Light carpet projection control method, device, computer equipment and readable storage medium

Abstract

The present application relates to a light carpet projection control method, device, computer equipment and readable storage medium. The method includes: when a vehicle projects a light carpet, obtaining a road image captured by a vehicle camera at a current time step; performing lane line detection and light carpet boundary detection on the road image, and determining the deviation information between the lane line and the light carpet boundary in the road image according to the detection result; based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information; adjusting the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information; controlling the vehicle to perform light carpet projection at the next time step according to the light carpet projection control information, so as to achieve accurate matching of the projected light carpet and the lane line under various road conditions, improve the driver's road perception ability, and ensure vehicle driving safety.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a light carpet projection control method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the development of computer technology and intelligent driving technology, vehicle lighting systems have gradually integrated active safety and assisted driving functions. Lane light blanket projection, as a technical means to enhance drivers' nighttime road perception, has gradually become a research hotspot.

[0003] In the related art, the control of lane light carpet projection is achieved based on the static calibration data or preset path of the vehicle's light carpet projection system. This method cannot effectively cope with the uncertainty and dynamic changes in actual roads, especially in complex scenarios such as slopes, bumpy roads and sharp turns. As a result, the projected light carpet deviates from the lane line and does not fit the lane line well, which reduces the driver's road perception ability and affects the driver's judgment and vehicle driving safety. Summary of the invention

[0004] Based on this, it is necessary to provide a light carpet projection control method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems, which can dynamically adjust the light carpet projection control information in real time so that the projected light carpet under various road conditions can be accurately matched with the lane line, thereby improving the driver's road perception ability and ensuring vehicle driving safety.

[0005] In a first aspect, the present application provides a light carpet projection control method, comprising:

[0006] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0007] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0008] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0009] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0010] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0011] In a second aspect, the present application also provides a light carpet projection control device, comprising:

[0012] An image acquisition module, used to obtain a road image acquired by a vehicle camera at a current time step when the vehicle projects a light blanket;

[0013] a deviation calculation module, configured to perform lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determine deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0014] a deviation mapping module, configured to map the deviation information from the image coordinate system to the light carpet projection coordinate system based on a perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, so as to obtain the mapped deviation information;

[0015] An adjustment module, used for adjusting the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information;

[0016] A control module is used to control the vehicle to perform light carpet projection at a next time step according to the light carpet projection control information, and use the next time step as an updated current time step.

[0017] In some embodiments, the light carpet projection control device further includes:

[0018] A posture compensation module, used to obtain vehicle posture data collected in real time by a posture sensor of the vehicle, wherein the vehicle posture data at least includes a pitch angle and a roll angle of the vehicle; and update a perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system according to the vehicle posture data;

[0019] The deviation mapping module is further used to map the deviation information from the image coordinate system to the light carpet projection coordinate system according to the perspective transformation matrix updated in real time, so as to obtain the mapped deviation information.

[0020] In some embodiments, the light carpet projection control device further includes:

[0021] A delay compensation module, used to obtain dynamic driving data of the vehicle, the dynamic driving data at least including vehicle driving speed and vehicle driving acceleration; predict the deviation information corresponding to the next time step of the current time step according to the dynamic driving data of the vehicle and the deviation information;

[0022] The deviation mapping module is further used to map the deviation information corresponding to the next time step from the image coordinate system to the light carpet projection coordinate system based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system to obtain the mapped deviation information.

[0023] In some embodiments, the delay compensation module is also used to obtain historical deviation information of the previous time step of the current time step; determine the previous deviation change based on the deviation information calculated at the current time step and the historical deviation information of the previous time step; and predict the deviation information corresponding to the next time step of the current time step based on the deviation information calculated at the current time step, the dynamic driving data of the vehicle and the previous deviation change.

[0024] In some embodiments, the deviation calculation module is also used to perform lane line detection and light carpet boundary detection on the road image to obtain the image coordinates of the lane line and the light carpet boundary in the road image; calculate the lateral position deviation between the lane line and the light carpet boundary based on the image coordinates of the lane line and the light carpet boundary in the road image; calculate the angular deviation between the lane line and the light carpet boundary based on the image coordinates of the lane line and the light carpet boundary in the road image.

[0025] In some embodiments, the deviation calculation module is also used to determine the image coordinates of the pixel points corresponding to the left lane line, the right lane line, the left light carpet boundary and the right light carpet boundary in the road image according to the image coordinates of the lane line and the light carpet boundary in the road image; calculate the lateral position deviation between the left lane line and the left light carpet boundary according to the difference between the image coordinates of the pixel points corresponding to the left lane line and the left light carpet boundary; calculate the lateral position deviation between the right lane line and the right light carpet boundary according to the difference between the image coordinates of the pixel points corresponding to the right lane line and the right light carpet boundary.

