An electronic rearview mirror image defogging method based on image information integration

Abstract

The present application discloses an electronic rearview mirror image defogging method based on image information integration, including: S101: Obtain real-time ambient light data and dynamically adjust the contrast and brightness of the image according to the data; S102: Generate an optimized basic image based on the adjusted image parameters; S103: Adjust the parameters of the image edge enhancement algorithm according to real-time meteorological conditions; S104: Apply the adjusted parameters to the basic image to output a clear defogged image, which can dynamically adjust the contrast and brightness of the image according to the change of ambient light to solve the problem of blurred imaging, and adjust the parameters of the image edge enhancement algorithm according to real-time meteorological conditions to solve the problem of unclear image boundaries in foggy days.

Description

Technical Field

[0001] The present application relates to the technical field of electronic rearview mirror image processing, and in particular to an electronic rearview mirror image defogging method based on image information integration. Background Art

[0002] The electronic rearview mirror image defogging method with image information integration is a technology designed to improve the image quality of the electronic rearview mirror under adverse weather conditions, especially in foggy days. It integrates a variety of advanced image processing technologies to effectively reduce or remove the negative impact of fog on the field of vision on the basis of capturing the external environment image, so that the image can be restored to a clearer and more realistic state.

[0003] There are two key technical issues it faces: the first is how to dynamically adjust the contrast and brightness of the image according to the changes in ambient light to solve the problem of blurred imaging. This is because the different intensity of external light will greatly affect the color saturation and brightness of the image captured by the camera. If the image is overexposed or underexposed under different lighting conditions, the visual information will be damaged;

[0004] The second is to adjust the parameters of the image edge enhancement algorithm according to the real-time meteorological conditions to solve the problem of unclear image boundaries in low visibility conditions such as foggy days. Because when the fog is thick, the scattering effect of particulate matter in the air on light increases significantly, which makes the outline of objects blurred and difficult to recognize. Therefore, it is necessary to adaptively correct the corresponding settings in the image processing model according to the actual climate conditions to ensure that the output results have higher resolution and sharpness. Summary of the invention

[0005] In view of this, an embodiment of the present disclosure provides an electronic rearview mirror image defogging method based on image information integration, which at least partially solves the problems existing in the above-mentioned prior art.

[0006] An electronic rearview mirror image defogging method based on image information integration, comprising:

[0007] S101: Acquire real-time ambient light data, and dynamically adjust the contrast and brightness of the image according to the data;

[0008] S102: generating an optimized basic image based on the adjusted image parameters;

[0009] S103: adjusting parameters of the image edge enhancement algorithm according to real-time meteorological conditions;

[0010] S104: Applying the adjusted parameters to the base image to output a clear defogging image.

[0011] In a specific embodiment, it further includes: determining an initial brightness enhancement coefficient A0 based on the vehicle speed and the camera viewing angle range, where the faster the vehicle speed and the larger the camera viewing angle range, the larger the value of A0;

[0012] According to the real-time ambient light intensity E, use the brightness adjustment formula: A = A0 * (1 + tanh(E / (Es * Ec))); where Es is the ambient light intensity threshold, Ec is the ambient light intensity center offset, and tanh is the hyperbolic tangent function used to map the input value to the interval (-1, 1);

[0013] Dynamically update the photosensitivity of the camera sensor G = Gbase + A * ΔG, where Gbase is the base sensitivity and ΔG is the photosensitivity gain change;

[0014] If the current ambient light intensity E is greater than the preset maximum light intensity Em, set A = 1 and keep G unchanged to prevent overexposure.

[0015] In a specific embodiment, it further includes: initially selecting a suitable fog segmentation strategy S0 based on the precipitation R in the weather information;

[0016] After performing grayscale processing on the image, use the Sobel operator to calculate the gradient. If the average gradient M < Th, use high-pass filtering to enhance the image;

[0017] Calculate the local contrast enhancement factor Cy: Cy = exp(α * M^2 / σs^2); where α and σs are the contrast influence coefficient and standard deviation respectively, and exp is the exponential function;

[0018] Fuse the original image and the filtered image by weighted average per pixel: W = (Img_original + C * Img_filter) / 2.

[0019] In a specific embodiment, it further includes: adjusting the sharpening intensity K0 = V / Vmax according to the vehicle speed V according to a preset rule. The faster the vehicle speed, the greater the sharpening intensity;

[0020] Pre-adjust the contrast parameter of the image for the predicted humidity H in the next few frames, and correct it using the following formula: B = β(H50), where β is the humidity change response factor;

[0021] Real-time detect and feedback the current visual visibility VD, and set the visibility compensation coefficient γ(VD) = 7 + 1 * sqrt(abs(log(VD / 10))). When VD reaches the set threshold Tvd, reduce the K weight to protect the user's eye health;

[0022] Loop the above operations at different time intervals to ensure the stability and real-time performance of the video stream.

