Image generation method, device, system and equipment and vehicle

Abstract

The invention discloses an image generation method, device, system and equipment and a vehicle. The method comprises the following steps: acquiring image style description information; extracting style information from the image style description information to obtain an image style label corresponding to the style information, and determining an image style parameter corresponding to the image style label as a target image style parameter according to a corresponding relationship between a preset style label and the image style parameter; processing the target image style parameter to obtain a target image signal processing parameter of an image signal processor; and sending the target image signal processing parameter to an image signal processor, so that the image signal processor controls image acquisition according to the target image signal processing parameter to obtain a target image. On the basis, the image style description information required by the user is converted into the target image signal processing parameter, and the image signal processor acquires the image according to the target image signal processing parameter, so that the target image is obtained, and the requirements of the user are better met.

Description

Technical Field

[0001] This application belongs to the field of vehicle control technology, and in particular relates to an image generation method, apparatus, system, device and vehicle. Background Technology

[0002] Typically, the image style generated by a camera system is pre-defined by the manufacturer. Users cannot determine the final image style during the early image generation stage of the ISP, let alone add their own personalized requirements for the final generated image.

[0003] Even if some camera systems support manual style adjustment modes, these modes are limited to adjusting parameters related to the 3A (auto focus (AF), auto exposure (AE), and auto white balance (AWB)), and still cannot generate images that truly meet the user's desired style in real time. Currently, post-processing techniques are usually required to obtain images that meet the user's desired style. Summary of the Invention

[0004] This application provides an image generation method, apparatus, system, device, and vehicle that can better meet users' image needs.

[0005] According to a first aspect of this application, an image generation method is provided, the method comprising:

[0006] Obtain image style description information;

[0007] Extract style information from image style description information to obtain image style labels corresponding to the style information;

[0008] Based on the correspondence between preset style labels and image style parameters, the image style parameters corresponding to the image style labels are determined as the target image style parameters;

[0009] The target image style parameters are processed to obtain the target image signal processing parameters of the image signal processor;

[0010] The target image signal processing parameters are sent to the image signal processor, so that the image signal processor controls image acquisition according to the target image signal processing parameters to obtain the target image.

[0011] Optionally, the parameter types of the target image signal processing parameters include at least one, and the image signal processor includes an image processing module corresponding to the target image signal processing parameters of each parameter type;

[0012] Image signal processing parameters are sent to the image signal processor, enabling the image signal processor to acquire an image based on the image signal processing parameters and obtain the target image, including:

[0013] Based on the parameter type, determine the image processing module corresponding to each parameter type;

[0014] Each target image signal processing parameter is sent to the corresponding image processing module so that the image processing module can acquire the image according to the target image signal processing parameters and obtain the target image.

[0015] Optionally, the parameter types of the target image signal processing parameters include at least one of the following: color temperature parameter, brightness parameter, saturation parameter, detail texture parameter, size parameter, and resolution parameter;

[0016] Each target image signal processing parameter is sent to the corresponding image processing module, so that the image processing module controls image acquisition according to the target image signal processing parameters to obtain the target image, including at least one of the following:

[0017] The brightness parameters are sent to the corresponding automatic white balance module, so that the automatic white balance module controls image acquisition according to the brightness parameters to obtain the target image;

[0018] The color temperature parameter is sent to the corresponding brightness adjustment module, so that the brightness adjustment module controls image acquisition according to the color temperature parameter to obtain the target image;

[0019] The saturation parameter is sent to the corresponding color adjustment module, so that the color adjustment module controls image acquisition according to the saturation parameter to obtain the target image;

[0020] The detail texture parameters are sent to the corresponding sharpening adjustment module, so that the sharpening adjustment module controls image acquisition according to the detail texture parameters to obtain the target image;

[0021] The size parameters are sent to the corresponding image size adjustment module, so that the image size adjustment module controls image acquisition according to the size parameters to obtain the target image;

[0022] The resolution parameters are sent to the corresponding resolution adjustment module, so that the resolution adjustment module controls image acquisition according to the resolution parameters to obtain the target image.

