Streaming media rearview mirror image processing method with intelligent image processing function

Abstract

The invention provides an intelligent environment self-adaptive streaming media rearview mirror image processing method. The method comprises the following steps: acquiring original image data of a streaming media rearview mirror of a vehicle, illumination intensity data around a vehicle body and surface temperature and humidity data of a camera; acquiring vehicle positioning information, navigation route data and vehicle body state signals; acquiring weather forecast information of the driving path from the cloud; predicting a lens fogging risk level through a dew point calculation model according to the camera surface temperature and humidity data and the predicted weather information; generating a graded heating control instruction according to the fogging risk grade; and according to the illumination intensity data around the vehicle and the predicted illumination intensity change data, the display content of the streaming media rearview mirror is optimized. According to the method, image processing and risk prediction of the streaming media rearview mirror are carried out by combining vehicle positioning, navigation routes and vehicle body state signals, so that the whole system can more intelligently and comprehensively sense the environment condition of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of electronic rearview mirror technology, and in particular to a streaming media rearview mirror image processing method with intelligent image processing function. Background Technology

[0002] Traditional car rearview mirrors are relatively simple in function, primarily providing the driver with a view behind the vehicle, but they have many limitations. Ordinary optical rearview mirrors are easily affected by factors such as weather and lighting, and their design inherently includes blind spots, limiting the driver's field of vision and making it difficult to fully understand the surrounding environment. In adverse weather conditions, such as rain or fog, fogging of the rearview mirrors can severely impair the driver's vision, increasing driving risks. Furthermore, traditional rearview mirrors cannot integrate with other electronic systems in the vehicle, making it difficult to meet the development trends of modern automotive intelligence and connectivity.

[0003] With the continuous advancement of automotive electronics technology, streaming rearview mirrors have emerged. By combining cameras and displays, streaming rearview mirrors provide drivers with a wider field of view and clearer images. However, current streaming rearview mirror technology still faces some challenges. For example, stitching gaps and distortion differences may occur during the fusion process of images captured by multiple cameras, affecting image quality and visual effects. Furthermore, issues such as flickering from external light sources, camera performance degradation in low-temperature environments, and rearview mirror fogging still negatively impact the performance and reliability of streaming rearview mirrors. Summary of the Invention

[0004] This invention provides a streaming rearview mirror image processing method with intelligent image processing function. By combining vehicle positioning, navigation route and vehicle status signals, the method performs image processing and risk prediction for the streaming rearview mirror, enabling the entire system to perceive the vehicle's environmental conditions more intelligently and comprehensively.

[0005] The first aspect of this invention provides a streaming media rearview mirror image processing method with intelligent image processing function, comprising the following steps: Acquire raw image data from the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data from the camera surface; acquire vehicle location information, navigation route data, and vehicle status signals; Based on navigation route data and vehicle positioning information, weather forecast information for the driving route is obtained from the cloud. The weather forecast information includes data on changes in humidity, fog concentration, and light intensity in the future period. Based on the camera surface temperature and humidity data and predicted weather information, the lens fogging risk level is predicted using a dew point calculation model; a graded heating control command is generated based on the fogging risk level, and the camera is heated according to the heating control adjustment. The content displayed on the streaming rearview mirror is optimized based on the light intensity data around the vehicle and the predicted light intensity change data.

[0006] Furthermore, the step of predicting the lens fogging risk level based on camera surface temperature and humidity data and predicted weather information using a dew point calculation model includes the following steps: Acquire raw fogged images, real-time fog concentration estimates calculated by temperature and humidity sensors, and visibility prediction data for the vehicle's location; Real-time acquisition of fogging feature values ​​from raw camera images, fog concentration estimates calculated by temperature and humidity sensors, and visibility prediction data for the grid area where the vehicle is located provided by the cloud; The first risk coefficient is calculated based on the difference between the camera surface temperature and the ambient dew point temperature, wherein the ambient dew point temperature is calculated from the humidity data in the predicted weather information. Based on the fogging characteristic value, fog concentration estimate, and visibility prediction data, a second risk coefficient is generated and output. Based on the first risk coefficient and the second risk coefficient, the final quantitative value of the fogging risk level is generated.

