A vehicle light control method and vehicle

Abstract

The embodiment of the application provides a vehicle light control method and a vehicle, the method comprises the following steps: acquiring the intensity value of the indoor ambient light; if the intensity value of the indoor ambient light is lower than the first threshold value and the duration is greater than the first duration, acquiring the object posture image of the indoor object and the indoor panoramic image; performing electronic device use detection on the object posture image to obtain a detection result, calculating the global average brightness of the indoor panoramic image, and calculating the local area average brightness of the indoor panoramic image, wherein the detection result is used to indicate whether the indoor object is in the posture of using the electronic device; if it is determined that the indoor object uses the electronic device based on the detection result, the global average brightness and the local area average brightness, the target lighting device corresponding to the seat where the indoor object sits is turned on, and the target lighting device is controlled to irradiate the target area. The application solves the technical problems of unintelligent vehicle light control and inaccurate floodlighting in the traditional scheme.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically, to a vehicle lighting control method and a vehicle. Background Technology

[0002] Using mobile phones while traveling is a frequent activity for passengers. The significant difference in light between localized bright areas and overall dimness can easily lead to visual fatigue, posing a risk of damaging eye health and reducing travel comfort.

[0003] Existing rear seat lighting in vehicles mainly relies on manual switches or door linkages, resulting in rigid control logic that is detached from actual passenger behavior. Furthermore, existing reading lights mostly use wide-beam floodlighting, which has low illuminance and diffused light, failing to accurately illuminate the area where mobile phones are used.

[0004] There is currently no good solution to the above problems. Summary of the Invention

[0005] This application provides a vehicle lighting control method and a vehicle to at least solve the technical problems of unintelligent vehicle lighting control and inaccurate floodlighting in traditional solutions.

[0006] According to one aspect of the embodiments of this application, a vehicle lighting control method is provided, comprising: acquiring an ambient light intensity value inside the vehicle; if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is greater than a first duration, acquiring an object posture image of an object inside the vehicle and a panoramic image inside the vehicle; performing electronic device usage detection on the object posture image to obtain a detection result, calculating the global average brightness of the panoramic image inside the vehicle, and calculating the local average brightness of the panoramic image inside the vehicle, wherein the detection result is used to indicate whether the object inside the vehicle is in a posture of using an electronic device; if it is determined based on the detection result, the global average brightness, and the local average brightness that the object inside the vehicle is using an electronic device, turning on a target lighting device corresponding to the seat where the object inside the vehicle is sitting, and controlling the target lighting device to illuminate a target area, wherein the target area covers the electronic device and the hand of the object inside the vehicle.

[0007] Furthermore, obtaining the ambient light intensity value inside the vehicle includes: using an ambient light sensor integrated in the rear roof of the vehicle to sample the ambient light signal inside the vehicle according to a preset frequency to obtain an ambient light intensity sequence inside the vehicle; and performing digital filtering on the ambient light intensity sequence inside the vehicle to obtain the ambient light intensity value inside the vehicle.

[0008] Furthermore, the electronic device usage detection is performed on the object's pose image, and the detection results include: using a pose recognition model to perform pose analysis on the object's pose image to obtain analysis results, wherein the analysis results are used to represent the current pose of the object inside the vehicle; and comparing the analysis results with a preset pose set to obtain detection results.

[0009] Furthermore, the preset posture set includes at least one of the following: the object inside the vehicle is holding a rectangular object with a preset aspect ratio, the object inside the vehicle is in a downward posture with its gaze directed toward the area of ​​the object being held, and the object inside the vehicle is in a bent and holding posture.

[0010] Furthermore, calculating the global average brightness of the in-vehicle panoramic image includes: converting the in-vehicle panoramic image to a target color space and extracting the brightness component image in the target color space; obtaining the brightness values ​​of the pixels in the brightness component image; summing the brightness values ​​of the pixels to obtain the total brightness value; and determining the global average brightness based on the total brightness value.

[0011] Furthermore, calculating the average brightness of local areas in the in-vehicle panoramic image includes: segmenting the in-vehicle panoramic image using an image segmentation algorithm to obtain multiple local areas; and determining the average brightness of any local area among the multiple local areas.

[0012] Furthermore, the method also includes: if the object inside the vehicle is in a posture of using electronic devices, selecting candidate local regions based on the local average brightness and the global average brightness, wherein the local average brightness of the candidate local region is higher than the global average brightness; comparing the spatial position coordinates of the candidate local region with the spatial position coordinates of the current posture to obtain the overlap ratio; if the overlap ratio is higher than a second threshold, determining that the object inside the vehicle is using electronic devices.

[0013] Furthermore, controlling the target lighting device to illuminate the target area includes: acquiring the screen color temperature of the electronic device and adjusting the output color temperature of the target lighting device according to the screen color temperature; after adjusting the output color temperature of the target lighting device, determining the projection angle according to the position of the target lighting device and the position of the electronic device; and controlling the target lighting device to illuminate the target area according to the projection angle.

[0014] Furthermore, the method also includes: in response to the target lighting device being turned on, starting a timer; if the recording duration of the timer exceeds a third threshold, controlling the audio device to play a prompt voice and resetting the timer, wherein the prompt voice is used to remind the object in the vehicle to pay attention to the duration of eye use and to take a break.

[0015] According to another aspect of the embodiments of this application, a vehicle lighting control device is also provided, comprising: a first acquisition module, configured to acquire an ambient light intensity value inside the vehicle; a second acquisition module, configured to acquire an object posture image of an object inside the vehicle and a panoramic image inside the vehicle if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is greater than a first duration; a detection module, configured to perform electronic device usage detection on the object posture image, obtain a detection result, calculate the global average brightness of the panoramic image inside the vehicle, and calculate the local average brightness of the panoramic image inside the vehicle, wherein the detection result is used to indicate whether the object inside the vehicle is in a posture of using an electronic device; and a determination module, configured to, if it is determined based on the detection result, the global average brightness, and the local average brightness that the object inside the vehicle is using an electronic device, turn on a target lighting device corresponding to the seat where the object inside the vehicle is sitting, and control the target lighting device to illuminate a target area, wherein the target area covers the electronic device and the hand of the object inside the vehicle.

[0016] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0017] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0018] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0019] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the methods in various embodiments of this application.

[0020] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0021] In this embodiment of the application, a vehicle lighting control method is adopted. This embodiment of the application provides a vehicle lighting control method and a vehicle. The method includes: acquiring the ambient light intensity value inside the vehicle; if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is greater than a first duration, acquiring an object posture image of an object inside the vehicle and a panoramic image inside the vehicle; performing electronic device usage detection on the object posture image to obtain a detection result, calculating the global average brightness of the panoramic image inside the vehicle, and calculating the local average brightness of the panoramic image inside the vehicle, wherein the detection result is used to indicate whether the object inside the vehicle is in a posture of using an electronic device; if it is determined based on the detection result, the global average brightness, and the local average brightness that the object inside the vehicle is using an electronic device, turning on the target lighting device corresponding to the seat where the object inside the vehicle is sitting, and controlling the target lighting device to illuminate the target area, wherein the target area covers the electronic device and the hand of the object inside the vehicle, achieving the purpose of automatically providing local directional supplementary lighting in dim lighting and when passengers are using mobile phones, thereby achieving the technical effect of accurately covering the target area with light and avoiding interference with other occupants, effectively relieving visual fatigue, and thus solving the technical problems of unintelligent vehicle lighting control and inaccurate floodlighting in traditional solutions. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0023] Figure 1 This is a flowchart of a vehicle lighting control method according to an embodiment of this application;

[0024] Figure 2 This is a schematic diagram of the steps of a vehicle lighting control method according to an embodiment of this application;

[0025] Figure 3 This is a schematic flowchart of a vehicle lighting control method according to an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of a vehicle lighting layout according to an embodiment of this application;

[0027] Figure 5 A structural block diagram of a vehicle lighting control device according to an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] With the widespread use of mobile smart devices, using mobile phones during travel has become a frequent activity for passengers. However, when a vehicle is at night or entering a tunnel, there are significant regional differences in the distribution of light inside the cabin: while the driver's area is usually kept relatively well-lit by the dashboard, central control screen, and other devices, the rear passenger area is often plunged into a relatively darker environment due to the physical obstruction of the front seats. At this time, the rear passengers' mobile phone screens become the main, or even the only, high-brightness light source, creating a strong contrast between light and dark in the cabin environment. This significant difference between localized brightness and overall darkness can easily lead to visual fatigue for passengers, posing a potential risk of damaging eye health and reducing travel comfort. The traditional solution is to provide conventional reading lights for the rear seats, but their light intensity is generally limited and the light distribution is relatively diffuse, making it difficult to accurately and sufficiently illuminate the key dark areas around the passengers' hands and the screen. Therefore, even with existing lighting, the problem of strong light and dark contrast faced by rear passengers remains unresolved, and their eye health and experience quality urgently require a smarter and more suitable lighting solution to improve.