[0023] In a specific embodiment, it further includes: obtaining the average light intensity Ep_avg and the standard deviation σEp within the previous second;

[0024] When rapid environmental light fluctuations are detected,

[0025] that is, abs(Ep_current - Ep_previous)>τ*σEp, where τ is the sensitivity threshold, and transient adaptive adjustment is performed;

[0026] Color balance optimization ColorAdj is performed, and the non - linear mapping relationship of L, a*, b* is separated and transformed using the Lab color space;

[0027] The formula F(C)=θ*C²+(1 - θ)*C is used to adjust the interaction between channels in the color space to ensure the best final image quality, where C represents the intensity of any single color channel and θ is the balance adjustment parameter.

[0028] In a specific embodiment, it further includes: accurately selecting the degree of image edge enhancement e0 according to the current atmospheric humidity HR;

[0029] When HR < hr_limit, the low - humidity mode is executed: the target edge is refined through a bilateral filter;

[0030] If high humidity triggers the high - humidity protection mechanism: F_HighHR = w_α*max(exp(μt*t), w_ω*cos(π*f*d)), t∈[t1, t2]

[0031] The improved bilateral filtering function is applied to process the image I = F(I, f, d), making the vehicle edges in the fog environment more clearly visible. f is the spatial filtering radius, d is the spatial distance, μt, wt control the smoothing effect in the time dimension, w_{ω} controls the frequency weight, and hr_limit represents the critical humidity limit.

[0032] In a specific embodiment, it further includes: introducing an intelligent environment assessment model to predict possible future environmental changes and making adaptive configuration changes in advance;

[0033] Define the comprehensive evaluation index Zeta to judge the effectiveness of image processing: Zeta(i)=Σ[Wi*log(δi*(Cy - Di))^(η)], where Cy is the statistical attribute value of the processed image such as the mean square error, etc., and Di is the corresponding ideal value;

[0034] Determine the direction of the image defogging strategy in the next cycle guided by the maximum Zeta value obtained under specific conditions;

[0035] If the calculation results show a significant decline for two or more consecutive times, start the reset learning phase to re-learn the optimal parameter sets Wi, η, etc.

[0036] In a specific embodiment, it further includes: comprehensively considering the changes in the illumination angle and direction to automatically correct the influence degree factor_dirction of the direct light source. The influence of the direct light source on the image can be calculated according to the illumination angle and direction by establishing an illumination model, and corresponding corrections can be made.

[0037] Divide the collected data into two parts. One part of the training samples is used to construct the short-term trend prediction engine model_shortTermPred, and the other part is the verification data testdata_valiation.

[0038] Use cross-validation to determine the optimal hyperparameters of the model; sets_optimParam, such as learningRate, nHiddenLayers, etc.

[0039] Enable the special mode when encountering extreme climate phenomena, that is, if WeatherExt == True: useExtremeProcessingAlgo().

[0040] In a specific embodiment, it further includes: establishing a personalized memory bank Memory_bank in combination with historical driving scenarios. Each time the user encounters a similar situation, they can retrieve previous successful cases for reference and comparison.

[0041] Set the corresponding priority prio according to the terrain class terrainClass where the vehicle is located, and arrange the subsequent steps accordingly.

[0042] Calculate the number of effective elements N_effective in each frame of the image. For cases where it is less than threshold_num, perform additional magnification or enhancement to avoid missing important details.

[0043] Introduce context-related information contextInfo to assist in identifying the background noise interference source ContextFilter(contextInfo)=contextImportanceWeightedMean(contextStrength).

[0044] In a specific embodiment, it further includes: continuously improving the denoising performance NoiseRedutionPerformance_improvememt(CloudResrouce) of the local port by means of the deep learning resources provided by the cloud data center, monitoring the network connection quality networkStableLevel to ensure stable transmission efficiency, and starting the contingency offline operation plan ContingencyPlanofflineMode() when there are packet losses or the latency is not ideal NetworkQuality <= low_threshold. Here, the improvement of the denoising performance can be achieved by using the deep learning model in the cloud to denoise the local images and then feeding back the processing results to the local port;

[0045] Check whether there are any unfixed bugs BugReport_latest in the latest version of the software and promptly push the patch package PatchDeployment();

[0046] In a specific embodiment, it further includes: analyzing the driver's habitual actions and preferences habit_patterns to select the appropriate image presentation mode Presentation_mode(habit_pattern).

