A method and system for controlling LED lamps based on artificial intelligence

Abstract

The present invention relates to the technical field of vehicle lamp control, and provides an artificial intelligence-based LED lamp control method and system, the method comprising: generating the turning sight point range that each vehicle driver is accustomed to through historical data, and setting a steering prediction observation area according to real-time eye data, when the trend direction of driving steering is consistent with the driver's sight point, setting the LED lamp offset angle according to the predicted observation area, and providing lighting assistance for the driver to observe the road conditions when turning when the road lighting is poor, thereby improving the steering safety of the driver while driving and optimizing the vehicle experience.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle lamp control, and in particular to an artificial intelligence-based LED lamp control method and system. Background Art

[0002] In the prior art, the vehicle lights shine directly in front of the vehicle during driving, and only the turn signal is used as a signal indicator when turning; when the road lighting is poor, the driver's observation of the road conditions in the turning direction is limited, affecting driving safety. Summary of the invention

[0003] The present invention provides an artificial intelligence-based LED lamp control method, which is used to solve the problem in the prior art that observation of road conditions in the direction of vehicle turning is limited by ambient lighting, thus affecting driving safety.

[0004] A first aspect of the present invention provides an artificial intelligence-based LED lamp control method, comprising:

[0005] Obtain historical eyeball data and historical driving data, divide the data based on driver identity, and establish the turning sight point range of each driver;

[0006] Monitor the eye data of the person, obtain the current driver's identity and real-time sight point, combine the real-time sight point with the driving sight point range corresponding to the current driver's identity, and obtain the driver's predicted observation area;

[0007] Monitor the current driving data and obtain the driving trend direction; if the real-time sight point is consistent with the driving trend direction, calculate the LED lamp offset angle based on the driver's predicted observation area and the driving trend direction, and correct the vehicle LED lighting based on the offset angle.

[0008] Optionally, if the real-time sight point is consistent with the driving trend direction, the method further includes:

[0009] The eyeball coordinates are obtained according to the eyeball data and substituted into the blind spot monitoring model. If the blind spot value is less than the preset threshold, it is determined that the current driver has a blind spot observation requirement, and the LED lamp is controlled to deflect based on the preset blind spot angle. The blind spot monitoring model is specifically:

[0010]

[0011] Among them, S is the blind spot value, h1 is the eyeball height, h2 is the sight point height, d is the sight point offset distance, l is the horizontal distance between the sight point and the eyeball, and L is the horizontal distance between the sight point and the eyeball. It is the functional relationship between the sight point offset value and the blind spot length.

[0012] Optionally, also include:

[0013] After receiving the vehicle direction return signal, a return command is sent to the LED lamp.

[0014] The second aspect of the present application provides an artificial intelligence-based LED lamp control system, comprising:

[0015] The driving habit generation module is used to obtain historical eyeball data and historical driving data, and divide the data based on the driver's identity to establish the turning sight point range of each driver;

[0016] The eyeball data processing module is used to monitor the eyeball data of the person, obtain the current driver's identity and real-time sight point, combine the real-time sight point with the driving sight point range corresponding to the current driver's identity, and obtain the driver's predicted observation area;

[0017] The lighting control module is used to monitor the current driving data and obtain the driving trend direction; if the real-time sight point is consistent with the driving trend direction, the LED lamp offset angle is calculated according to the driver's predicted observation area and the driving trend direction, and the vehicle LED lighting is corrected based on the offset angle.

[0018] Optionally, in the lamp control module, if the real-time sight point is consistent with the driving trend direction, it also includes:

[0019] The eyeball coordinates are obtained according to the eyeball data and substituted into the blind spot monitoring model. If the blind spot value is less than the preset threshold, it is determined that the current driver has a blind spot observation requirement, and the LED lamp is controlled to deflect based on the preset blind spot angle. The blind spot monitoring model is specifically:

[0020]

[0021] Among them, S is the blind spot value, h1 is the eyeball height, h2 is the sight point height, d is the sight point offset distance, l is the horizontal distance between the sight point and the eyeball, and L is the horizontal distance between the sight point and the eyeball. It is the functional relationship between the sight point offset value and the blind spot length.

