Ar navigation light carpet projection correction method and control system based on road surface wetness degree detection

Abstract

The present application relates to the technical field of intelligent lighting, and more particularly to an AR navigation light carpet projection correction method and control system based on road surface wetness detection. The control system comprises a vehicle perception and data acquisition module, a processor and an execution layer. The vehicle perception and data acquisition module acquires road condition information, environmental information and vehicle information. The acquired multi-modal information is normalized, and a wetness index is calculated based on the multi-modal information. The processor adjusts the light projection range, projection brightness and contrast based on the wetness index, and controls the headlight projection through the execution layer. By introducing the wetness index, the light projection range, brightness and contrast are adjusted, and the corrected navigation light carpet is accurately projected into the dynamically adjusted road surface area in front of the vehicle, thereby realizing clear, distortion-free and anti-glare navigation guidance in a wet and slippery environment.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting technology, and in particular to an AR navigation light carpet projection correction method and control system based on road surface slippage detection. Background Technology

[0002] Intelligent vehicle lighting technologies, especially projection headlight systems based on digital light luminaires (DLP) or high-pixel Micro-LEDs, have been widely used in augmented reality (AR) navigation functions, using perspective projection transformation algorithms to generate navigation arrows or driving light carpet maps.

[0003] Existing light carpet projection technologies typically rely on an ideal Lambertian diffuse reflection model, assuming constant road surface optical characteristics and lacking a real-time perception and adaptive adjustment mechanism for slippery road conditions. When vehicles travel on rainy, snowy, flooded, or icy roads, the road surface characteristics drastically change from diffuse reflection to specular reflection. This change in optical characteristics first leads to a severe decrease in visibility: within the set projection range, most light is specularly reflected away from the driver's line of sight, resulting in uneven brightness, lack of contrast, or even complete invisibility of the projected pattern. Second, it poses a glare safety hazard: high-intensity light without targeted brightness control can easily be reflected through slippery surfaces into the vision of oncoming vehicles or pedestrians, causing severe glare. Furthermore, the refractive effect and morphological changes of the water film can cause nonlinear optical distortion in the projected image, distorting the AR navigation information. Existing systems cannot overcome these environmental interferences, severely limiting the practicality and safety of intelligent vehicle lights under complex weather conditions. Summary of the Invention

[0004] The technical problem to be solved by this invention is: in order to improve the practicality and safety of intelligent vehicle lights under complex weather conditions, this invention provides an AR navigation light carpet projection correction method and control system based on road surface slippage detection.

[0005] The technical solution adopted by this invention to solve its technical problem is: An AR navigation light carpet projection correction method based on road surface slippage detection includes: Step 1: Obtain road condition information, environmental information, and vehicle information; Step two: Normalize the multimodal information obtained in step one, and calculate the slip index based on the multimodal information. ; Step 3: Adjust the light projection range, projection brightness, and contrast based on the slipperiness index, and control the headlight projection.

[0006] This application introduces a slipperiness index to adjust the projection range, brightness, and contrast of the lights, accurately projecting the calibrated navigation light carpet onto the dynamically adjusted road surface area in front of the vehicle, thereby achieving clear, distortion-free navigation guidance that meets anti-glare requirements in slippery environments.

[0007] Furthermore, in step one, the road condition information includes visual perception components acquired through a camera, the environmental information includes environmental perception components acquired through a rain sensor, and the vehicle information includes dynamic perception components acquired through an ESP system.

[0008] Furthermore, in step two, based on the normalized visual perception components... Environmental perception component Dynamic sensing components Calculate the instantaneous slip index For instantaneous slip index The slip index is obtained after filtering. .

[0009] Furthermore, the instantaneous slip index ,in, , , These are the weighting coefficients for the visual perception component, the environmental perception component, and the dynamic perception component, respectively, and they satisfy... + + = 1.

[0010] Furthermore, the slip index ,in, This represents the final slip index output at the current moment. This is the output value from the previous time step; The instantaneous value calculated at the current moment; This is the filtering smoothing factor, with a value range of (0, 1).