[0047] Regularly maintain an online knowledge graph KnowledgeGraph_online to collect new information NewRoadInfo about road conditions and update it in a timely manner;

[0048] Judge whether to activate certain feature functions feature_activation_status according to the latest traffic regulations TrafficRegulations and the real-time weather situation RealTimeWeaherSituation;

[0049] In response to emergency braking or other emergencies EmergencyResponse(), quickly capture and save the accident scene images for subsequent retrospective review InCydentReviewProcess().

[0050] An embodiment of the present disclosure provides an electronic rearview mirror image defogging method based on image information integration. By acquiring the original image collected by an external camera, and then entering the preprocessing stage. In this process, a light sensor and other components are used to sense the ambient light intensity. When the light conditions are good, the system will adopt a relatively mild filtering algorithm to reduce image noise and protect the original details of the image. When it is detected that the environment is in low light or variable light conditions, it can perform intelligent compensation on the image to dynamically improve the contrast and brightness, thereby solving the problem of dynamically adjusting the contrast and brightness of the image according to the change of ambient light to solve the problem of blurred imaging.

[0051] By completing the post-processing process of the image: such as removing moiré patterns or correcting geometric distortion. All the above steps achieve automatic control on the premise of ensuring safety and reliability, and fully consider the extremely high delay requirements of the vehicle's high-speed operation characteristics. Therefore, the entire algorithm runs very efficiently and quickly, and the resource consumption is reasonable, meeting the needs of modern automotive applications. This not only improves the visual effect in rainy, snowy, and foggy conditions, but also improves the driving safety guarantee coefficient, and can solve the problem of adjusting the parameters of the image edge enhancement algorithm according to real-time weather conditions to solve the problem of unclear image boundaries in foggy days. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present disclosure, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a flowchart of an electronic rearview mirror image defogging method based on image information integration. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0055] Next, the specific implementation steps of the electronic rearview mirror image defogging method based on image information integration of the present invention are described with reference to the accompanying drawings, and the process of how to solve the image contrast and brightness blurring caused by ambient light changes and the unclear edge of foggy images. The method includes multiple core links, aiming to improve the imaging quality of the electronic rearview mirror under different weather conditions through advanced image processing algorithms, thereby ensuring driving safety.

[0056] First, collect images of actual road scenes with atmospheric attenuation factors. In actual operation, a high-resolution camera is installed on the rear side of the vehicle body to capture the scene behind the vehicle in real time and obtain the initial grayscale image and RGB color image. To ensure the integrity and reliability of the data, these input frames need to undergo a series of pre-filtering processes, such as histogram equalization to eliminate the noise introduced by the inherent defects of optical devices, and then obtain one or more clear, clean images that can truly reflect the characteristics of the surrounding environment for further calculation.

[0057] After that, multi-scale decomposition is performed to separate the atmospheric light components, capture the hidden structural features from the detail level, and estimate the global haze intensity coefficient value in order to compensate for the effective texture information lost due to the scattering effect in the later stage, and initially establish a map of transmittance, which provides a basis for the next step of accurately restoring the polluted target, and on this basis, build a performance model framework with robust performance in complex environments. For example, on a cloudy day, when the sensor detects a low amount of light and determines that the current concentration is in the range of light haze, a more relaxed threshold condition can be adopted to reduce the risk of excessive suppression of high-frequency signals, thereby avoiding excessive sharpening and distortion that affects the overall visual experience.

[0058] Next, in order to solve the problem of dynamically adjusting the contrast and brightness according to the changes in ambient light mentioned above, we adopt a local adaptive dual enhancement strategy. On the one hand, we combine the exposure balance principle to adjust the differences in pixel density distribution between each sub-window; on the other hand, we use the gamma correction function mapping method to effectively extend the grayscale range to expand the visibility in the dark area, narrow the excessive gap between the two, and ensure the output result. It can present bright and saturated colors while having a high enough resolution, so that even in low light, it can still maintain a high resolution and reduce the probability of blurring.

[0059] To solve the problem of imaging blurring, an intelligent prediction module is introduced. By mining and refining the historical statistical data accumulated in the early stage, an empirical rule model is summarized and formed. Based on this, the system guides the selection of the most suitable parameter combination form in the current state transition process, automatically matches the best effect setting to achieve the purpose of real-time synchronization. In one embodiment, the system will monitor various lighting conditions such as sunny, evening or night outdoors, and autonomously learn and master the best response mechanism corresponding to each situation through an embedded learning algorithm. Once triggered, it will immediately switch the working mode and quickly complete the relevant correction actions to ensure that high-quality images are always presented for the driver to view.