[0031] In traditional solutions, control logic is primarily based on manual operation of physical switches or electrical linkage with the opening and closing status of vehicle doors. The former relies on active triggering by passengers, while the latter depends on basic vehicle status signals. Furthermore, from an optical design perspective, traditional rear-seat lighting devices (such as reading lights) typically employ wide-beam-angle optical schemes, resulting in a more diffuse light distribution in space and consequently, lower illuminance in localized lighting areas.

[0032] Specifically, as shown in Table 1, although traditional methods also involve adjusting in-vehicle lighting parameters, their objectives and methods are fundamentally different from those of this application.

[0033] Table 1

[0034] Core Objectives Universal reading light dimming system Dim interior lighting system for mobile phones The scenario is further refined to include using a mobile phone inside a car. Core content 1. Filter out interference from external ambient light, calibrate ambient light, and improve the accuracy of subsequent adjustments; 2. Based on coordinates, classify the positions inside the vehicle into layers, and for vehicles in the same row, dynamically match user priorities according to their distance from the center of the reading lights to generate lighting parameters. 1. Detection of ambient light intensity inside the vehicle; 2. Judgment of mobile phone usage status (recognition of mobile phone posture and screen brightness); 3. Providing voice prompts when using a mobile phone for an extended period of time in dim lighting. Traditional methods focus on "environmental calibration" and "space allocation," which fall under the category of in-vehicle environment optimization. This application leans more towards "behavioral perception" and "health care," achieving a leap from lighting management to proactive care. Dependent on devices Ultra-wideband (UWB) positioning and weight sensing modules, millimeter-wave radar Ambient light sensor, Occupant Monitoring System (OMS) camera, voice assistant /

[0035] It can be seen that traditional methods still have obvious limitations, mainly in the following three aspects.

[0036] Limited Control Modes: Traditional methods for controlling interior lighting (such as reading lights) primarily rely on manual switches or simple mechanical logic linked to vehicle doors. This approach requires users to actively interrupt their current activity, posing safety and convenience risks. Furthermore, its control logic is completely detached from the perception and understanding of passengers' specific activities during the journey (such as using mobile phones), thus failing to achieve automatic and precise lighting that matches the needs of real-world scenarios.

[0037] Rigid lighting angles: Current lighting solutions for the rear seats of vehicles are essentially global or floodlight modes. When such lighting is turned on, the light usually spreads outwards at a large angle. While this can increase the overall brightness of the cabin, it inevitably illuminates non-target areas, forcing other occupants to passively receive the light, and failing to achieve personalized lighting that does not interfere with each other.

[0038] Lack of contextual adaptation capability: Because the system cannot identify whether occupants are engaged in specific activities requiring localized lighting (such as using a mobile phone), its control logic is completely disconnected from the dynamic needs of users. This reflects the lack of a key intelligent closed loop of "scene perception - intent judgment - precise execution" in the existing system, thus it can only provide rigid and passive lighting services and cannot achieve the transformation from "humans adapting to light" to "light adapting to humans".

[0039] According to an embodiment of this application, a method for controlling vehicle lights is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0040] This embodiment provides a vehicle lighting control method. Figure 1 This is a flowchart of a vehicle lighting control method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps:

[0041] Step S11: Obtain the ambient light intensity value inside the vehicle.

[0042] In this embodiment, the vehicle lighting control system first acquires the ambient light intensity value inside the vehicle. This ambient light intensity value can be the intensity of light illuminating the interior space of the vehicle, collected in real time by sensors, and can be quantified in lux. It objectively characterizes the current brightness state inside the vehicle and is a fundamental physical parameter for determining whether artificial lighting or supplemental lighting is needed. For example, the vehicle lighting control system needs to accurately capture light intensities of different levels, such as low illumination at night (e.g., below 10 lux), dim conditions in tunnels (e.g., 50-100 lux), cloudy conditions during the day (e.g., 200-500 lux), and bright conditions under direct midday sunlight (e.g., above 1000 lux).

[0043] It can be seen that the vehicle lighting control system can output real-time intensity values ​​that reflect the current ambient light level through ambient light sensors deployed in key locations such as the rear roof of the vehicle.

[0044] This provides a reliable data foundation for accurately determining the degree of darkness in the environment.

[0045] Step S12: If the ambient light intensity value inside the vehicle is lower than the first threshold and the duration is longer than the first duration, acquire the object pose image of the object inside the vehicle and the panoramic image inside the vehicle.

[0046] In this embodiment, if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is longer than a first duration, the vehicle lighting control system will acquire an object pose image of an object inside the vehicle and a panoramic image of the vehicle interior. Here, the object inside the vehicle refers to a passenger located in the rear seat of the vehicle.

[0047] Object pose images refer to visual data captured by in-vehicle cameras that include passenger body movements and the shape of objects held in their hands. Examples of object pose images include the angle of a passenger's head tilt, the degree of arm bending, and the outline of a rectangular object held in their hand (such as a smartphone). In-vehicle panoramic images refer to wide-field-of-view image data that covers multiple local areas around the passenger. These images are used to analyze overall illumination distribution. Examples of in-vehicle panoramic images include a complete view of the passenger's face, hands, phone screen, and surrounding background areas such as seats and windows, used to calculate global and local brightness differences.

[0048] The first threshold refers to the preset lower limit of ambient light intensity for the vehicle's lighting control system, used to define the physical boundary of dimly lit environments. When the ambient light intensity inside the vehicle is lower than this value, the vehicle's lighting control system considers that natural light or regular ambient light is insufficient for passengers to clearly view their mobile phone screens, thus determining that supplemental lighting is needed. The specific setting of this value can be customized according to the vehicle model's positioning or user needs, for example, it can be set to 150 lux, 100 lux, or 50 lux, aiming to balance energy saving and visual comfort, and avoid accidental triggering of lighting when there is sufficient natural light.

[0049] The first duration refers to the minimum cumulative time during which the ambient light intensity remains below a first threshold, used to filter out instantaneous fluctuations or brief obstructions in ambient light. This parameter aims to prevent misjudgments by the vehicle's lighting control system due to transient factors such as the vehicle passing through a tunnel entrance, cloud cover blocking sunlight, or passengers temporarily obstructing the sensors. For example, the first duration can be set to 2 seconds, 3 seconds, or 5 seconds to ensure that the vehicle's lighting control system only considers the user to be in a real scene requiring lighting when the dimness persists and stabilizes, thereby improving the robustness of the control logic.

[0050] It can be seen that when the vehicle lighting control system confirms that the ambient light is below the set threshold and the duration is up to standard, it automatically acquires and records the object posture image of the passenger's current limb movements and the panoramic image of the vehicle interior for illumination analysis, providing the raw visual data source for subsequent behavior recognition and brightness comparison.

[0051] For example, when it is determined that the dimness inside the vehicle lasts for more than 2 seconds, the vehicle lighting control system activates the camera and captures a close-up image showing the passenger looking down and holding a mobile phone, as well as a wide-angle image containing the passenger and the surrounding environment. These two types of image data are then passed to the image processing module for further analysis.

[0052] Therefore, by acquiring image data only after the environment has been dark for a certain period of time, the frequency of invalid operation of the camera is effectively reduced, saving vehicle computing power and energy.

[0053] Step S13: Perform electronic device usage detection on the object pose image to obtain the detection result, calculate the global average brightness of the in-vehicle panoramic image, and calculate the local average brightness of the in-vehicle panoramic image. The detection result is used to indicate whether the object inside the vehicle is in a pose of using electronic devices.

[0054] In this embodiment of the application, the vehicle lighting control system performs electronic device usage detection on the object posture image, obtains the detection result, and calculates the global average brightness of the panoramic image inside the vehicle and the local average brightness of the panoramic image. The detection result is used to indicate whether the object inside the vehicle is in a posture of using electronic devices.