[0011] Furthermore, in step three, the original image coordinates to be projected are converted into coordinates of the deformed image projected onto the slippery ground based on the slipperiness index WI. , Where (u, v) are the pixel coordinates in the original image source, and (u', v') are the corrected pre-deformation coordinates, where u corresponds to the lane width direction and v corresponds to the driving distance direction; This is the horizontal trapezoidal correction factor, used to slightly widen the edges to compensate for visual shrinkage; The vertical compression factor is used to compress the image source vertically to counteract the physical stretching. This is a weighting function related to the projection distance.

[0012] The geometric anti-distortion unit calls the pre-set optical path reflection model library based on WI, calculates the "reverse distortion matrix" according to the water film refractive index and reflection angle, and performs nonlinear pre-deformation processing (such as longitudinal compression or lateral stretching) on ​​the original AR navigation image to counteract the optical elongation or distortion caused by the wet and slippery medium.

[0013] Furthermore, in step three, the slippage index WI is used to evaluate the grayscale values ​​of the original image pixels. Correction is performed to overcome the light energy loss caused by specular reflection, resulting in a corrected output grayscale value. Among them, dynamic compensation gain for ,in, This is the ambient light sensitivity coefficient; the stronger the ambient light, the greater the required contrast gain. The angle of incidence of the light ray; The road surface specular reflectivity factor; This is a truncation function to ensure that the output value does not exceed the maximum brightness limit of the DLP module.

[0014] The brightness and contrast enhancement unit monitors when the WI exceeds a preset threshold and automatically switches the image rendering mode from grayscale gradient to high-contrast monochrome outline mode. It also dynamically increases the brightness gain of key pixels according to ambient light to overcome the loss of light intensity caused by specular reflection.

[0015] Furthermore, in step three, the optimal projection distance is calculated. , ,in, This is the baseline projection distance under dry conditions, which is positively correlated with the current vehicle speed. The threshold for triggering position adjustment, when < At this time, the system maintains the reference distance projection and does not pull back; It can be a step activation function or a linear rectifier function; The value used to control the rate at which the projection distance decreases with increasing slipperiness is typically between 0.3 and 0.6.

[0016] The optimal projection distance is calculated based on the WI, a new region of interest (ROI) window coordinate is generated, and a near-field pull-back strategy is executed to avoid glare-prone areas in the distance.

[0017] A control system for implementing the AR navigation light carpet projection correction method based on road surface slippage detection as described above, comprising: The vehicle perception and data acquisition module includes a forward-facing camera, a rain and light sensor, and a dynamic sensor group integrated into the chassis. The processor is connected to the vehicle perception and data acquisition module and calculates the image projection control signal based on the data acquired by the vehicle perception and data acquisition module. The execution layer is connected to the processor and controls the headlight projection according to the control signal.

[0018] Furthermore, the processor includes a preprocessing module, a road surface slippage calculation module, a geometric distortion correction unit, a brightness and contrast enhancement unit, and a projection position adjustment unit. The preprocessing module is connected to the road surface slippage calculation module, and the geometric distortion correction unit, brightness and contrast enhancement unit, and projection position adjustment unit are all connected to the road surface slippage calculation module.

[0019] As the core of the system's computation, the processor's operation constructs a closed-loop control architecture from multi-source perception to precise execution. The starting point of the logic processing is located in the slipperiness index calculation module, which acts as the data fusion hub, receiving and aggregating real-time visual data from the camera, environmental data from the rain sensor, and ESP and vehicle speed signals from the perception input. Through an internally pre-built fusion algorithm, this module transforms the above heterogeneous signals into a standardized slipperiness index, thereby quantifying the optical reflectivity of the current road surface. The slipperiness index, as a key decision variable, is simultaneously distributed to three subsequent parallel processing branches to drive differentiated correction strategies: within the correction algorithm logic block, the geometric anti-distortion unit calculates the inverse deformation parameters based on the index to offset the graphic distortion caused by water film refraction, while the brightness / contrast adjustment unit simultaneously optimizes the image's grayscale distribution and gain based on the index to ensure visibility under specular reflection conditions; at the same time, the independent projection position adjustment module also dynamically calculates the optimal projection distance coordinates based on the slipperiness index, executing an anti-glare pull-back strategy. Ultimately, the corrected image data and position coordinate instructions output from these three parallel branches are aggregated at the logic end and transmitted to the DLP headlight module at the execution output end, driving it to project an AR navigation light carpet with a proper geometric shape, appropriate brightness, and precise position in physical space.

