Vehicle-mounted image quality optimization method and system

Abstract

The invention discloses a vehicle-mounted image quality optimization method, which comprises the following steps that: a far-end server preliminarily selects an image quality adjustment parameter corresponding to each scene according to environmental conditions and historical operation data of different scenes in a preset route of vehicle operation, generates an image quality adjustment parameter set, sends the image quality adjustment parameter set to a vehicle, and preloads the image quality adjustment parameter set in the local of the vehicle; when the vehicle arrives at a certain scene, the scene around the vehicle is shot in real time, the current image quality is analyzed, and the optimal image quality adjusting parameter is selected and output through a transverse comparison test; in the vehicle running process, image quality parameters are continuously collected, the optimal image quality adjusting parameters are adjusted in real time, and the images are optimized in real time. According to the embodiment of the invention, the image effect meeting the standard requirement is provided for the automatic driving algorithm at any time through the seamless switching of the image quality adjustment parameters, and the traffic accident caused by the confusion of the automatic driving algorithm logic due to the frequent jumping of the image is avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle-mounted technology, and in particular to a vehicle-mounted image quality optimization method and system, electronic equipment and storable medium. Background Art

[0002] With the rapid development of technology, in-vehicle intelligent driving algorithms have increasingly higher requirements for the accuracy of image display of scenes around the vehicle. In in-vehicle intelligent driving algorithms, the image quality of the camera needs to meet specific requirements to ensure the recognition accuracy of the autonomous driving algorithm.

[0003] For different scenes around the vehicle, the same camera module requires different image quality adjustment parameters to ensure that the output image is displayed normally. Any abnormality or delay in image display may affect the recognition accuracy of the autonomous driving algorithm, thereby endangering driving safety.

[0004] The traditional scene switching process is that when the camera module obtains an image frame, it calculates the obtained frame to determine whether the brightness, contrast and other parameters of the frame are within the threshold range of the current image quality adjustment parameter scene. If not within the threshold range, the image quality adjustment parameter is switched to achieve switching to the appropriate image quality adjustment parameter after 3-4 frames.

[0005] The real-time switching of image quality adjustment parameters may cause frame loss or abnormal effect frames, thus affecting the intelligent driving algorithm's image recognition of the surrounding scene. If there are more than two image quality adjustment parameters that need to be switched, there may be jumps, thus affecting the intelligent driving process. Summary of the invention

[0006] One of the purposes of the embodiments of the present invention is to provide a method and system for optimizing vehicle image quality, an electronic device and a storage medium, which are used to solve the problem that the efficiency of switching image quality adjustment parameters of vehicle cameras is low, thereby reducing the recognition accuracy of intelligent driving algorithms.

[0007] In order to solve the above technical problems, in a first aspect, an embodiment of the present invention provides a method for optimizing vehicle image quality, the method comprising:

[0008] The remote server preliminarily selects the image quality adjustment parameters corresponding to each scene according to the environmental conditions and historical operation data of different scenes in the preset route of the vehicle, and generates an image quality adjustment parameter set;

[0009] Sending the image quality adjustment parameter set to the vehicle, and preloading the image quality adjustment parameter set locally in the vehicle;

[0010] When the vehicle arrives at a certain scene, it will take real-time photos of the scene around the vehicle and analyze the current image quality. Through horizontal comparison tests, it will select the optimal image quality adjustment parameters for output.

[0011] During the operation of the vehicle, image quality parameters are continuously collected, the optimal image quality adjustment parameters are adjusted in real time, and the image is optimized in real time.

[0012] Preferably, the environmental conditions include, but are not limited to: vehicle location, geographical environment, road type, weather conditions and lighting conditions.

[0013] Preferably, the selecting of the image quality adjustment parameters corresponding to each scene specifically includes:

[0014] The system uses a parameter selection model to predict the optimal set of image quality adjustment parameters based on historical operating data and environmental conditions.

