Image processing method, device, storage medium and chip

Abstract

The present disclosure relates to a method, device, storage medium and chip for image processing, and relates to the technical field of multimedia. The method comprises: obtaining first image data in a first format; taking the first image data as an input of a super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel point in the second format image data is greater than the number of bytes corresponding to each pixel point in the first format image data; and generating target image data according to the second image data. The present disclosure outputs image data processed by the super-resolution algorithm in the second format, can more realistically and effectively restore multi-color high dynamic range images, and reduces the number of format conversions in the image processing process, thereby reducing memory overhead and improving image processing rate.

Description

Technical Field

[0001] This disclosure relates to the field of multimedia technology, and in particular to methods, apparatus, storage media and chips for image processing. Background Technology

[0002] In related technologies, for shooting scenarios with telephoto lenses, the 8-bit YUV420 format is typically used as the output format for super-resolution algorithms. Through multiple format conversions and internal processing within the super-resolution algorithm, high-resolution, high dynamic range, and high-saturation images captured by telephoto lenses are reproduced. Because the image processing involves multiple additional format conversions, it increases performance and memory overhead in the processing flow, resulting in a slower perceived image quality when clicked by the user. Furthermore, storing images in 8-bit YUV420 format reduces the number of high dynamic range pixels, making it difficult to effectively reproduce true images in multi-color, high-dynamic-range environments. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides an image processing method, apparatus, storage medium, and chip.

[0004] According to a first aspect of the present disclosure, an image processing method is provided, the method comprising:

[0005] Obtain the first image data in the first format;

[0006] The first image data is used as input to the super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel in the second format image data is greater than the number of bytes corresponding to each pixel in the first format image data;

[0007] Based on the second image data, target image data is generated.

[0008] Optionally, generating target image data based on the second image data includes:

[0009] Based on the second image data, determine the third image data in the first format;

[0010] The third image data is converted into the target image data.

[0011] Optionally, determining the third image data in the first format based on the second image data includes:

[0012] The second image data is downsampled to obtain the downsampled second image data;

[0013] The third image data is obtained based on the second image data and the downsampled second image data.

[0014] Optionally, obtaining the third image data based on the second image data and the downsampled second image data includes:

[0015] The second image data and the downsampled second image data are converted into their formats to obtain the third image data.

[0016] Optionally, converting the third image data into the target image data includes:

[0017] The image format of the third image data is converted to obtain the target image data.

[0018] Optionally, acquiring the first image data in the first format includes:

[0019] Acquire raw image data from the image sensor;

[0020] The original image data is converted into the first image data in the first format.

[0021] Optionally, the output format of the super-resolution algorithm is the second format, and the storage format of the image buffer of the super-resolution algorithm is the second format.

[0022] According to a second aspect of the present disclosure, an image processing apparatus is provided, the apparatus comprising:

[0023] The acquisition module is configured to acquire first image data in a first format;

[0024] The processing module is configured to take the first image data as input to a super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel in the second format image data is greater than the number of bytes corresponding to each pixel in the first format image data.

[0025] The generation module is configured to generate target image data based on the second image data.

[0026] Optionally, the generation module includes:

[0027] The determination submodule is configured to determine third image data in the first format based on the second image data;

[0028] The conversion submodule is configured to convert the third image data into the target image data.

[0029] Optionally, the submodule is determined and configured as follows:

[0030] The second image data is downsampled to obtain the downsampled second image data;

[0031] The third image data is obtained based on the second image data and the downsampled second image data.

[0032] Optionally, the determining submodule is configured as follows:

[0033] The second image data and the downsampled second image data are converted into their formats to obtain the third image data.

[0034] Optionally, the conversion submodule is configured as follows:

[0035] The image format of the third image data is converted to obtain the target image data.

[0036] Optionally, the acquisition module is configured as follows:

[0037] Acquire raw image data from the image sensor;

[0038] The original image data is converted into the first image data in the first format.

[0039] Optionally, the output format of the super-resolution algorithm is the second format, and the storage format of the image buffer of the super-resolution algorithm is the second format.

[0040] According to a third aspect of the present disclosure, an image processing apparatus is provided, comprising:

[0041] processor;

[0042] Memory used to store processor-executable instructions;

[0043] The processor is configured as follows:

[0044] Obtain the first image data in the first format;

[0045] The first image data is used as input to the super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel in the second format image data is greater than the number of bytes corresponding to each pixel in the first format image data;

[0046] Based on the second image data, target image data is generated.

[0047] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the method described in the first aspect of the present disclosure.