[0055] Electronic device usage detection refers to the process of using computer vision algorithms to analyze passengers' body movements and the characteristics of objects they hold in order to determine whether they are operating electronic devices, such as mobile phones, tablets, e-readers, and computers.

[0056] Global average brightness refers to the arithmetic mean of the brightness of all pixels in the entire panoramic image inside the vehicle, reflecting the overall lighting level of the cabin, and can be denoted as L_global.

[0057] Local average brightness refers to the average brightness of pixels in a specific region of interest (such as near a passenger's hand or head) in an image. It reflects the illumination intensity at a specific location and can be denoted as L_local.

[0058] As can be seen, firstly, the vehicle lighting control system calls the posture recognition model to process the object posture image and identify whether the passenger is holding a rectangular object or looking down. Secondly, the vehicle lighting control system performs color space conversion on the panoramic image inside the vehicle to extract the brightness component, calculates the sum of the brightness of all pixels in the image and divides it by the total number of pixels to obtain the global average brightness. At the same time, it uses image segmentation technology to divide the local area centered on the passenger and calculates its average brightness, thereby obtaining key data reflecting the contrast of the environment.

[0059] For example, the vehicle lighting control system detects that a passenger's arm is bent and they are holding an object with an aspect ratio of 16:9, 18:9, 19.5:9, 20:9, 19.9:9, or other custom ratios, and determines that this is a posture of using electronic devices. Simultaneously, it calculates that the average brightness of the entire vehicle is 20 lux, while the average brightness in the passenger's hand area is as high as 800 lux. The vehicle lighting control system records these two brightness values ​​and the posture detection result for subsequent comprehensive judgment.

[0060] Therefore, by combining posture recognition with brightness distribution analysis, not only was the passenger's behavioral intention confirmed, but by quantifying the difference between local and global brightness, the situation where the passenger was only holding the phone but the screen was off or the ambient light was sufficient was effectively ruled out. This improved the accuracy of recognizing the specific scenario of using a mobile phone in dim environments and provided a dual verification basis for subsequently turning on local lighting.

[0061] Step S14: If it is determined that the object inside the vehicle is using an electronic device based on the detection results, global average brightness and local area average brightness, turn on the target lighting device corresponding to the seat where the object is sitting, and control the target lighting device to illuminate the target area, wherein the target area covers the electronic device and the hand of the object inside the vehicle.

[0062] In this embodiment of the application, if it is determined that the object inside the vehicle is using an electronic device based on the detection results, the global average brightness and the local area average brightness, the vehicle lighting control system will turn on the target lighting device corresponding to the seat where the object is sitting, and control the target lighting device to illuminate the target area. The target area covers the electronic device and the hand of the object inside the vehicle, such as an elliptical or rectangular light spot covering the mobile phone screen and the palm, with clear boundaries and very little light spillage. For example, the diameter of the light spot is about 20-30 centimeters, and it is strictly limited to the front of the upper body of the passenger.

[0063] Target lighting devices refer to independent lighting units that correspond one-to-one with specific seats and have directional projection capabilities. Examples include light-emitting diode (LED) reading lights equipped with micro servo motors that can rotate the lamp head, or intelligent light sources that use digital micromirror devices (DMDs) to achieve pixel-level light shape control.

[0064] It can be seen that when the vehicle lighting control system comprehensively judges that the passenger is using electronic devices and the environment is dim, it generates a lighting command and sends it to the corresponding target lighting device, driving it to adjust the optical structure or optical path, and emit a beam of light with an appropriate color temperature at a preset projection angle to ensure that the central axis of the beam points to the passenger's hand and mobile phone screen, forming a local bright area. At the same time, it limits the light overflow through the light shield or optical design to avoid illuminating the driver or other passenger areas.

[0065] For example, when the vehicle lighting control system detects that the passenger in the right rear seat is looking at his mobile phone in a dim environment, it controls the independent light in the right rear to adjust the beam angle downward by 15 degrees and focus it to project a light spot with uniform brightness but limited range, which just covers the mobile phone screen and hands in the passenger's hands, while the light does not spread to the passenger on the left or the front seat, thus achieving precise local supplemental lighting.

[0066] Thus, by directional illumination of specific target areas, the system can meet passengers' needs for viewing their mobile phones while avoiding visual interference with other areas and people inside the vehicle, achieving intelligent zoning of the light environment.

[0067] In summary, the vehicle lighting control method of this application first acquires the ambient light intensity value inside the vehicle, thus providing a reliable data foundation for accurately judging the degree of ambient darkness. Secondly, if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is longer than a first duration, an object pose image of the object inside the vehicle and a panoramic image of the vehicle interior are acquired. This effectively reduces the invalid operating frequency of the camera and saves onboard computing power and energy by acquiring image data only after the environment has been dark for a certain period. Then, electronic device usage detection is performed on the object pose image to obtain the detection result. The global average brightness of the panoramic image inside the vehicle and the average brightness of local areas of the panoramic image inside the vehicle are calculated. The detection result... This is used to indicate whether an object inside the vehicle is in a posture of using an electronic device. By combining posture recognition with brightness distribution analysis, not only is the passenger's behavioral intention confirmed, but the difference in brightness between local and global areas is also quantified. Finally, if it is determined that the object inside the vehicle is using an electronic device based on the detection results, global average brightness, and local average brightness, the target lighting device corresponding to the seat where the object is sitting is turned on, and the target lighting device is controlled to illuminate the target area. The target area covers the electronic device and the object's hands. Thus, by directionally illuminating a specific target area, the need for passengers to view their mobile phones is met while avoiding visual interference with other areas and people inside the vehicle, achieving intelligent zoning of the light environment.

[0068] The above steps of this application involve: using the ambient light intensity value inside the vehicle; if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is greater than a first duration, acquiring an object posture image of the object inside the vehicle and a panoramic image inside the vehicle; detecting the use of electronic devices on the object posture image to obtain the detection result; calculating the global average brightness of the panoramic image inside the vehicle and the local average brightness of the panoramic image inside the vehicle, wherein the detection result is used to indicate whether the object inside the vehicle is in a posture of using electronic devices; if it is determined based on the detection result, the global average brightness, and the local average brightness that the object inside the vehicle is using electronic devices, turning on the target lighting device corresponding to the seat where the object is sitting, and controlling the target lighting device to illuminate the target area, wherein the target area covers the electronic devices and the hands of the object inside the vehicle, achieving the purpose of automatically providing local directional supplementary lighting in dim lighting and when passengers are using mobile phones, thereby achieving the technical effect of accurately covering the target area with light and avoiding interference with other occupants, effectively alleviating visual fatigue, and thus solving the technical problems of unintelligent vehicle lighting control and inaccurate floodlighting in traditional solutions.

[0069] Optionally, obtaining the ambient light intensity value inside the vehicle includes:

[0070] Step S111: Using the ambient light sensor integrated in the rear roof of the vehicle, the ambient light signal inside the vehicle is sampled according to a preset frequency to obtain the ambient light intensity sequence inside the vehicle.

[0071] Step S112: The ambient light intensity sequence inside the vehicle is digitally filtered to obtain the ambient light intensity value inside the vehicle.

[0072] In this embodiment, the vehicle lighting control system first uses an ambient light sensor integrated in the rear roof of the vehicle to sample the ambient light signal inside the vehicle at a preset frequency, thereby obtaining an ambient light intensity sequence inside the vehicle. The ambient light sensor is a photoelectric conversion device deployed inside the rear roof of the vehicle to sense the intensity of light inside the passenger compartment; the sensor can be a photodiode or a photoresistor, etc.

[0073] The preset frequency refers to the fixed time interval set by the vehicle lighting control system. It is used to control the periodicity of sensor data acquisition and ensure the continuity and real-time performance of the data. The preset frequency can be 10Hz (10 samples per second), 20Hz, or 50Hz, etc.

[0074] The in-vehicle ambient light intensity sequence refers to a series of discrete light intensity values ​​continuously collected by sensors at a preset frequency, reflecting the dynamic process of light changes over time. For example, the in-vehicle ambient light intensity sequence is a series of numbers such as [120, 118, 122, 119, 121] lux, used to capture minute fluctuations in light.

[0075] It can be seen that the vehicle lighting control system calls the ambient light sensor integrated in the rear roof and periodically reads the ambient light signal in the cabin according to the preset sampling frequency. It converts the analog light signal into a digital signal and stores it sequentially, thereby constructing a time series array that reflects the recent trend of changes in the lighting inside the vehicle.