[0015] Preferably, the system uses a parameter selection model to predict the optimal image quality adjustment parameter set based on historical operation data and environmental conditions, specifically including:

[0016] The vehicle position, road type, weather conditions, and lighting conditions in the historical operating data are input into a preset parameter selection model. The multi-mode loop algorithm of the parameter selection model performs calculations and predictions based on the historical operating data and environmental conditions, and screens out image quality adjustment parameters corresponding to each operating scenario, thereby forming an image quality adjustment parameter set for each scenario under the vehicle's preset operating route.

[0017] Preferably, the analyzing the current image quality specifically includes:

[0018] The raw image data obtained by shooting is re-injected to obtain the effect diagrams corresponding to different image quality adjustment parameters, and the image attribute parameters are calculated.

[0019] Preferably, the image attribute parameters specifically include but are not limited to brightness, contrast, and clarity, which correspond to the histogram grayscale distribution, histogram brightness standard deviation, and histogram brightness histogram entropy in the effect diagram, respectively.

[0020] Preferably, the real-time adjustment of the optimal image quality adjustment parameters specifically includes:

[0021] When a scene switch is detected or the image quality is lower than a set quality threshold, the optimal image quality adjustment parameters are reselected.

[0022] In a second aspect, in order to solve the technical problem of the present invention, an embodiment of the present invention further provides a vehicle-mounted image quality optimization system, the system comprising:

[0023] The remote server is used to preliminarily select image quality adjustment parameters corresponding to each scene according to environmental conditions and historical operation data of different scenes in the preset route of the vehicle, and generate an image quality adjustment parameter set;

[0024] The remote server is also used to send the image quality adjustment parameter set to the vehicle and preload the image quality adjustment parameter set locally in the vehicle;

[0025] The vehicle-mounted system, when the vehicle arrives at a certain scene, the vehicle-mounted camera takes real-time photos of the scene around the vehicle. The vehicle-mounted system analyzes the current image quality and selects the optimal image quality adjustment parameters for output through horizontal comparison tests. During the operation of the vehicle, the image quality parameters are continuously collected, the optimal image quality adjustment parameters are adjusted in real time, and the image is optimized in real time.

[0026] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method as described above.

[0027] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor or a computer, the processor executes the method as described above.

[0028] Compared with the prior art, the vehicle-mounted image quality optimization method and system provided by the embodiment of the present invention have at least the following beneficial effects:

[0029] The embodiment of the present invention can provide the autonomous driving algorithm with image effects that meet the standard requirements at any time through seamless switching of image quality adjustment parameters, avoid frequent image jumps, and thus avoid the occurrence of traffic accidents caused by confusing the algorithm logic of the autonomous driving, thereby improving the recognition accuracy and stability of the self-driving system in a variety of complex environments. Compared with the switching back and forth of two sets of parameters in the prior art, the technical solution of the embodiment of the present invention can access more different groups of parameters, thereby more finely ensuring the stability and accuracy of the image effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The preferred implementation modes will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.

[0031] Figure 1 A schematic diagram of a vehicle-mounted image quality optimization method according to an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a vehicle-mounted image quality optimization system according to an embodiment of the present invention;

[0033] Figure 3 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0035] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0036] The following mainly takes some specific embodiments as examples to describe in detail the implementation of the technical solution of the present invention.

[0037] like Figure 1 As shown, in order to achieve the purpose of the present invention, an embodiment of the present invention provides a method for optimizing vehicle image quality, the method comprising:

[0038] S1. The remote server preliminarily selects image quality adjustment parameters corresponding to each scene according to the environmental conditions and historical operation data of different scenes in the preset route of the vehicle, and generates an image quality adjustment parameter set;

[0039] S2, sending the image quality adjustment parameter set to the vehicle, and preloading the image quality adjustment parameter set locally in the vehicle;

[0040] S3. When the vehicle arrives at a certain scene, the scene around the vehicle is photographed in real time and the current image quality is analyzed. Through horizontal comparison test, the optimal image quality adjustment parameters are selected for output;

[0041] S4. During the operation of the vehicle, continuously collect and calculate image quality parameters, adjust the optimal image quality adjustment parameters in real time, and optimize the image in real time.

[0042] Preferably, the environmental conditions include, but are not limited to: vehicle location, geographical environment, road type, weather conditions and lighting conditions.

