Vehicle rearview mirror adjusting method and device, storage medium and program product

Abstract

One or more embodiments of the present application provide a rearview mirror adjustment method and apparatus, a storage medium and a program product, the method comprising: acquiring visual information of a driver, the visual information being used for representing a visual focus orientation of the driver; determining a target rearview mirror which the driver intends to adjust according to the visual information; and in response to a received adjustment instruction, executing an adjustment operation on the target rearview mirror. According to the method, intuitive operation is achieved, the transfer of sight and attention of a driver from a front road in the adjusting process is reduced, the driving safety is effectively improved, meanwhile, the operation complexity and the misoperation possibility are reduced, and rearview mirror fine adjustment in the driving process becomes more convenient.

Description

TECHNICAL FIELD

[0001] One or more embodiments of the present application relate to the technical field of vehicle control, and in particular to a rearview mirror adjustment method and device for a vehicle, a storage medium and a program product. BACKGROUND

[0002] Modern cars are generally equipped with electrically adjustable outside rearview mirrors. The traditional adjustment method relies on a physical control module on the driver's side door panel, which usually includes a switch for selecting the left or right rearview mirror and a multi-directional adjustment rocker. The driver must manually operate the selection switch to select the target rearview mirror and then adjust the angle through the rocker. This operation logic requires the driver's line of sight and attention to be diverted from the road ahead to the door panel control area, which poses a significant safety hazard during driving. Meanwhile, the two-step operation procedure is cumbersome and prone to misoperation, and it is extremely inconvenient to make fine adjustments while the vehicle is moving. There has been an urgent need in the industry for a more intuitive, safe and convenient adjustment solution.

[0003] In related technologies, rearview mirror adjustment buttons are usually integrated into the steering wheel to reduce the movement distance and operation difficulty of the driver's hands. However, these improved solutions have not essentially simplified the core operation logic: the driver still needs to manually trigger a "selection" function to specify the target rearview mirror first, and then perform angle adjustment. Therefore, the driver's attention is still diverted from the driving task to locate and operate specific selection buttons, and the fundamental problems of safety hazards and cumbersome operation steps have not been completely solved. SUMMARY

[0004] Therefore, one or more embodiments of the present application provide technical solutions as follows: According to a first aspect of one or more embodiments of the present application, a rearview mirror adjustment method for a vehicle is provided, comprising: obtaining visual information of a driver of the vehicle, the visual information being used to represent the visual focal point position of the driver; determining a target rearview mirror intended to be adjusted by the driver in the vehicle according to the visual information; performing adjustment operation on the target rearview mirror in response to the received adjustment instruction. According to a second aspect of the present application, a computer-readable storage medium is provided, which stores a computer program, and the program is executed by a processor to implement the steps of the method of the first aspect.

[0005] According to a third aspect of the present application, a computer program product is provided, which includes computer programs / instructions that are executed by a processor to implement the steps of the method of the first aspect.

[0006] From the above embodiments, it can be seen that the application determines the target rearview mirror intended to be adjusted by the driver according to the acquired visual information of the driver, so that the driver no longer needs to manually perform the operation step of selecting the rearview mirror, thereby fundamentally simplifying the adjustment process. In other words, the method converts the natural line-of-sight direction of the driver into an explicit adjustment instruction, realizes intuitive operation, reduces the diversion of the line-of-sight and attention of the driver from the front road in the adjustment process, and effectively improves the driving safety. At the same time, since the independent selection step is omitted and the adjustment is allowed to be triggered in multiple ways, the method also reduces the operation complexity and the possibility of misoperation, so that it becomes more convenient to make fine adjustment of the rearview mirror during driving. BRIEF DESCRIPTION OF DRAWINGS

[0007] Figure 1 is a rearview mirror adjustment system architecture diagram shown by an embodiment of the application; Figure 2 is a flowchart of a rearview mirror adjustment method of a vehicle shown by an embodiment of the application; Figure 3 is a specific architecture diagram of a rearview mirror adjustment system of a vehicle shown by an embodiment of the application; Figure 4 is a flowchart of another rearview mirror adjustment method of a vehicle shown by an embodiment of the application; Figure 5 is a schematic structural diagram of an electronic device shown by an embodiment of the application; Figure 6 is a block diagram of a rearview mirror adjustment device of a vehicle shown by an embodiment of the application. DETAILED DESCRIPTION

[0008] The exemplary embodiments will be described in detail herein with reference to the attached drawings. When the description below refers to accompanying drawings, unless otherwise noted, the same numbers in different drawings refer to the same or similar elements. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the application.