[0026] In some embodiments, the deviation calculation module is also used to calculate the angle between the line segment vector corresponding to the lane line and the line segment vector corresponding to the light carpet boundary, as the angular deviation between the lane line and the light carpet boundary, when it is determined according to their respective image coordinates in the road image that the lane line and the light carpet boundary are both straight lines; when it is determined according to their respective image coordinates in the road image that the lane line and the light carpet boundary are both curves, respectively segment the lane line and the light carpet boundary to obtain multiple groups of curve segments, perform straight line fitting on each group of curve segments to obtain multiple groups of fitted straight line segments, calculate the angle between each group of fitted straight line segments, and obtain the angular deviation between the lane line and the light carpet boundary.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0029] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0030] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0031] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0032] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0034] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0035] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0036] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0037] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0038] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0039] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0040] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0041] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0042] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0043] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0044] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0045] The above-mentioned light carpet projection control method, device, computer equipment, computer-readable storage medium and computer program product, when the vehicle projects a light carpet, obtains a road image captured by the vehicle camera at the current time step; performs lane line detection and light carpet boundary detection on the road image to obtain detection results, and determines the deviation information between the lane line and the light carpet boundary in the road image according to the detection results; maps the deviation information from the image coordinate system to the light carpet projection coordinate system based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system to obtain the mapped deviation information; adjusts the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information; and controls the vehicle to perform light carpet projection at the next time step according to the light carpet projection control information.

[0046] By real-time detection of the deviation information between the lane line and the light carpet boundary, combined with closed-loop feedback control and delay compensation, the light carpet projection control information corresponding to the next time step of the current time step can be dynamically adjusted in real time. This can ensure that when the light carpet is projected in the next time step, the projected light carpet and the lane line are accurately matched under various road conditions, thereby enhancing the driver's road perception ability at night and in low-visibility environments, and ensuring vehicle driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 is an application environment diagram of a light carpet projection control method in one embodiment;

[0049] Figure 2 is a flow chart of a light carpet projection control method in one embodiment;

[0050] Figure 3is a flow chart of a light carpet projection control method in another embodiment;

[0051] Figure 4 is a flow chart of a light carpet projection control method in yet another embodiment;

[0052] Figure 5 A schematic diagram of a flow chart of a light carpet projection control method in yet another embodiment;

[0053] Figure 6 A schematic diagram of a flow chart of a light carpet projection control method in another embodiment;

[0054] Figure 7 is a structural block diagram of a light carpet projection control device in one embodiment;

[0055] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] Lane light carpet is a vehicle lighting technology used to provide drivers with clear driving route guidance at night or in low-light environments to enhance driving safety. Lane light carpets are usually implemented through Digital Matrix LED headlight technology, which can project a clear and bright light strip on the lane to indicate the vehicle's route and help drivers better understand the driving direction and distance. In addition, lane light carpets can not only provide clear lighting on dark roads, but also illuminate the lane that the driver wants to change lanes in advance according to the signal of the turn signal when changing lanes, reducing blind spots and improving driving safety.

[0058] Lane lines are the boundary lines of lanes on both sides of the road where vehicles are traveling. In the related art, the lane light carpet projection system has obvious limitations under complex road conditions, and the projected light carpet cannot accurately fit the lane line in real time, especially on slopes, bumpy roads and curved environments. Specifically, on the one hand, the lane light carpet projection system in the related art cannot adapt to the changes in the pitch angle and roll angle of the vehicle on bumpy roads, resulting in the position of the light carpet offset. On the other hand, the related art fails to monitor the deviation between the light carpet boundary and the lane line in real time, and cannot adjust the projection based on the deviation feedback. On the other hand, the related art lacks precise closed-loop feedback control, and cannot dynamically adjust the light carpet projection control information based on the actual deviation, resulting in the deviation of the light carpet boundary and lane line in bumpy or sharp bend scenarios.

[0059] The light carpet projection control method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. The application environment includes a vehicle 100, and the light carpet projection control system on the vehicle 100 includes a visual perception system 101, a light carpet projection lamp 102, and a projection control system 103. In some embodiments, the visual perception system 101, the light carpet projection lamp 102, and the projection control system 103 can send or receive messages to each other.

[0060] In some embodiments, the visual perception system 101 is used to monitor and analyze the conditions of the road around the vehicle in real time and obtain visual information around the vehicle. In some embodiments, the visual perception system 101 may include a vehicle camera, such as a roof camera, which is usually installed on the top of a car or other vehicle to provide a view of the vehicle's surroundings. In some embodiments, the visual perception system 101 can capture images and / or video data of the road ahead through the vehicle camera, and use computer vision and deep learning technologies to recognize the collected images and / or video data.

[0061] In some embodiments, the projection control system 103 is used to receive and analyze the visual information of the visual perception system 101, and implement light carpet projection control in combination with the sensor data collected by the sensor system.

[0062] In some embodiments, the light carpet projector 102 is a lighting module installed at the front of the vehicle, independent of the low beam and high beam, and uses a high-definition matrix LED light source. The projection control system 103 can control the light carpet projector 102 to accurately project a light beam along the boundary line of the lane in which the vehicle is traveling.