[0076] Therefore, by obtaining a continuous light intensity sequence through high-frequency sampling, the dynamic characteristics of light changes can be fully captured, avoiding the random errors that may exist in a single sampling, and providing a sufficient data foundation for subsequent digital filtering processing.

[0077] Then, the vehicle lighting control system performs digital filtering on the in-vehicle ambient light intensity sequence to obtain the in-vehicle ambient light intensity value.

[0078] Digital filtering refers to the techniques used to smooth, denoise, or calculate the mean of discrete digital signal sequences using mathematical algorithms to extract useful signals and suppress random noise. Common digital filtering algorithms include moving average filtering, median filtering, and Kalman filtering. For example, moving average filtering calculates the arithmetic mean of the most recent N sample values.

[0079] As can be seen, the vehicle lighting control system receives the ambient light intensity sequence inside the vehicle, applies a preset digital filtering algorithm to process the data in the sequence, filters out high-frequency noise and instantaneous fluctuation interference, calculates the representative value of stable illumination intensity at the current moment, and outputs it to the control logic as the final ambient light intensity value.

[0080] Therefore, digital filtering effectively eliminates data jitter caused by sensor noise, instantaneous light interference, or electromagnetic interference, making the output ambient light intensity value smoother, more accurate, and more stable, improving the reliability of subsequent judgments, and preventing malfunctions in the vehicle lighting control system caused by data jumps.

[0081] Optionally, electronic device usage detection is performed on the object pose image to obtain detection results including:

[0082] Step S131: Use a pose recognition model to perform pose analysis on the object pose image to obtain the analysis result, wherein the analysis result is used to represent the current pose of the object inside the vehicle.

[0083] Step S132: Compare the analysis results with the preset pose set to obtain the detection results.

[0084] In this embodiment of the application, the vehicle lighting control system uses a posture recognition model to perform posture analysis on the object posture image and obtains the analysis result. The analysis result is used to represent the current posture of the object inside the vehicle. Specifically, it can refer to the quantitative data on the joint angles, relative positions, or skeletal structures of various parts of the passenger's body output by the model, which is used to describe the passenger's current body shape and movement state.

[0085] A pose recognition model refers to a trained artificial intelligence algorithm model that can process visual images and extract spatial position information of key parts of the human body. This model can be a human pose estimation network based on deep learning. Object pose images may contain the coordinates of key points such as the passenger's head, shoulders, elbows, and wrists. Object pose images refer to two-dimensional or three-dimensional visual data containing the movements of the passenger's limbs, head, and hands.

[0086] As can be seen, the vehicle lighting control system inputs the acquired object posture image into a preset posture recognition model. The model performs feature extraction and inference calculation on the image, identifies the positional relationship of key points on the passenger's body, and generates an analysis result describing the current limb movement pattern of the passenger, providing structured data support for subsequent behavior judgment.

[0087] Therefore, by transforming unstructured image data into structured posture data through posture recognition models, passengers' body movements can be objectively and quantitatively described. This provides a data foundation for accurately determining whether a passenger is in a specific posture of using electronic devices, thereby improving the automation level and accuracy of behavior recognition.

[0088] Then, the vehicle lighting control system compares the analysis results with the preset posture set to obtain the detection results.

[0089] The preset posture set refers to a pre-stored set of standard data templates or rule bases representing typical postures when using electronic devices. It usually includes specific limb angle ranges, key point distance relationships, or feature vectors. The preset posture set may include a combination of feature rules such as "looking down + holding a rectangular object + looking downwards", or a set of standard mobile phone usage posture key point coordinate templates.

[0090] As can be seen, the vehicle lighting control system matches and compares the analysis results with the stored preset posture set. By calculating similarity, judging whether key features meet preset conditions, or using a classifier for classification, it determines whether the current posture conforms to the definition of using electronic devices, and thus outputs the final detection result.

[0091] Therefore, by comparing the real-time posture with a standard posture set, it is possible to effectively distinguish between "using electronic devices" and other postures such as "resting" and "talking," ensuring the specificity and accuracy of the detection results and providing a clear decision basis for subsequent lighting control.

[0092] Optionally, the preset pose set includes at least one of the following: the object inside the vehicle is holding a rectangular object with a preset aspect ratio, the object inside the vehicle is in a head-down posture with its gaze directed toward the area of ​​the object being held, and the object inside the vehicle is in a bent-grip posture.

[0093] In this embodiment of the application, a rectangular object with a preset aspect ratio refers to a solid object with a specific geometric ratio (such as 16:9 or 18:9 commonly found in smartphones) and a regular rectangular outline.

[0094] The head-down posture refers to a passenger's head center of gravity being below the horizontal plane, and the neck exhibiting an angle characteristic of tilting forward and downward. It can be set to an angle greater than 15 degrees between the neck axis and the vertical line.

[0095] The direction of the gaze toward the area of ​​the object being held refers to the fact that the passenger's face or the point of eye focus overlaps or points in the direction of the object being held in their hand in space.

[0096] A bent-arm gripping posture refers to a passenger's upper arm and forearm forming a specific angle, with the hand positioned within a certain range in front of the torso. This posture is typical of supporting or holding an object, usually characterized by a flexed elbow, an upward or forward extension of the forearm, and a relatively fixed hand position for stable operation. The specific angle range can be defined as an elbow angle between 60 and 120 degrees, with the hand position confined to the vertical range between the chest and waist, and within 30 centimeters horizontally from the center line of the torso. This posture is commonly seen when passengers hold their phones with both hands or one hand to view or operate them, as opposed to a posture where the arms are naturally hanging down or fully extended.

[0097] It can be seen that the vehicle lighting control system analyzes the spatial coordinates of key points such as the shoulder, elbow, and wrist in the object's posture image, calculates the angle between the upper arm vector and the forearm vector, and combines the positional relationship of the hand relative to the shoulder and torso to determine whether the passenger is in a typical holding and bending state, thus serving as one of the important auxiliary features for recognizing the use of electronic devices.

[0098] For example, the vehicle lighting control system identifies the passenger's left shoulder coordinates as (x1, y1), left elbow coordinates as (x2, y2), and left wrist coordinates as (x3, y3). It calculates that the angle between the left upper arm and left forearm is 90 degrees, and the wrist position is higher than the elbow, which meets the characteristic of "forearm bent upward". At the same time, the wrist is located in front of the chest, and it is determined that "the arm is in a bent holding posture".

[0099] Therefore, by quantifying the degree of arm flexion and grip position, it is possible to effectively distinguish whether a passenger is holding an electronic device, thereby improving the accuracy and confidence of the vehicle lighting control system in judging the use of electronic devices.

[0100] Optionally, calculating the global average brightness of the in-vehicle panoramic image includes:

[0101] Step S133: Convert the in-vehicle panoramic image to the target color space and extract the luminance component image from the target color space.

[0102] Step S134: Obtain the brightness value of the pixel in the brightness component image.

[0103] Step S135: The brightness values ​​of the pixels are summed to obtain the total brightness value.

[0104] Step S136: Determine the global average brightness based on the sum of the brightness values.

[0105] In this embodiment, the vehicle lighting control system first converts the in-vehicle panoramic image to a target color space and extracts the luminance component image from the target color space. The target color space refers to a color model that decomposes image color information into luminance and chrominance components, facilitating the separate processing of light intensity. The target color space may include a luminance / chrominance component format (YUV), a color difference component format (YCbCr), or a hue, saturation, and value model (Hue, Saturation, Value, HSV), etc. Specifically, in the YUV color space, the Y channel specifically represents luminance, while U and V represent chrominance.

[0106] A luminance component image is a grayscale image extracted from an original color image that contains only brightness and darkness information. Pixel values ​​can be used to directly reflect the light intensity at a given location. A luminance component image can be a single-channel matrix, and its pixel values ​​typically range from 0 to 255. Higher values ​​indicate brighter areas.

[0107] As can be seen, the vehicle lighting control system first receives the original panoramic image inside the vehicle, converts it from the default color space to the target color space, and then separates and extracts the luminance component representing the light intensity from the converted image data to generate a luminance component image that only reflects the distribution of light and dark inside the vehicle, in preparation for subsequent accurate calculation of luminance values.

[0108] For example, the vehicle lighting control system acquires a 1920x1080 Red-Green-Blue (RGB) panoramic image of the vehicle interior, calls a color conversion algorithm to convert it to YUV format, and then extracts the Y channel data to generate a grayscale image of the same resolution. This grayscale image is the luminance component image, where white areas represent highlights and black areas represent shadows.