[0007] Furthermore, the step of obtaining weather forecast information for the driving route from the cloud based on navigation route data and vehicle positioning information includes the following steps: Divided into multiple geographical regions based on the navigation path; Zoom in on screenshots of each geographical region and request micro-weather forecasts for future periods for each region according to time series. The forecast data is weighted and fused with real-time data from the vehicle-mounted rain sensor.

[0008] Furthermore, the graded heating control commands include: low-risk level, where the heating element power is less than or equal to 20% to maintain the basic temperature of the heating element; medium-risk level, where the heating element power is 50-70% to maintain the heating element within a specified range; and high-risk level, where the heating element power is greater than or equal to 90% to maintain the heating element at a higher temperature without damaging it.

[0009] Furthermore, it also includes rain scene enhancement; the rain scene enhancement includes the following steps: The rainy weather environment is confirmed by the signal from the vehicle-mounted rain sensor. Real-time analysis of the original image to identify and locate blurred areas and noise caused by raindrops; For the identified raindrop interference areas, a color and contrast compensation algorithm is activated to correct the image color distortion caused by the raindrops; The image sharpening intensity is dynamically adjusted based on real-time vehicle speed.

[0010] Furthermore, it also includes snow scene enhancement, which includes the following steps: Based on ambient temperature sensor data and the distribution ratio of overly bright areas in camera images, determine driving conditions in snowy weather; Intelligent region segmentation of images identifies overexposed areas caused by snow cover or strong light reflection; Perform local brightness adjustment on overexposed areas.

[0011] Furthermore, it also includes fog scene enhancement, which includes the following steps: When the fog risk level predicted by the system reaches or exceeds the medium risk level, the fog image enhancement mode is activated. Based on the atmospheric scattering physics model, the loss of detail and contrast attenuation caused by haze in the image are estimated and restored. To address the graying effect in images caused by fog scattering, adaptive color restoration is performed to correct color cast and restore the true colors of the scene.

[0012] A second aspect of the present invention provides a streaming media rearview mirror image processing system with intelligent image processing function, including a first computing unit for acquiring raw image data of the vehicle's streaming media rearview mirror, light intensity data around the vehicle body, and temperature and humidity data of the camera surface; acquiring vehicle positioning information, navigation route data, and vehicle status signals; The second computing unit is used to obtain weather forecast information for the driving route from the cloud based on navigation route data and vehicle positioning information. The weather forecast information includes data on changes in humidity, fog concentration and light intensity in the future period. The third calculation unit is used to predict the lens fogging risk level based on the camera surface temperature and humidity data and predicted weather information using a dew point calculation model; generate graded heating control commands based on the fogging risk level, and adjust the heating of the camera accordingly; The fourth calculation unit is used to optimize the display content of the streaming rearview mirror based on the light intensity data around the vehicle and the predicted light intensity change data.

[0013] A third aspect of the present invention provides a computer device, comprising: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is used to execute the program in the memory, including executing the above-described streaming media rearview mirror image processing method with intelligent image processing function; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

[0014] A fourth aspect of the present invention provides a readable storage medium storing computer-readable instructions, characterized in that, when executed by a processor, the computer-readable instructions implement the steps of the streaming media rearview mirror image processing method with intelligent image processing function described above.

[0015] As can be seen from the above technical solutions, the present invention has the following advantages: This invention acquires raw image data from the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data from the camera surface. Combined with vehicle positioning, navigation routes, and vehicle status signals, the image processing is predicted and optimized, enabling the entire system to perceive the vehicle's environmental conditions more intelligently and comprehensively.

[0016] Meanwhile, based on the navigation route and vehicle positioning, weather forecast information for the driving path is obtained from the cloud, including data on changes in humidity, fog concentration, and light intensity. This enables advance prediction of possible weather changes that the vehicle may encounter during driving, enhancing the vehicle's adaptability to complex weather conditions.

[0017] Furthermore, by combining the temperature and humidity data of the camera surface with predicted weather information, a dew point calculation model is used to predict the risk level of lens fogging, and a graded heating control command is generated to adjust the camera heating accordingly. This effectively prevents and eliminates lens fogging problems. Moreover, through precise control of graded heating, energy waste is avoided while ensuring the effect, improving energy utilization efficiency and helping to extend the service life of the heating element.