[0063] In some embodiments, the visual perception system 101 is used to obtain the road image captured by the vehicle camera at the current time step when the vehicle projects a light carpet, perform lane line detection and light carpet boundary detection on the road image, and obtain the detection result. The projection control system 103 is used to determine the deviation information between the lane line and the light carpet boundary in the road image according to the detection result; based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, the deviation information is mapped from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information; according to the mapped deviation information, the light carpet projection control information corresponding to the next time step of the current time step is adjusted; according to the light carpet projection control information, the light carpet projection lamp 102 of the vehicle is controlled to perform light carpet projection at the next time step. In addition, as time passes, the next time step can be used as the updated current time step. When the vehicle projects a light carpet, the road image captured by the vehicle camera at the current time step continues to be acquired and subsequent steps are executed to realize real-time update and dynamic adjustment of the light carpet projection control information.

[0064] The light carpet projection control method provided in the embodiment of the present application can be executed by a computer device. The computer device can be an electronic device on the vehicle, such as a terminal. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc.

[0065] In an exemplary embodiment, Figure 2 As shown, a light carpet projection control method is provided, which is described by taking the method applied to a computer device on a vehicle as an example, and includes the following steps 202 to 210. Among them:

[0066] Step 202 : When the vehicle projects a light blanket, obtain a road image captured by the vehicle camera at the current time step.

[0067] Among them, the vehicle camera can be an electronic rearview mirror, a front-view camera, etc. of the vehicle. In some embodiments, the camera of the vehicle collects the road image in front of the road where the vehicle is located in real time. In the case of the vehicle projecting a light carpet, the computer device can obtain the road image collected by the vehicle camera at the current time step. ‌Timestep‌ has different definitions and applications in different fields. In each time step, the state of the system will be updated and evolved according to physical laws and calculation methods. In the embodiment of the present application, the light carpet projection control information will be adjusted once at each time step. It can also be understood that the time interval for each adjustment of the light carpet projection control information is a time step. Therefore, in the case of the vehicle projecting a light carpet, the computer device must obtain the road image collected by the vehicle camera at the current time step at each time step. For example, a time step can be spaced at an interval of 100ms, and the computer device obtains the road image collected by the vehicle camera at an interval of 100ms. It can be understood that with the migration of time, the time step is constantly updated. For example, the next time step t+1 of the current time step t, with the migration of time, the current time step t will become the latest previous time step t-1, and the next time step t+1 will become the latest current time step t.

[0068] In some embodiments, the computer device can obtain the original image captured by the vehicle camera, perform image preprocessing on the original image, and obtain the road image. In some embodiments, the image preprocessing includes denoising, white balance, etc. The image clarity can be enhanced through image preprocessing to provide high-quality image data for lane line and light blanket boundary detection. In some embodiments, the original image can be an image captured in real time by the vehicle camera.

[0069] Step 204 , lane line detection and light carpet boundary detection are performed on the road image to obtain detection results, and deviation information between the lane line and the light carpet boundary in the road image is determined according to the detection results.

[0070] Among them, lane line detection is the process of detecting the position of lane lines in the road image, and light carpet boundary detection is the process of detecting the position of light carpet boundaries in the road image. The detection result includes the position information of lane lines in the road image, and the position information of lane lines can be represented by the image coordinates of several pixel points in the area where the lane lines are located. For example, the pixel point in the upper left corner of the road image is used as the origin in the image coordinate system, and the image coordinates of each pixel point in the road image are determined according to the pixel distance to the origin. The detection result includes the position information of light carpet boundaries in the road image, and the position information of light carpet boundaries can be represented by the image coordinates of several pixel points in the area where the light carpet boundaries are located.

[0071] In some embodiments, the computer device may call a lane line detection model to perform lane line detection on a road image to obtain position information of the lane lines in the road image.

[0072] In some embodiments, the computer device may call a light carpet boundary detection model to perform light carpet boundary detection on the road image to obtain position information of the light carpet boundary in the road image.

[0073] In some embodiments, the computer device may call a multi-task detection model to perform lane line detection and light carpet boundary detection on the road image to obtain a detection result. The multi-task detection model may be a computer vision model based on deep learning, and the multi-task detection model has the ability to perform lane line detection and light carpet boundary detection simultaneously after model training.

[0074] Since the lane lines of the lane where the vehicle is located are located on both sides of the lane, the light carpet boundaries projected along the lane lines are also located on both sides of the lane. In order to calculate the deviation information, in some embodiments, the computer device can perform lane line detection and light carpet boundary detection on the road image. In addition to obtaining the position information of the lane lines and light carpet boundaries in the road image, it is also necessary to identify the correspondence between the lane lines and the light carpet boundaries, that is, identify the left lane line R1 and the left light carpet boundary L1, and identify the right lane line R2 and the right light carpet boundary L2, and then calculate the deviation information between the left lane line R1 and the left light carpet boundary L1, and calculate the deviation information between the right lane line R2 and the right light carpet boundary L2.

[0075] The computer device can calculate the deviation information between the lane line in the road image and the light carpet boundary according to the position information of the lane line in the road image and the position information of the light carpet boundary. The deviation information is the deviation information in the image coordinate system.

[0076] In some embodiments, the deviation information includes lateral position deviation and angular deviation.

[0077] Step 206 : Based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, the deviation information is mapped from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information.