[0109] Therefore, by converting the image to the target color space and extracting the luminance component, it is possible to effectively separate illumination information from color information, eliminate the interference of color on luminance calculation, and improve the robustness of global average luminance calculation.

[0110] Secondly, the vehicle lighting control system acquires the brightness values ​​of pixels in the brightness component image. A pixel is the smallest unit that makes up a digital image and is the basic data carrier of the brightness component image. For example, for an 8-bit brightness component image, the brightness value of a single pixel ranges from 0 to 255, where 0 represents pure black (no light) and 255 represents pure white (brightest). The number of pixels equals the total resolution of the image; for example, a 1920x1080 image contains 2,073,600 pixels.

[0111] The brightness value refers to the numerical value carried by each pixel in the brightness component image. It is usually an integer used to quantify the light intensity at the location of the pixel.

[0112] It can be seen that the vehicle lighting control system performs a traversal operation on the brightness component image, sequentially reading the brightness value corresponding to each pixel in the image, collecting these values ​​as independent data items, and forming a set of raw data containing the brightness information of all pixels.

[0113] Therefore, by obtaining the brightness value of each pixel individually, a complete and detailed data foundation is provided for subsequent averaging, ensuring the comprehensiveness of the statistical results.

[0114] Then, the vehicle lighting control system sums up the brightness values ​​of the pixels to obtain the total brightness value.

[0115] The total luminance value refers to the arithmetic sum of the luminance values ​​of all pixels in the luminance component image, reflecting the total amount of light energy in the entire image area. Accumulation refers to the mathematical operation of sequentially adding a series of values.

[0116] As can be seen, the vehicle lighting control system uses addition to accumulate the brightness values ​​of all pixels one by one, and calculates the sum of the brightness values ​​of all pixels in the entire brightness component image. This sum represents the total brightness contribution of the current in-vehicle panoramic image in terms of numerical value.

[0117] Therefore, by calculating the sum of brightness values, the data structure is simplified.

[0118] Finally, the vehicle lighting control system determines the global average brightness based on the sum of the brightness values. The global average brightness is the arithmetic mean of the brightness values ​​of all pixels in the brightness component image, used to characterize the overall intensity level of the ambient light inside the vehicle.

[0119] As can be seen, the vehicle lighting control system acquires the total number of pixels in the brightness component image, divides the sum of the brightness values ​​by the total number of pixels, and performs a division operation to obtain the global average brightness value. This value is the final basis for subsequent judgment of whether the environment is dark.

[0120] For example, the vehicle lighting control system has a known total brightness value of 1,500,000 and a total image pixel count of 1,000,000 (approximately 2 million pixels for 1920x1080, simplified for this example). The vehicle lighting control system executes... This yields a global average brightness of 1.5 (if normalized) or an actual Lux value, such as 15 lux, based on the specific scaling ratio.

[0121] This condenses complex image lighting information into a single, intuitive value, enabling the vehicle lighting control system to quickly determine whether the current interior environment is dim, thus improving the response speed and decision-making efficiency of the vehicle lighting control system.

[0122] Optionally, calculating the average brightness of a local area in the in-vehicle panoramic image includes:

[0123] Step S137: Use an image segmentation algorithm to segment the panoramic image inside the vehicle to obtain multiple local regions.

[0124] Step S138: Determine the average brightness of any local area among multiple local areas.

[0125] In this embodiment, the vehicle lighting control system utilizes an image segmentation algorithm to segment the panoramic image inside the vehicle, obtaining multiple local regions. The image segmentation algorithm is a computer vision processing technique designed to divide a digital image into multiple non-overlapping regions with similar features (such as color, texture, brightness, or semantic content). Image segmentation algorithms can use deep learning-based semantic segmentation models, superpixel-based segmentation methods, etc. A local region refers to a subset of the image generated by the segmentation algorithm, representing a specific spatial location or object in the vehicle's interior scene, such as a passenger's head area, hand area, or seat area. The specific shape of a local region might be a circular mask surrounding the passenger's face, an irregular polygon covering the hand, or a rectangular grid divided according to the seat position. For example, the algorithm might segment the panoramic image into a left rear seat area, a right rear seat area, and a central aisle area.

[0126] As can be seen, the vehicle lighting control system calls a preset image segmentation algorithm to classify or divide the input in-vehicle panoramic image at the pixel level, identify independent blocks with different semantic or spatial attributes in the image, and thus decompose the originally continuous panoramic image into a set of several non-overlapping local regions, laying the foundation for subsequent brightness analysis of specific regions.

[0127] For example, the vehicle lighting control system uses a semantic segmentation model to process the rear panoramic image. The model identifies semantic tags such as "passenger A's head", "passenger A's hand", and "passenger B's head", and divides the panoramic image into these specific local regions. Each region contains only the pixel data of the corresponding semantic part.

[0128] Therefore, by segmenting the panoramic image into local regions, the vehicle lighting control system can independently assess the lighting conditions at different locations inside the vehicle, avoiding interference from global lighting on the brightness judgment of key local areas, and improving the pertinence and accuracy of subsequent local brightness calculations.

[0129] The vehicle lighting control system then determines the average brightness of any one of the multiple local regions. Here, any local region refers to any sub-region in the segmentation result set, such as a specific passenger's head or hand area. If the hand area contains 1000 pixels and its total brightness value is 50,000, then the average brightness of that local region is 50 lux.

[0130] As can be seen, the vehicle lighting control system traverses any one of the multiple local areas, extracts the pixel data within that area, calculates the sum of these pixel brightness values ​​and divides it by the number of pixels, thereby obtaining the average brightness value of that specific local area, which is used to characterize the illumination level of that local space.

[0131] Therefore, by calculating the average brightness of a local area, it is possible to accurately capture the lighting details near the passenger's hand or the screen, effectively distinguishing local high brightness from the brightness of the surrounding environment. This provides key quantitative evidence for subsequent judgment on whether the passenger is using the high-brightness screen in a dim environment, and enhances the sensitivity of the vehicle lighting control system to recognize specific behavioral scenarios.

[0132] Optionally, the method further includes:

[0133] Step S15: If the object inside the vehicle is in the posture of using electronic devices, candidate local regions are selected based on the local average brightness and the global average brightness, wherein the local average brightness of the candidate local region is higher than the global average brightness.

[0134] Step S16: Spatial overlap comparison is performed between the spatial coordinates of the candidate local region and the spatial coordinates of the current pose to obtain the overlap ratio.

[0135] Step S17: If the overlap ratio is higher than the second threshold, it is determined that the object inside the vehicle is using an electronic device.

[0136] In this embodiment, if an object inside the vehicle is in a posture of using electronic devices, the vehicle lighting control system will filter candidate local regions based on the average brightness of local areas and the global average brightness, wherein the average brightness of the candidate local regions is higher than the global average brightness. A candidate local region refers to a set of sub-regions with higher luminous characteristics retained after brightness filtering from multiple local regions. For example, if the global average brightness is 20 lux, the average brightness of local region A is 15 lux, and the average brightness of local region B is 120 lux, then local region B is selected as a candidate local region.

[0137] As can be seen, after the vehicle lighting control system obtains the average brightness value of each local area, it compares it with the global average brightness one by one, eliminates areas with brightness lower than or equal to the background brightness, and retains only those areas with local brightness significantly higher than the average level of the environment as candidate local areas, thereby initially locking in the bright objects that may exist in the picture.

[0138] Therefore, by introducing global brightness as a benchmark for screening, interference caused by ambient light reflection or bright background objects can be effectively eliminated, initially focusing on significant luminous targets in the image, narrowing the search range for subsequent spatial comparison, and improving the computational efficiency and anti-interference ability of the recognition algorithm.

[0139] Then, the vehicle lighting control system compares the spatial coordinates of the candidate local region with the spatial coordinates of the current posture to obtain the overlap ratio. Here, the spatial coordinates refer to the geometric position information of the local region on the two-dimensional plane of the image. The spatial coordinates can be represented by the coordinates of a rectangle [x1, y1, x2, y2], for example, the coordinates of the hand region are [100, 200, 150, 250].

