.

[0086] Texture preference test: Users observe a set of images with varying texture complexity from low to high and choose the texture type they prefer.

[0087] This allows us to record the user's marked areas in the texture discrimination test and their choices in the texture preference test. If a user pays more attention to complex texture areas (such as high-frequency interlaced patterns), this indicates they are more interested in complex textures. If a user prefers simple texture areas (such as regular lines), this indicates they are more interested in low-frequency textures. Based on these test results, we can determine the user's texture complexity preference.

[0088] Thus, the personalized perception configuration includes the brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference. The image can be personalized compressed according to the personalized perception configuration.

[0089] In step S12, a target image captured by a high-precision CMOS image sensor is acquired.

[0090] In step S13, a perception weight map associated with the target image is generated according to the personalized perception configuration.

[0091] In a possible implementation, generating a perception weight map associated with the target image according to the personalized perception configuration includes:

[0092] A user perception vector is generated according to the personalized perception configuration, where the user perception vector includes a brightness sensitivity dimension, a color sensitivity dimension, a contrast sensitivity dimension, and a texture complexity preference dimension.

[0093] Continuing with the above example, we can normalize brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference to generate a user perception vector. For example, the user perception vector can be: U = [0.4, 0.3, 0.2, 0.1].

[0094] Among them, brightness sensitivity has a weight of 0.4, which is biased towards low brightness areas. Color sensitivity has a weight of 0.3, which is biased towards light blue areas. Contrast sensitivity has a weight of 0.2, which is biased towards high contrast areas. Texture complexity preference has a weight of 0.1, which is biased towards complex texture areas.

[0095] Furthermore, a feature map of the target image may be generated, wherein each pixel in the feature map includes brightness features, color features, contrast features, and texture features. For the feature map, each pixel in the feature map is weightedly superimposed with the user perception vector to obtain the perception weight map.

[0096] Exemplarily, for an input target image, multiple brightness feature maps, color feature maps, contrast feature maps, and texture feature maps may be extracted.

[0097] The brightness feature map can represent the brightness distribution of each pixel in the target image. The color feature map can describe the color components of each pixel in the target image (such as the L, a, and b values in the CIELAB color space). The contrast feature map can be used to extract high-contrast areas using edge detection algorithms. The texture feature map can be used to extract the complexity of the texture in the image using filters (such as Gabor filters).

[0098] Thus, each feature map reflects the information of the image in a specific dimension. Combined with the feature map, each pixel can have brightness features, color features, contrast features and texture features.

[0099] In this way, the feature map can be weighted and superimposed on each pixel in the feature map and the user perception vector to obtain the perception weight map. For example, the brightness feature of the pixel can be multiplied by the brightness dimension of the user perception vector, and the color feature of the pixel can be multiplied by the color dimension of the user perception vector. Similarly, contrast features and texture features can also be processed to ultimately obtain the perception weight map.

[0100] In step S14, the perception weight map is divided into multiple regions, and the weight of each region is calculated.

[0101] For example, the perceptual weight map can be divided into fixed-size blocks (e.g., 8×8 pixels). Similarly, since the perceptual weight map corresponds to the target image, the target image can also be divided into fixed-size blocks (e.g., 8×8 pixels). The blocks obtained by dividing the perceptual weight map correspond one-to-one with the blocks divided into the target image.

[0102] Optionally, dividing the perception weight map into a plurality of regions and calculating the weight of each region includes:

[0103] dividing the perceptual weight map into a plurality of regions;

[0104] For each region, calculating the weighted average of the pixels in the region;

[0105] The weighted average is used as the weight of the region.

[0106] That is, the values of the pixels in the region in the perception weight map may be averaged to obtain the weight of the region.

[0107] In step S15 , the importance level of each area is determined according to the weight of each area.

[0108] In one embodiment, determining the importance level of each area according to the weight of each area includes:

[0109] For each region, when the weight of the region is greater than a first threshold, determining the importance level of the region as the first level;

[0110] When the weight of the area is greater than a second threshold and less than or equal to the first threshold, determining the importance level of the area to be a second level;

[0111] When the weight of the area is greater than a third threshold and less than or equal to the second threshold, determining the importance level of the area to be a third level;

[0112] The third threshold is smaller than the second threshold, the second threshold is smaller than the first threshold, and the importance of the first level, the second level, and the third level decreases in sequence.