[0078] Deviation information is deviation information in the image coordinate system, while the light carpet projection control information is determined in the light carpet projection coordinate system. The perspective transformation matrix reflects the geometric projection model relationship between the image coordinate system and the light carpet projection coordinate system, that is, it reflects the relative position and rotation angle between the vehicle camera and the light carpet projection system. Usually, the perspective transformation matrix is ​​obtained by statically calibrating the vehicle camera and the light carpet projection system, and during calibration, the vehicle is located on the horizontal ground. The computer device can map the deviation information obtained in the image coordinate system from the image coordinate system to the light carpet projection coordinate system through the perspective transformation matrix to obtain the deviation information in the light carpet projection coordinate system, that is, the mapped deviation information.

[0079] Step 208: adjusting the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information.

[0080] Among them, the light carpet projection control information includes at least one of the projection direction, projection position and brightness of the light carpet. Due to the time delay between image detection and light carpet projection adjustment, the real-time detection result of the deviation may have changed at the next light carpet projection. To this end, the computer device adjusts the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information to ensure the precise fit between the light carpet boundary and the lane line. In some embodiments, the computer device may be based on the light carpet projection control information corresponding to the current time step, and make adjustments according to the mapped deviation information to obtain the light carpet projection control information corresponding to the next time step.

[0081] Step 210: Control the vehicle to perform light carpet projection in the next time step according to the light carpet projection control information.

[0082] Specifically, the computer device controls the vehicle to perform light carpet projection at the next time step according to the light carpet projection control information corresponding to the next time step.

[0083] After step 210 , the computer device may use the next time step as the updated current time step and return to step 202 , where the step of acquiring the road image captured by the vehicle camera at the current time step continues when the vehicle projects the light carpet.

[0084] The above-mentioned light carpet projection control method can dynamically adjust the light carpet projection control information corresponding to the next time step of the current time step in real time by detecting the deviation information between the lane line and the light carpet boundary in real time, combined with closed-loop feedback control and delay compensation. It can ensure that when the light carpet is projected in the next time step, the projected light carpet and the lane line are accurately matched under various road conditions, thereby enhancing the driver's road perception ability at night and in low visibility environments, and ensuring vehicle driving safety.

[0085] Figure 3 This is a flow chart of a light carpet projection control method provided by other embodiments of the present application. Figure 3 , the method further comprises the following steps:

[0086] Step 302, obtaining vehicle posture data collected in real time by a posture sensor of the vehicle, the vehicle posture data at least including a pitch angle and a roll angle of the vehicle;

[0087] Among them, the pitch angle of the vehicle is the angle between the front and rear direction of the vehicle and the ground plane. Under normal circumstances, the pitch angle of the vehicle should be 0 degrees, that is, the vehicle is running smoothly on a flat surface. The roll angle of the vehicle is used to describe the degree of inclination of the vehicle body when the vehicle makes a sharp turn. The size of the roll angle is usually affected by multiple factors, including the center of gravity position of the vehicle, the specifications of the wheels, and the characteristics of the suspension system. A lower center of gravity position helps to improve the stability of the vehicle and thus reduce the roll angle.

[0088] Specifically, the computer device can obtain the vehicle posture data of the vehicle in real time through the vehicle body posture sensor, and the vehicle posture data at least includes the pitch angle and roll angle of the vehicle.

[0089] Step 304, updating the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system according to the vehicle posture data;

[0090] The perspective transformation matrix is ​​usually obtained by calibrating the vehicle camera and the light carpet projection system when the vehicle is in a static and good state. During the calibration, the vehicle is usually located on a horizontal ground. However, when the posture of the vehicle changes, for example, in a ramp and turning environment, the posture of the vehicle will change, and the perspective transformation matrix obtained by calibration will no longer be applicable. In order to ensure that the projected light carpet remains accurately aligned with the lane line when the vehicle posture changes, the computer device can dynamically compensate the perspective transformation matrix between the vehicle camera and the light carpet projection system based on the real-time posture data of the vehicle. That is, the computer device can update the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system based on the vehicle posture data.

[0091] Step 206, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information, includes: mapping the deviation information from the image coordinate system to the light carpet projection coordinate system according to the real-time updated perspective transformation matrix to obtain the mapped deviation information.

[0092] In this embodiment, the perspective transformation matrix between the vehicle camera and the light carpet projection system is dynamically compensated according to the vehicle posture, which can cope with interference such as vehicle posture changes and bumps, achieve dynamic and stable light carpet projection, and enhance the driver's road perception ability.

[0093] Figure 4 This is a flow chart of a light carpet projection control method provided by some other embodiments of the present application. Figure 4 , the method further comprises the following steps:

[0094] Step 402, obtaining dynamic driving data of the vehicle, the dynamic driving data at least including the vehicle driving speed and the vehicle driving acceleration;

[0095] Step 404, predicting the deviation information corresponding to the next time step of the current time step based on the dynamic driving data and the deviation information of the vehicle;

[0096] In view of the system delay between image acquisition, image detection and light carpet projection, in order to compensate for this system delay, the computer device can predict the deviation information corresponding to the next time step of the current time step based on the dynamic driving data and deviation information of the vehicle. In some embodiments, the computer device can use a Kalman filter method or a linear prediction method to predict the deviation information corresponding to the next time step based on the dynamic driving data of the vehicle and the deviation information corresponding to the current time step. In this way, the future deviation change is predicted at each time step to compensate for the lag caused by the delay, ensuring that the adjustment of the light carpet projection in the closed-loop control can "foresee" the posture change of the vehicle.