[0009] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0010] It should be understood that, although the terms first, second, third, etc. can be employed in this application to describe various information, these information should not be limited to these terms. These terms are only used to differentiate one piece of information from another. For example, without departing from the scope of the application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0011] The user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards in the relevant region, and provide corresponding operation portal for user to choose authorization or refusal.

[0012] Figure 1 is a schematic diagram of an architecture of a rearview mirror adjustment system provided by an example embodiment. As shown, the system can at least include a vision acquisition device 12, a vision information processing device 14 and a rearview mirror adjustment device 16 in a vehicle 10. Figure 1

[0013] The vision acquisition device 12 is usually integrated in a position convenient for capturing the face region of the driver, such as the center of the steering wheel, the left and right spokes, the instrument panel or the A-pillar, and contains at least one face image sensor facing the driver, such as an infrared camera, a visible light camera or a 3D depth sensor, etc. Its main function is to continuously or triggeredly acquire image or video data containing the eye and head region of the driver, and provide these raw visual data to the subsequent processing unit as the basis for determining the visual focus position.

[0014] The vision information processing device 14 can be an electronic control unit (ECU) of the vehicle or a dedicated image processing module. The device receives raw data from the vision acquisition device 12, analyzes and processes the image by running the built-in algorithm or model; it can also send the data to a cloud server with stronger computing power through the vehicle-mounted network for processing, and return the result. Finally, the information representing the "visual focus position" of the driver is output, and based on this, the driver's intention to adjust the left, right or rearview mirror inside the vehicle is judged, so as to complete the intelligent selection of the target rearview mirror, replacing the traditional manual selection operation.

[0015] ​The rearview mirror adjustment device 16 can be further divided into two functional modules: one is an adjustment input module, such as a five-way rocker integrated on the steering wheel or central console, a touchpad, or a voice / gesture recognition interface, which is responsible for receiving specific adjustment instructions from the driver, such as orientation signals indicating up, down, left, and right; the second is a rearview mirror driving module, usually composed of a motor and a control circuit, which receives target rearview mirror selection signals from the visual information processing device 14 and adjustment instructions from the input module, drives the corresponding left and right outside rearview mirrors or interior rearview mirror to perform precise angle adjustment actions, thereby completing the entire adjustment process.

[0016] Figure 2 is a flowchart of a rearview mirror adjustment method of a vehicle according to an exemplary embodiment of the present application. As shown in Figure 2 the method can include the following steps: Step S202, obtaining visual information of a driver of a vehicle, the visual information being used to represent the visual focus position of the driver.

[0017] First, the relevant information containing the facial features of the driver can be captured by the on-board visual acquisition device, and by analyzing the key areas such as the eyes and head, the visual information representing the current visual focus position of the driver can be extracted. This information provides a basic input for subsequent intelligent judgment of the driver's adjustment intention.

[0018] Specifically, the process of obtaining the driver's visual information can be divided into the collection and analysis of facial images. The visual acquisition device can first capture static images or video frames containing the driver's facial region. Subsequently, the system can perform visual analysis processing on these image data, calculate the parameters representing the driver's line of sight direction or head orientation by extracting and analyzing the facial key features, and then comprehensively derive the visual focus position as the above-mentioned visual information.

[0019] Further, the above processing process calculates the driver's line of sight direction and / or head orientation by detecting and tracking facial features in the image, such as eye contours, pupil positions, head contours, and postures. Among them, the line of sight direction can be estimated by the relative position of the pupil and the eye reference point, and the head orientation can be obtained by the three-dimensional posture estimation technology. Based on the obtained line of sight direction and / or head orientation, the system determines the driver's visual focus position in the vehicle space coordinate system through geometric mapping, coordinate conversion, or data fusion, etc.