[0020] The beneficial effects of this invention are that its core lies in deeply integrating inverse optical modeling based on correction algorithms into the AR navigation light carpet projection system. By treating the road surface as a dynamically changing optical medium, the invention utilizes the following key technical points to achieve active compensation and precise correction of the reflective characteristics of slippery road surfaces: 1. Quantitative Perception of Road Surface Properties: The system breaks through the traditional single-sensor mode that relies solely on rain sensors, and constructs a multi-source heterogeneous data fusion model. By aggregating texture gloss data from the forward-looking camera, ambient humidity data from the rain sensor, and wheel slip rate data from the ESP system in real time, a weighted normalized wet skid index (WI) is calculated. This index can quantitatively characterize the physical degree of the current road surface transitioning from diffuse reflection to specular reflection, providing a precise quantitative basis for subsequent optical compensation.

[0021] 2. Dual Correction Algorithm Based on Reverse Optics: The system establishes an optical physical model of water film refraction and reflection, and executes algorithmic intervention in real time based on the slip index (WI). Based on Snell's law of refraction, the inverse distortion matrix is ​​calculated, and longitudinal nonlinear compression and trapezoidal correction are performed on the original image to generate a "pre-deformed" image source to counteract the visual stretching caused by water film refraction. Using a dynamic gain compensation algorithm, when a high slip index is detected, binarization thresholding is automatically triggered, switching to a high-contrast contour mode to overcome the light intensity loss caused by specular reflection. Attached Figure Description

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0023] Figure 1 This is a schematic diagram of the control system in this invention.

[0024] Figure 2 This is a schematic diagram illustrating the implementation logic of the control system in this invention.

[0025] Figure 3 This is a schematic diagram of the control flow of the control system in this invention.

[0026] Figure 4 This is a schematic diagram of the wet and slippery road surface correction process in this invention.

[0027] Figure 5 This is a schematic diagram comparing the optical effects of the correction algorithm in this invention. Detailed Implementation

[0028] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0029] Example 1: like Figure 1 The image shows Embodiment 1 of the present invention. Embodiment 1 provides a control system for an AR navigation light carpet projection correction method based on road surface slippage detection. The processing system includes three subsystems: a vehicle perception and data acquisition module, a processor, and an execution layer. The three subsystems are connected via a vehicle bus (such as CAN / LIN) for communication.

[0030] Specifically, the vehicle perception and data acquisition module includes a front-view camera located at the front of the vehicle to capture road surface texture and reflective gloss features; a rain and light sensor to detect environmental precipitation and light conditions; and a dynamic sensor group integrated into the chassis (such as wheel speed sensors, electronic stability control system (ESP), vehicle attitude sensor, and inertial measurement unit (IMU)) to monitor wheel slip rate and vehicle pitch attitude in real time.

[0031] The processor, the lighting control unit (ECU), serves as the core computing hub of the system. It includes a microprocessor and drive circuitry. The microprocessor is configured to fuse the aforementioned multi-source data to calculate the road surface slippage index and calls upon an internally pre-built optical path reflection model library to perform geometric distortion correction and brightness / contrast enhancement processing on the original AR navigation image based on inverse optics. The microprocessor contains a preprocessing module, a road surface slippage calculation module, a geometric distortion correction unit, a brightness and contrast enhancement unit, and a projection position adjustment unit. The geometric distortion correction unit and the brightness and contrast enhancement unit incorporate correction algorithms to adjust the projection area, brightness, and contrast, respectively.

[0032] The processed control signal is finally transmitted to the execution layer, which consists of DLP (Digital Lighting Platform) or Micro-LED matrix light source and optical lens group. It can respond to ECU commands and accurately project the corrected navigation light carpet onto the dynamically adjusted road surface area in front of the vehicle, so as to achieve clear, distortion-free navigation guidance that meets anti-glare requirements in wet and slippery environments.

[0033] The data acquisition and preprocessing interface, acting as a logical input, is responsible for receiving raw signals from external sensor arrays in real time via the vehicle bus. These signals include road texture image data captured by the forward-facing camera, ambient humidity levels from the rain sensor, and wheel slip ratio and vehicle attitude parameters provided by the chassis system. After filtering and synchronization, this heterogeneous data is fed into the road surface slippage calculation module. This module incorporates a multi-source information fusion algorithm, which weights the visual road surface gloss characteristics with the dynamic friction coefficient characteristics to output a continuously changing value—the slippage index (WI)—used to quantify the degree to which the current road surface transitions from diffuse to specular reflection.