[0097] Step 206, based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, the deviation information is mapped from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information, including: based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, the deviation information corresponding to the next time step is mapped from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information.

[0098] In this way, the computer device calculates and predicts the deviation information corresponding to the next time step based on the deviation information corresponding to the current time step at each time step, so as to automatically adjust the light carpet projection control information according to the deviation information corresponding to the next time step, and continuously dynamically adjusts, feedbacks, and adjusts... until the projected light carpet is completely aligned with the lane line. Under this closed-loop feedback mechanism, it can quickly adapt to changes in real-time road conditions, thereby adjusting the light carpet projection control information in advance, and the light carpet projection can remain accurate regardless of bumps, slopes, or curves.

[0099] In an exemplary embodiment, based on the dynamic driving data and deviation information of the vehicle, predicting the deviation information corresponding to the next time step of the current time step includes: obtaining the historical deviation information of the previous time step of the current time step; determining the previous deviation change amount based on the deviation information calculated at the current time step and the historical deviation information of the previous time step; predicting the deviation information corresponding to the next time step of the current time step based on the deviation information calculated at the current time step, the dynamic driving data of the vehicle and the previous deviation change amount. For example, the computer device can predict the current deviation change amount based on the dynamic driving data of the vehicle and the previous deviation change amount, and predict the deviation information corresponding to the next time step of the current time step based on the deviation information calculated at the current time step and the predicted current deviation change amount.

[0100] In this embodiment, based on the current state and dynamic driving data of the vehicle, future deviation changes are predicted in advance, and real-time adjustments can be made under high-speed conditions and complex road conditions to prevent error accumulation due to system delays, thereby ensuring a high light carpet projection accuracy in a delayed environment.

[0101] In an exemplary embodiment, lane line detection and light carpet boundary detection are performed on a road image to obtain detection results, and deviation information between the lane line and the light carpet boundary in the road image is determined based on the detection results, including: performing lane line detection and light carpet boundary detection on the road image to obtain the image coordinates of the lane line and the light carpet boundary in the road image; calculating the lateral position deviation between the lane line and the light carpet boundary based on the image coordinates of the lane line and the light carpet boundary in the road image; calculating the angular deviation between the lane line and the light carpet boundary based on the image coordinates of the lane line and the light carpet boundary in the road image.

[0102] In this embodiment, the deviation information between the lane line and the light carpet boundary in the road image includes the lateral position deviation and the angular deviation between the lane line and the light carpet boundary. The lateral position deviation and the angular deviation between the lane line and the light carpet boundary are calculated according to their respective image coordinates in the road image. This deviation information is used as the basis for light carpet projection control, and the projection control information of the light carpet projection lamp is adjusted in real time to make the light carpet boundary dynamically fit the lane line.

[0103] In an exemplary embodiment, the lateral position deviation between the lane line and the light carpet boundary is calculated based on their respective image coordinates in the road image, including: determining the image coordinates of the pixel points corresponding to the left lane line, the right lane line, the left light carpet boundary and the right light carpet boundary in the road image based on their respective image coordinates; calculating the lateral position deviation between the left lane line and the left light carpet boundary based on the difference between the image coordinates of the pixel points corresponding to the left lane line and the left light carpet boundary; calculating the lateral position deviation between the right lane line and the right light carpet boundary based on the difference between the image coordinates of the pixel points corresponding to the right lane line and the right light carpet boundary.

[0104] In this embodiment, the lateral position deviation between the lane line and the light carpet boundary in the road image includes the difference between the image coordinates of the pixel points corresponding to the left lane line and the left light carpet boundary, and also includes the lateral position deviation between the right lane line and the right light carpet boundary.

[0105] In some embodiments, the computer device can obtain the lateral position deviation based on the distance between the image coordinates of the left lane line and the corresponding pixel points on the left light carpet boundary. The lateral direction refers to the lateral direction of the road. The computer device can also obtain the lateral position deviation based on the distance between the image coordinates of the right lane line and the corresponding pixel points on the right light carpet boundary. The lateral position deviation is the lateral distance of a series of pixel points in the image coordinate system.

[0106] In some embodiments, the computer device may also select a number of key pixel points to represent the lateral position deviation according to the distance of the image coordinates between the key pixel points. The key pixel point may be a pixel point selected from the lane line and located in the middle of the lane line. Correspondingly, the key pixel point on the light carpet boundary is a pixel point selected from the light carpet boundary and located in the middle of the light carpet boundary.

[0107] In an exemplary embodiment, calculating the angle deviation between the lane line and the light carpet boundary according to the image coordinates of the lane line and the light carpet boundary in the road image includes:

[0108] When the lane line and the light carpet boundary are determined to be straight lines according to their respective image coordinates in the road image, the angle between the line segment vector corresponding to the lane line and the line segment vector corresponding to the light carpet boundary is calculated as the angle deviation between the lane line and the light carpet boundary. That is, the direction vectors of the lane line and the light carpet boundary are used to calculate the angle deviation of the two lines through the vector angle formula.