[0018] Finally, the display content of the streaming rearview mirror is optimized based on the ambient light intensity around the vehicle and predicted changes in ambient light intensity. Whether in strong or low light conditions, adjusting display parameters ensures the driver has a clear and accurate rear view, improving visibility during driving and helping the driver to promptly detect potential hazards behind, thus effectively enhancing driving safety. In conclusion, this invention significantly improves the performance and reliability of the streaming rearview mirror in complex and changing environments, providing strong protection for safe driving.

[0019] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from an examination of the following, or may be learned from the practice of the invention. Attached Figure Description

[0020] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0021] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “corresponding to,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] Example 1 The implementation method in this embodiment can be implemented in a system, on a server, or on a terminal; no specific limitation is made. The method in this application will be described from the perspective of system implementation below. As shown in the figure, a streaming media rearview mirror image processing method with intelligent image processing function includes the following steps: Acquire raw image data from the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data from the camera surface; acquire vehicle location information, navigation route data, and vehicle status signals; Based on navigation route data and vehicle positioning information, weather forecast information for the driving route is obtained from the cloud. The weather forecast information includes data on changes in humidity, fog concentration, and light intensity in the future period. Based on the camera surface temperature and humidity data and predicted weather information, the lens fogging risk level is predicted using a dew point calculation model; a graded heating control command is generated based on the fogging risk level, and the camera is heated according to the heating control adjustment. The content displayed on the streaming rearview mirror is optimized based on the light intensity data around the vehicle and the predicted light intensity change data.

[0023] The system collects raw image data from the vehicle's streaming rearview mirror and acquires light intensity data around the vehicle, reflecting the ambient lighting conditions. Additionally, it collects temperature and humidity data from the camera surface to predict the risk of lens fogging. Vehicle location information and navigation route data determine the vehicle's current position and direction of travel, while vehicle status signals help understand the vehicle's operational status. Based on navigation route data and vehicle location information, the system retrieves weather forecast information for the driving route from the cloud, including data on future changes in humidity, fog density, and light intensity, allowing the system to anticipate potential weather changes the vehicle may encounter during its journey.

[0024] By combining camera surface temperature and humidity data with forecast weather information, a dew point calculation model is used to predict the risk level of lens fogging. Based on the predicted risk level, graded heating control commands are generated to adjust the heating power of the camera, thereby preventing or eliminating lens fogging and ensuring high image clarity. For example, when a high risk of fogging is predicted, the system increases the power of the heating element, raising the camera surface temperature and preventing moisture condensation.

[0025] Based on data on the light intensity around the vehicle and predicted changes in light intensity, the display content of the streaming rearview mirror is optimized. For example, in bright light environments, parameters such as display brightness and contrast may be adjusted to avoid overexposure and ensure the driver can clearly see the scene behind them; in low light environments, image brightness and contrast may be enhanced to improve image visibility.

[0026] Example 2 The difference between this embodiment and Implementation 1 is that the step of predicting the lens fogging risk level based on camera surface temperature and humidity data and predicted weather information using a dew point calculation model includes the following steps: Acquire raw fogged images, real-time fog concentration estimates calculated by temperature and humidity sensors, and visibility prediction data for the vehicle's location; Real-time acquisition of fogging feature values ​​from raw camera images, fog concentration estimates calculated by temperature and humidity sensors, and visibility prediction data for the grid area where the vehicle is located provided by the cloud; The first risk coefficient is calculated based on the difference between the camera surface temperature and the ambient dew point temperature, wherein the ambient dew point temperature is calculated from the humidity data in the predicted weather information. Based on the fogging characteristic value, fog concentration estimate, and visibility prediction data, a second risk coefficient is generated and output. Based on the first risk coefficient and the second risk coefficient, the final quantitative value of the fogging risk level is generated.

[0027] Among them, when the dew point calculation model predicts the risk level of lens fogging, it obtains the original fogging image, the fog concentration estimate calculated in real time by the temperature and humidity sensor, and the visibility prediction data of the area where the vehicle is located; it also obtains the fogging feature value in the original image of the camera, the fog concentration estimate calculated by the temperature and humidity sensor, and the visibility prediction data of the grid area where the vehicle is located provided by the cloud in real time.