[0034] Example 2: An augmented reality (AR) navigation light carpet projection correction method based on road surface slippage detection includes: Step 1: Data Collection and Preprocessing The vehicle perception and data acquisition module receives raw signals from external sensor groups in real time via the vehicle bus, including road texture image data captured by the forward-facing camera, ambient humidity level feedback from the rain sensor, and wheel slip ratio and vehicle attitude parameters provided by the chassis system.

[0035] The preprocessing module in the ECU filters and synchronizes this multimodal heterogeneous data. The processed data is then sent to the road surface slippage calculation module.

[0036] Step 2, Road surface condition calculation The road surface gloss characteristics (visual) and friction coefficient characteristics (dynamic) are weighted and calculated to output a continuously changing value—the Wet Skid Index (WI)—which quantifies the degree to which the current road surface is transitioning from diffuse to specular reflection. The road surface wet skid degree calculation module uses a multi-source data weighted fusion algorithm to calculate the Wet Skid Index WI. The specific calculation logic includes three steps: data normalization, weighted fusion, and time-domain filtering.

[0037] S2.1 Data Normalization Because the data outputs from the camera, rain sensor, and ESP system have different dimensions, the preprocessing module in the system first performs dimensionless normalization on them, mapping them to the [0, 1] interval: Visual perception components acquired by the camera Based on the proportion of highlight areas in the camera image.

[0038]

[0039] in, This refers to the total area of ​​pixels within the projection region whose brightness exceeds a threshold (e.g., 230). The total pixel area of ​​the projection region. This is the visual gain coefficient.

[0040] Environmental sensing components acquired by rain gauges Rainfall intensity based on rain gauges.

[0041]

[0042] in, The current rainfall sensing level (0-10). This is the maximum range of the sensor.

[0043] Dynamic sensing components acquired by the ESP system Based on wheel longitudinal slip ratio.

[0044]

[0045] in, To drive the linear speed of the wheel, For reference speed of the vehicle body, To prevent the minimum value from being divided by zero.

[0046] S2.2 Multi-source weighted fusion computing The road surface slippage calculation module sets weighting coefficients based on the contribution of each sensor to the road surface's optical properties. Since the core of this invention is solving optical correction, the visual signal (directly reflecting reflectivity) has the highest weight. Instantaneous slippage index. The calculation formula is as follows:

[0047] in, , , These are the visual, environmental, and dynamic weight coefficients, respectively, and they satisfy... + + = 1. In this embodiment, the value set by the present invention is: =0.5, =0.3, =0.2.

[0048] S2.3 Time Domain Filtering To avoid frequent flickering of the projected image due to transient noise from the sensor (such as sudden changes in the slip rate caused by road bumps, or interference from oncoming vehicle headlights), the system introduces a first-order low-pass filtering algorithm to calculate the final output slip index. :

[0049] in, This represents the final slip index output at the current moment. This is the output value from the previous time step; The instantaneous value calculated at the current moment; This is the filtering smoothing factor, with a value range of (0, 1]. The smaller the value, the smoother the numerical change and the stronger the anti-interference ability.

[0050] Step 3, Projection Control The slipperiness index (WI), as a key decision variable, is simultaneously distributed to three parallel processing branches (geometric anti-distortion unit, brightness and contrast enhancement unit, and projection position adjustment unit) to drive differentiated correction strategies. Within the correction algorithm logic block, the geometric anti-distortion unit calculates inverse deformation parameters based on the index to offset the graphic distortion caused by water film refraction, while the brightness / contrast adjustment unit simultaneously optimizes the image's grayscale distribution and gain based on the index to ensure visibility under specular reflection conditions. Meanwhile, the independent projection position adjustment module dynamically calculates the optimal projection distance coordinates based on the slipperiness index and executes an anti-glare pull-back strategy. Finally, the corrected image data and position coordinate instructions output from these three parallel branches are aggregated at the logic end and transmitted to the DLP headlight module at the execution output end, driving it to project an AR navigation light carpet with a correct geometric shape, appropriate brightness, and precise position in physical space. In other embodiments, the geometric anti-distortion unit, brightness and contrast enhancement unit, and projection position adjustment unit can also be processed serially.