[0023] Optionally, the image style description information is speech information;

[0024] Style information is extracted from image style description information to obtain image style labels corresponding to the style information, including:

[0025] Speech information is converted into text information using a speech conversion model;

[0026] The text information is segmented to obtain multiple text units;

[0027] Based on the correspondence between preset text units and preset style tags, determine the corresponding style tag for each text unit;

[0028] The various style tags are combined to obtain image style tags.

[0029] Optionally, the target image style parameters are processed to obtain the target image signal processing parameters for the image signal processor, including:

[0030] Obtain the fixed-point number format and the range of signal processing parameter values. The range of signal processing parameter values ​​and the fixed-point number format are related to the image signal processor.

[0031] The scaling factor is determined based on the ratio of the range of image style parameters to the range of signal processing parameters, where the range of image style parameters is the range of target image style parameters.

[0032] The target image style parameters are converted according to the fixed-point format and scaling factor to obtain the target image signal processing parameters.

[0033] According to a second aspect of this application, an image generation apparatus is provided, comprising:

[0034] The acquisition module is used to acquire image style description information;

[0035] The tagging module is used to extract style information from image style description information and obtain image style tags corresponding to the style information.

[0036] The determination module is used to determine the image style parameters corresponding to the image style tags as the target image style parameters based on the correspondence between preset style tags and image style parameters.

[0037] The processing module is used to process the style parameters of the target image to obtain the target image signal processing parameters of the image signal processor;

[0038] The transmitting module is used to send the target image signal processing parameters to the image signal processor, so that the image signal processor can control image acquisition according to the target image signal processing parameters to obtain the target image.

[0039] According to a third aspect of this application, an image generation system is provided, comprising:

[0040] Such as the image generating apparatus of any of the second aspects;

[0041] An image signal processor is communicatively connected to an image generating device. It receives target image signal processing parameters sent by the image generating device and controls image acquisition based on the target image signal processing parameters to obtain the target image.

[0042] An image acquisition unit, which communicates with an image signal processor, is used to acquire images based on target image signal processing parameters.

[0043] According to a fourth aspect of this application, an embodiment of this application provides an image generation apparatus, which includes: a processor and a memory storing computer program instructions;

[0044] When the processor executes computer program instructions, it implements an image generation method such as any of the first aspects.

[0045] According to a fifth aspect of this application, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the image generation method of any one of the first aspects.

[0046] According to a sixth aspect of this application, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform an image generation method as described in any of the first aspects.

[0047] According to a seventh aspect of this application, an embodiment of this application provides a vehicle that includes any one of the image generating apparatus of any of the second aspects, the image generating system of any of the third aspects, and the image generating device of any of the fourth aspects.

[0048] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0049] This application provides an image generation method, apparatus, system, device, and vehicle. By acquiring image style description information required by the user, extracting style information from the image style description information, and obtaining an image style tag corresponding to the style information, the target image style parameters corresponding to the image style tag can be determined based on the image style tag. The target image style parameters are then converted into target image signal processing parameters that can be processed by an image signal processor, and sent to the image signal processor. The image signal processor then acquires an image based on the target image signal, thereby obtaining the target image. Based on this, by converting the image style description information required by the user into target image signal processing parameters that the image signal processor can process, and by having the image signal processor acquire an image based on the target image signal processing parameters, the target image required by the user is obtained, thus better meeting the user's needs.

[0050] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0052] Figure 1 This is a flowchart illustrating an image generation method according to an exemplary embodiment;

[0053] Figure 2 This is a structural block diagram of an image generation apparatus according to an exemplary embodiment;

[0054] Figure 3 This is a structural block diagram of an image generation system according to an exemplary embodiment;

[0055] Figure 4 This is a structural block diagram of an image generation device according to an exemplary embodiment. Detailed Implementation

[0056] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0057] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0058] As described in the background section, existing image generation technologies cannot generate images that truly meet the user's desired style in real time. Currently, post-processing techniques are typically required to obtain images that satisfy the user's desired style.