[0113] It should be noted that the first threshold, the second threshold, and the third threshold can be set as needed. When the weight is greater than the first threshold, it means that in the user's perception, the importance of the area is the highest (easiest to perceive), and therefore the importance level of the area is the first level. When the weight is greater than the second threshold and less than or equal to the first threshold, it means that in the user's perception, the importance of the area is high, but not as high as the first level. Therefore, the importance level of the area is the second level. When the weight is greater than the third threshold and less than or equal to the second threshold, it means that in the user's perception, the importance of the area is the lowest, and therefore the importance level of the area is the third level.

[0114] In step S16, the portion of the target image associated with the region is compressed according to the importance level.

[0115] In one embodiment, compressing the portion of the target image associated with the region according to the importance level includes:

[0116] When the importance level of the region is a first level, compressing a portion of the target image associated with the region to a first degree;

[0117] When the importance level of the region is the second level, compressing the portion of the target image associated with the region to a second degree;

[0118] When the importance level of the region is the third level, performing a third degree of compression on a portion of the target image associated with the region;

[0119] Among them, at the first degree, the second degree, and the third degree, the compression degree of the portion of the target image associated with the region gradually increases.

[0120] As an example, the image is a JPEG image, and when the importance level of the area is the first level, the first degree of compression is performed on the portion of the target image associated with the area, including: compressing the portion of the target image associated with the area by a quality factor of 10-30.

[0121] When the importance level of the region is the second level, compressing the portion of the target image associated with the region to a second degree includes: compressing the portion of the target image associated with the region using a quality factor of 50-70;

[0122] When the importance level of the region is the third level, compressing the portion of the target image associated with the region to a third degree includes compressing the portion of the target image associated with the region by a quality factor of 90-100.

[0123] In this way, in JPEG, different levels of quantization tables can be used to compress areas of different importance (for example, discrete cosine transform and quantization can be performed block by block for compression). For areas of high importance that are easily perceived by users, less compression is performed, while for areas of low importance that are not easily perceived by users, more compression is performed.

[0124] In this solution, user behavior data can be combined to generate a personalized perception weight map, reflecting the user's level of attention to different image regions. This can then be combined with an adaptive compression algorithm to differentially compress images based on the importance of each region, achieving a balance between high-fidelity storage of critical areas and efficient compression of non-critical areas. Ultimately, this significantly improves image storage and transmission efficiency while meeting users' personalized image quality needs.

[0125] Of course, in the final compression result, the compressed image data (the compression results of all image blocks), regional importance levels (for easy restoration during decoding) and weight perception maps can be retained, which can be stored as additional data to guide image reconstruction during decoding.

[0126] Based on the same inventive concept, a high-precision CMOS image sensor data storage optimization device based on an adaptive compression algorithm is also provided. Figure 2 This is a block diagram of a high-precision CMOS image sensor data storage optimization device based on an adaptive compression algorithm. Figure 2 , the device comprises:

[0127] The first module 201 is configured to determine, with the user's permission, a personalized perception configuration of the user for the image based on the user's behavior data;

[0128] The second module 202 is used to obtain a target image captured by a high-precision CMOS image sensor;

[0129] A third module 203 is configured to generate a perception weight map associated with the target image according to the personalized perception configuration;

[0130] The fourth module 204 is configured to divide the perception weight map into a plurality of regions and calculate the weight of each region;

[0131] The fifth module 205 is used to determine the importance level of each area according to the weight of each area;

[0132] The sixth module 206 is configured to compress the portion of the target image associated with the region according to the importance level.

[0133] In this solution, user behavior data can be combined to generate a personalized perception weight map, reflecting the user's level of attention to different image regions. This can then be combined with an adaptive compression algorithm to differentially compress images based on the importance of each region, achieving a balance between high-fidelity storage of critical areas and efficient compression of non-critical areas. Ultimately, this significantly improves image storage and transmission efficiency while meeting users' personalized image quality needs.