[0051] First, the geometric anti-distortion unit calls the pre-set optical path reflection model library based on WI, calculates the "inverse distortion matrix" according to the water film refractive index and reflection angle, and performs non-linear pre-deformation processing (such as longitudinal compression or lateral stretching) on ​​the original AR navigation image to counteract the optical elongation or distortion caused by the wet and slippery medium. Second, the brightness and contrast enhancement unit monitors when WI exceeds the preset threshold, automatically switches the image rendering mode from grayscale gradient to high-contrast monochrome outline mode, and dynamically increases the brightness gain of key pixels according to the ambient light to overcome the light intensity loss caused by specular reflection. Third, the projection position adjustment unit calculates the optimal projection distance based on WI, generates new region of interest (ROI) window coordinates, and executes a near-field pull-back strategy to avoid high-glare areas in the distance.

[0052] S3.1 Geometric Distortion Adjustment The primary function of the anti-distortion algorithm in the geometric anti-distortion unit is to eliminate the optical refraction shift and visual stretching effect caused by the water film on the road surface. Under dry road conditions (diffuse reflection), the image pixel P(x, y) follows a standard perspective projection transformation with respect to the road surface projection point. However, when a water film is present on the road surface, light refracts as it enters and reflects from the bottom of the water film, and specular reflection causes a longitudinal visual blur (smear effect) in the driver's view. To counteract this physical deformation, this unit establishes an inverse pre-distortion model based on the slip index WI. Assuming the pixel coordinates in the original image source are (u, v), and the corrected pre-distortion coordinates are (u', v'), the system performs the following nonlinear transformation:

[0053] Where u is the horizontal coordinate of the image (corresponding to the lane width direction), v is the vertical coordinate (corresponding to the driving distance direction); WI is the previously calculated slip index, with a value range of [0, 1]. This is the lateral trapezoidal correction factor. Since the Fresnel reflectivity of the water film surface varies with the incident angle, causing a decrease in image edge brightness, this term is used to slightly widen the edges to compensate for visual shrinkage. This is the longitudinal compression factor. Because slippery surfaces cause visual elongation of the image in the depth direction, it is necessary to... The image source is compressed vertically (pre-flattened) to counteract the physical stretching; The weighting function is related to the projection distance, typically The larger the value (the farther the projection distance), the more obvious the refraction distortion, hence the greater the weight.

[0054] The system generates a pre-distorted image that is "wider at the top and narrower at the bottom" and "compressed longitudinally" using the formula above. After being reflected by the wet road surface, the image is restored to its normal geometric shape in the driver's eyes.

[0055] S3.2 Brightness / Contrast Adjustment Under normal road conditions, AR navigation icons typically incorporate rich grayscale gradients (e.g., feathered arrow edges or a fading-in / fading-out effect on the light carpet) to provide good visual texture. However, when the road surface is completely covered by a film of water, creating a specular reflection, these low-brightness grayscale details (i.e., in the formula) become less effective. (Some of these) stray lights are easily submerged by ambient light or completely lost due to reflection from the water surface, making it impossible for the driver to see them clearly; at the same time, these "seemingly bright but not actually bright" stray lights can easily become glare sources.

[0056] In the brightness and contrast enhancement unit, the main function of the brightness / contrast adjustment algorithm is to overcome the light energy loss caused by specular reflection and enhance the image's recognizability. On slippery roads, most light is specularly reflected and moves away from the driver's line of sight (off-axis reflection), resulting in reduced effective brightness. A significant decrease. To maintain visibility, the system employs a method based on... The dynamic gain compensation algorithm. The grayscale value of the original image pixels is set to... (0~255), corrected output grayscale value The calculation formula is as follows:

[0057] Among them, dynamic compensation gain Defined as:

[0058] in, This is the ambient light sensitivity coefficient. The stronger the ambient light (such as during the day or on a rainy day), the greater the required contrast gain. The angle of incidence of the light ray; This is the road surface specular reflectivity factor. The denominator term... The reflection loss in the Fresnel equation, i.e., the degree of slippage, was simulated. The higher the angle of incidence or the smaller the incident angle, the greater the optical loss and the higher the required compensation gain. The larger it is; This is a truncation function to ensure that the output value does not exceed the maximum brightness limit of the DLP module.