[0140] Spatial overlap comparison refers to calculating the proportion of the overlapping area of ​​two spatial regions on the image plane to the area of ​​a certain region. The overlap ratio refers to the degree of overlap between the candidate local region and the current pose region at the pixel level. The overlap ratio can be quantified by calculating the intersection area divided by the union area or the intersection area divided by the candidate region area. The value ranges from 0 to 1. For example, if the candidate region completely overlaps with the hand region, the overlap ratio is 1.0.

[0141] As can be seen, the vehicle lighting control system matches the geometric position data of the candidate local area with the geometric position data of the passenger's current posture, calculates the spatial overlap between the two on the image plane, and obtains a quantified overlap ratio value, which is used to evaluate whether the bright object is within the passenger's effective operating range.

[0142] Therefore, by comparing spatial overlap, it is ensured that the identified light source is indeed the device being used by the passenger, rather than other irrelevant bright objects inside the vehicle (such as streetlights outside the window), thus improving the spatial logic accuracy of behavior judgment.

[0143] If the overlap ratio exceeds a second threshold, the vehicle lighting control system will determine that an object inside the vehicle is using electronic equipment. The second threshold is a preset critical value used to determine the spatial overlap, assessing whether the overlap between the candidate region and the pose region is sufficiently close to confirm that behavior has occurred. The specific value of the second threshold can be set based on experimental data, for example, 0.6, 0.7, or 0.8. If the overlap ratio is higher than 0.7, it is determined as "using electronic equipment"; if it is lower than 0.7, it may be determined as a "false alarm" or "no behavior".

[0144] As can be seen, the overlap ratio is compared with the preset second threshold. If the overlap ratio is greater than or equal to the second threshold, it is considered that the height of the bright object is consistent with the height of the passenger's hand / head, thus finally determining that the object in the vehicle is in the state of using electronic devices, and triggering the subsequent lighting control logic.

[0145] Therefore, by setting an overlap ratio threshold for the final decision, high-brightness interference items with mismatched spatial positions are effectively filtered out, ensuring that the vehicle lighting control system only activates when it is confirmed that a passenger is using a mobile phone.

[0146] Optionally, controlling the target lighting device to illuminate the target area includes:

[0147] Step S141: Obtain the screen color temperature of the electronic device and adjust the output color temperature of the target lighting device according to the screen color temperature.

[0148] Step S142: After adjusting the output color temperature of the target lighting device, determine the projection angle based on the position of the target lighting device and the position of the electronic device.

[0149] Step S143: Control the target lighting device to illuminate the target area according to the projection angle.

[0150] In this embodiment, the vehicle lighting control system first obtains the screen color temperature of the electronic device and adjusts the output color temperature of the target lighting device according to the screen color temperature.

[0151] Screen color temperature refers to the color characteristics of the light emitted by an electronic device's display screen, usually measured in Kelvin (K), reflecting the warmth or coolness of the light. The color temperature range of common electronic screens is typically between 3000K (warm yellow light) and 6500K (cool white light). For example, in night mode, the screen may display a neutral color of 4500K.

[0152] The output color temperature of a target lighting device refers to the color characteristics of the light emitted by the vehicle's intelligent lighting system. Vehicle lighting devices can achieve different color temperatures, such as 3000K, 4000K, and 5000K, through LED light mixing or single-color-temperature LEDs. Adjusting the output color temperature involves changing the spectral distribution or RGB channel ratio of the lighting source via a controller to match or harmonize the emitted light color with the screen color. This adjustment process may involve changes to the Pulse Width Modulation (PWM) signal or digital signal control.

[0153] As can be seen, the vehicle lighting control system first identifies or obtains the color temperature value of the screen of the electronic device currently in use, and then uses this value as a reference to adjust the color temperature of the target lighting device's output light to a value that is consistent with or similar to the color temperature of the screen, so as to achieve a harmonious unity of visual color between the light source and the screen.

[0154] For example, the vehicle lighting control system detects that the passenger's mobile phone screen is currently in nighttime eye protection mode, with a screen color temperature of 3200K (warm yellow). The control module then instructs the lighting device located above the passenger's head to adjust its LED beads to output 3200K warm yellow light, so that the color of the light shining on the passenger's hands and screen is consistent with the color of the screen light.

[0155] Therefore, by matching the screen color temperature with the lighting color temperature, visual discomfort or glare caused by large differences in color temperature is avoided, providing passengers with a consistent and soft local lighting environment and improving viewing comfort.

[0156] Then, after adjusting the output color temperature of the target lighting device, the vehicle lighting control system determines the projection angle based on the position of the target lighting device and the position of the electronic equipment.

[0157] The projection angle refers to the angle between the central axis of the light beam of the illumination device and a reference plane (such as a horizontal or vertical plane). It determines the direction and spatial distribution of the light illumination. Determining the projection angle means calculating the optimal light illumination direction based on the spatial relative position of the light source and the target. For example, the projection angle can be expressed in polar coordinates or as pitch and yaw angles. For instance, a pitch angle of -45 degrees indicates that the light beam is tilted downwards by 45 degrees. Calculating the projection angle usually involves obtaining the direction vector through vector subtraction, and then calculating the angle using the arctangent function.

[0158] It can be seen that after adjusting the color temperature, the vehicle lighting control system obtains the fixed installation coordinates of the target lighting device inside the vehicle and the real-time spatial coordinates of the electronic device. Through geometric calculation, it obtains the direction vector from the lighting device to the electronic device, and calculates the angle of the lens that the lighting device needs to rotate or adjust to ensure that the beam can accurately cover the target area.

[0159] For example, the lighting device is installed at the center coordinates (0, 0, 1.2) of the rear roof, and a mobile phone is detected in the hand of the passenger in the right rear seat at coordinates (0.5, 0.3, 0.9). The vehicle lighting control system calculates the vector from (0, 0, 1.2) to (0.5, 0.3, 0.9), and determines that the beam needs to be deflected to the right and tilted downwards by a certain angle. Finally, the projection angle is determined to be 15 degrees to the right and 30 degrees downwards.

[0160] Therefore, by precisely calculating the projection angle, the light is ensured to illuminate only the mobile phone and hand areas that need to be illuminated, avoiding light scattering into the driver's line of sight, the faces of other passengers, or non-target areas, thus improving lighting efficiency and reducing interference with others.

[0161] Finally, the vehicle lighting control system controls the target lighting device to illuminate the target area according to the projection angle.

[0162] As can be seen, the vehicle lighting control system drives the target lighting device to perform actions based on the projection angle, adjusts its light output direction, and projects the light at a specified angle onto the target area defined by the position of the electronic device, thereby completing the directional supplementary lighting for passengers using mobile phones.

[0163] For example, the vehicle's lighting control system can send a command to a micro-servo motor within the lighting unit, causing it to rotate 15 degrees to the right and 30 degrees downward. The lighting unit then emits a beam of warm yellow light, precisely projecting it onto the mobile phone screen and hands of the passenger in the right rear seat, forming a bright and well-defined spot of light, while the surrounding area remains relatively dark.

[0164] Thus, localized directional lighting is achieved by executing precise angle control.

[0165] Optionally, the method further includes:

[0166] Step S18: In response to the target lighting device being turned on, start the timer.

[0167] Step S19: If the recording duration of the timer exceeds the third threshold, control the audio device to play a prompt voice and reset the timer. The prompt voice is used to remind people in the car to pay attention to their screen time and take a break.

[0168] In this embodiment of the application, when the target lighting device is turned on, the vehicle lighting control system starts a timer.

[0169] It can be seen that when the vehicle lighting control system determines that a passenger is using a mobile phone in a dim environment and turns on the rear reading light, the control module simultaneously calls the timer function, sets the initial value of the timer to 0, and starts to accumulate in increments of 1 second. At this time, the timer displays "00:00:01", "00:00:02", etc., recording the duration of the lighting.

[0170] Therefore, by introducing a timing mechanism, the vehicle lighting control system can quantify the time passengers spend continuously using electronic devices, monitor eye health, and provide a data basis for subsequent proactive health interventions.

[0171] When the recording duration of the timer exceeds the third threshold, the vehicle lighting control system will control the audio equipment to play a prompt voice and reset the timer. The prompt voice is used to remind people in the vehicle to pay attention to the duration of eye use and to take a break.

[0172] The third threshold refers to a preset time threshold used to define the standard for prolonged eye use. Exceeding this value is considered to pose a risk of visual fatigue. The specific value of the third threshold can be set according to medical advice or user experience, such as 15 minutes, 30 minutes, or 45 minutes.