[0048] According to a fifth aspect of the present disclosure, a chip is provided, including a processor and an interface; the processor is configured to read instructions to execute the method described in the first aspect of the present disclosure.

[0049] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0050] This disclosure first acquires first image data in a first format and uses it as input to a super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm. Then, target image data is generated based on the second image data. The number of bytes corresponding to each pixel in the second format image data is greater than the number of bytes corresponding to each pixel in the first format image data. This disclosure outputs the image data processed by the super-resolution algorithm in the second format, which can more realistically and effectively restore multi-color, high dynamic range images and reduce the number of format conversions during image processing, thereby reducing memory overhead and improving image processing speed.

[0051] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0053] Figure 1 This is a flowchart illustrating an image processing method according to an exemplary embodiment.

[0054] Figure 2 It is based on Figure 1 An example of an image processing flowchart is shown.

[0055] Figure 3 It is based on Figure 1 The example shows a comparison of the image effects corresponding to the two formats.

[0056] Figure 4 This is a flowchart illustrating another image processing method according to an exemplary embodiment.

[0057] Figure 5 It is based on Figure 4 The embodiment illustrates another image processing flowchart.

[0058] Figure 6 This is a block diagram illustrating an image processing apparatus according to an exemplary embodiment.

[0059] Figure 7 This is a block diagram illustrating another image processing apparatus according to an exemplary embodiment.

[0060] Figure 8 This is a block diagram illustrating an apparatus according to an exemplary embodiment. Detailed Implementation

[0061] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0062] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0063] Before introducing the image processing methods, apparatus, storage media, and chips shown in the embodiments of this disclosure, the application scenarios involved in the embodiments of this disclosure will be introduced first.

[0064] Currently, for shooting scenarios requiring higher image resolution, such as those using telephoto lenses, SuperResolution (SR) algorithms are typically used to process image data acquired by the image sensor to increase image resolution. In related technologies, 8-bit YUV420 format is used as both the input and output format for the SR algorithm. The output 8-bit YUV420 image data is stored in an image buffer, with each pixel occupying one byte, for subsequent image post-processing. However, for shooting scenarios with high dynamic range and high brightness, such as images with ambient brightness far exceeding the 256 values ​​that 8 bits can represent, the 8-bit YUV420 storage method reduces the number of pixels in the high dynamic range, failing to effectively reproduce the true image of the scene. Furthermore, after being processed by the super-resolution algorithm, the image enters the post-processing flow. It is necessary to use the IPE (Image Processing Engine) 37 module again to convert the 8-bit YUV420 format image data from 8 bits to 10 bits. Then, the 10-bit format image data is input into the IPE38 module for downsampling. The downsampled image data and the 10-bit format image data output by the IPE37 module are then input into the IPE39 module for conversion from 10 bits to 8 bits. These multiple cumbersome conversions not only incur additional overhead on memory and performance, but also fail to meet the requirements for image saturation restoration in high dynamic range environments with multiple colors, resulting in a significant deterioration in user perception and experience.

[0065] Figure 1 This is a flowchart illustrating an image processing method according to an exemplary embodiment, such as... Figure 1 As shown, the method may include the following steps.

[0066] In step 101, first image data in a first format is acquired.

[0067] For example, when a user takes a photo using a telephoto lens at a preset zoom level, the camera will trigger the SuperResolution shooting scene. The preset zoom level could be, for example, greater than 1.4x. Figure 2 The image processing flow shown first involves the image sensor outputting raw image data in Bayer format. Then, the raw Bayer format image data is processed using Bayer2Yuv to convert it into first image data in a first format. This first format can be 8-bit YUV420 format.

[0068] In step 102, the first image data is used as input to the super-resolution algorithm to obtain the second image data in the second format output by the super-resolution algorithm.

[0069] In the second format of image data, the number of bytes corresponding to each pixel is greater than the number of bytes corresponding to each pixel in the first format of image data.

[0070] For example, the input format of the super-resolution algorithm is a first format, and the output format is a second format. The first image data in the first format is input into the super-resolution algorithm, and the super-resolution algorithm processes the resolution of the first image data to output the second image data in the second format.

[0071] In one embodiment, the image buffer of the super-resolution algorithm is stored in a second format. The super-resolution algorithm can allocate an image buffer in memory according to the second format and set the storage parameters of the image buffer to target parameters conforming to the second format. The target parameters may include width, height, stride, and plane. In this way, the second image data in the second format can be effectively stored in the image buffer for subsequent image post-processing processes (such as YUVReprocess) to read.