[0059] In addition, when detected In cases of severe flooding, this unit will forcibly activate binarization thresholding, as shown in the following formula:

[0060] Where I is the brightness value of the pixel. This represents the pixel brightness before the judgment, which is the theoretical brightness value obtained after the previous step (dynamic gain compensation). It represents the brightness that the system wants to display, including the details of the original image; This represents the final output brightness command. This is the final value actually sent to the DLP headlight module for execution; This represents the brightness cutoff threshold in high contrast mode.

[0061] S3.3 Initial Projection Distance Calculation The system first determines the current vehicle speed. Determine the reference projection distance under dry conditions Subsequently, a slip correction factor was introduced. Perform weighted calculations.

[0062] Optimal shooting distance The calculation formula is as follows:

[0063] in, The reference distance is positively correlated with the current vehicle speed; The real-time road surface slippage index calculated by the aforementioned module has a value range of [0, 1], where 0 represents completely dry and 1 represents completely covered by a water film; The threshold value for triggering position adjustment (e.g., set to 0.3, this value can be customized according to actual conditions) is when... < At this time, the system maintains the reference distance projection and does not pull back; For a step activation function or a linear rectified function (ReLU), ensure that only when... A positive correction is generated when the threshold is exceeded; slippery surface correction factor. The value used to control the rate at which the projection distance decreases with increasing slipperiness is typically between 0.3 and 0.6.

[0064] It should be noted that the main flow of the AR navigation light carpet projection control method provided in this embodiment is a real-time cyclical monitoring and decision-making process. After the process starts, the system first executes the data acquisition step, reading the raw signals from the camera, rain sensor, and chassis dynamics system in real time through the hardware interface, and then using a multi-source information fusion algorithm to calculate the slip index (WI), which characterizes the optical reflectivity of the current road surface, in the subsequent calculation step. Next, the system enters the crucial threshold determination step, comparing the real-time calculated WI value with the system's preset slip threshold to identify whether the current road surface has specular reflection conditions. If the determination result is "no" (i.e., WI does not exceed the threshold), the system confirms that the road surface is dry, maintains the normal AR projection mode, and outputs the navigation image according to the standard optical path parameters; conversely, if the determination result is "yes" (i.e., WI exceeds the threshold), the system confirms that there is water accumulation or slippery risk on the road surface, and then triggers the branch logic, calling the slip correction subroutine (the specific execution logic of this subroutine is detailed in [link to relevant documentation]). Figure 5 The system performs targeted optical compensation processing on the image source. After the corresponding mode is completed, the current loop ends and the next frame of data is processed, thereby achieving dynamic adaptive response to changes in the driving environment.

[0065] See Figure 5 This diagram visually illustrates the comparison between the optical reflection paths and the final visual effects of existing technologies and the solutions of this invention in a slippery road environment. The diagram is divided into two parts: the right side shows the optical path failure mechanism without the application of this correction algorithm, and the left side shows the optical path optimization mechanism after applying the correction algorithm.

[0066] First, such as Figure 5The small figure (b) illustrates the effect of light carpet projection on wet roads in existing technologies: In current AR navigation projection, the system does not adjust for changes in the road surface medium, still projecting the light beam into the far field at a small incident angle (i.e., a small angle between the light and the road surface). When the road surface is covered with a wet, slippery water film, the water film acts as a specular medium. According to the Fresnel reflection principle, a small incident angle causes most of the light energy to undergo specular reflection. Since the incident angle equals the reflection angle, this high-energy, strongly specularly reflected beam will "bounce" out at a relatively flat angle, directly over the driver's head, causing the driver, who is in an upward view, to not receive a valid light signal; at the same time, only a very small amount of light undergoes diffuse reflection and enters the human eye, making the navigation icon extremely dim or even invisible to the driver. In addition, the strong reflected stray light projected into the distance can easily enter the oncoming lane area, causing severe glare interference to other vehicles.