[0043] Preferably, the selecting of the image quality adjustment parameters corresponding to each scene specifically includes:

[0044] The system uses a parameter selection model to predict the optimal set of image quality adjustment parameters based on historical operating data and environmental conditions.

[0045] Preferably, the system uses a parameter selection model to predict the optimal image quality adjustment parameter set based on historical operation data and environmental conditions, specifically including:

[0046] The vehicle position, road type, weather conditions, and lighting conditions in the historical operating data are input into a preset parameter selection model. The multi-mode loop algorithm of the parameter selection model performs calculations and predictions based on the historical operating data and environmental conditions, and screens out image quality adjustment parameters corresponding to each operating scenario, thereby forming an image quality adjustment parameter set for each scenario under the vehicle's preset operating route.

[0047] Preferably, the analyzing the current image quality specifically includes:

[0048] The raw image data obtained by shooting is re-injected to obtain the effect diagrams corresponding to different image quality adjustment parameters, and the image attribute parameters are calculated.

[0049] Preferably, the image attribute parameters specifically include but are not limited to brightness, contrast, and clarity, which correspond to the histogram grayscale distribution, histogram brightness standard deviation, and histogram brightness histogram entropy in the effect diagram, respectively.

[0050] Preferably, the real-time adjustment of the optimal image quality adjustment parameters specifically includes:

[0051] When a scene switch is detected or the image quality is lower than a set quality threshold, the optimal image quality adjustment parameters are reselected.

[0052] For intelligent vehicle systems, when vehicles are driving in different scenarios, intelligent driving algorithms need standard images to identify specific key objects.

[0053] During the driving of the vehicle, the technical solution of the embodiment of the present invention is used to automatically predict the image quality adjustment parameters that will be needed, and the image quality adjustment parameters to be used are pre-selected.

[0054] After the vehicle enters the actual scene, the camera collects image data in real time. The intelligent vehicle system will calculate the image attribute parameter values ​​based on contrast, brightness standard deviation, brightness histogram entropy, etc. These image attribute parameters are used to characterize the image quality and select the current image quality adjustment parameter set.

[0055] For example, the image attribute parameters that are automatically adjusted by environmental factors are brightness (contrast) and clarity (noise reduction). Brightness corresponds to one-dimensional histogram entropy and histogram standard deviation, clarity corresponds to two-dimensional histogram entropy, and color has no standard for the time being. Since the exposure time of the module is fixed, overexposure and underexposure can only be adjusted by modifying the exposure gain in the image quality adjustment parameters.

[0056] Overexposure and underexposure can be directly judged by whether there are a large number of pixels accumulated at brightness values ​​of 0 or 255. Underexposure requires gain enhancement, and overexposure requires gain reduction. Then, tone mapping is adjusted according to the histogram distribution. Tone mapping mainly modifies GTM, using automatic brightness curve for parameter matching.

[0057] The clarity depends on the two-dimensional grayscale entropy. If it is not lower than the low threshold, no adjustment is required. However, if it is lower than the low threshold, it is necessary to improve the noise reduction in the image quality adjustment parameters so that the value of the two-dimensional grayscale entropy is greater than the high threshold.

[0058] Here, the automatic brightness curve includes two modes: S-curve enhancement and extreme value suppression;

[0059] S-curve enhancement is to enhance the image contrast through a nonlinear brightness curve, making the details of the bright and dark parts richer while maintaining the balance of the midtones. It is often used in applications such as HDR mapping, image contrast enhancement, and display adjustment.

[0060] Extreme value suppression reduces noise and unnatural brightness differences by limiting the extreme brightness values ​​in the image. It is widely used in HDR image processing, low-light image enhancement, and medical image processing.

[0061] In addition, you can also adaptively distinguish between day and night modes by adjusting the module sensitivity intensity in the image quality adjustment parameters.