[0060] Finally, a complete automated evaluation system is studied for the problem of parameter regulation of the edge enhancement algorithm under real-time weather conditions. The main idea is to first define several key quantitative indicators based on physical characteristics, such as the uniformity of the contrast boundary slope, etc. Then, a simulation environment is built with the help of deep convolutional neural network technology to simulate all typical situations that may occur in nature, and finally determine the different disturbance levels caused by various factors such as different types of clouds, fog, and rain. Based on this, a corresponding fine-tuning rule library is set up to facilitate the program to directly query and reference and instantaneously correct the weight factor online until it completely matches the expected output characteristics, thoroughly improving the problems such as the rough edge transition commonly existing in the original system, and greatly improving the accuracy of target recognition.

[0061] Generally speaking, in order to cope with the unpredictable weather conditions in reality, this new type of image information integrated interactive processing platform integrates a variety of advanced technical means, comprehensively utilizes the prior theoretical knowledge of statistics to carefully construct a multi-level progressive architecture, realizes a functional closed-loop covering the entire business logic chain, and can always maintain a stable high-performance level under various extreme working conditions, meeting the higher requirements for the intelligence of vehicle-mounted auxiliary equipment in the field of modern intelligent transportation. Specifically, this solution not only significantly reduces the accident rate of driving line-of-sight interference caused by bad weather, but also greatly improves the comfort and satisfaction of passengers and promotes more user-friendly human-computer interaction.

[0062] Next, the present invention is described for obtaining real-time ambient light data and dynamically adjusting the contrast and brightness of an image according to the data. The whole process is divided into several steps, and each step has a clear execution function to ensure accurate adjustment, optimize the image quality and the user's viewing experience. First, the system needs to collect the light intensity information from external sensors. Here, the external sensors usually refer to one or more photodetectors placed around the electronic rearview mirror device for measuring the ambient light intensity (unit: Lux, from 0 to 100,000 Lux). The goal of this operation is to capture the most immediate change in the brightness level that matches the real world. For example, when the electronic rearview mirror is exposed to the sudden strong light at the tunnel exit, this component can quickly sense the information of the sharp rise in ambient light.

[0063] Next, after accurate data is collected, the algorithm proceeds to the next step of preprocessing the original video frames. That is, the obtained light intensity value is converted into an input parameter suitable for the contrast enhancement calculation model. To accomplish this step, in one embodiment, a linear transformation of the ambient light intensity L is performed through the formula L = a * L + b to generate a new ambient light intensity L. In the above expression, a is the proportionality constant, whose value lies between [0.5, 2] and the optimal choice depends on the requirements of the actual scenario. For example, it is recommended to be set to 1 in the automotive rearview camera system; b is an offset, usually taking integer values in the range [-50, +50], and setting -30 may be more appropriate for reducing night noise. The purpose of this formula is to scale and calibrate the information captured from the physical world to ensure consistency with the subsequent contrast enhancement logic.

[0064] After the above preprocessing step, the system is ready to automatically correct the picture features based on the transformed L. On the one hand, the overall picture brightness B is adjusted. Specifically, if it is detected that the current ambient illumination is too bright, then according to the inverse proportional function B = (K / (L + E)), the average brightness of the output image is gradually reduced to avoid overexposure problems. In this relationship, K represents the upper limit of the saturation point (the maximum recommended value is 650), and E represents a very small normal constant to prevent the denominator from approaching zero (set to about 1), thus avoiding the abnormal increase of the calculation result in extreme cases and damaging the display stability.

[0065] On the other hand, the dynamic adjustment of the contrast Cy is carried out. Similarly, it is achieved by using a certain mapping relationship. Assume the formula Cy = max(c * (L - D), Cy_min), where c represents the gain coefficient, whose floating range is set within [0.75, 1.33]. It is preferably adaptively selected according to different road conditions. For example, a smaller value such as 0.9 is selected on urban streets to maintain a stable visual transition. D is used as a threshold control to offset the influence of atypical weather factors (such as thick fog, heavy rain, etc.). In this context, it can be taken as about 45. And C_min ensures that the final contrast is not lower than a certain basic standard (set to 50) so that a basically recognizable picture can be maintained even in bad weather conditions.

[0066] For example, in an actual application scenario, the electronic rearview mirror image defogging method based on image information integration involves the situation of a vehicle driving out of an underground garage during a rainy night. In such a scenario, due to the rapid increase in external light and the presence of a large number of reflective interference sources, the uncorrected camera images often appear gray or too pale. However, after applying the above technical improvements, thanks to the intelligent perception of external light conditions and timely fine-tuning of display parameters, the driver can not only obtain clear and visible feedback on the rear and both sides of the vehicle, but also reduce the possibility of eye fatigue during long-term viewing. Through dynamic optimization post-processing, the main factors affecting visual safety in various adverse optical environments can be effectively overcome.