[0028] First, a first risk coefficient based on a physical model is calculated, using a dew point calculation model to determine whether the physical conditions for condensation exist on the camera lens surface. The system uses ambient temperature and relative humidity from cloud-based forecast weather information and substitutes them into the Magnus formula to calculate the current ambient dew point temperature. Then, the difference between the real-time monitored camera lens surface temperature and the ambient dew point temperature is calculated. This temperature difference is a direct physical representation of the fogging risk: when the lens surface temperature is higher than the dew point temperature, the condensation risk is low; when the two are close to or lower, the risk increases significantly. The system performs segmented mapping based on this temperature difference; for example, a temperature difference greater than 3°C indicates extremely low risk, while a temperature difference less than -3°C indicates extremely high risk, thus generating a quantified first risk coefficient between 0 and 1. This coefficient reveals the physical probability of lens fogging.

[0029] Simultaneously, the system calculates a second risk coefficient based on real-time observation and prediction. This second risk coefficient cross-validates the degree of environmental fogging at the phenomenological level. The system integrates three types of data: first, fogging feature values ​​extracted from the original camera images (such as the degree of attenuation of overall image contrast and saturation), used to directly assess the blurring status of the current image; second, fog concentration estimates calculated in real-time by temperature and humidity sensors; and third, visibility prediction data for the vehicle's location provided by the cloud. These three dimensions of data are assigned weights and weighted fusion to generate another second risk coefficient between 0 and 1, reflecting the current status and trend of environmental fogging as depicted by internal and external sensors and cloud data.

[0030] Finally, the first and second risk coefficients are weighted and fused. The first risk coefficient focuses on the theoretical prediction of whether fog will occur, while the second risk coefficient focuses on the actual observation of the degree of fog formation in the environment; the two are complementary. Through a fusion algorithm (such as linear weighting), a final, more comprehensive, and reliable quantitative value for the fog risk level is generated.

[0031] Example 3 The difference between this embodiment and Embodiment 2 is that the step of obtaining weather forecast information for the driving route from the cloud based on navigation route data and vehicle positioning information includes the following steps: Divided into multiple geographical regions based on the navigation path; Zoom in on screenshots of each geographical region and request micro-weather forecasts for future periods for each region according to time series. The forecast data is weighted and fused with real-time data from the vehicle-mounted rain sensor.

[0032] The navigation path is divided into multiple geographical intervals; each geographical interval is zoomed in and screenshotted, and micro-weather forecasts for future periods are requested for each interval according to time series; the forecast data is then weighted and fused with real-time data from the vehicle-mounted rain sensor.

[0033] First, the system performs fine-grained geographical segmentation of the navigation path. Traditional weather forecasts cover too large a range and cannot meet the vehicle's need for local microclimate perception while driving. To address this issue, the system dynamically divides the complete navigation path into multiple consecutive geographical segments based on road curvature, key nodes (such as tunnels, bridges, and valleys), and fixed distance intervals (such as every 5 kilometers). Each segment is treated as an independent forecast unit, and the system generates a geographical bounding box for each segment.

[0034] Next, the system initiates a time-series-based micro-weather forecast request, simulating the vehicle's driving process and sending requests to the cloud-based weather server according to the time sequence. For the current and the next geographical area the vehicle will enter, the system will request micro-weather forecasts with higher time resolution for the next 30 to 60 minutes.

[0035] Finally, the system performs adaptive weighted fusion of multi-source data. To obtain a reliable comprehensive weather condition assessment, the system weights and fuses the data. When the system detects that the onboard rain sensor signal is stable and consistent with the short-term forecast, it assigns a higher weight to the real-time data to ensure a sensitive response to sudden weather changes. When the vehicle is in the event of a weather change predicted by the forecast data, but the sensor has not yet detected it, the weight of the forecast data is appropriately increased to activate the protective function.

[0036] Example 4 The difference between this embodiment and Embodiment 3 is that the graded heating control commands include: low risk level, where the heating element power is less than or equal to 20% to maintain the basic temperature of the heating element; medium risk level, where the heating element power is 50-70% to maintain the heating element within a specified range; and high risk level, where the heating element power is greater than or equal to 90% to maintain the heating element at a higher temperature without damaging it.