[0072] The second format can be a storage format larger than 8 bits, such as P010YUV420, P016YUV420, P210YUV422, P216YUV422, or 14-bit Ultra RAW. The P010YUV420 and P210YUV422 formats use 16 bits (two bytes) per pixel, with 10 bits used to store image data and 6 bits padded with zeros in memory. The P016YUV420 and P216YUV422 formats also use 16 bits (two bytes) per pixel, with 16 bits used to store image data. The 14-bit Ultra RAW format is a format used in ultra-high-definition portrait mode. Furthermore, data can be interoperated and exchanged between these various formats. In this embodiment, the super-resolution algorithm outputs image data with a larger number of bytes per pixel, and correspondingly increases the number of bytes stored for each pixel in the super-resolution algorithm output image data. This allows for the complete storage of brightness information for higher-brightness pixels, improving the image quality of high dynamic range images. Furthermore, it processes 16-bit data, which has a larger number of bytes, faster than 8-bit data, thus improving image processing performance and reducing processing time.

[0073] Actual tests were conducted using the first format (8-bit YUV420) and the second format (P010YUV420), and the comparison of the computation time of the super-resolution algorithm is shown in the table below.

[0074] 8bit YUV420 P010YUV420 Difference 447.8ms 363ms -84ms

[0075] Table 1

[0076] As shown in Table 1, using P010YUV420 as the output of the super-resolution algorithm reduces its runtime and improves its performance. Furthermore, actual testing shows that BouncyCastleProvider memory usage is reduced by 40MB, and ION memory manager memory usage is reduced by 104MB. Figure 3 As shown, the left image is stored in 8-bit YUV420 format, and the right image is stored in P010YUV420 format. Processing the 8-bit YUV420 image data using a super-resolution algorithm and then storing it in P010YUV420 format greatly preserves high dynamic range pixels. The continuous color range of the image data stored in P010YUV420 format effectively corrects the wavy discontinuity problem caused by the 8-bit YUV420 format. Furthermore, the P010YUV420 format, utilizing a 16-bit storage format, boasts high computational performance, significantly improving the processing time of the algorithm in super-resolution adaptation scenarios, resulting in a substantial improvement in both performance and image quality.

[0077] In step 103, target image data is generated based on the second image data.

[0078] For example, after obtaining the second image data in the second format, the second image data can be input into a post-processing module for further processing to obtain the target image data. In some embodiments, the second image data in the second format can be downsampled first to output the third image data in the first format, and then the image format of the third image data can be converted to convert the third image data in the first format into the target image data in the target format, which can then be saved to the album for user use. Taking the first format as 8-bit YUV420 and the target format as jpeg as an example, the 8-bit YUV420 format third image data can be converted into the jpeg format target image data using a VTcamera virtual camera.

[0079] In summary, this disclosure first acquires first image data in a first format and uses it as input to a super-resolution algorithm to obtain second image data in a second format output by the algorithm. Then, target image data is generated based on the second image data. Notably, the number of bytes per pixel in the second format image data is greater than the number of bytes per pixel in the first format image data. This disclosure outputs the image data processed by the super-resolution algorithm in a second format, which can more realistically and effectively restore multi-color, high dynamic range images and reduces the number of format conversions during image processing, thereby reducing memory overhead and improving image processing speed.

[0080] Figure 4 This is a flowchart illustrating another image processing method according to an exemplary embodiment, such as... Figure 4 As shown, step 103 can be achieved through the following steps:

[0081] In step 1031, the third image data in the first format is determined based on the second image data.

[0082] In step 1032, the third image data is converted into target image data.

[0083] For example, such as Figure 5 As shown, in related technologies, the first format image data output by the super-resolution algorithm needs to be converted to a second format image data by the IPE37 module, and then the second format image data is input into the IPE38 module for downsampling processing. Since the second image data output by the super-resolution algorithm in this disclosure is in a second format, there is no need to convert the second image data; further post-processing can be performed directly on the second image data to obtain the third image data in the first format. In one embodiment, one implementation of step 1031 can be: first, downsampling the second image data to obtain downsampled second image data; then, based on the second image data and the downsampled second image data, obtaining the third image data. Figure 2 As shown, the second image data and the second image data after downsampling by the IPE38 module can be input into the IPE39 module to convert the second image data in the second format and the downsampling second image data to obtain the third image data in the first format. Since the format conversion process via the IPE37 module is eliminated in the post-processing, memory consumption is reduced, system processing performance is improved, and further optimization of processing time is guaranteed.