[0059] To address the problems of existing technologies, embodiments of this application convert the image style description information required by the user into target image signal processing parameters that can be processed by the image signal processor, and then acquire an image according to the target image signal processing parameters by the image signal processor, thereby obtaining the target image required by the user, thus better meeting the user's needs.

[0060] Based on this, this application provides an image generation method, apparatus, system, device, and vehicle. The image generation method provided in the embodiments of this application will be described first. The system includes:

[0061] Figure 1 A structural block diagram of an image generation method provided in one embodiment of this application is shown. For example... Figure 1As shown, in one embodiment, the method may include:

[0062] S101, Obtain image style description information;

[0063] S102, Extract style information from image style description information to obtain image style labels corresponding to style information;

[0064] S103, Based on the correspondence between preset style labels and image style parameters, determine the image style parameters corresponding to the image style labels as the target image style parameters;

[0065] S104, Process the target image style parameters to obtain the target image signal processing parameters of the image signal processor;

[0066] S105, the target image signal processing parameters are sent to the image signal processor so that the image signal processor controls image acquisition according to the target image signal processing parameters to obtain the target image.

[0067] Based on the above embodiments, this application obtains the image style description information required by the user, extracts style information from the image style description information to obtain the image style tag corresponding to the style information. Therefore, the target image style parameters corresponding to the image style tag can be determined based on the image style tag. The target image style parameters are then converted into target image signal processing parameters that can be processed by an image signal processor, and these parameters are sent to the image signal processor so that the processor can acquire an image from the target image signal, thereby obtaining the target image. In this way, by converting the image style description information required by the user into target image signal processing parameters that the image signal processor can process, and by having the image signal processor acquire an image based on these parameters, the target image required by the user is obtained, thus better meeting the user's needs.

[0068] In S101 above, the image style may include: image brightness, image resolution, image contrast, etc.

[0069] Image style description information refers to the user's description of the image style, such as: adjust the image resolution to 1920×1080, increase the image resolution, etc.

[0070] Image style description information can be obtained in response to user operation information, which may include user actions to adjust the image style according to their needs, such as adjusting controls, clicking on the display screen, etc.

[0071] In S102 above, each style description information may contain a lot of information unrelated to the image style. Taking the style description information as speech information as an example, information unrelated to the style may include interjections, etc. For example: "Please adjust the image style description information to 1920×1080, is that okay?" The words "please" and "is that okay?" are noise unrelated to the image style and need to be removed. Similarly, when the image style description information is operation information, the user's machine opening operation (such as power-on operation), the interface selection operation on the display screen, etc., also need to be removed.

[0072] Therefore, it is necessary to extract style information related to the image style from the style description information, and then determine the image style label corresponding to the style information based on the style information.

[0073] Image style tags can take the form of words, phrases, or sentences.

[0074] As an example, the image style description information is "adjust the image resolution to 1920×1080". The style information includes the image resolution, the adjusted resolution, and 1920×1080. The label corresponding to the image resolution can be A1, and the label corresponding to 1920×1080 can be B1. That is, the image style label corresponding to adjusting the image resolution to 1920×1080 can be A1B1.

[0075] In another example, the image style label can also be obtained by simplifying the image description information. For example, if the image style description information is to adjust the image resolution to 1920×1080, then after simplification, the image style label can be obtained as image resolution 1920×1080.

[0076] In the above S103, by presetting, each preset style label can be determined to correspond to a preset image style parameter, and a correspondence is formed between the two. After obtaining the image style label, the corresponding target image style parameter can be determined from the correspondence. The target image style parameter may include style type and parameter value.

[0077] As an example, a preset network model is used, which contains the above-mentioned correspondence. The target image style parameters are obtained by recognizing image style labels through the preset network model.

[0078] The preset network model can be Style Net (style parameter generation network model), which can convert image style labels into numerical feature vectors or parameters (target image style parameters).

[0079] In the above S104, the image signal processor has specific parameter format requirements. Therefore, by converting the target image style parameters, the target image signal processing parameters that meet the requirements of the image signal processor are obtained, so that the image signal processor can process the image according to the image signal processing parameters.