[0173] The prompt voice refers to a pre-recorded or synthesized audio file containing health tips such as reminding users to pay attention to eye hygiene and suggesting breaks, for example, "You have been using your phone for 15 minutes. We suggest you rest your eyes and look into the distance to relax." Voice playback can be achieved through the car audio system, headrest speakers, or voice assistant module. Resetting the timer means clearing the current accumulated value of the timer to zero, returning it to its initial state to prepare for the next lighting cycle.

[0174] As can be seen, the vehicle lighting control system continuously monitors the recording duration of the timer. Once the detected duration exceeds the preset third threshold, it determines that the user has been using their eyes for an extended period of time. At this time, it controls the in-vehicle audio equipment to play a preset health reminder voice message, and after the voice message is played (or simultaneously), it resets the timer value to zero, ends the current cycle, and waits for the next trigger.

[0175] For example, the vehicle lighting control system presets a third threshold of 15 minutes. When the timer accumulates 15 minutes, the vehicle lighting control system triggers an alarm logic and plays a 10-second voice message through the vehicle's speaker: "Friendly reminder, you have been using your mobile phone continuously for 15 minutes. Please take a break and protect your eyesight." After the message finishes playing, the vehicle lighting control system resets the timer value to 0 and begins recording the time for the next lighting activation.

[0176] Therefore, by setting time thresholds and executing voice reminders, passengers can be effectively reminded to pay attention to eye hygiene and relieve visual fatigue.

[0177] The vehicle lighting control method provided in this application can solve three major pain points of existing rear seat lighting equipment in vehicles: "cannot automatically turn on the lights", "cannot provide local lighting", and "cannot be linked to passenger behavior".

[0178] Specifically, this application overcomes the shortcomings of existing lighting systems that rely on manual operation and cannot autonomously decide and activate lighting when the environment is dim and passengers require illumination, leading to user experience disruption and operational burden. This application also overcomes the shortcomings of existing lighting solutions that mostly use floodlighting, resulting in a large light diffusion range and a lack of directional control, inevitably causing visual interference to other occupants while illuminating the target area. Furthermore, this application overcomes the shortcomings of traditional systems where lighting control logic is completely disconnected from the actual activity state of occupants, failing to provide lighting based on behavioral recognition results.

[0179] Figure 2 This is a schematic diagram illustrating the steps of a vehicle lighting control method according to an embodiment of this application. This method can solve the problem of automatic supplemental lighting for rear-seat passengers using electronic devices in dimly lit environments, taking a mobile phone as an example. Figure 2 As shown, the feature includes the following steps:

[0180] Step S21, dual condition perception: The ambient light intensity inside the vehicle is perceived in real time by the ambient light sensor and compared with the preset dimness threshold and timed; the in-vehicle image acquisition device is used to identify whether the rear passengers are using mobile phones.

[0181] Step S22, Linked Decision Making and Parameter Matching: When the two conditions of "ambient light continuously below the threshold" and "passenger using a mobile phone" are met successively, a smart lighting instruction is generated. This instruction includes at least: matching a preset target beam projection angle based on the identified passenger's location; and matching a preset lighting source color temperature that is compatible with the color temperature of the electronic device screen.

[0182] Step S23, Directional light output and control: Control an adjustable directional lighting device to operate according to instructions, directing a beam of light with an appropriate color temperature to cover the upper body area of ​​the target passenger according to the projection angle.

[0183] Step S24, Status Monitoring and Exit: During lighting output, continuously monitor the above dual conditions; when either condition is no longer met, control the lighting device to turn off.

[0184] Therefore, this application achieves a shift from "passive manual" to "active intelligent" lighting control by automatically recognizing rear-seat passengers using their mobile phones, solving the problems of rigidity and detachment from practical use cases in traditional lighting methods. Simultaneously, the vehicle lighting control system, through precise directional localized lighting, confines the light to the area where passengers need to move, providing effective supplementary lighting while completely avoiding interference with other areas inside the vehicle, achieving intelligent zoning of the lighting environment and an overall improved experience.

[0185] Figure 3 This is a flowchart illustrating a vehicle lighting control method according to an embodiment of this application, as shown below. Figure 3 As shown, the vehicle lighting control system first starts and initializes. Once the vehicle starts, the vehicle lighting control system is ready. Whether driving or resting, the interior lighting equipment can provide automatic service to the user as long as the triggering conditions are met.

[0186] Secondly, the vehicle lighting control system determines whether the interior environment is dim. An ambient light sensor integrated into the rear roof collects real-time ambient light data and periodically samples the light signal at a preset frequency (e.g., 10Hz) to obtain a raw light intensity sequence. After digital filtering, a stable and reliable real-time ambient light intensity value is obtained. Furthermore, the vehicle lighting control system has preset dimness thresholds (e.g., 150 lux) and minimum duration thresholds (e.g., 2 seconds). During operation, the lighting control system continuously compares the filtered real-time ambient light intensity with the dimness thresholds. When the detected light intensity is below the dimness threshold, the vehicle lighting control system starts an internal timer. If the light intensity remains below this threshold in subsequent sampling cycles, and the cumulative duration reaches or exceeds the preset minimum duration threshold, the vehicle lighting control system ultimately determines that the "interior environment is continuously dim." Conversely, if the light intensity rises above the threshold within the specified duration, the timer is reset, and no determination is triggered.

[0187] Next, the vehicle's lighting control system determines the user's posture while using a mobile phone. When the system determines that the interior environment is dimly lit, requiring localized lighting, it activates a passenger posture recognition technology to intelligently determine whether a rear passenger is using a mobile phone, thus deciding whether to trigger subsequent directional lighting.

[0188] Specifically, this application references and employs a vision-based passenger posture recognition method. This passenger posture recognition system is configured to perform the following steps:

[0189] Step S301, Module Activation and Initialization: Upon successful detection of a dim environment, the passenger posture recognition system automatically activates the passenger posture recognition module. The passenger posture recognition module initiates the preset in-vehicle image acquisition device (e.g., the OMS located in the rear roof) and calls or initializes the pre-installed target detection and posture recognition algorithm model, putting the passenger posture recognition system into the intelligent lighting decision-ready state.

[0190] Step S302, Posture Recognition and Judgment: The image acquisition device acquires real-time images of the rear passenger area. The passenger posture recognition system analyzes the image using a posture recognition algorithm model, the core of which is to identify whether the passenger is exhibiting a typical posture of using a mobile phone. This judgment can be based on a combination of one or more features, such as, but not limited to: detecting that the passenger is holding a rectangular object with a typical screen aspect ratio; recognizing that the passenger's head is in a downward posture and the direction of their gaze is pointing towards the area of ​​the held object; recognizing that the passenger's arm is in a bent grip posture. When the above features are continuously recognized to the preset confidence and duration thresholds, the passenger posture recognition system ultimately determines that the rear passenger is using a mobile phone.

[0191] To ensure accurate identification of passengers actively using their phones (e.g., operating with the screen on) rather than passively holding them (e.g., resting with the screen off or listening to music), this application, in addition to recognizing the holding posture, further introduces a brightness difference judgment mechanism between the screen and the environment. Specifically, the passenger posture recognition system uses the rear-seat OMS camera to capture panoramic images of the carriage and extracts its brightness components (e.g., the Y component in the YUV color space). This is used to calculate the global average brightness (L_global) of all pixels in the image, serving as a benchmark for characterizing the overall illumination level inside the vehicle. The OMS divides the panoramic view into several local regions using an image segmentation algorithm, calculates the average brightness (L_local) of each region, and identifies locally bright areas that are significantly brighter than the environmental benchmark by comparing the difference between L_local and L_global. This brightness difference detection method is based on mature image processing technology and will not be elaborated further here.

[0192] When the bright area identified by OMS (Optical Mode System) and the area where a person is using their phone overlaps spatially, the passenger posture recognition system can accurately determine that a rear passenger is using their phone in a dimly lit environment, thus triggering subsequent lighting.

[0193] Subsequently, the system activates the lighting devices to provide supplemental lighting. When rear passengers use their mobile phones in dimly lit environments, the vehicle's lighting control system automatically activates and controls the lighting devices to provide localized, directional auxiliary lighting. The lighting devices are installed on the rear ceiling of the vehicle, corresponding to the number of rear seats: two lighting devices are installed if there are two rear seats, and three lighting devices are installed if there are three rear seats, ensuring that each seat has an independent lighting unit.