[0109] In the case where the lane line and the light carpet boundary are determined to be curves according to their respective image coordinates in the road image, the lane line and the light carpet boundary are segmented to obtain multiple groups of curve segments, and each group of curve segments is fitted with a straight line to obtain multiple groups of fitted straight line segments, and the angle between each group of fitted straight line segments is calculated to obtain the angle deviation between the lane line and the light carpet boundary. That is, the lane line and the light carpet boundary are segmented into multiple curve segments, and the fitted straight line segment of each curve segment is calculated according to the image coordinates of multiple pixel points representing each curve segment, and then the angle between the fitted straight line segments is calculated. In this way, the angle between the multiple groups of fitted straight line segments can be obtained as the angle deviation between the lane line and the light carpet boundary.

[0110] Figure 5 This is a flow chart of a light carpet projection control method provided by some other embodiments of the present application. Figure 5 , the method further comprises the following steps:

[0111] Step 502, in the case where the vehicle projects a light blanket, obtaining a road image captured by the vehicle camera at the current time step;

[0112] Step 504, performing lane line detection and light carpet boundary detection on the road image to obtain detection results, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection results;

[0113] Step 506, obtaining dynamic driving data of the vehicle, the dynamic driving data at least including the vehicle driving speed and the vehicle driving acceleration, and predicting the deviation information corresponding to the next time step of the current time step according to the dynamic driving data of the vehicle and the deviation information;

[0114] Step 508, obtaining vehicle posture data collected in real time by a posture sensor of the vehicle, the vehicle posture data at least including a pitch angle and a roll angle of the vehicle, and updating a perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system according to the vehicle posture data;

[0115] Step 510, mapping the deviation information corresponding to the next time step from the image coordinate system to the light carpet projection coordinate system according to the perspective transformation matrix updated in real time, to obtain the mapped deviation information;

[0116] Step 512, adjusting the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information;

[0117] Step 514, controlling the vehicle to perform light carpet projection in the next time step according to the light carpet projection control information.

[0118] In this embodiment, by real-time monitoring of the deviation information between the lane line and the light carpet boundary, a closed-loop feedback system is used to ensure the precise fit of the light carpet projection under various road conditions. The vehicle posture data is used to dynamically compensate for the deviation changes, and it is able to cope with vehicle posture changes and disturbances such as bumps, to achieve dynamic and stable light carpet projection. Regardless of complex road conditions such as straight roads, bumpy roads or curves, a stable light carpet projection effect can be provided, thereby enhancing the driver's road perception ability at night and in low-visibility environments.

[0119] In one embodiment, the light carpet projection control system implemented by the light carpet projection control method includes:

[0120] 1. An image acquisition module, such as a vehicle-mounted camera, is used to capture images of the road in front of the vehicle in real time.

[0121] 2. Attitude sensor module, such as IMU (inertial measurement unit), is used to obtain the vehicle's pitch angle, roll angle and other attitude information.

[0122] 3. Data processing module: The data processing module can integrate a deep learning-based detection model, a deviation calculation unit, a prediction unit and a closed-loop control unit to obtain light carpet projection control information.

[0123] 4. A light carpet projection module, such as a DLP projection lamp, is used to project a lane light carpet according to the light carpet projection control information.

[0124] Figure 6 A flowchart of a light carpet projection control method in one embodiment includes the following steps:

[0125] Step 602: Acquire a road image captured by a vehicle-mounted camera in real time at a fixed frame rate.

[0126] Step 604: perform image preprocessing on each frame of road image to ensure the stability and accuracy of the detection result.

[0127] Step 606: Use a deep learning-based detection model to detect lane lines and light carpet boundaries in real time on the road image, and generate position information for each lane line and light carpet boundary.

[0128] Step 608 , performing real-time deviation calculation on the detected lane line and light carpet boundary, including lateral position deviation and angle deviation.

[0129] Step 610: Acquire the pitch angle and roll angle of the vehicle collected by the attitude sensor, and update the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system according to the pitch angle and roll angle of the vehicle.

[0130] Step 612, obtaining dynamic driving data of the vehicle, the dynamic driving data including at least the vehicle driving speed and the vehicle driving acceleration; predicting the deviation information corresponding to the next time step of the current time step based on the dynamic driving data and the deviation information of the vehicle.

[0131] Step 614: adjust the light carpet projection control information in real time according to the deviation information corresponding to the next time step.

[0132] Step 616: The deviation information corresponding to the next time step continues to be used as a feedback signal to implement closed-loop dynamic adjustment control.

[0133] The light carpet projection control method provided in the embodiment of the present application ensures the precise fit of the light carpet with the lane line under various road conditions by real-time detection of the position deviation between the lane line and the light carpet boundary, combined with closed-loop feedback control and dynamic vehicle posture compensation, thereby enhancing the driver's road perception ability at night and in low-visibility environments.

[0134] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0135] Based on the same inventive concept, the embodiment of the present application also provides a light carpet projection control device for implementing the light carpet projection control method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more light carpet projection control device embodiments provided below can refer to the limitations of the light carpet projection control method above, and will not be repeated here.