[0067] On the contrary, such as Figure 5 The small figure (a) illustrates the method of this invention for projecting a light blanket onto a slippery road surface. When the system detects a slippery condition, the control unit actively intervenes and adjusts the projection strategy, performing a "near-field pullback" operation. At this time, the beam emitted by the DLP light source is redirected to the near end of the vehicle, significantly increasing the incident angle when the light contacts the water film (making the angle steeper). By changing the incident geometry, the reflected light path is deflected, causing the strong reflected beam that would originally cross overhead to be lowered and redirected, precisely covering the area where the driver's eye (Eye Box) is located. This change not only allows the driver to directly capture the high-intensity reflected light signal, achieving a clear visual effect, but also effectively changes the propagation path of stray light, significantly reducing invalid reflected light directed towards oncoming vehicles, thereby improving visibility while achieving an anti-glare safety effect.

[0068] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method for correcting the projection of an AR navigation light carpet based on road surface slippage detection, characterized in that, include: Step 1: Obtain multimodal information, including road condition information, environmental information, and vehicle information; Step two: Normalize the multimodal information obtained in step one, and calculate the slip index based on the multimodal information. ; Step 3: Adjust the light projection range, projection brightness, and contrast based on the slipperiness index, and control the headlight projection.

2. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 1, characterized in that: In step one, the road condition information includes visual perception components acquired by a camera, the environmental information includes environmental perception components acquired by a rain sensor, and the vehicle information includes dynamic perception components acquired by the ESP system.

3. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 2, characterized in that: In step two, based on the normalized visual perception components... Environmental perception components Dynamic sensing components Calculate the instantaneous slip index For instantaneous slip index The slip index is obtained after filtering. .

4. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 3, characterized in that: The instantaneous slip index ,in, , , These are the weighting coefficients for the visual perception component, the environmental perception component, and the dynamic perception component, respectively, and they satisfy... + + = 1.

5. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 1, characterized in that: The slipperiness index ,in, This represents the final slip index output at the current moment. This is the output value from the previous time step; The instantaneous value calculated at the current moment; This is the filtering smoothing factor, with a value range of (0, 1).

6. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 1, characterized in that: In step three, the coordinates of the original image to be projected are converted into coordinates of the deformed image projected onto the slippery ground based on the slipperiness index WI. , Where (u, v) are the pixel coordinates in the original image source, and (u', v') are the corrected pre-deformation coordinates, where u corresponds to the lane width direction and v corresponds to the driving distance direction; This is the horizontal trapezoidal correction factor, used to slightly widen the edges to compensate for visual shrinkage; The vertical compression factor is used to compress the image source vertically to counteract the physical stretching. This is a weighting function related to the projection distance.

7. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 1, characterized in that: In step three, the wet slip index WI is used to evaluate the grayscale values ​​of the original image pixels. Correction is performed to overcome the light energy loss caused by specular reflection, resulting in a corrected output grayscale value. Among them, dynamic compensation gain for ,in, This is the ambient light sensitivity coefficient; the stronger the ambient light, the greater the required contrast gain. The angle of incidence of the light ray; The road surface specular reflectivity factor; This is a truncation function to ensure that the output value does not exceed the maximum brightness limit of the DLP module.

8. The AR navigation light carpet projection correction method based on road surface slippage detection according to claim 1, characterized in that: In step three, the optimal projection distance is calculated. , ,in, This is the baseline projection distance under dry conditions, which is positively correlated with the current vehicle speed; The threshold for triggering position adjustment, when < At this time, the system maintains the reference distance projection and does not pull back; It can be a step activation function or a linear rectifier function; The value used to control the rate at which the projection distance decreases with increasing slipperiness is typically between 0.3 and 0.

6.

9. A control system, said control system being used to implement the AR navigation light carpet projection correction method based on road surface slippage detection as described in any one of claims 1-8, characterized in that, include: The vehicle perception and data acquisition module includes a forward-facing camera, a rain and light sensor, and a dynamic sensor group integrated into the chassis. The processor is connected to the vehicle perception and data acquisition module and calculates the image projection control signal based on the data acquired by the vehicle perception and data acquisition module. The execution layer is connected to the processor and controls the headlight projection according to the control signal.

10. The method for AR navigation light carpet projection correction based on road surface slippage detection according to claim 9, characterized in that: The processor includes a preprocessing module, a road surface slipperiness calculation module, a geometric distortion correction unit, a brightness and contrast enhancement unit, and a projection position adjustment unit. The preprocessing module is connected to the road surface slipperiness calculation module, and the geometric distortion correction unit, brightness and contrast enhancement unit, and projection position adjustment unit are all connected to the road surface slipperiness calculation module.

Images