[0067] Next, the invention is described to generate an optimized basic image based on the adjusted image parameters; in this process, the following steps are included: collecting image data, determining and adjusting image parameters, applying these parameters to the image, and finally evaluating and optimizing the quality of the basic image.

[0068] Specifically: First, in the process of acquiring images, a collection of images of the original electronic rearview mirror scene is captured from multiple sources such as cameras to build a raw image library for processing. In this example, it is assumed that the image is collected from a moving car on a busy road to ensure that the image data can fully represent the real situation that may be encountered.

[0069] After that, the necessary image parameters are selected and adjusted according to specific needs. This includes contrast, brightness, color temperature, and haze removal coefficient. In this link, special attention is paid to how to set image parameter values ​​that are closely related to weather or visibility. For example, for electronic rearview mirror image defogging, an important adjustment is to finely control the variable of transmittance t (range 0 to 1, when t is closer to 1, it means less fog); and atmospheric light value A (dynamically changes according to the actual environment). In order to achieve the ideal effect, the ideal range of transmittance t is set to about 0.5 to 0.8; atmospheric light A needs to obtain the most suitable value range for the current scene based on real-life testing to ensure that the set parameters can maximize the improvement of image visibility and color accuracy after being disturbed by fog.

[0070] In one embodiment, a mathematical formula I=frac{IA}{t}+A is used, where I is the processed image intensity, I is the original image input, A refers to the ambient atmospheric light, and t is the adjusted transmission rate parameter mentioned above. The principle of this formula is to try to restore clear scene information without fog and reduce the problem of visual distortion caused by dense fog.

[0071] Specifically, after completing the above calculations and adjustments, the adjusted parameters are then applied to the originally collected base images. By performing corresponding algorithms or technical means such as histogram equalization and sharpness enhancement, the optimized base images can be made to more closely approximate the real picture quality that can be directly perceived by the human naked eye, while also improving the recognition efficiency of the objects in the images.

[0072] Subsequently, it enters the quality assessment and optimization stage. Pre-defined criteria such as the root mean square error (RMSE) or subjective scoring methods are used to measure the differences between the images before and after improvement, and targeted adjustments are made to continuously iterate until the expected effect is achieved. For example, in an actual test case, if the optimized image fails to effectively eliminate the problem of reduced recognition of road edges in the case of heavy fog, it may be necessary to go back and fine-tune the values of A or t until the most suitable combination is found.

[0073] Next, the parameters of the image edge enhancement algorithm according to the real-time meteorological conditions of the present invention are described.

[0074] First, the steps include meteorological condition detection, analyzing real-time data to determine the haze or haze density level, adjusting the filtering parameters and intensity coefficients based on the analysis results, and finally improving the image processing effect by optimizing the parameters. Meteorological condition detection refers to using specific devices such as meteorological sensors to obtain key data such as temperature, humidity, and atmospheric visibility. This step is crucial for the entire process because accurately understanding the external situation lays a solid foundation for subsequent calculations. This information not only affects the final visual quality but also determines the subsequent parameter setting strategy. For example, in the case of high humidity, water vapor condensation is likely to occur, resulting in a hazy image. At this time, appropriate adjustments must be made to improve the imaging clarity.

[0075] Analyzing the real-time data means extracting useful features from the previously obtained data set and calculating the haze value HazeLevel. Specifically, the HazeLevel formula is defined as: HazeLevel = α × humidity + β × Visibility^γ, where humidity represents relative humidity, and the value range is [0, 100]; Visibility represents visibility (in kilometers), and the normal environment value is greater than 0. α and β are proportionality coefficients, usually set as constants between 0 and 1, and γ is the power term, which is default set to 0.5. The establishment of this formula is to reflect the influence of humidity and visible distance on the image in a weighted manner. The greater the humidity and the lower the visibility, the greater the HazeLevel. This indicator can evaluate the severity of the actual situation to select corresponding response measures.

[0076] Then, fine-tune the weights w of the edge detection operator (e.g., Sobel) and the values of sigmaColor and sigmaSpace of the bilateral filter according to different haze situations. The weight w belongs to the range [0 - 1], and when facing thick fog, it will increase to nearly 1 to make the image boundaries more prominent, helping the driver to see the details around the vehicle more clearly. For σColor and σSpace, they respectively control the tolerance limits of color and smoothness. In an environment with light fog or mild air pollution, σColor takes a small positive value (such as 2 - 5), while in a heavy weather condition, σColor expands accordingly to ensure that both noise can be reduced and the object outlines can be maintained; similarly, σSpace also has a similar variation rule, which generally fluctuates between 2 - 8 to maintain the best filtering performance.