[0136] In an exemplary embodiment, Figure 7 As shown, a light carpet projection control device 700 is provided, comprising: an image acquisition module 702, a deviation calculation module 704, a deviation mapping module 706, an adjustment module 708 and a control module 710, wherein:

[0137] An image acquisition module 702 is used to acquire a road image acquired by a vehicle camera at a current time step when the vehicle projects a light blanket;

[0138] The deviation calculation module 704 is used to perform lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determine the deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0139] A deviation mapping module 706 is used to map the deviation information from the image coordinate system to the light carpet projection coordinate system based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system to obtain the mapped deviation information;

[0140] An adjustment module 708, used to adjust the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information;

[0141] The control module 710 is used to control the vehicle to perform light carpet projection at a next time step according to the light carpet projection control information, and use the next time step as an updated current time step.

[0142] In some embodiments, the light carpet projection control device 700 further includes:

[0143] The posture compensation module is used to obtain the vehicle posture data collected by the vehicle posture sensor in real time, and the vehicle posture data at least includes the pitch angle and roll angle of the vehicle; and update the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system according to the vehicle posture data;

[0144] The deviation mapping module 706 is further used to map the deviation information from the image coordinate system to the light carpet projection coordinate system according to the perspective transformation matrix updated in real time, so as to obtain the mapped deviation information.

[0145] In some embodiments, the light carpet projection control device 700 further includes:

[0146] The delay compensation module is used to obtain dynamic driving data of the vehicle, the dynamic driving data at least including the vehicle driving speed and the vehicle driving acceleration; according to the dynamic driving data of the vehicle and the deviation information, predict the deviation information corresponding to the next time step of the current time step;

[0147] The deviation mapping module 706 is further used to map the deviation information corresponding to the next time step from the image coordinate system to the light carpet projection coordinate system based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system to obtain the mapped deviation information.

[0148] In some embodiments, the delay compensation module is also used to obtain historical deviation information at the previous time step of the current time step; determine the previous deviation change based on the deviation information calculated at the current time step and the historical deviation information of the previous time step; and predict the deviation information corresponding to the next time step of the current time step based on the deviation information calculated at the current time step, the dynamic driving data of the vehicle and the previous deviation change.

[0149] In some embodiments, the deviation calculation module 704 is also used to perform lane line detection and light carpet boundary detection on the road image to obtain the image coordinates of the lane line and the light carpet boundary in the road image; calculate the lateral position deviation between the lane line and the light carpet boundary based on the image coordinates of the lane line and the light carpet boundary in the road image; calculate the angular deviation between the lane line and the light carpet boundary based on the image coordinates of the lane line and the light carpet boundary in the road image.

[0150] In some embodiments, the deviation calculation module 704 is also used to determine the image coordinates of the pixel points corresponding to the left lane line, the right lane line, the left light carpet boundary and the right light carpet boundary in the road image according to the image coordinates of the lane line and the light carpet boundary in the road image; calculate the lateral position deviation between the left lane line and the left light carpet boundary according to the difference between the image coordinates of the pixel points corresponding to the left lane line and the left light carpet boundary; calculate the lateral position deviation between the right lane line and the right light carpet boundary according to the difference between the image coordinates of the pixel points corresponding to the right lane line and the right light carpet boundary.

[0151] In some embodiments, the deviation calculation module 704 is also used to calculate the angle between the line segment vector corresponding to the lane line and the line segment vector corresponding to the light carpet boundary, as the angular deviation between the lane line and the light carpet boundary, when it is determined that the lane line and the light carpet boundary are both straight lines according to their respective image coordinates in the road image; when it is determined that the lane line and the light carpet boundary are both curves according to their respective image coordinates in the road image, respectively segment the lane line and the light carpet boundary to obtain multiple groups of curve segments, perform straight line fitting on each group of curve segments to obtain multiple groups of fitted straight line segments, calculate the angle between each group of fitted straight line segments, and obtain the angular deviation between the lane line and the light carpet boundary.

[0152] The above-mentioned light carpet projection control device 700, when the vehicle projects a light carpet, obtains a road image captured by the vehicle camera at the current time step; performs lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determines the deviation information between the lane line and the light carpet boundary in the road image according to the detection result; maps the deviation information from the image coordinate system to the light carpet projection coordinate system based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system to obtain the mapped deviation information; adjusts the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information; and controls the vehicle to perform light carpet projection at the next time step according to the light carpet projection control information. By real-time detection of the deviation information between the lane line and the light carpet boundary, combined with closed-loop feedback control and delay compensation, the light carpet projection control information corresponding to the next time step of the current time step can be dynamically adjusted in real time, so as to ensure that when the light carpet is projected at the next time step, the projected light carpet and the lane line are accurately fitted under various road conditions, thereby enhancing the driver's road perception ability at night and in low-visibility environments, and ensuring vehicle driving safety.