[0080] As an example, the Parameters module can be used to perform fixed-point transformation on the target image style parameters to obtain target image signal processing parameters that meet the requirements of the image signal processor.

[0081] As an example, the target image style parameter refers to the image style parameter that meets the requirements. The image style parameter may include at least one of the following: color temperature parameter, brightness parameter, saturation parameter, detail texture parameter, size parameter, and resolution parameter.

[0082] In S105 above, after obtaining the target image signal processing parameters, the target image signal processing parameters are sent to the image signal processor, so that the image signal processor can process the original image according to the target image signal processing parameters to obtain the target image, or it can obtain a new target image according to the target image signal processing parameters.

[0083] As an example, if the resolution of the original image is 1280×1080, then after sending the target image signal processing parameters to the image signal processor, the image signal processor can adjust the resolution of the original image from 1280×1080 to a target image of 1920×1280.

[0084] In another example, after the target image signal processing parameters are sent to the image signal processor, the image signal processor directly acquires a target image with an image resolution of 1280×1080 through the imaging device.

[0085] As an example, the image signal processor can be an ISP module.

[0086] To improve user satisfaction with the target image, this application also provides another implementation of the image generation method.

[0087] The target image signal processing parameters include at least one parameter type, and the image signal processor includes an image processing module corresponding to the target image signal processing parameters of each parameter type;

[0088] The above S105 may include:

[0089] S201, Based on the parameter type, determine the image processing module corresponding to each parameter type;

[0090] S202, each target image signal processing parameter is sent to the corresponding image processing module so that the image processing module can acquire the image according to the target image signal processing parameters and obtain the target image.

[0091] Based on the above embodiments, by setting an image processing module in the image signal processor that corresponds to the type of target image signal processing parameters, the image signal processor can process any type of target image signal processing parameter, thereby improving the processing effect of each target image signal processing parameter and enabling users to obtain more satisfactory target images.

[0092] In the above S201, the image signal processing module in the image signal processor can only process its corresponding target image signal processing parameters. For example, the resolution image processing module can only process target image signal processing parameters of type resolution, and the brightness image processing module can only process target image signal processing parameters of type brightness.

[0093] The image signal processor is equipped with image processing modules corresponding to the types of target image signal processing parameters. Therefore, based on the type of target image signal processing parameters, the image processing module that can process that type of target image signal processing parameters is determined.

[0094] As an example, the parameter types of the target image signal processing parameters may include at least one of the following: color temperature parameter, brightness parameter, saturation parameter, detail texture parameter, size parameter, and resolution parameter.

[0095] The image signal processor may include: an AWB (Automatic White Balance) module corresponding to the color temperature parameter, a brightness adjustment module corresponding to the brightness parameter, a color adjustment module corresponding to the saturation parameter, a sharpening adjustment module corresponding to the detail and texture parameter, a size adjustment module corresponding to the size parameter, and a resolution adjustment module corresponding to the resolution parameter.

[0096] In S202 above, the target image signal processing parameters are sent to the corresponding image processing modules so that the image processing modules can process the image signal processing parameters.

[0097] As an example, the target image signal processing parameters may include multiple types of parameters. The parameters corresponding to each type are then sent to their respective image processing modules for processing. For instance, these may include resolution and brightness. During the transmission process, the parameters corresponding to the resolution component are distributed to the resolution image processing module, and the parameters corresponding to the brightness component are sent to the brightness image processing module.

[0098] Specifically, S202 may also include:

[0099] The brightness parameters are sent to the corresponding automatic white balance module, so that the automatic white balance module controls image acquisition according to the brightness parameters to obtain the target image;

[0100] The color temperature parameter is sent to the corresponding brightness adjustment module, so that the brightness adjustment module controls image acquisition according to the color temperature parameter to obtain the target image;

[0101] The saturation parameter is sent to the corresponding color adjustment module, so that the color adjustment module controls image acquisition according to the saturation parameter to obtain the target image;

[0102] The detail texture parameters are sent to the corresponding sharpening adjustment module, so that the sharpening adjustment module controls image acquisition according to the detail texture parameters to obtain the target image;

[0103] The size parameters are sent to the corresponding image size adjustment module, so that the image size adjustment module controls image acquisition according to the size parameters to obtain the target image;

[0104] The resolution parameters are sent to the corresponding resolution adjustment module, so that the resolution adjustment module controls image acquisition according to the resolution parameters to obtain the target image.