[0077] The last step aims to perform corrected rendering on the initial input photo using the adjusted new parameters, and repeatedly compare with the original state to verify the effectiveness of the improvement to ensure the feasibility of the solution, continuously approaching the ideal goal so as to provide a stable and reliable auxiliary tool to serve the actual needs. In one embodiment, assume that an electronic rearview mirror image defogging method based on image information integration faces the test of variable outdoor factors. When the monitoring shows that the current is under the condition of haze coverage, adjust the relevant coefficients in a timely manner according to the above logic to make the image restoration degree higher and then enhance the safety. At the same time, through the dual tests of subjective evaluation by human eyes and objective numerical comparison, it is proved that the algorithm after dynamic adjustment does improve the visibility and detail presentation ability within the monitoring field of view in complex climates.

[0078] Next, describe the application of the adjusted parameters to the base image to output a clear defogged image in the present invention. This process is divided into the following steps: obtaining the base image, calculating the atmospheric light value and the transmission map, performing defogging processing according to the optimization formula, and applying the parameter optimization results.

[0079] Specifically, obtaining the base image involves the electronic rearview mirror sensor capturing the initial scene information to form a raw picture. The visual quality of this image may decline due to factors such as fog. In this example, assume there is a method based on image information integration. First, collect a road photo with thick fog from the rearview camera equipped on the vehicle as the object to be processed. For example, in one embodiment, this step provides data support for the subsequent algorithm.

[0080] Subsequently, after obtaining the original foggy image, the second step is entered, namely estimating the atmospheric light A and solving the transmission map t(x). The former is the brightness of the light source component with the most severe scattering in the air, while the latter represents the proportionality coefficient of the object passing through a certain thickness of the medium to reach the camera. Generally speaking, 0 < t < 1, t = 0 means invisible, and t = 1 refers to the limiting case where there is no scattering phenomenon; and the atmospheric light intensity value should preferably be selected as the pixel value with the highest gray level in the non-sky area to exclude the misleading influence caused by the sky. For example, in this embodiment, by automatically selecting multiple dark color blocks (excluding the sky area) and finding the maximum brightness for each of the RGB three channels within these blocks to estimate a globally applicable atmospheric light A, and setting the range 0.5 < A < 2.0, and the best value is about 1.3 for generality considerations under different conditions. In addition, deep learning technology or empirical formulas are used to predict the actual transmission ratio factors at each point to form a complete mapping chart, so that even in a large-scale diffuse natural environment, it can be ensured that each pixel corresponds to a reasonable transmission attribute, thus ensuring that the accuracy of the whole process is not affected by weather changes. Among them, models such as the dark channel prior method or neural network are used to establish an accurate physical model to estimate the transmission rate function, ensuring good adaptability to various complex road conditions.

[0081] After obtaining the above two key elements, the next step is immediately executed, that is, removing the haziness in the picture and improving the overall visual clarity according to the pre-constructed and adjusted algorithm expression. Here, the restoration formula I(j) = ((Rc(j) - Ac)) / max(βt(i), τ)) + Ac is introduced. Inside this formula, I(j) represents the color vector form of any point j in the finally presented target image, and Rc(j) indicates the corresponding position color vector representation received by the noisy observation input port. At the same time, Ac represents the atmospheric light constant mentioned above; max(βt(j), τ) means that in order to prevent the denominator from approaching zero, a minimum guarantee line τ is set and multiplied by the attenuation coefficient β to ensure that the result output will not deviate too much from the actual situation. Generally, 0.1 ≤ τ ≤ 0.4 and 0 < β ≤ 1 are set here. In the ideal case, selecting β = 0.9 and τ = 0.1 can effectively suppress the detail distortion caused by excessive amplification. Specifically, in this implementation case, the calculated atmospheric light A and the transmission matrix are used to complete the entire image quality conversion operation.

[0082] The last step is to feedback the adjusted parameters back into the system and check again to verify whether they are correct, and then generate the final version. During this process, the differences between the same scene before and after the experiment will be repeatedly compared until satisfactory. For example, in this implementation example, it is continuously optimized and adjusted until the rearview mirror image on the display screen reaches the best state of matching well with the actual situation and without losing any details, and then the entire process ends.

[0083] A method for dehazing electronic rearview mirror images based on image information integration according to the present invention includes:

[0084] This method first obtains the original images collected by an external camera. Then, it enters the preprocessing stage. During this process, a light sensor, etc., is used to sense the ambient light intensity. When the light conditions are good, the system will adopt a relatively mild filtering algorithm to reduce image noise and protect the original details of the image; while when it detects that the environment is under low light or variable light conditions, it can perform intelligent compensation on the image to dynamically increase the contrast and brightness. For example, in the dark or in a dim tunnel, the algorithm can appropriately increase the dynamic range of the image histogram, highlight important information, and make the driving vision clearer and more definite. Conversely, it reduces the saturation gain to ensure color accuracy and avoid overexposure.