[0084] In some embodiments, taking an 8-bit YUV420 format as the first format and a P010 YUV420 format as the second format as an example, such as... Figure 2 As shown, the image sensor first outputs raw image data in Bayer format, which is then processed using Bayer2Yuv to convert it into 8-bit YUV420 format first image data. This 8-bit YUV420 first image data can then be used as input to a super-resolution algorithm to obtain P010YUV420 format second image data. This P010YUV420 second image data can be directly input to the IPE38 module for downsampling, resulting in downsampled P010YUV420 format second image data. Both the downsampled P010YUV420 second image data and the downsampled second image data are then input to the IPE39 module to obtain 8-bit YUV420 format third image data. Finally, the VTcamera virtual camera can convert this 8-bit YUV420 format third image data into JPEG format target image data, outputting the final image, which is then saved to the user's album.

[0085] In summary, this disclosure first acquires first image data in a first format and uses it as input to a super-resolution algorithm to obtain second image data in a second format output by the algorithm. Then, target image data is generated based on the second image data. Notably, the number of bytes per pixel in the second format image data is greater than the number of bytes per pixel in the first format image data. This disclosure outputs the image data processed by the super-resolution algorithm in a second format, which can more realistically and effectively restore multi-color, high dynamic range images and reduces the number of format conversions during image processing, thereby reducing memory overhead and improving image processing speed.

[0086] Figure 6 This is a block diagram illustrating an image processing apparatus according to an exemplary embodiment, such as... Figure 6 As shown, the device 200 includes:

[0087] The acquisition module 201 is configured to acquire first image data in a first format.

[0088] Processing module 202 is configured to take the first image data as input to a super-resolution algorithm to obtain second image data in a second format, which is the output of the super-resolution algorithm. The number of bytes corresponding to each pixel in the second format image data is greater than the number of bytes corresponding to each pixel in the first format image data.

[0089] The generation module 203 is configured to generate target image data based on the second image data.

[0090] Figure 7 This is a block diagram illustrating another image processing apparatus according to an exemplary embodiment, such as... Figure 7 As shown, the generation module 203 includes:

[0091] The determination submodule 2031 is configured to determine third image data in a first format based on the second image data.

[0092] The conversion submodule 2032 is configured to convert the third image data into the target image data.

[0093] In one embodiment, the determination submodule 2031 is configured as follows:

[0094] The second image data is downsampled to obtain the downsampled second image data.

[0095] The third image data is obtained based on the second image data and the downsampled second image data.

[0096] In another embodiment, the determination submodule 2031 is configured as follows:

[0097] The format of the second image data and the downsampled second image data are converted to obtain the third image data.

[0098] In another embodiment, the conversion submodule 2032 is configured as follows:

[0099] The image format of the third image data is converted to obtain the target image data.

[0100] In another embodiment, the acquisition module 201 is configured to:

[0101] Acquire raw image data from the image sensor.

[0102] The original image data is converted into first image data in a first format.

[0103] In another embodiment, the output format of the super-resolution algorithm is a second format, and the storage format of the image buffer of the super-resolution algorithm is a second format.

[0104] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0105] In summary, this disclosure first acquires first image data in a first format and uses it as input to a super-resolution algorithm to obtain second image data in a second format output by the algorithm. Then, target image data is generated based on the second image data. Notably, the number of bytes per pixel in the second format image data is greater than the number of bytes per pixel in the first format image data. This disclosure outputs the image data processed by the super-resolution algorithm in a second format, which can more realistically and effectively restore multi-color, high dynamic range images and reduces the number of format conversions during image processing, thereby reducing memory overhead and improving image processing speed.

[0106] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the image processing method provided in this disclosure.

[0107] Figure 8 This is a block diagram illustrating an image processing apparatus 300 according to an exemplary embodiment. For example, apparatus 300 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0108] Reference Figure 8 The device 300 may include one or more of the following components: processing component 302, memory 304, power supply component 306, multimedia component 308, audio component 310, input / output interface 312, sensor component 314, and communication component 316.

[0109] Processing component 302 typically controls the overall operation of device 300, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the image processing method described above. Furthermore, processing component 302 may include one or more modules to facilitate interaction between processing component 302 and other components. For example, processing component 302 may include a multimedia module to facilitate interaction between multimedia component 308 and processing component 302.

[0110] Memory 304 is configured to store various types of data to support the operation of device 300. Examples of such data include instructions for any application or method operating on device 300, contact data, phonebook data, messages, pictures, videos, etc. Memory 304 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.