[0020] As will be appreciated by those skilled in the art, the visual information generated by the system as a quantitative representation of the driver's gaze intention can be characterized and delivered in the form of structured data. Specifically, it can be presented as directional parameters in the vehicle's spatial coordinate system, such as a three-dimensional vector representing the gaze direction, or in the form of Euler angles decomposed into horizontal and vertical pitch angles. This information can also be fused with auxiliary data such as confidence levels, time stamps, etc. to more accurately describe the projected position of the visual focus in the vehicle's environment, thereby providing a directly processable data basis for subsequent matching with predefined orientation regions of the side mirrors, or as an input to a classification model.

[0021] Furthermore, in order to accurately map the driver's physiological characteristics, i.e. the aforementioned gaze direction and head orientation, to a specific gaze position in the vehicle's environment, the system needs to employ appropriate determination logic depending on the data completeness and reliability in different situations. This process aims to provide an accurate and robust output of the visual focus position, the specific implementation of which includes but is not limited to the following cases: 1. When the system only successfully obtains or calculates valid gaze direction data, for example when the head pose is stable but the driver only observes the side by eye movement, the system will directly determine the driver's visual focus position based on the gaze direction through a pre-defined coordinate transformation model, such as converting the gaze vector in the eye coordinate system to the vehicle's global coordinate system. In this case, the gaze direction, as a direct reflection of the eye pointing, is considered the most accurate data source to express the visual intention.

[0022] 2. When the system only successfully obtains or calculates valid head orientation data, for example in certain lighting conditions or when facial features are partially obscured, making it difficult to extract eye features, the system will instead estimate and determine the driver's visual focus position based on the head orientation through a pre-defined statistical association model between head pose and gaze direction. At this time, the head orientation serves as a reliable alternative indicator of the general gaze direction.

[0023] 3. When the system simultaneously obtains valid gaze direction and head orientation data, and determines through calculation that the two are consistent in direction or the deviation is within a pre-defined tolerance threshold, it indicates that the driver's gaze behavior is coordinated. The system can optionally choose one of them, of course, the gaze direction with higher accuracy is usually preferred, or perform data fusion such as weighted averaging on both to determine the final visual focus position, thereby improving the stability and confidence of the result.

[0024] 4、When the system simultaneously obtains valid line-of-sight direction and head orientation data, but the two are inconsistent and the deviation exceeds the preset tolerance threshold, it indicates that the driver may be observing obliquely or that the data is temporarily abnormal. To ensure accurate judgment of the driver's true gaze intention, the system sets the line-of-sight direction as the priority basis to determine the visual focus position. This is based on the physiological principle that eye movement can more directly and agilely reflect the instantaneous direction of visual attention. It can be understood that this priority logic helps to accurately capture the driver's adjustment intention in complex situations, and is a key design to improve the accuracy and safety of the system.

[0025] In summary, the above multi-modal decision logic ensures that the system can generate reliable visual focus position information in various actual driving scenarios and under different data quality conditions, providing a solid foundation for subsequent intelligent recognition of the target rearview mirror.

[0026] It is worth mentioning that the present scheme introduces "rearview mirror adjustment starting condition" as an intelligent switch to trigger the subsequent adjustment process. This design means that all steps including this step in the present application are executed on the premise of meeting at least one starting condition, that is, before obtaining the visual information of the driver of the vehicle, it is required to determine that the preset rearview mirror adjustment starting condition is met. This pre-judgment mechanism is the default and necessary operation logic of the present scheme, and its core purpose is not only to optimize system resources, that is., to avoid the burden of computing power and power consumption caused by continuous operation, but more importantly, to solve a fundamental safety hazard: if this condition is not set, it means that the system will continuously perform visual intention recognition while the vehicle is driving. At this time, for example, the driver's normal observation behavior of checking the two side rearview mirrors to judge the road conditions, is easy to be misjudged as an adjustment intention by the system, resulting in accidental adjustment of the rearview mirror during vehicle driving, which seriously interferes with the driving view and may cause traffic accidents. Therefore, setting the starting condition is a necessary guarantee to prevent false triggering and ensure that the function is activated only in controlled scenarios from the perspective of safety design.