[0085] Subsequently, after determining the current weather condition (such as sunny or foggy), this invention has made improvements for special situations in a haze environment. Due to the scattering effect caused by fog, the image boundaries are not clear. For this, an adaptive edge enhancement technique is adopted. That is, relying on real-time meteorological data, such as air quality and climate parameters provided by a humidity sensor, a PM2.5 detector, etc., to dynamically adjust the high-pass factor value in the edge extraction filter, ensuring ideal clarity under any meteorological conditions. At the same time, the adjustment intensity will also change accordingly for different concentrations of haze. In the case of mild haze pollution, the soft mode can meet the needs; if heavy haze strikes, the enhanced processing mechanism is activated, and through multi-scale convolution kernel iterative operations, the true shape and boundary lines of the target object are gradually restored from coarse-grained to fine-grained, thereby effectively improving the driver's ability to identify external scenery under harsh conditions.

[0086] Finally, the image post-processing process is completed: such as removing moiré patterns or correcting geometric distortion. All the above steps achieve automatic control on the premise of ensuring safety and reliability, and fully consider the extremely high delay requirements for the high-speed operation characteristics of the vehicle. Therefore, the entire algorithm runs very efficiently and quickly, and the resource consumption is reasonable, meeting the requirements of modern automotive applications. This not only improves the visual effect in rainy, snowy, foggy, and misty conditions, but also increases the driving safety guarantee coefficient. In addition, this solution can also be closely combined with autonomous driving technology, contributing to the key role of more accurate road recognition and obstacle avoidance and other intelligent functions.

[0087] The above is the preferred implementation mode of this application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle described in this invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. An electronic rearview mirror image defogging method based on image information integration, characterized in that, Including: S101: Obtain real-time ambient light data and dynamically adjust the contrast and brightness of the image according to the data; S102: Generate an optimized base image based on the adjusted image parameters; S103: Adjust the parameters of the image edge enhancement algorithm according to real-time weather conditions; S104: Apply the adjusted parameters to the base image to output a clear dehazed image; The step S103 includes: Adjust the sharpening intensity K0 = V / Vmax according to the vehicle speed V according to a preset rule. The faster the vehicle speed, the greater the sharpening intensity; Pre-adjust the contrast parameter of the image for the predicted humidity H in the next few frames and correct it using the following formula: B = β(H - 50), where β is the humidity change response factor; Real-time detect and feedback the current visual visibility VD, and set the visibility compensation coefficient γ(VD) = 7 + 0.1*sqrt(abs(log(VD / 10))). When VD reaches the set threshold Tvd, reduce the K weight; The step S104 includes: Obtain the average light intensity Ep_avg and standard deviation σEp within the previous second; When it is detected that the ambient light fluctuates rapidly, that is, abs(Ep_current - Ep_previous) > τ*σEp, where τ is the sensitivity threshold, perform transient adaptive adjustment; Perform color balance optimization ColorAdj and use the Lab color space to separate and convert the non-linear mapping relationship of L, a*, b*; Use the formula F(C0) = θ*C0²+(1 - θ)*C0 to adjust the interaction between the channels of the color space, where C0 represents the intensity of any single color channel and θ is the balance adjustment parameter.

2. The method for dehazing an electronic rearview mirror image based on image information integration according to claim 1, wherein The step S101 includes: Determine the initial brightness enhancement coefficient A0 based on the vehicle speed and the camera viewing angle range. The faster the vehicle speed and the larger the camera viewing angle range, the larger the value of A0; According to the real-time ambient light intensity E, adopt the brightness adjustment formula: A = A0*(1 + tanh(E / (Es*Ec))); Where, Es is the ambient light intensity threshold, Ec is the ambient light intensity center offset, and tanh is the hyperbolic tangent function, which is used to map the input value to the interval (-1, 1); Dynamically update the photosensitivity of the camera sensor G = Gbase + A*ΔG; Where, Gbase is the base sensitivity, and ΔG is the photosensitivity gain change; If the current ambient light intensity E is greater than the preset maximum light intensity Em, then set A = 1 and keep G unchanged.