[0194] The lighting uses a preset color temperature, which is close to the color temperature range of common electronic device screens (e.g., 3000K). The purpose is to reduce the visual conflict between the screen and the ambient light from the light source spectrum, create a local environment with a consistent color temperature for the human eye, and fundamentally improve viewing comfort.

[0195] To achieve the goal of illuminating the target passenger without affecting others, the vehicle's lighting control system performs directional projection control: based on the posture recognition module, the system determines the location of the target passenger. The system then directs the illumination beam to the upper body area of ​​the target passenger, creating a light spot covering their screen and hands. Overflow light is effectively limited, thus achieving spatial zoning of the light and avoiding interference with the driver's vision and that of other passengers.

[0196] Then, the system activates voice prompts. When the lighting is turned on, the vehicle's lighting control system simultaneously starts a dedicated timer, accumulating the user's continuous screen time from the moment the lighting is turned on. If the timer reaches a preset threshold (e.g., 15 minutes), the vehicle's lighting control system will automatically activate the in-vehicle voice interaction module, playing a pre-set health reminder voice message to remind the user to pay attention to the duration of continuous screen time and suggest taking breaks to guide the user to stop the current activity. After the voice message finishes playing, the vehicle's lighting control system automatically resets the timer, clearing the accumulated time to zero.

[0197] Finally, the system also needs to monitor lighting maintenance conditions.

[0198] During dynamic tracking, the vehicle lighting control system simultaneously monitors whether the user's valid behavior is still ongoing and whether the ambient light inside the vehicle is still dim. The system continues lighting tracking only when both conditions are met: "continued behavior" and "dim ambient light." If either condition is no longer met, the system determines that lighting needs to be terminated. When the termination condition is met, the vehicle lighting control system shuts off the lighting device. Finally, the entire vehicle lighting control system resets, returning to ambient monitoring mode, awaiting the next trigger.

[0199] This vehicle lighting control system centers on seamless service. While supporting traditional voice control and manual switching to fully respect individual user preferences, it can automatically recognize user behavior. The system continuously monitors the in-vehicle lighting environment and occupants' eye use. When it detects prolonged mobile phone use in dim lighting, it not only alleviates visual strain through adaptive supplemental lighting but also proactively initiates a voice reminder when the duration exceeds a set threshold, guiding the user to take a break. This demonstrates the system's human-centered approach to visual health. Thus, the vehicle lighting control system achieves fully autonomous service from environmental perception and intent understanding to health intervention, spectral adaptation, and spatially confined lighting. This essentially transforms general in-vehicle lighting into a system that adapts to visual physiology, considers individual needs, prioritizes passenger safety, and provides eye-care.

[0200] Figure 4 This is a schematic diagram of a vehicle lighting layout according to an embodiment of this application, such as... Figure 4 As shown, the Figure 4 Taking a top-down view of the rear passenger compartment as an example, the diagram illustrates the corresponding installation relationship between the rear seats and the overhead lighting devices. In the illustrated embodiment, the rear seats are arranged in a two-seat layout, with a first lighting device and a second lighting device independently installed on the headliner corresponding to the left and right rear seats, respectively. The first lighting device is located directly above or offset from the left rear seat, and the second lighting device is located directly above or offset from the right rear seat. Each lighting device is spatially independent and does not interfere with the others. Furthermore, each device's beam projection range primarily covers the passenger area on its corresponding seat. This ensures that when a passenger in one seat is using a mobile phone, the corresponding lighting device is activated for directional supplemental lighting, while the lighting device on the other side remains off, preventing light from interfering with other occupants or the driver. This achieves personalized and localized control of the lighting environment.

[0201] Figure 5 This is a structural block diagram of a vehicle lighting control device according to an embodiment of this application, such as... Figure 5 As shown, taking a vehicle lighting control device 500 as an example, the device includes: a first acquisition module 501, used to acquire the ambient light intensity value inside the vehicle; a second acquisition module 502, used to acquire an object posture image of an object inside the vehicle and a panoramic image inside the vehicle if the ambient light intensity value inside the vehicle is lower than a first threshold and the duration is greater than a first duration; a detection module 503, used to perform electronic device usage detection on the object posture image, obtain a detection result, calculate the global average brightness of the panoramic image inside the vehicle, and calculate the local average brightness of the panoramic image inside the vehicle, wherein the detection result is used to indicate whether the object inside the vehicle is in a posture of using electronic devices; and a determination module 504, used to turn on the target lighting device corresponding to the seat where the object inside the vehicle is sitting if it is determined based on the detection result, the global average brightness, and the local average brightness, and the target lighting device illuminates the target area, wherein the target area covers the electronic device and the hand of the object inside the vehicle.

[0202] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this application when it runs.

[0203] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0204] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0205] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0206] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application.

[0207] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0208] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0209] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0210] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0211] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0212] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A vehicle lighting control method, characterized in that, The method includes: Obtain the ambient light intensity value inside the vehicle; If the ambient light intensity value inside the vehicle is lower than the first threshold and the duration is greater than the first duration, acquire the object pose image of the object inside the vehicle and the panoramic image inside the vehicle. Electronic device usage detection is performed on the object's pose image to obtain detection results. The global average brightness of the in-vehicle panoramic image and the local average brightness of the in-vehicle panoramic image are calculated. The detection results are used to indicate whether the object in the vehicle is in a pose of using an electronic device. If, based on the detection results, the global average brightness, and the local average brightness, it is determined that the object inside the vehicle is using the electronic device, the target lighting device corresponding to the seat where the object is sitting is turned on, and the target lighting device is controlled to illuminate the target area, wherein the target area covers the electronic device and the hand of the object inside the vehicle.

2. The method according to claim 1, characterized in that, The acquisition of the in-vehicle ambient light intensity value includes: By using an ambient light sensor integrated in the rear roof of the vehicle, the ambient light signal inside the vehicle is sampled according to a preset frequency to obtain an ambient light intensity sequence inside the vehicle. The in-vehicle ambient light intensity sequence is digitally filtered to obtain the in-vehicle ambient light intensity value.

3. The method according to claim 1, characterized in that, The electronic device usage detection performed on the object's pose image yields the following detection results: The pose recognition model is used to perform pose analysis on the pose image of the object to obtain the analysis result, wherein the analysis result is used to represent the current pose of the object inside the vehicle; The analysis results are compared with the preset pose set to obtain the detection results.

4. The method according to claim 3, characterized in that, The preset posture set includes at least one of the following: the person inside the vehicle is holding a rectangular object with a preset aspect ratio, the person inside the vehicle is looking down with their gaze directed toward the area of ​​the object being held, and the person inside the vehicle is holding the object with their arm bent.

5. The method according to claim 1, characterized in that, The calculation of the global average brightness of the in-vehicle panoramic image includes: The in-vehicle panoramic image is converted to a target color space, and the luminance component image in the target color space is extracted. Obtain the brightness value of the pixel in the brightness component image; The brightness values ​​of the pixels are summed to obtain the total brightness value; The global average brightness is determined based on the sum of the brightness values.

6. The method according to claim 1, characterized in that, The calculation of the average brightness of a local area in the panoramic image inside the vehicle includes: The in-vehicle panoramic image is segmented using an image segmentation algorithm to obtain multiple local regions; Determine the average brightness of any one of the plurality of local regions.

7. The method according to claim 4, characterized in that, The method further includes: If the object inside the vehicle is in a posture of using the electronic device, candidate local regions are selected based on the average brightness of the local region and the average brightness of the global region, wherein the average brightness of the local region of the candidate local region is higher than the average brightness of the global region. The spatial coordinates of the candidate local region are compared with the spatial coordinates of the current attitude to obtain the overlap ratio. If the overlap ratio is higher than the second threshold, it is determined that the object inside the vehicle is using the electronic device.

8. The method according to claim 1, characterized in that, The control of the target lighting device to illuminate the target area includes: The screen color temperature of the electronic device is obtained, and the output color temperature of the target lighting device is adjusted according to the screen color temperature; After adjusting the output color temperature of the target lighting device, the projection angle is determined based on the position of the target lighting device and the position of the electronic device; Control the target lighting device to illuminate the target area according to the projection angle.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: In response to the target lighting device being turned on, a timer is started; If the recording duration of the timer exceeds the third threshold, the audio device is controlled to play a prompt voice, and the timer is reset. The prompt voice is used to remind the person in the vehicle to pay attention to the duration of eye use and to take a break.

10. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the vehicle lighting control method according to any one of claims 1 to 9.

Images