[0037] When the risk level of lens fogging is low, the heating element power is activated at less than or equal to 20%, only maintaining the base temperature of the heating element. At this time, the environmental conditions are good, and the relationship between the camera surface and the ambient temperature and humidity is stable. Only low-power heating is needed to prevent slight condensation, while avoiding unnecessary energy waste.

[0038] If the risk level reaches medium risk, activate the heating element at 50-70% power to maintain it within the specified temperature range. In this situation, there is a certain risk of fogging. Appropriately increasing the heating element power to raise the camera surface temperature to a certain level can effectively prevent water vapor from condensing into fog without overheating the heating element and affecting its lifespan.

[0039] When the risk level is high, activate the heating element at 90% or higher power to maintain a high temperature without damaging it. In such harsh environmental conditions with a very high risk of fogging, high-power heating rapidly raises the camera's surface temperature, effectively preventing condensation and ensuring clear images.

[0040] Example 5 The difference between this embodiment and embodiment four is that it also includes rain scene enhancement; the rain scene enhancement includes the following steps: The rainy weather environment is confirmed by the signal from the vehicle-mounted rain sensor. Real-time analysis of the original image to identify and locate blurred areas and noise caused by raindrops; For the identified raindrop interference areas, a color and contrast compensation algorithm is activated to correct the image color distortion caused by the raindrops; The image sharpening intensity is dynamically adjusted based on real-time vehicle speed.

[0041] An onboard rain sensor acquires rainfall data of the vehicle's driving environment. The raw images are then analyzed in real time to identify raindrop noise. Raindrops adhering to the lens hood form tiny lenses, causing geometric distortion and blurring in localized areas of the image. By detecting these specific blur patterns and edge distortion features, raindrop interference areas are located in the image. After identifying the interference areas, a color and contrast compensation algorithm is activated, selectively enhancing the color saturation and contrast of these areas to effectively suppress color distortion and clearly reproduce the scene in the raindrop-covered areas.

[0042] Finally, the system dynamically adjusts the sharpening intensity based on vehicle speed, demonstrating proactive compensation for motion blur. Higher vehicle speeds result in faster relative movement between the camera and the environment, leading to stronger motion blur. This, combined with static blur caused by raindrops, severely degrades image quality. By dynamically increasing the sharpening intensity, the system actively counteracts this blur, providing the driver with stable and clear images at various speeds.

[0043] Example 6 The difference between this embodiment and embodiment five is that it also includes snow scene enhancement, which includes the following steps: Based on ambient temperature sensor data and the distribution ratio of overly bright areas in camera images, determine driving conditions in snowy weather; Intelligent region segmentation of images identifies overexposed areas caused by snow cover or strong light reflection; Perform local brightness adjustment on overexposed areas.

[0044] Snowy conditions are determined by combining ambient temperature and the proportion of bright areas in the image. Low temperature is a necessary condition for the existence and persistence of snow accumulation, and large, bright areas in the image are a direct reflection of snow.

[0045] Subsequently, intelligent region segmentation is performed on the image to identify overexposed areas, dividing the image into multiple blocks with similar visual features. In snowy scenes, snow-covered roads, vehicles, and building surfaces create extensive specular and diffuse reflections, appearing as bright, white spots on the image that lack detail. These overexposed areas are separated from the normal scene and used as processing targets. Finally, local brightness adjustment is performed within the segmented overexposed areas.

[0046] Example 7 The difference between this embodiment and embodiment six is ​​that it also includes fog scene enhancement, which includes the following steps: When the fog risk level predicted by the system reaches or exceeds the medium risk level, the fog image enhancement mode is activated. Based on the atmospheric scattering physics model, the loss of detail and contrast attenuation caused by haze in the image are estimated and restored. To address the graying effect in images caused by fog scattering, adaptive color restoration is performed to correct color cast and restore the true colors of the scene.

[0047] By intelligently linking a trigger mechanism with a fog risk prediction model, image enhancement is initiated before any visually perceptible image quality degradation, shifting from passive processing to active maintenance. Next, the system performs defogging based on an atmospheric scattering model, describing foggy imaging as the superposition of ambient light after the original scene light has been attenuated by atmospheric particles. The processing first analyzes image features to estimate the global atmospheric illumination intensity and scene transmittance distribution, then reverse-engineers a clear image under fog-free conditions.