[0062] In day mode, the histogram of normal urban roads should be distributed in as many grayscales as possible (0-255) in a normally distributed state. In night mode, the histogram of normal urban roads will be mainly distributed in grayscales of 0-n. The size of n will directly affect the perception of night images. n is generally around 128, and a standard can be set for this. In addition, the ratio of histogram entropy to the number of effective grayscales (n) can also be used as a standard for measuring contrast at night.

[0063] In addition, in the embodiment of the present invention, the ISP (image signal processor) also involves a series of other image quality adjustment parameters that affect the image quality, mainly including the following categories:

[0064] Noise Reduction Strength: Used to reduce image noise. The Noise Reduction Strength determines the degree of noise suppression.

[0065] Sharpening parameters: Improve the clarity of image details.

[0066] Color correction parameters: Adjust the color performance of the image, including color matrix, saturation, and white balance.

[0067] Dynamic Range Parameters: Adjust the image brightness range to enhance highlight and shadow details.

[0068] Gamma correction parameters: adjust image brightness and contrast, affecting the overall visual experience of the image.

[0069] Distortion correction parameters: correct geometric distortion caused by the lens and eliminate dispersion problems.

[0070] Auto-exposure and auto-focus parameters: Auto-exposure controls the bright and dark parts of the image, and auto-focus adjusts the focus position and stability of the image.

[0071] In the selection of ISP image quality adjustment parameter set, white balance is adjusted according to color temperature to ensure natural tones, automatic exposure is adjusted according to brightness value to ensure proper exposure, dynamic range is optimized to retain highlight and shadow details, noise reduction intensity is adjusted based on brightness information to achieve noise reduction in low-light environments, detail restoration is enhanced to improve clarity, thereby comprehensively improving image quality.

[0072] In an ideal state, the embodiment of the present invention can achieve no frame loss and no abnormal effect frame. In this way, in scenarios where rapid switching is required, such as when a vehicle enters a tunnel, seamless connection of multiple scenes can be achieved, thereby improving the safety of autonomous driving.

[0073] In a specific implementation, the specific process of the embodiment of the present invention is as follows:

[0074] First connect to the external data source:

[0075] Obtain weather, sunshine, and location data. At this time, the system will prepare multiple image quality adjustment parameters that may be used, obtain image attribute parameters such as contrast, color, brightness, and clarity. The image attribute parameters characterize the image quality, and adjust the image quality adjustment parameters based on these image attribute parameters to improve image quality to meet the needs of different scenarios.

[0076] In a specific implementation, the vehicle connects to various functional websites through mobile data and is interconnected through a website interface (API). For example, the direction of sunlight can be calculated through the following example website:

[0077] https: / / www.sunearthtools.com / dp / tools / pos_sun.php?lang=cn

[0078] Then, the vehicle position is obtained and the direction data is collected, and the brightness mapping parameters under front light or back light are selected (i.e., the brightness mapping parameters in the image quality adjustment parameters);

[0079] After the vehicle presets the GPS route, each scene is predicted based on the historical data of the vehicle's surrounding environment on different types of road sections in the route (such as expressways, highways, tunnels, etc.). After the prediction is completed, the corresponding image quality adjustment parameters are selected for preloading to achieve the purpose of the vehicle system being able to switch image quality adjustment parameters in real time in various scenarios.

[0080] That is, mainly based on external factors such as geographical location, road type, weather conditions, lighting conditions, etc., the parameter selection model is used for analysis to select the image quality adjustment parameter set corresponding to the current preset route.

[0081] Before the vehicle starts running, the remote server uses a parameter selection model based on the real-time collected vehicle position (latitude and longitude) and direction data. The parameter selection model uses a multi-mode loop algorithm to predict the optimal set of image quality adjustment parameters based on historical data and environmental conditions to ensure rapid switching when entering different scenes (hereinafter referred to as the above operation as initial screening).

[0082] The specific method is to input the vehicle's real-time position, road type (such as expressways, highways, tunnels, etc.), weather conditions (such as sunny days, rainy days, haze, etc.), and lighting conditions (such as daytime, nighttime, etc.) into a preset parameter selection model. The multi-mode loop algorithm of the parameter selection model calculates and predicts based on historical data and environmental conditions, and screens out image quality adjustment parameters suitable for the current scene. That is, according to the vehicle's GPS position and direction, some environmental information is obtained through the network, such as weather and sunshine direction, and judgment is made locally in the vehicle. Finally, the camera image parameters required for the location that the vehicle is about to arrive at are selected in advance to complete the prediction function.