[0022] Optionally, also include:

[0023] The lamp return module is used to send a return instruction to the LED lamp after receiving the vehicle direction return signal.

[0024] The third aspect of the present application provides an artificial intelligence-based LED lamp control method device, the device comprising a processor and a memory:

[0025] The memory is used to store program code and transmit the program code to the processor;

[0026] The processor is used to execute the artificial intelligence-based LED lamp control method described in any one of the first aspects of the present invention according to the instructions in the program code.

[0027] The fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute an artificial intelligence-based LED lamp control method as described in any one of the first aspects of the present invention.

[0028] It can be seen from the above technical scheme that the present invention has the following advantages: the turning sight point range that each vehicle driver is accustomed to is generated through historical data, and the steering prediction observation area is set according to the real-time eye data. When the trend direction of driving steering is consistent with the driver's sight point, the offset angle of the LED lamp is set according to the predicted observation area. When the road lighting is poor, lighting assistance is provided for the driver to observe the road conditions when turning, thereby improving the steering safety of the driver while driving and optimizing the vehicle experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0030] Figure 1 It is a flow chart of an LED lamp control method based on artificial intelligence;

[0031] Figure 2 It is a top view of the driver's line of sight;

[0032] Figure 3 It is the side view of the driver’s sight line;

[0033] Figure 4 This is a structural diagram of an LED lighting control system based on artificial intelligence. DETAILED DESCRIPTION

[0034] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] The present invention provides an artificial intelligence-based LED lamp control method, which is used to solve the problem in the prior art that observation of road conditions in the direction of vehicle turning is limited by ambient lighting, thus affecting driving safety.

[0036] See also Figure 1 , Figure 1 The present invention provides a first flow chart of an artificial intelligence-based LED lamp control method according to an embodiment of the present invention.

[0037] S100, obtaining historical eyeball data and historical driving data, and dividing the data based on the identity of the driver to establish the turning sight point range of each driver;

[0038] It should be noted that during each driving, artificial intelligence combined with eye tracking technology can collect and record the driver's eye movement and gaze, determine the driver's identity through iris recognition or face recognition, and simultaneously record the driving speed and steering situation according to the vehicle system; the eye tracking eye tracker will preset a vertical plane where the eye tracker is located, which is perpendicular to the driver's direct driving direction, as the sight point plane, and combine artificial intelligence eye tracking technology to calculate the coordinates of the sight point on the sight point plane, and convert the eye rotation angle into coordinate data, which is convenient for subsequent processing and calculation;

[0039] Every time the driver turns the steering wheel when the vehicle turns, he needs to observe the road conditions left and right. The driver's eye rotation angle will be recorded at this time. The rotation here includes not only the eye rotation itself, but also the eye rotation driven by the driver's head rotation. Therefore, the eye rotation angle of this embodiment is the collected pupil overall rotation data; the long-term gaze point during straight driving is identified in the historical eye data, and the long-term gaze point when turning is identified, and the rotation angle between the two gaze points is regarded as the turning sight point range; each driver has different driving habits, and therefore has their own corresponding turning sight point range, and the data of the sight point range in eye tracking is the coordinate data range.

[0040] S200, monitoring eyeball data of a person, obtaining the current driver's identity and real-time sight point, combining the real-time sight point with the driving sight point range corresponding to the current driver's identity, and obtaining the driver's predicted observation area;

[0041] It should be noted that the eye tracking technology in this embodiment needs to be combined with machine vision algorithms and machine-perceived artificial intelligence technology to improve the accuracy and efficiency of eye tracking. The driver's identity can be identified by iris recognition, but the cost of iris recognition is relatively high, so a simple facial recognition technology can be used. When the current driver is driving, the human eye data is monitored in real time to calculate the line of sight. In this embodiment, only the horizontal coordinate of the line of sight on the line of sight plane is considered, that is, the value related to horizontal steering. Taking the current line of sight point horizontal coordinate as the reference, the coordinate distance of the steering line of sight point range is extended in both directions of the horizontal coordinate axis, which is the corresponding predicted observation area of ​​the driver in the left and right directions, that is, in the case of steering, it corresponds to the current driver's field of vision deflection range when observing oncoming vehicles in the left and right directions.