[0048] Finally, adaptive color restoration is performed. Because atmospheric particles scatter light of different wavelengths to varying degrees, images generally exhibit a grayish-white color cast. The system, in a color space (such as YCbCr), analyzes the statistical distribution of color components to adaptively reconstruct the color information weakened by scattering effects. It performs precise color compensation and balance on distorted areas, suppressing the grayish-white tone of the image and ensuring that key color information such as road signs and vehicle taillights is presented realistically and vividly, providing drivers with more accurate visual references.

[0049] Example 8 A streaming rearview mirror image processing system with intelligent image processing function includes a first computing unit for acquiring raw image data of the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data of the camera surface; acquiring vehicle positioning information, navigation route data, and vehicle status signals; The second computing unit is used to obtain weather forecast information for the driving route from the cloud based on navigation route data and vehicle positioning information. The weather forecast information includes data on changes in humidity, fog concentration and light intensity in the future period. The third calculation unit is used to predict the lens fogging risk level based on the camera surface temperature and humidity data and predicted weather information using a dew point calculation model; generate graded heating control commands based on the fogging risk level, and adjust the heating of the camera accordingly; The fourth calculation unit is used to optimize the display content of the streaming rearview mirror based on the light intensity data around the vehicle and the predicted light intensity change data.

[0050] Example 9 A computer device, comprising: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is used to execute the program in the memory, including executing the above-described streaming media rearview mirror image processing method with intelligent image processing function; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

[0051] Example 10 A readable storage medium storing computer-readable instructions, characterized in that, when executed by a processor, the computer-readable instructions implement the steps of the above-described streaming media rearview mirror image processing method with intelligent image processing function.

[0052] In summary, this invention acquires raw image data from the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data from the camera surface. By combining this with vehicle positioning, navigation routes, and vehicle status signals, the system predicts and optimizes image processing, enabling the entire system to perceive the vehicle's environmental conditions more intelligently and comprehensively.

[0053] Meanwhile, based on the navigation route and vehicle positioning, weather forecast information for the driving path is obtained from the cloud, including data on changes in humidity, fog concentration, and light intensity. This enables advance prediction of possible weather changes that the vehicle may encounter during driving, enhancing the vehicle's adaptability to complex weather conditions.

[0054] Furthermore, by combining the temperature and humidity data of the camera surface with predicted weather information, a dew point calculation model is used to predict the risk level of lens fogging, and a graded heating control command is generated to adjust the camera heating accordingly. This effectively prevents and eliminates lens fogging problems. Moreover, through precise control of graded heating, energy waste is avoided while ensuring the effect, improving energy utilization efficiency and helping to extend the service life of the heating element.

[0055] Finally, the display content of the streaming rearview mirror is optimized based on the ambient light intensity around the vehicle and predicted changes in ambient light intensity. Whether in strong or low light conditions, adjusting display parameters ensures the driver has a clear and accurate rear view, improving visibility during driving and helping the driver to promptly detect potential hazards behind, thus effectively enhancing driving safety. In conclusion, this invention significantly improves the performance and reliability of the streaming rearview mirror in complex and changing environments, providing strong protection for safe driving.

[0056] It is understood that those skilled in the art can combine various implementation methods in the above embodiments under the guidance of the above examples to obtain technical solutions with multiple implementation methods.

[0057] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0058] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0059] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0060] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0061] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A streaming media rearview mirror image processing method with intelligent image processing function, characterized in that, Includes the following steps: Acquire raw image data from the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data from the camera surface; Acquire vehicle location information, navigation route data, and vehicle status signals; Based on navigation route data and vehicle positioning information, weather forecast information for the driving route is obtained from the cloud. The weather forecast information includes data on changes in humidity, fog concentration, and light intensity in the future period. Based on the surface temperature and humidity data of the camera and the predicted weather information, the risk level of lens fogging is predicted by a dew point calculation model. A graded heating control command is generated based on the fogging risk level, and the camera is heated according to the heating control adjustment. The content displayed on the streaming rearview mirror is optimized based on the light intensity data around the vehicle and the predicted light intensity change data.