[0134] In one embodiment, the first module is configured to:

[0135] Conducting a brightness sensitivity test on the user to obtain the user's brightness sensitivity to the image;

[0136] Conducting a color sensitivity test on the user to obtain the user's color sensitivity to the image;

[0137] Performing a contrast sensitivity test on the user to obtain the user's contrast sensitivity to the image;

[0138] Conducting a texture complexity preference test on users to obtain their texture complexity preferences for images;

[0139] The personalized perception configuration includes the brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference.

[0140] In one embodiment, the third module is used to:

[0141] Generating a user perception vector according to the personalized perception configuration, the user perception vector including a brightness sensitivity dimension, a color sensitivity dimension, a contrast sensitivity dimension, and a texture complexity preference dimension;

[0142] Generating a feature map of the target image, wherein each pixel in the feature map includes brightness features, color features, contrast features, and texture features;

[0143] For the feature map, each pixel in the feature map is weightedly superimposed with the user perception vector to obtain the perception weight map.

[0144] In one embodiment, the fourth module is used to:

[0145] dividing the perceptual weight map into a plurality of regions;

[0146] For each region, calculating the weighted average of the pixels in the region;

[0147] The weighted average is used as the weight of the region.

[0148] In one embodiment, the fifth module is used to:

[0149] For each region, when the weight of the region is greater than a first threshold, determining the importance level of the region as the first level;

[0150] When the weight of the area is greater than a second threshold and less than or equal to the first threshold, determining the importance level of the area to be a second level;

[0151] When the weight of the area is greater than a third threshold and less than or equal to the second threshold, determining the importance level of the area to be a third level;

[0152] The third threshold is smaller than the second threshold, the second threshold is smaller than the first threshold, and the importance of the first level, the second level, and the third level decreases in sequence.

[0153] In one embodiment, the sixth module is used to:

[0154] When the importance level of the region is a first level, compressing a portion of the target image associated with the region to a first degree;

[0155] When the importance level of the region is the second level, compressing the portion of the target image associated with the region to a second degree;

[0156] When the importance level of the region is the third level, performing a third degree of compression on a portion of the target image associated with the region;

[0157] Among them, at the first degree, the second degree, and the third degree, the compression degree of the portion of the target image associated with the region gradually increases.

[0158] In one embodiment, the image is a JPEG image, and compressing the portion of the target image associated with the region to a first degree comprises: compressing the portion of the target image associated with the region by a quality factor of 10-30;

[0159] The compressing the portion of the target image associated with the region to a second degree comprises: compressing the portion of the target image associated with the region by a quality factor of 50-70;

[0160] The compressing the portion of the target image associated with the region to a third degree includes compressing the portion of the target image associated with the region using a quality factor of 90-100.

[0161] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method of the present invention when executed by a processor.

[0162] The present invention also provides a device comprising:

[0163] a memory having a computer program stored thereon;

[0164] A processor is used to execute the computer program in the memory to implement the steps of the above method of the present invention.

[0165] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0166] Figure 3 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 3 As shown, the electronic device 700 may include: a processor 701 , a memory 702 , and may further include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0167] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above method. The memory 702 is used to store various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data such as contact information, sent and received messages, images, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0168] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0169] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided, wherein the program instructions, when executed by a processor, implement the steps of the above method. For example, the computer-readable storage medium may be the memory 702 including the program instructions, which may be executed by the processor 701 of the electronic device 700 to perform the above method.

[0170] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a processor. When the computer program is executed by the processor, the steps of the above method are implemented.