[0042] S300, monitoring current driving data and obtaining the driving trend direction; if the real-time sight point is consistent with the driving trend direction, calculating the LED lamp offset angle according to the driver's predicted observation area and the driving trend direction, and correcting the vehicle LED lighting based on the offset angle;

[0043] It should be noted that the vehicle computer system will monitor and record the vehicle driving data, record the current vehicle speed and steering wheel steering conditions. During the vehicle turning process, under the same steering wheel steering, the turning radius will increase with the increase of vehicle speed. The driving trend direction is the actual turning situation under the combination of vehicle speed and steering wheel steering. Based on the preset corresponding relationship, the driving trend direction is also converted into a corresponding coordinate value. The driving trend direction includes left turn trend and right turn trend except straight driving. The real-time sight point has a corresponding coordinate, and a reference straight coordinate value range can be preset according to the driver's position. When the real-time sight point coordinate exceeds the reference straight coordinate value range, it is regarded as a turning intention, and the turning intention direction is determined according to the specific coordinate value. If it is consistent with the driving trend direction, LED lamps are required for lighting assistance. In this embodiment, the driving situation where the lighting conditions are poor and the vehicle lights need to be turned on is considered;

[0044] In addition to assisting vehicle drivers in observing road conditions, vehicle lights also serve as signal indicators to other vehicles in traffic. Therefore, the deflection of LED auxiliary lights needs to be consistent with the vehicle's turning direction to avoid misleading other drivers. For example, when the vehicle turns, the driver must observe the other direction in addition to the vehicle's turning direction. However, the LED auxiliary lights cannot be offset to the left and right due to the driver's two-way observation, and the lighting cannot be offset back and forth. This will cause other drivers to misunderstand the direction of the vehicle and affect road safety.

[0045] During driving, automobile headlights are mainly laser headlights, xenon lamps and halogen lamps to illuminate the direction of vehicle travel. They cannot deviate from the current driving lane. LED lamps are used for field of vision fill-in lighting to assist the driver in observing road conditions. After determining that the real-time line of sight point is consistent with the driving trend direction, the LED lamp needs to be deflected. At the coordinates corresponding to the driving trend direction, the road condition can be illuminated by the automobile headlights. Therefore, the predicted observation area and the driving trend direction can be combined to perform offset angle calculation to improve the fill-in lighting efficiency of LED lamps. The predicted observation area in this embodiment is consistent with the driving trend direction. For example, the coordinates of the two ends of the predicted observation area are a and b respectively, and the coordinate corresponding to the driving trend direction is c. The coordinates are determined according to the size relationship of the three coordinate values ​​​​abc. In the case of required LED lighting steering fill light, when a>b>c, the area where the driver turns to observe the road condition will not be illuminated by the car headlights. When a>c>b, the area where the driver turns to observe the road condition will be illuminated by the car headlights. For both, the angle corresponding to the midpoint between coordinates a and c can be used to control the offset of the LED lamp. A relationship model formula will be preset according to the steering of the LED lamp and the coordinates of the sight point. After obtaining the midpoint coordinates between ac, the LED lamp offset correction is controlled at the corresponding angle to perform road condition observation fill light for the driver. In this embodiment, the LED lamps can be set on the left and right sides of the vehicle, but when turning, only the LED lamps consistent with the driving trend direction need to be turned on and controlled.