3. The method for de - fogging the electronic rear - view mirror image based on image information integration according to claim 2, wherein, The step S102 includes: The fog segmentation strategy S0 initially selected based on the precipitation R in the weather information; After grayscale processing the image, use the Sobel operator to calculate the gradient. If the average gradient M < Th, use high-pass filtering to enhance the image; Calculate the local contrast enhancement factor Cy: Cy = exp(α*M^2 / σs^2); Where, α and σs are the contrast influence coefficient and standard deviation respectively, and exp is the exponential function; Fuse the original image and the filtered image and perform pixel-weighted averaging: W = (Img_original + C*Img_filter) / 2.

4. A method for dehazing an electronic rearview mirror image based on image information integration according to claim 3, characterized in that, The step S103 includes: Precisely select the image edge enhancement degree e0 according to the current atmospheric humidity HR; When HR < hr_limit, execute the low-humidity mode: refine the target edge through a bilateral filter; If high humidity triggers the high-humidity protection mechanism: F_HighHR = w_α * max(exp(μt * t), w_ω * cos(π * f * d)), t ∈ [t1, t2]; Apply an improved bilateral filtering function to process the image I = F(I, f, d), making the vehicle edges in the fog environment more clearly visible. f is the spatial filtering radius, d is the spatial distance, μt and w_α jointly control the smoothing effect in the time dimension, w_ω controls the frequency weight, and hr_limit represents the critical humidity limit.

5. A method for de - fogging an electronic rear - view mirror image based on image information integration according to claim 4, wherein, The step S103 includes: Introduce an intelligent environment assessment model to predict possible future environmental changes and make adaptive configuration changes in advance; Define a comprehensive evaluation index Zeta to judge the effectiveness of image processing: Zeta(i) = Σ[Wi * log(δi * (Cy - Di))^(η)], Cy is the mean square error of the processed image, and Di is the corresponding ideal value; Use the maximum Zeta value obtained under specific conditions as the guiding principle to determine the direction of the image dehazing strategy in the next cycle; If the calculation results show a significant decrease for two or more consecutive times, start the reset learning stage to re-learn the optimal parameter sets Wi, η.

6. A method for defogging an electronic rearview mirror image based on image information integration according to claim 5, characterized in that, The step S101 includes: Automatically correct the influence degree factor_dirction of the direct light source by comprehensively considering the changes in the illumination angle and direction. By establishing an illumination model, calculate the influence of the direct light source on the image according to the illumination angle and direction, and make corresponding corrections; Divide the collected data into two parts, one part of the training samples is used to construct a short-term trend prediction engine model_shortTermPred, and the other part is the verification data testdata_valiation; Use cross-validation to determine the optimal hyperparameters sets_optimParam of the model. When encountering extreme climate phenomena, enable the special mode, that is, if WeatherExt == True: useExtremeProcessingAlgo().

7. A method for dehazing an electronic rearview mirror image based on image information integration according to claim 6, characterized in that, The step S104 includes: Establish a personalized memory bank Memory_bank in combination with historical driving scenarios. Each time the user encounters a similar situation, retrieve past successful cases for reference and comparison; Set the corresponding priority prio according to the terrain class terrainClass where the vehicle is located, and arrange the subsequent steps accordingly; Calculate the number of effective elements N_effective in each frame of the image. For cases with less than threshold_num, perform additional amplification or enhancement; Introduce context-related information contextInfo to assist in identifying background noise interference sources ContextFilter(contextInfo) = contextImportanceWeightedMean(contextStrength).

8. A method for dehazing an electronic rearview mirror image based on image information integration according to claim 7, characterized in that, The step S103 includes: Continuously improve the noise reduction performance of the local port, NoiseRedutionPerformance_improvememt(CloudResrouce), by leveraging the deep learning resources provided by the cloud data center, and monitor the network connection quality, networkStableLevel, to ensure stable transmission efficiency; when packet loss or unsatisfactory latency occurs, NetworkQuality <= low_threshold, initiate the contingency offline operation plan, ContingencyPlanofflineMode(). Here, the noise reduction performance improvement involves using the deep learning model in the cloud to denoise the local images and then feeding the processed results back to the local port; Check whether there are unfixed vulnerabilities in the latest version of the software, BugReport_latest, and promptly push the patch package, PatchDeployment(); Further analyze the driver's habitual actions and preferences, habit_patterns, to select an appropriate image presentation mode, Presentation_mode(habit_pattern); Regularly maintain an online knowledge graph, KnowledgeGraph_online, collect new information about road conditions, NewRoadInfo, and update it in a timely manner; Determine whether to activate certain feature functions, feature_activation_status, based on the latest traffic regulations, TrafficRegulations, and the real-time weather situation, RealTimeWeaherSituation; In response to emergency braking or other emergencies, EmergencyResponse(), quickly capture and save the accident scene images for post-event retrospective review, InCydentReviewProcess().

Images