[0083] Then preload the image quality adjustment parameters for preliminary screening locally:

[0084] The remote server sends the image quality adjustment parameter set obtained by the initial screening to the vehicle, and preloads the image quality adjustment parameter set obtained by the initial screening locally in the vehicle, so that the vehicle system is ready to switch the required image quality adjustment parameters in different scenarios to achieve rapid response.

[0085] The embodiment of the present invention also realizes real-time shooting of real-time scenes and selection of image quality adjustment parameters through a preset multiple mode cycle:

[0086] That is, when the vehicle arrives at the actual scene, the scene around the vehicle is photographed in real time and the current image quality is analyzed.

[0087] The raw image data obtained by shooting is re-injected to obtain the effect diagrams corresponding to different image quality adjustment parameters, and the image attribute parameters (contrast, brightness standard deviation, one-dimensional grayscale entropy and two-dimensional grayscale entropy, which represent the quality) are calculated. Then, the optimal image quality adjustment parameters are selected for output through horizontal comparison test.

[0088] Through real-time monitoring and continuous acquisition of image quality parameters, real-time dynamic adjustment is performed. If the scene does not change or the image quality parameters do not fluctuate significantly, the system continues to output the current optimal image quality adjustment parameters.

[0089] If a scene switch (such as entering an open area from a tunnel) or a significant decrease in image quality (below a set threshold) is detected, the image quality adjustment parameters are reselected and image quality adjustment is performed.

[0090] The tuning process mainly considers three dimensions: brightness, contrast, and clarity, corresponding to the histogram grayscale distribution, histogram brightness standard deviation, and histogram brightness histogram entropy.

[0091] Preferably, if it is detected that the vehicle deviates from the preset GPS route, the image quality adjustment parameter set is reset, and during the actual operation of the vehicle, the image quality adjustment parameters are adjusted according to the real-time feedback of the image quality to ensure that the best image effect is always output on different road sections.

[0092] Based on the above image optimization process, the optimized image can meet the recognition requirements of autonomous driving, so the optimized image can be directly sent to the autonomous driving algorithm module of the vehicle computer for subsequent processing.

[0093] In the specific implementation process, the remote server performs initial screening through data such as vehicle location, weather and sunshine conditions in the area, GPS navigation preset route, and vehicle head direction to obtain a set of image quality adjustment parameters for each scene under the preset route, and forms a preloaded parameter list with the image quality adjustment parameter set.

[0094] For example, the remote server obtains the current driving scene of the vehicle, that is, at 15:00 pm on November 1, 2024, Eastern Time, the vehicle is driving northeast along American Avenue in New York City, New York, USA, and the weather is clear.

[0095] According to the preset GPS navigation route, several sets of parameters that may be required for each scenario are initially screened to form a preloaded parameter list.

[0096] During vehicle driving, the algorithm of the multi-mode loop structure of the parameter selection model preloads the parameter set that may be needed for the next point for the vehicle based on historical data, current driving scenarios and preset routes. The driving scenarios include lighting conditions, current vehicle position, road type, and weather conditions.

[0097] The types of roads here include expressways, highways, tunnels, etc. The weather conditions include sunny days, rainy days, smog, etc. The lighting conditions include daytime, nighttime, etc.

[0098] In an example driving route, the vehicle needs to pass through scenes of direct sunlight, direct sunlight blocked by buildings, tunnels, and bridges. The preloaded parameters of direct sunlight, direct sunlight blocked by buildings, tunnels, and bridges will correspond to these four upcoming scenes respectively. At the same time, the parameters of dark light and strong light will be preloaded as a backup as a result of the initial screening.

[0099] Example of initial screening and preload judgment: When the vehicle travels to 32nd Street, the environment of 46th Street 100 meters away is predicted based on the GPS preset route, and the corresponding image quality adjustment parameters are preloaded for this section in advance.