[0153] Each module in the light carpet projection control device 700 can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a light carpet projection control method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0155] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0157] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0158] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0159] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0160] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0161] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0162] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0163] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0164] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0165] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0166] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0167] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0168] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0169] In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step;

[0170] Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result;

[0171] Based on a perspective transformation matrix between an image coordinate system and a light carpet projection coordinate system, mapping the deviation information from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information;

[0172] According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step;

[0173] The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0175] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0176] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0177] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A light carpet projection control method, characterized in that: The method comprises: In the case where the vehicle projects a light blanket, obtain the road image captured by the vehicle camera at the current time step; Performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result; Acquire dynamic driving data of the vehicle, the dynamic driving data at least including vehicle driving speed and vehicle driving acceleration, and predict deviation information corresponding to a next time step of the current time step based on the dynamic driving data of the vehicle and the deviation information; Based on the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, mapping the deviation information corresponding to the next time step from the image coordinate system to the light carpet projection coordinate system to obtain mapped deviation information; According to the mapped deviation information, adjusting the light carpet projection control information corresponding to the next time step of the current time step; The vehicle is controlled to perform light carpet projection at a next time step according to the light carpet projection control information.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring vehicle posture data collected in real time by a posture sensor of the vehicle, the vehicle posture data at least including a pitch angle and a roll angle of the vehicle; updating the perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system according to the vehicle posture data; Mapping the deviation information corresponding to the next time step from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information includes: According to the perspective transformation matrix updated in real time, the deviation information corresponding to the next time step is mapped from the image coordinate system to the light carpet projection coordinate system to obtain the mapped deviation information.

3. The method according to claim 1, characterized in that The step of predicting the deviation information corresponding to the next time step of the current time step according to the dynamic driving data of the vehicle and the deviation information includes: Obtaining historical deviation information at a time step previous to the current time step; Determine the last deviation change amount according to the deviation information calculated at the current time step and the historical deviation information at the last time step; The deviation information corresponding to the next time step of the current time step is predicted based on the deviation information calculated at the current time step, the dynamic driving data of the vehicle and the previous deviation change.

4. The method according to any one of claims 1 to 3, characterized in that The performing lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determining deviation information between the lane line and the light carpet boundary in the road image according to the detection result, includes: Performing lane line detection and light carpet boundary detection on the road image to obtain image coordinates of the lane line and the light carpet boundary in the road image; Calculating a lateral position deviation between the lane line and the light carpet boundary according to the image coordinates of the lane line and the light carpet boundary in the road image; The angle deviation between the lane line and the light carpet boundary is calculated according to the image coordinates of the lane line and the light carpet boundary in the road image.

5. The method according to claim 4, characterized in that The calculating the lateral position deviation between the lane line and the light carpet boundary according to the image coordinates of the lane line and the light carpet boundary in the road image includes: Determine the image coordinates of the pixel points corresponding to the left lane line, the right lane line, the left light carpet boundary and the right light carpet boundary in the road image, respectively, according to the image coordinates of the lane line and the light carpet boundary in the road image; Calculating a lateral position deviation between the left lane line and the left light carpet boundary according to a difference between image coordinates of pixel points corresponding to the left lane line and the left light carpet boundary, respectively; The lateral position deviation between the right lane line and the right light carpet boundary is calculated according to the difference between the image coordinates of the pixel points corresponding to the right lane line and the right light carpet boundary respectively.

6. The method according to claim 4, characterized in that The calculating the angle deviation between the lane line and the light carpet boundary according to the image coordinates of the lane line and the light carpet boundary in the road image includes: When it is determined according to the image coordinates of the lane line and the light carpet boundary in the road image that the lane line and the light carpet boundary are both straight lines, calculating the angle between the line segment vector corresponding to the lane line and the line segment vector corresponding to the light carpet boundary as the angle deviation between the lane line and the light carpet boundary; When it is determined that both the lane line and the light carpet boundary are curves according to their respective image coordinates in the road image, the lane line and the light carpet boundary are respectively segmented to obtain multiple groups of curve segments, and straight line fitting is performed on each group of curve segments to obtain multiple groups of fitted straight line segments. The angle between each group of fitted straight line segments is calculated to obtain the angular deviation between the lane line and the light carpet boundary.

7. A light carpet projection control device, characterized in that: The device comprises: An image acquisition module, used to obtain a road image acquired by a vehicle camera at a current time step when the vehicle projects a light blanket; a deviation calculation module, configured to perform lane line detection and light carpet boundary detection on the road image to obtain a detection result, and determine deviation information between the lane line and the light carpet boundary in the road image according to the detection result; A delay compensation module, used to obtain dynamic driving data of the vehicle, the dynamic driving data at least including vehicle driving speed and vehicle driving acceleration, and predict the deviation information corresponding to the next time step of the current time step according to the dynamic driving data of the vehicle and the deviation information; a deviation mapping module, configured to map the deviation information corresponding to the next time step from the image coordinate system to the light carpet projection coordinate system based on a perspective transformation matrix between the image coordinate system and the light carpet projection coordinate system, so as to obtain the mapped deviation information; An adjustment module, used for adjusting the light carpet projection control information corresponding to the next time step of the current time step according to the mapped deviation information; A control module is used to control the vehicle to perform light carpet projection in a next time step according to the light carpet projection control information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images