[0105] To obtain more accurate image style labels, this application also provides another implementation of the image generation method.

[0106] Image style description information is speech information;

[0107] The above S102 may include:

[0108] S301 converts speech information into text information through a speech conversion model;

[0109] S302, the text information is segmented to obtain multiple text units;

[0110] S303, Determine the corresponding style tag for each text unit based on the correspondence between preset text units and preset style tags;

[0111] S304 combines the various style tags to obtain image style tags.

[0112] Based on the above embodiments, by recognizing speech information, converting it into text information, and then determining the style tag corresponding to each text unit in the text information, the style tags can be combined to obtain accurate image style tags. Based on this, it is possible to recognize and convert the user's speech information to obtain image style tags, thereby improving the accuracy of obtaining image style tags from speech information.

[0113] In the above S301, the speech information is recognized by the speech conversion model and converted into the corresponding text information;

[0114] As an example, a speech conversion model may include the Language2text model.

[0115] In S302 above, the text information contains a lot of content. Based on the content, semantics and other multiple text information expressed by the text information, multiple text units are obtained.

[0116] As an example, if the text message is: Please adjust the resolution to 1920×1280, then the text message can be segmented into multiple text units such as "please adjust", "resolution", "adjust to", and "1920×1280".

[0117] In S303 above, the style tag corresponding to each text unit is determined by the pre-set correspondence between preset text units and preset style tags.

[0118] It should be noted that some text units may be invalid and do not have corresponding style tags. For example, "please" is just a polite interjection used by the user and has no substantial relationship with the image style, so it does not have a corresponding style tag.

[0119] In S304 above, the various style tags are combined to form a complete image style tag.

[0120] As an example, image style tags may have format and length requirements, so the initial image style tags after splicing and combining may need to be deleted or added during the combination process to obtain a complete image style tag.

[0121] As an example, the image style label can be determined based on the text information using a tokenizer, thereby achieving the operations described in S302-S304 above.

[0122] To improve the accuracy of the target image signal processing parameters, this application also provides another implementation of the image generation method.

[0123] The above S104 may include:

[0124] S401, obtain the fixed-point format and signal processing parameter value range. The signal processing parameter value range and fixed-point format are related to the image signal processor.

[0125] S402, determine the scaling factor based on the ratio of the value range of the image style parameter to the value range of the signal processing parameter, wherein the value range of the image style parameter is the value range of the target image style parameter;

[0126] S403 performs format conversion on the target image style parameters according to the fixed-point format and scaling factor to obtain the target image signal processing parameters.

[0127] Based on the above embodiments, by determining the scaling factor suitable for the image signal processor according to the fixed-point format and signal processing parameter value range related to the image signal processor, and the ratio of the image style parameter value range to the signal processing parameter value range, the target image style parameters are converted according to the scaling factor and the fixed-point format, thereby making them suitable for the target image signal processing parameters of the image signal processor and improving the accuracy of the target image signal processing parameters.

[0128] In S401 above, the range of signal processing parameter values ​​that the image signal processor can normally process with respect to the signal processing parameters is obtained, as well as the fixed-point number format required by the image signal processor for the signal processing parameters.

[0129] As an example, a fixed-point number is a method of numerical representation where the position of the decimal point remains constant. In computer science and digital processing, fixed-point numbers are commonly used in scenarios such as binary counting systems and digital signal processing. Fixed-point numbers mainly come in two forms: fixed-point decimals and fixed-point integers.

[0130] In step S402 above, the range of image style parameters refers to the range of values ​​that the image style parameters can take under normal circumstances. The ratio of the range of image style parameters to the range of signal processing parameters determines the scaling factor required to convert the image style parameters into signal processing parameters in the image signal processor.