[0046] In this embodiment, the turning sight point range that each vehicle driver is accustomed to is generated through historical data, and a steering prediction observation area is set according to real-time eye data. When the trend direction of driving steering is consistent with the driver's sight point, the offset angle of the LED lamp is set according to the predicted observation area. When the road lighting is poor, lighting assistance is provided to assist the driver in observing the road conditions when turning, thereby improving the driver's steering safety while driving and optimizing the vehicle experience.

[0047] The above is a detailed description of the first embodiment of an artificial intelligence-based LED lamp control method provided by the present application. The following is a detailed description of the second embodiment of an artificial intelligence-based LED lamp control method provided by the present application.

[0048] In this embodiment, a method for controlling LED lamps based on artificial intelligence is further provided. In the aforementioned step S300, if the real-time sight point is consistent with the driving trend direction, the method further includes:

[0049] The eyeball coordinates are obtained according to the eyeball data and substituted into the blind spot monitoring model. If the blind spot value is less than the preset threshold, it is determined that the current driver has a blind spot observation requirement, and the LED lamp is controlled to deflect based on the preset blind spot angle. The blind spot monitoring model is specifically:

[0050]

[0051] Among them, S is the blind spot value, h1 is the eyeball height, h2 is the sight point height, d is the sight point offset distance, l is the horizontal distance between the sight point and the eyeball, and L is the horizontal distance between the sight point and the eyeball. It is the functional relationship between the sight point offset value and the blind spot length;

[0052] It should be noted that when the real-time sight point is consistent with the driving trend direction, it means that the current driver's field of vision is consistent with the driving direction and driving assistance is needed. However, the vehicle itself blocks the driver's observation during driving, which will bring blind spots. Eye tracking technology is based on optical principles and measures the position and movement of the eyeballs, but can be further combined with artificial intelligence technology to identify the distance between the current driver's eyes and the sight point plane, as well as the coordinates of the plane where the driver's eyes are located. The plane where the driver's eyes are located and the sight point plane use the same spatial coordinate system. The plane coordinate system of the original sight point plane can be composed of a height coordinate axis z and an offset distance coordinate axis x. Compared with the aforementioned step S100, this step adds a horizontal distance coordinate axis y to convert the plane coordinates into spatial coordinates. Please refer to Figure 2 and Figure 3 , Figure 2 This is the side view of the driver's line of sight. Figure 3: is a top view of the driver's line of sight, in which 1 is the driver's eyeball, 2 is the real-time line of sight point, 3 is the line of sight landing point, 4 is the plane where the driver's eyeball is located, and 5 is the line of sight point plane. The real-time line of sight point 2 is the intersection of the driver's line of sight and the vertical plane preset by eye tracking. The blind spot of the field of vision is the obstruction caused by the vehicle body itself. In this embodiment, the vehicle body and the eye tracker can be regarded as being on the same horizontal plane. Therefore, the horizontal plane where the vehicle body is located is set as the line of sight landing point plane, and the line of sight landing point 3 is the intersection of the driver's line of sight and the line of sight landing point plane. The distance between the driver's line of sight at the current driver's eyeball and the line of sight point plane is the horizontal distance l between the line of sight point and the eyeball, that is, the coordinate value difference on the horizontal distance coordinate axis y; the line of sight point offset distance d is the coordinate value difference between the eyeball coordinates and the line of sight point on the coordinate axis x; the eyeball height h1 and the line of sight point height h2 are the coordinate value differences between the eyeball coordinates and the line of sight point coordinates and the preset reference height on the height coordinate axis z, where the reference height is consistent with the line of sight landing point plane and can be used as the origin height of the spatial coordinate system; the vehicle blind spot The blind spot is generally composed of the vehicle body and is related to the vehicle body size. The vehicle body size is irregular, so the relationship between the vehicle body length in the y-axis direction and the x-axis coordinate can be established to obtain the functional relationship between the sight point offset value and the blind spot length, that is, the functional relationship can calculate the corresponding blind spot length based on the value of the sight point on the x-axis. Because the area between the eyeball plane and the sight point plane belongs to the inside of the vehicle, the visual field blind spot should actually be the area on the other side of the sight point plane relative to the eyeball plane. In the second formula of the blind spot monitoring model, f(D) calculates the blind spot length under the sight point x, and Ll calculates the visual field distance of the sight point in the blind spot. The positive and negative values ​​of the blind spot value subtracted from the two can determine whether the sight point is blocked by the blind spot. Because the driver will not look directly at the blind spot of the vehicle body when observing, the preset threshold can be set based on the empirical values ​​of the vehicle body and the visual field. When the blind spot value is less than the preset threshold, it can be set that the driver's sight point is very close to the visual field blind spot, part of the visual field is blocked by the vehicle body, and there is a need for blind spot observation.