[0100] According to the data of sunlight direction (northeast) and vehicle head direction (northeast), it is judged that the parameter set required for the current situation is biased towards front light.

[0101] The remote server automatically determines the image quality adjustment parameters required by each camera of the vehicle based on the real-time shooting picture after the vehicle arrives at the actual scene, and sends a signal to the vehicle. In this step, due to the large changes in the actual scene, the remote server needs to roughly select multiple sets (preliminary screening) of parameters that may be required to increase redundancy for environmental changes.

[0102] For example, when a vehicle drives under an elevated road, it is difficult to determine whether the vehicle is under the elevated road based on the vehicle GPS alone. Therefore, the vehicle needs to pre-screen and pre-load the parameters on and under the elevated road at the same time.

[0103] This mechanism of pre-screening and pre-loading multiple sets of parameters ensures that the system responds quickly in a variety of scenarios and avoids frequent algorithm jumps.

[0104] The embodiment of the present invention uses one-dimensional grayscale entropy and two-dimensional grayscale entropy to quantify the clarity and contrast of an image, thereby determining the brightness distribution of the image. The historical data of the previous frames are used to select and match parameters to ensure the stability of the real-time adjustment process.

[0105] The parameter Grayscale Histogram Entropyper level is used to compare the information content of images under different brightness environments. Based on the amount of information in the image, the system can automatically adjust the parameters.

[0106] For example, in a tunnel, due to the low brightness, the system first determines whether the contrast is appropriate based on the brightness standard deviation and the number of grayscales, and then calculates the brightness histogram entropy. Although the histogram entropy is low at night, when the histogram entropy grayscale ratio can reach more than 80%, the system will determine that the image effect is better.

[0107] Different thresholds and expected values ​​are preset for different scenes to automatically adjust the image quality adjustment parameters to ensure the best image effect under various lighting conditions.

[0108] The ISP image quality adjustment parameters optimize the light and dark performance (brightness) of the image through automatic exposure and gamma correction to avoid over-darkness and overexposure; enhance details through sharpening, remove noise through noise reduction, and adjust clarity to ensure a clearer image.

[0109] The difference between bright and dark areas is adjusted through global brightness mapping, and the highlight and shadow details are enhanced through dynamic range optimization, making the details richer and the bright and dark areas better presented.

[0110] Second, as Figure 2 As shown, in order to solve the technical problem, an embodiment of the present invention further provides a vehicle-mounted image quality optimization system, the system comprising:

[0111] The remote server is used to preliminarily select image quality adjustment parameters corresponding to each scene according to environmental conditions and historical operation data of different scenes in the preset route of the vehicle, and generate an image quality adjustment parameter set;

[0112] The remote server is also used to send the image quality adjustment parameter set obtained by the initial screening to the vehicle, and preload the image quality adjustment parameter set locally in the vehicle;

[0113] The vehicle-mounted system, when the vehicle arrives at a certain scene, the vehicle-mounted camera takes real-time photos of the scene around the vehicle. The vehicle-mounted system analyzes the current image quality and selects the optimal image quality adjustment parameters for output through horizontal comparison tests. During the operation of the vehicle, the image quality parameters are continuously collected, the optimal image quality adjustment parameters are adjusted in real time, and the image is optimized in real time.

[0114] In the method embodiment, its implementation method is the same as the system implementation method, and will not be described in detail here.

[0115] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor or calculator is configured to call the program instructions to execute the method as described above.

[0116] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor or a computer, the processor or the computer executes the method as described above.

[0117] like Figure 3 As shown, an electronic device provided by an embodiment of the present application, the vehicle-mounted device 1000 includes a processor or a calculator (not shown in the figure) 1001 and a memory 1002, and the processor or calculator 1001 and the memory 1002 can be interconnected through a communication bus 1003. The communication bus 1003 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1003 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the memory 1002 is used to store a computer program, and the computer program includes program instructions. The processor 1001 is configured to call the program instructions, and the above program includes a method for executing some or all of the steps in the aforementioned method.