[0111] Power supply component 306 provides power to various components of device 300. Power supply component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 300.

[0112] Multimedia component 308 includes a screen that provides an output interface between the device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 308 includes a front-facing camera and / or a rear-facing camera. When the device 300 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0113] Audio component 310 is configured to output and / or input audio signals. For example, audio component 310 includes a microphone (MIC) configured to receive external audio signals when device 300 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 304 or transmitted via communication component 316. In some embodiments, audio component 310 also includes a speaker for outputting audio signals.

[0114] Input / output interface 312 provides an interface between processing component 302 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, start buttons, and lock buttons.

[0115] Sensor assembly 314 includes one or more sensors for providing status assessments of various aspects of device 300. For example, sensor assembly 314 may detect the on / off state of device 300, the relative positioning of components such as the display and keypad of device 300, changes in the position of device 300 or a component of device 300, the presence or absence of user contact with device 300, the orientation or acceleration / deceleration of device 300, and temperature changes of device 300. Sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 314 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0116] Communication component 316 is configured to facilitate wired or wireless communication between device 300 and other devices. Device 300 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0117] In an exemplary embodiment, the apparatus 300 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-described image processing method.

[0118] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, which can be executed by a processor 320 of the device 300 to complete the image processing method described above. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0119] The aforementioned device can be a standalone electronic device or a part of a standalone electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be a single IC or a collection of multiple ICs. The chip can include, but is not limited to, the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), and SoC (System on Chip). The aforementioned integrated circuit or chip can be used to execute executable instructions (or code) to implement the aforementioned image processing method. The executable instructions can be stored in the integrated circuit or chip or obtained from other devices or equipment. For example, the integrated circuit or chip includes a processor, memory, and an interface for communicating with other devices. The executable instructions can be stored in the memory, and when the executable instructions are executed by the processor, the above-described image processing method can be implemented; alternatively, the integrated circuit or chip can receive the executable instructions through the interface and transmit them to the processor for execution to implement the above-described image processing method.

[0120] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described image processing method when executed by the programmable device.

[0121] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of this disclosure. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0122] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method of image processing, characterized by, The method comprises: acquiring first image data in a first format; inputting the first image data into a super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel point in the second format image data is greater than the number of bytes corresponding to each pixel point in the first format image data; the output format of the super-resolution algorithm is the second format, and the storage format of the image buffer of the super-resolution algorithm is the second format; performing downsampling processing on the second image data to obtain the second image data after downsampling processing; obtaining third image data according to the second image data and the second image data after downsampling processing; converting the third image data into target image data.

2. The method of claim 1, wherein, The third image data is obtained according to the second image data and the second image data after downsampling processing, comprising: performing format conversion on the second image data and the second image data after downsampling processing to obtain the third image data.

3. The method of claim 1, wherein, The third image data is converted into the target image data, comprising: converting the image format of the third image data to obtain the target image data.

4. The method of claim 1, wherein, The first image data in the first format is acquired, comprising: acquiring original image data acquired by an image sensor; converting the original image data into the first image data in the first format.

5. An apparatus for image processing, characterized by The device comprises: an acquisition module configured to acquire first image data in a first format; a processing module configured to input the first image data into a super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel point in the second format image data is greater than the number of bytes corresponding to each pixel point in the first format image data; the output format of the super-resolution algorithm is the second format, and the storage format of the image buffer of the super-resolution algorithm is the second format; a generation module configured to generate target image data according to the second image data; The generation module comprises: a determination submodule configured to perform downsampling processing on the second image data to obtain the second image data after downsampling processing; and obtain third image data according to the second image data and the second image data after downsampling processing; a conversion submodule configured to convert the third image data into target image data.

6. An apparatus for image processing, characterized by comprise: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: acquire first image data in a first format; input the first image data into a super-resolution algorithm to obtain second image data in a second format output by the super-resolution algorithm; the number of bytes corresponding to each pixel point in the second format image data is greater than the number of bytes corresponding to each pixel point in the first format image data; the output format of the super-resolution algorithm is the second format, and the storage format of the image buffer of the super-resolution algorithm is the second format; downsample the second image data to obtain downsampled second image data; obtain third image data according to the second image data and the downsampled second image data; convert the third image data into target image data.

7. A computer-readable storage medium having stored thereon computer program instructions, wherein, The program instruction is executed by the processor to realize the steps of the method in any one of claims 1-4.

8. A chip, characterized by The processor is used to read instructions to execute the method in any one of claims 1-4.

Images