2. The streaming media rearview mirror image processing method with intelligent image processing function according to claim 1, characterized in that, The method of predicting the lens fogging risk level based on camera surface temperature and humidity data and predicted weather information using a dew point calculation model includes the following steps: Acquire raw fogged images, real-time fog concentration estimates calculated by temperature and humidity sensors, and visibility prediction data for the vehicle's location; Real-time acquisition of fogging feature values ​​from raw camera images, fog concentration estimates calculated by temperature and humidity sensors, and visibility prediction data for the grid area where the vehicle is located provided by the cloud; The first risk coefficient is calculated based on the difference between the camera surface temperature and the ambient dew point temperature, wherein the ambient dew point temperature is calculated from the humidity data in the predicted weather information. Based on the fogging characteristic value, fog concentration estimate, and visibility prediction data, a second risk coefficient is generated and output. Based on the first risk coefficient and the second risk coefficient, the final quantitative value of the fogging risk level is generated.

3. The streaming media rearview mirror image processing method with intelligent image processing function according to claim 1, characterized in that, The step of obtaining weather forecast information for the driving route from the cloud based on navigation route data and vehicle positioning information includes the following steps: Divided into multiple geographical regions based on the navigation path; Zoom in on screenshots of each geographical region and request micro-weather forecasts for future periods for each region according to time series. The forecast data is weighted and fused with real-time data from the vehicle-mounted rain sensor.

4. The streaming media rearview mirror image processing method with intelligent image processing function according to claim 1, characterized in that, The graded heating control commands include: low risk level, where the heating element power is less than or equal to 20% to maintain the basic temperature of the heating element; medium risk level, where the heating element power is 50-70% to maintain the heating element within a specified range; and high risk level, where the heating element power is greater than or equal to 90% to maintain the heating element at a higher temperature without damaging it.

5. The streaming media rearview mirror image processing method with intelligent image processing function according to claim 1, characterized in that, It also includes rain scene enhancement; the rain scene enhancement includes the following steps: The rainy weather environment is confirmed by the signal from the vehicle-mounted rain sensor. Real-time analysis of the original image to identify and locate blurred areas and noise caused by raindrops; For the identified raindrop interference areas, a color and contrast compensation algorithm is activated to correct the image color distortion caused by the raindrops; The image sharpening intensity is dynamically adjusted based on real-time vehicle speed.

6. The streaming media rearview mirror image processing method with intelligent image processing function according to claim 1, characterized in that, It also includes snow scene enhancement, which includes the following steps: Based on ambient temperature sensor data and the distribution ratio of overly bright areas in camera images, determine driving conditions in snowy weather; Intelligent region segmentation of images identifies overexposed areas caused by snow cover or strong light reflection; Perform local brightness adjustment on overexposed areas.

7. The streaming media rearview mirror image processing method with intelligent image processing function according to claim 1, characterized in that, It also includes fog scene enhancement, which includes the following steps: When the fog risk level predicted by the system reaches or exceeds the medium risk level, the fog image enhancement mode is activated. Based on the atmospheric scattering physics model, the loss of detail and contrast attenuation caused by haze in the image are estimated and restored. To address the graying effect in images caused by fog scattering, adaptive color restoration is performed to correct color cast and restore the true colors of the scene.

8. A streaming media rearview mirror image processing system with intelligent image processing function, characterized in that, It includes a first computing unit, used to acquire raw image data of the vehicle's streaming rearview mirror, light intensity data around the vehicle body, and temperature and humidity data of the camera surface; and to acquire vehicle positioning information, navigation route data, and vehicle status signals. The second computing unit is used to obtain weather forecast information for the driving route from the cloud based on navigation route data and vehicle positioning information. The weather forecast information includes data on changes in humidity, fog concentration and light intensity in the future period. The third calculation unit is used to predict the risk level of lens fogging based on the camera surface temperature and humidity data and predicted weather information through a dew point calculation model. A graded heating control command is generated based on the fogging risk level, and the camera is heated according to the heating control adjustment. The fourth calculation unit is used to optimize the display content of the streaming rearview mirror based on the light intensity data around the vehicle and the predicted light intensity change data.

9. A computer device, characterized in that, include: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is used to execute programs in the memory, including executing a streaming media rearview mirror image processing method with intelligent image processing function as described in any one of claims 1 to 7; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

10. A readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, they implement the steps of the streaming media rearview mirror image processing method with intelligent image processing function as described in any one of claims 1 to 7.

Images