[0053] For blind spots in the field of vision, visual perception technology can be used for auxiliary monitoring. However, the image acquisition technology of visual perception technology is similar to that of the human eye. It uses instruments such as cameras and does not actively emit light. Lighting assistance is required in dim road conditions. Therefore, the preset blind spot angle of the LED lamp can be controlled to deflect horizontally downward in the vertical direction. The embodiment of the aforementioned step S300 controls the horizontal deflection of the LED auxiliary lamp. This embodiment controls the vertical deflection of the LED auxiliary lamp. The blind spot angle is a fixed angle preset according to the vehicle's external dimensions.

[0054] Furthermore, after the aforementioned step S300, it also includes: after receiving the vehicle direction return signal, sending a return instruction to the LED lamp; it should be noted that the vehicle system continuously monitors the driving data, and after the steering wheel returns to the center, there is no turning trend at this time, and there is no need for auxiliary observation lighting, so the LED lamp can also be returned to the direct position to assist the vehicle headlights in illuminating the straight road.

[0055] The above is a detailed description of an artificial intelligence-based LED lamp control method provided in the first aspect of the present application. The following is a detailed description of an embodiment of an artificial intelligence-based LED lamp control system provided in the second aspect of the present application.

[0056] See also Figure 4 , Figure 4 This embodiment provides a LED lamp control system based on artificial intelligence, including:

[0057] The driving habit generation module 10 is used to obtain historical eyeball data and historical driving data, and divide the data based on the driver's identity to establish the turning sight point range of each driver;

[0058] The eyeball data processing module 20 is used to monitor the eyeball data of the person, obtain the current driver identity and the real-time sight point, combine the real-time sight point with the driving sight point range corresponding to the current driver identity, and obtain the driver's predicted observation area;

[0059] The lamp control module 30 is used to monitor the current driving data and obtain the driving trend direction; if the real-time sight point is consistent with the driving trend direction, the LED lamp offset angle is calculated according to the driver's predicted observation area and the driving trend direction, and the vehicle LED lighting is corrected based on the offset angle.

[0060] Furthermore, in the lamp control module 30, if the real-time sight point is consistent with the driving trend direction, it also includes:

[0061] The eyeball coordinates are obtained according to the eyeball data and substituted into the blind spot monitoring model. If the blind spot value is less than the preset threshold, it is determined that the current driver has a blind spot observation requirement, and the LED lamp is controlled to deflect based on the preset blind spot angle. The blind spot monitoring model is specifically:

[0062]

[0063] Among them, S is the blind spot value, h1 is the eyeball height, h2 is the sight point height, d is the sight point offset distance, l is the horizontal distance between the sight point and the eyeball, and L is the horizontal distance between the sight point and the eyeball. It is the functional relationship between the sight point offset value and the blind spot length.

[0064] Furthermore, it also includes:

[0065] The lamp return module 40 is used to send a return instruction to the LED lamp after receiving the vehicle direction return signal.

[0066] The third aspect of the present application also provides an artificial intelligence-based LED lamp control method device, including a processor and a memory: the memory is used to store program code and transmit the program code to the processor; the processor is used to execute the above-mentioned artificial intelligence-based LED lamp control method according to the instructions in the program code.