[0131] In S403 above, the target image style parameters are scaled according to the scaling factor, and the scaled target image style parameters are converted according to the fixed-point number format to obtain the target image signal processing parameters.

[0132] Each target image style parameter is multiplied by a scaling factor to obtain a scaled target image style parameter. The scaled target image style parameter is then converted to an integer (this usually involves rounding or truncating) to ensure that the converted integer is in a fixed-point format (i.e., it does not exceed the range of the integer part).

[0133] It should be noted that the application scenarios described in the above embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems; and, the new embodiments of this application can be combined with each other, and the new solutions formed by the combination of various embodiments are all within the protection scope of this application.

[0134] Based on the same inventive concept, this application also provides an image generation apparatus 510. (Specifically combined with...) Figure 2 Please provide a detailed explanation.

[0135] Figure 2 A schematic diagram of the hardware structure of the image generation apparatus 510 provided in an embodiment of the present invention is shown.

[0136] like Figure 2 As shown, the image generation apparatus 510 may include:

[0137] Module 511 is used to acquire image style description information;

[0138] The tagging module 512 is used to extract style information from image style description information and obtain image style tags corresponding to the style information.

[0139] The determining module 513 is used to determine the image style parameter corresponding to the image style label as the target image style parameter according to the correspondence between the preset style label and the image style parameter;

[0140] Processing module 514 is used to process the target image style parameters to obtain the target image signal processing parameters of the image signal processor;

[0141] The transmitting module 515 is used to send the target image signal processing parameters to the image signal processor, so that the image signal processor controls image acquisition according to the target image signal processing parameters to obtain the target image.

[0142] Based on the above embodiments, the acquisition module 511 acquires the image style description information required by the user, the tagging module 512 extracts style information from the image style description information to obtain the image style tag corresponding to the style information, and the determination module 513 can determine the target image style parameters corresponding to the image style tag according to the image style tag. The processing module 514 then converts the target image style parameters into target image signal processing parameters that can be processed by the image signal processor, and the sending module 515 sends the target image signal processing parameters to the image signal processor so that the image signal processor can acquire the image of the target image signal, thereby obtaining the target image. Based on this, by converting the image style description information required by the user into target image signal processing parameters that the image signal processor can process, and by having the image signal processor acquire the image according to the target image signal processing parameters, the target image required by the user is obtained, thereby better meeting the user's needs.

[0143] Optionally, the parameter types of the target image signal processing parameters include at least one, and the image signal processor includes an image processing module corresponding to the target image signal processing parameters of each parameter type;

[0144] The sending module 515 may include:

[0145] The first determining unit determines the image processing module corresponding to each parameter type based on the parameter type.

[0146] The transmitting unit is used to send each type of target image signal processing parameter to the corresponding image processing module, so that the image processing module can acquire the image according to the target image signal processing parameter and obtain the target image.

[0147] Optionally, the parameter types of the target image signal processing parameters include at least one of the following: color temperature parameter, brightness parameter, saturation parameter, detail texture parameter, size parameter, and resolution parameter;

[0148] The transmitting unit may include one of the following:

[0149] The first transmitting subunit is used to send the brightness parameters to the corresponding automatic white balance module, so that the automatic white balance module controls image acquisition according to the brightness parameters to obtain the target image;

[0150] The second transmitting subunit is used to send the color temperature parameters to the corresponding brightness adjustment module, so that the brightness adjustment module controls image acquisition according to the color temperature parameters to obtain the target image;

[0151] The third transmitting subunit is used to send the saturation parameter to the corresponding color adjustment module, so that the color adjustment module controls image acquisition according to the saturation parameter to obtain the target image;

[0152] The fourth sending subunit is used to send the detail texture parameters to the corresponding sharpening adjustment module, so that the sharpening adjustment module controls the image acquisition according to the detail texture parameters to obtain the target image;

[0153] The fifth transmitting subunit is used to send the size parameters to the corresponding image size adjustment module, so that the image size adjustment module controls image acquisition according to the size parameters to obtain the target image;

[0154] The sixth transmitting subunit is used to send the resolution parameters to the corresponding resolution adjustment module, so that the resolution adjustment module controls the image acquisition according to the resolution parameters to obtain the target image.