[0171] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0172] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0173] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A high-precision CMOS image sensor data storage optimization method based on an adaptive compression algorithm, characterized in that: include: With the user's permission, determining the user's personalized perception configuration of the image based on the user's behavior data; Acquire target images captured by high-precision CMOS image sensors; generating a perceptual weight map associated with the target image according to the personalized perceptual configuration; Dividing the perception weight map into multiple regions and calculating the weight of each region; Determining the importance level of each region according to the weight of each region, wherein the compression level corresponding to a region with a higher importance level is lower than the compression level corresponding to a region with a lower importance level; compressing a portion of the target image associated with the region according to the importance level; The determining of the user's personalized perception configuration of the image based on the user's behavior data includes: Conducting a brightness sensitivity test on the user to obtain the user's brightness sensitivity to the image; Conducting a color sensitivity test on the user to obtain the user's color sensitivity to the image; Performing a contrast sensitivity test on the user to obtain the user's contrast sensitivity to the image; Conducting a texture complexity preference test on users to obtain their texture complexity preferences for images; The personalized perception configuration includes the brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference; Generating a perception weight map associated with the target image according to the personalized perception configuration includes: Generating a user perception vector according to the personalized perception configuration, the user perception vector including a brightness sensitivity dimension, a color sensitivity dimension, a contrast sensitivity dimension, and a texture complexity preference dimension; Generating a feature map of the target image, wherein each pixel in the feature map includes brightness features, color features, contrast features, and texture features; For the feature map, each pixel in the feature map is weightedly superimposed with the user perception vector to obtain the perception weight map.

2. The method according to claim 1, characterized in that The step of dividing the perception weight map into a plurality of regions and calculating the weight of each region includes: dividing the perceptual weight map into a plurality of regions; For each region, calculating the weighted average of the pixels in the region; The weighted average is used as the weight of the region.

3. The method according to claim 2, characterized in that Determining the importance level of each area according to the weight of each area includes: For each region, when the weight of the region is greater than a first threshold, determining the importance level of the region as the first level; When the weight of the area is greater than a second threshold and less than or equal to the first threshold, determining the importance level of the area to be a second level; When the weight of the area is greater than a third threshold and less than or equal to the second threshold, determining the importance level of the area to be a third level; The third threshold is smaller than the second threshold, the second threshold is smaller than the first threshold, and the importance of the first level, the second level, and the third level decreases in sequence.

4. The method according to claim 3, characterized in that The compressing the portion of the target image associated with the region according to the importance level includes: When the importance level of the region is a first level, compressing a portion of the target image associated with the region to a first degree; When the importance level of the region is the second level, compressing the portion of the target image associated with the region to a second degree; When the importance level of the region is the third level, performing a third degree of compression on a portion of the target image associated with the region; Among them, at the first degree, the second degree, and the third degree, the compression degree of the portion of the target image associated with the region gradually increases.

5. The method according to claim 4, characterized in that The image is a JPEG image, The compressing the portion of the target image associated with the region to a first degree comprises: compressing the portion of the target image associated with the region by a quality factor of 10-30; The compressing the portion of the target image associated with the region to a second degree comprises: compressing the portion of the target image associated with the region by a quality factor of 50-70; The compressing the portion of the target image associated with the region to a third degree includes compressing the portion of the target image associated with the region using a quality factor of 90-100.

6. A high-precision CMOS image sensor data storage optimization device based on an adaptive compression algorithm, characterized in that: include: A first module is configured to determine, with the user's permission, a personalized perception configuration of the user for the image based on the user's behavior data; The second module is used to obtain the target image captured by the high-precision CMOS image sensor; A third module is configured to generate a perception weight map associated with the target image according to the personalized perception configuration; A fourth module is used to divide the perception weight map into multiple regions and calculate the weight of each region; A fifth module is configured to determine the importance level of each region according to the weight of each region, wherein the compression level corresponding to a region with a higher importance level is lower than the compression level corresponding to a region with a lower importance level; a sixth module, configured to compress a portion of the target image associated with the region according to the importance level; Wherein, the first module is used for: Conducting a brightness sensitivity test on the user to obtain the user's brightness sensitivity to the image; Conducting a color sensitivity test on the user to obtain the user's color sensitivity to the image; Performing a contrast sensitivity test on the user to obtain the user's contrast sensitivity to the image; Conducting a texture complexity preference test on users to obtain their texture complexity preferences for images; The personalized perception configuration includes the brightness sensitivity, color sensitivity, contrast sensitivity, and texture complexity preference; The third module is specifically used for: Generating a user perception vector according to the personalized perception configuration, the user perception vector including a brightness sensitivity dimension, a color sensitivity dimension, a contrast sensitivity dimension, and a texture complexity preference dimension; Generating a feature map of the target image, wherein each pixel in the feature map includes brightness features, color features, contrast features, and texture features; For the feature map, each pixel in the feature map is weightedly superimposed with the user perception vector to obtain the perception weight map.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images