[0118] The processor 1001 may be a general purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the above program.

[0119] The memory 1002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus. The memory may also be integrated with the processor.

[0120] The electronic device 1000 may further include a communication module 1004 and a display 1005. The communication module 1004 may be connected to the optical tracking device for communication. The communication module 1004 may be a wireless communication module (eg, a WiFi module, a Bluetooth module, etc.) or a wired communication module.

[0121] In addition, the electronic device 1000 may also include common components such as a communication interface (eg, a USB interface, a microphone interface, etc.), an antenna, etc., which will not be described in detail here.

[0122] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0123] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0127] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0128] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0129] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0130] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for optimizing vehicle image quality, characterized in that: The method comprises: The remote server preliminarily selects the image quality adjustment parameters corresponding to each scene according to the environmental conditions and historical operation data of different scenes in the preset route of the vehicle, and generates an image quality adjustment parameter set; Sending the image quality adjustment parameter set to the vehicle, and preloading the image quality adjustment parameter set locally in the vehicle; When the vehicle arrives at a certain scene, it will take real-time photos of the scene around the vehicle and analyze the current image quality. Through horizontal comparison tests, it will select the optimal image quality adjustment parameters for output. During the operation of the vehicle, image quality parameters are continuously collected, the optimal image quality adjustment parameters are adjusted in real time, and the image is optimized in real time.

2. The vehicle-mounted image quality optimization method according to claim 1, characterized in that: The environmental conditions include, but are not limited to, vehicle location, geographical environment, road type, weather conditions, and lighting conditions.

3. The vehicle-mounted image quality optimization method according to claim 1, characterized in that: The selecting of the image quality adjustment parameters corresponding to each scene specifically includes: The system uses a parameter selection model to predict the optimal set of image quality adjustment parameters based on historical operating data and environmental conditions.

4. The vehicle-mounted image quality optimization method according to claim 3, characterized in that: The system uses a parameter selection model to predict the optimal image quality adjustment parameter set based on historical operating data and environmental conditions, including: The vehicle position, road type, weather conditions, and lighting conditions in the historical operating data are input into a preset parameter selection model. The multi-mode loop algorithm of the parameter selection model performs calculations and predictions based on the historical operating data and environmental conditions, and screens out image quality adjustment parameters corresponding to each operating scenario, thereby forming an image quality adjustment parameter set for each scenario under the vehicle's preset operating route.

5. The vehicle-mounted image quality optimization method according to claim 1, characterized in that: The analyzing the current image quality specifically includes: The raw image data obtained by shooting is re-injected to obtain the effect diagrams corresponding to different image quality adjustment parameters, and the image attribute parameters are calculated.

6. The vehicle-mounted image quality optimization method according to claim 5, characterized in that: The image attribute parameters specifically include but are not limited to brightness, contrast, and clarity, which correspond to the histogram grayscale distribution, histogram brightness standard deviation, and histogram brightness histogram entropy in the effect diagram respectively.

7. The vehicle-mounted image quality optimization method according to claim 1, characterized in that: The real-time adjustment of the optimal image quality adjustment parameters specifically includes: When a scene switch is detected or the image quality is lower than a set quality threshold, the optimal image quality adjustment parameters are reselected.

8. A vehicle-mounted image quality optimization system, characterized in that: The system comprises: The remote server is used to preliminarily select image quality adjustment parameters corresponding to each scene according to environmental conditions and historical operation data of different scenes in a preset route of the vehicle, and generate an image quality adjustment parameter set; The remote server is also used to send the image quality adjustment parameter set to the vehicle and preload the image quality adjustment parameter set locally in the vehicle; The vehicle-mounted system, when the vehicle arrives at a certain scene, the vehicle-mounted camera takes real-time photos of the scene around the vehicle. The vehicle-mounted system analyzes the current image quality and selects the optimal image quality adjustment parameters for output through horizontal comparison tests. During the operation of the vehicle, the image quality parameters are continuously collected, the optimal image quality adjustment parameters are adjusted in real time, and the image is optimized in real time.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor or the computer executes the method according to any one of claims 1 to 7.

Images