[0155] Optionally, the image style description information is speech information;

[0156] Tagging module 512 may include:

[0157] The first conversion unit is used to convert speech information into text information through a speech conversion model;

[0158] A segmentation unit is used to divide text information into multiple text units;

[0159] The second determining unit is used to determine the style tag corresponding to each text unit based on the correspondence between preset text units and preset style tags;

[0160] The combination unit is used to combine various style tags to obtain image style tags.

[0161] Optionally, the processing module 514 may include:

[0162] The acquisition unit is used to acquire the fixed-point number format and the range of signal processing parameter values. The range of signal processing parameter values ​​and the fixed-point number format are related to the image signal processor.

[0163] The third determining unit is used to determine the scaling factor based on the ratio of the value range of the image style parameter to the value range of the signal processing parameter, wherein the value range of the image style parameter is the value range of the target image style parameter;

[0164] The second conversion unit is used to perform format conversion on the target image style parameters according to the fixed-point format and scaling factor to obtain the target image signal processing parameters.

[0165] The image generation device 510 provided in this embodiment can achieve... Figure 1 The various processes implemented in any one of the image generation method embodiments can achieve the same technical effect, and will not be described again here to avoid repetition.

[0166] like Figure 3The block diagram of the image generation system shown is illustrated. In one embodiment, the present invention also includes an image generation system 500.

[0167] Specifically, the image generation system may include:

[0168] Image generating apparatus 510;

[0169] The image signal processor 520 is communicatively connected to the image generating device 510. It is used to receive target image signal processing parameters sent by the image generating device 510 and control image acquisition according to the target image signal processing parameters to obtain the target image.

[0170] Image acquisition unit 530 is communicatively connected to image signal processor 520 and is used to acquire images according to target image signal processing parameters.

[0171] Figure 4 A schematic diagram of the hardware structure of the image generation device provided in an embodiment of the present invention is shown.

[0172] The image generating device may include a processor 601 and a memory 602 storing computer program instructions.

[0173] Specifically, the processor 601 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0174] Memory 602 may include mass storage for data or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 602 is non-volatile solid-state memory.

[0175] In certain embodiments, memory 602 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, generally, memory 602 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors 601), it is operable to perform the operations described with reference to the method according to one aspect of this application.

[0176] The processor 601 implements any of the image generation methods described in the above embodiments by reading and executing computer program instructions stored in the memory 602.

[0177] In one example, the image generation device may further include a communication interface 603 and a bus 604. As shown in the figure, the processor 601, memory 602, and communication interface 603 are connected via bus 604 and communicate with each other.

[0178] The communication interface 603 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of the present invention.

[0179] Bus 604 includes hardware, software, or both. For example, and not as a limitation, bus 604 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, a Wireless Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Control Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 604 may include one or more buses 604. Although specific bus 604s are described and illustrated in embodiments of this application, this application contemplates any suitable bus 604 or interconnect.

[0180] This image generation device can achieve a combination based on current image generation methods. Figures 1-2 The image generation method and image generation apparatus 510 described herein.

[0181] In addition, this application also provides a computer program product, including computer program instructions, which, when executed by processor 601, can implement the steps and corresponding content of the aforementioned method embodiments.

[0182] Finally, this application embodiment also provides a vehicle that includes the above-described image generation apparatus 510 and / or image generation device.

[0183] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0184] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0185] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0186] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable image generation apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable image generation apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0187] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. An image generation method, characterized in that, The method includes: Obtain image style description information; Extract style information from the image style description information to obtain image style tags corresponding to the style information; Based on the correspondence between preset style tags and image style parameters, the image style parameters corresponding to the image style tags are determined as the target image style parameters; The target image style parameters are processed to obtain the target image signal processing parameters of the image signal processor; The target image signal processing parameters are sent to the image signal processor, so that the image signal processor controls image acquisition according to the target image signal processing parameters to obtain the target image.