[0067] A fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute the above-mentioned artificial intelligence-based LED lamp control method.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0069] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0070] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0072] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0073] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling LED lamps based on artificial intelligence, characterized in that include: Obtain historical eyeball data and historical driving data, and divide the data based on the driver's identity, identify the gaze point coordinates of each driver during straight driving and turning, and establish the turning sight point range of each driver; Monitor the eye data of the person, obtain the current driver's identity and real-time sight point, combine the real-time sight point with the driving sight point range corresponding to the current driver's identity, and obtain the driver's predicted observation area; Monitor current driving data and obtain driving trend direction; If the real-time sight point is consistent with the driving trend direction, the LED lamp offset angle is calculated according to the driver's predicted observation area and the driving trend direction, specifically including: when the driving trend direction is within the driver's predicted observation area, the vehicle LED lighting is corrected based on the offset angle corresponding to the midpoint coordinates in the predicted observation area.

2. The artificial intelligence-based LED lamp control method according to claim 1, characterized in that: If the real-time sight point is consistent with the driving trend direction, the method further includes: The eyeball coordinates are obtained according to the eyeball data and substituted into the blind spot monitoring model. If the blind spot value is less than the preset threshold, it is determined that the current driver has a blind spot observation requirement, and the LED lamp is controlled to deflect based on the preset blind spot angle. The blind spot monitoring model is specifically: Among them, S is the blind spot value, h1 is the eyeball height, h2 is the sight point height, d is the sight point offset distance, l is the horizontal distance between the sight point and the eyeball, and L is the horizontal distance between the sight point and the eyeball. It is the functional relationship between the sight point offset value and the blind spot length.

3. The artificial intelligence-based LED lamp control method according to claim 1, characterized in that: Also includes: After receiving the vehicle direction return signal, a return command is sent to the LED lamp.

4. An artificial intelligence-based LED lamp control system, characterized in that: include: The driving habit generation module is used to obtain historical eye data and historical driving data, and divide the data based on the driver's identity, respectively identify the gaze point coordinates of each driver during straight driving and turning, and establish the turning sight point range of each driver; The eyeball data processing module is used to monitor the eyeball data of the person, obtain the current driver's identity and real-time sight point, combine the real-time sight point with the driving sight point range corresponding to the current driver's identity, and obtain the driver's predicted observation area; The lighting control module is used to monitor the current driving data and obtain the driving trend direction; If the real-time sight point is consistent with the driving trend direction, the LED lamp offset angle is calculated according to the driver's predicted observation area and the driving trend direction, specifically including: when the driving trend direction is within the driver's predicted observation area, the vehicle LED lighting is corrected based on the offset angle corresponding to the midpoint coordinates in the predicted observation area.

5. The artificial intelligence-based LED lamp control system according to claim 4, characterized in that: In the lamp control module, if the real-time sight point is consistent with the driving trend direction, it also includes: The eyeball coordinates are obtained according to the eyeball data and substituted into the blind spot monitoring model. If the blind spot value is less than the preset threshold, it is determined that the current driver has a blind spot observation requirement, and the LED lamp is controlled to deflect based on the preset blind spot angle. The blind spot monitoring model is specifically: Among them, S is the blind spot value, h1 is the eyeball height, h2 is the sight point height, d is the sight point offset distance, l is the horizontal distance between the sight point and the eyeball, and L is the horizontal distance between the sight point and the eyeball. It is the functional relationship between the sight point offset value and the blind spot length.

6. The artificial intelligence-based LED lamp control system according to claim 4, characterized in that: Also includes: The lamp return module is used to send a return instruction to the LED lamp after receiving the vehicle direction return signal.

7. An artificial intelligence-based LED lamp control device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the artificial intelligence-based LED lamp control method described in any one of claims 1-3 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program codes, and the program codes are used to execute the artificial intelligence-based LED lamp control method described in any one of claims 1-3.

Images