2. The method as described in claim 1, characterized in that, The parameter types of the target image signal processing parameters include at least one; the image signal processor includes an image processing module corresponding to the target image signal processing parameters of each parameter type; The step of sending the image signal processing parameters to the image signal processor, so that the image signal processor controls image acquisition according to the image signal processing parameters to obtain the target image, includes: Based on the parameter type, determine the image processing module corresponding to each parameter type; Each target image signal processing parameter is sent to the corresponding image processing module so that the image processing module controls image acquisition according to the target image signal processing parameters to obtain the target image.

3. The method as described in claim 2, characterized in that, The target image signal processing parameters include at least one of the following: color temperature parameter, brightness parameter, saturation parameter, detail texture parameter, size parameter, and resolution parameter; The step of sending each target image signal processing parameter to a corresponding image processing module, so that the image processing module controls image acquisition according to the target image signal processing parameters to obtain the target image, includes at least one of the following: The brightness parameters are sent to the corresponding automatic white balance module, so that the automatic white balance module controls image acquisition according to the brightness parameters to obtain the target image; The color temperature parameter is sent to the corresponding brightness adjustment module, so that the brightness adjustment module controls image acquisition according to the color temperature parameter to obtain the target image; The saturation parameter is sent to the corresponding color adjustment module, so that the color adjustment module controls image acquisition according to the saturation parameter to obtain the target image; The detailed texture parameters are sent to the corresponding sharpening adjustment module, so that the sharpening adjustment module controls image acquisition according to the detailed texture parameters to obtain the target image; The size parameters are sent to the corresponding image size adjustment module, so that the image size adjustment module controls image acquisition according to the size parameters to obtain the target image; The resolution parameters are sent to the corresponding resolution adjustment module, so that the resolution adjustment module controls image acquisition according to the resolution parameters to obtain the target image.

4. The method as described in claim 1, characterized in that, The image style description information is voice information; The step of extracting style information from the image style description information to obtain an image style tag corresponding to the style information includes: The speech information is converted into text information using a speech conversion model; The text information is segmented to obtain multiple text units; Based on the correspondence between preset text units and preset style tags, determine the style tag corresponding to each text unit; The style tags are combined to obtain the image style tags.

5. The method according to any one of claims 1-4, characterized in that, The process of processing the target image style parameters to obtain the target image signal processing parameters for the image signal processor includes: Obtain the fixed-point number format and the range of signal processing parameter values, wherein the range of signal processing parameter values ​​and the fixed-point number format are related to the image signal processor; The scaling factor is determined based on the ratio of the range of values ​​for the image style parameters to the range of values ​​for the signal processing parameters, wherein the range of values ​​for the image style parameters is the range of values ​​for the target image style parameters. The target image style parameters are format-converted according to the fixed-point format and the scaling factor to obtain the target image signal processing parameters.

6. An image generation apparatus, characterized in that, The device includes: The acquisition module is used to acquire image style description information; A tagging module is used to extract style information from the image style description information to obtain image style tags corresponding to the style information; The determination module is used to determine the image style parameter corresponding to the image style label as the target image style parameter based on the correspondence between the preset style label and the image style parameter; The processing module is used to process the style parameters of the target image to obtain the target image signal processing parameters of the image signal processor; The transmitting module is used to send the target image signal processing parameters to the image signal processor, so that the image signal processor controls image acquisition according to the target image signal processing parameters to obtain the target image.

7. An image generation system, characterized in that, The system includes: The image generation apparatus as described in claim 6; An image signal processor, communicatively connected to the image generating device, is used to receive the target image signal processing parameters sent by the image generating device, and control image acquisition according to the target image signal processing parameters to obtain the target image; An image acquisition device, which is communicatively connected to the image signal processor, is used to acquire images according to the target image signal processing parameters.

8. An image generation device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-5.

10. A vehicle, characterized in that, The vehicle includes at least one of the device as described in claim 6, the system as described in claim 7, and the equipment as described in claim 8.

Images