[0027] The starting condition is designed to capture the driver's explicit adjustment intention or typical scenarios where the vehicle enters a state that needs to be adjusted in multiple dimensions and multiple modalities, and its specific implementation includes but is not limited to the following three categories: The first type is driver-initiated instruction triggering: this condition corresponds to the driver's explicit and active adjustment intention expression. Specifically, when the above system receives the adjustment starting instruction triggered by the driver, it can be determined that the starting condition is met. The instruction usually comes from the driver's direct operation on the pre-set dedicated physical buttons in the vehicle, virtual controls on the touch screen, multi-function buttons on the steering wheel, or specific gestures. This way provides the most direct and reliable control entry for the driver, ensuring the certainty of function activation and the absolute authority of the user.

[0028] The second type is vehicle state automatic triggering: this condition is based on the change of the vehicle state, and the typical scenario is inferred that the rearview mirror may need to be adjusted. When the system detects that the preset vehicle state condition is met, the adjustment process is automatically triggered, wherein the vehicle state condition generally includes but is not limited to the following core scenarios: 1, vehicle power on / start: it means that the vehicle enters the power-on or start state from the off state, which usually means that a new driving cycle starts, and the driver needs to adjust the rearview mirror to the personal preferred position. 2, driver seating: the driver is detected to be seated through the seat pressure sensor or the vehicle-mounted camera, especially in combination with the vehicle supporting identity recognition, the system can infer that the new driver or the adjustment of the sitting posture may need to adjust the rearview mirror. 3, gear shifting: it is detected that the gear is switched from the parking gear (P gear) to the driving gear (such as D gear or R gear), which indicates that the vehicle is about to start moving, and at this time it is particularly important to ensure that the rearview mirror angle is correct for safety. By monitoring these key state nodes, the system can predict the demand and automatically enter the preparation state without the need for the driver to actively intervene, greatly improving the convenience.

[0029] The third type is driver visual intention pre-triggering: this way can determine the driver's visual focus by continuously providing the driver's visual focus position information through other vehicle systems such as independently running driver monitoring systems (DMS), and can determine that the driver's visual focus has been continuously in the position area associated with any rearview mirror for a preset time, for example, 2-3 seconds to trigger. Specifically, the visual focus data used for determination here is not temporarily initiated by this adjustment process, but comes from the data stream of other independently running systems, thereby decoupling the logic and resources from the subsequent "acquiring visual information" step. In other words, when the system determines that the driver continuously gazes at a certain rearview mirror position, it is inferred that there is a potential adjustment intention, thereby automatically activating the adjustment process, making the interaction process more smooth and intuitive.

[0030] The above three types of starting conditions can work independently, or can be logically combined according to design requirements, thereby jointly building a multi-level and three-dimensional trigger network. This ensures that the rearview mirror adjustment method can be activated at the most appropriate and safe time, fundamentally eliminating the risk of mis-triggering while driving, thereby improving convenience while primarily ensuring driving safety.

[0031] Step S204, determining the target rearview mirror intended to be adjusted by the driver in the vehicle according to the visual information.

[0032] Next, the visual focus position information obtained above can be processed and analyzed to determine the specific rearview mirror intended to be adjusted by the driver, including but not limited to the left, right, or rearview mirror inside the vehicle, etc. This process replaces the traditional manual selection operation, achieving automatic and accurate selection of the target rearview mirror.

[0033] To achieve the correct inference of the target rearview mirror, the application proposes a determination process based on a preset matching strategy, that is, the calculated visual focus position is associated with each candidate rearview mirror, and the most matched rearview mirror is found from at least two candidate rearview mirrors of the vehicle as the target rearview mirror through comparison or calculation. In specific implementation, the following two matching strategies can be flexibly selected according to system design requirements, hardware computing power, and requirements for precision and generalization ability to determine the target rearview mirror.

[0034] In an embodiment, a threshold matching strategy based on a preset position reference range can be used as a rule-defined and computationally efficient implementation. The principle of this strategy is to define a static position reference range, also known as a region of interest, for each candidate rearview mirror in the vehicle coordinate system. This range is a spatial angle range, which can be determined based on the common observation position of the rearview mirror in the driver's field of view, the vehicle body structure, and human engineering data. For example, the reference range of the left outside rearview mirror may cover a horizontal angle sector from the left front side to the left rear side of the vehicle.

[0035] In the matching process, the system can compare the real-time calculated driver visual focus position, for example, in the form of horizontal and vertical direction angles, with the preset position reference range of each candidate rearview mirror. The judgment logic is to check whether the visual focus position is within the boundary of a certain reference range. If there is only one match, that is, the visual focus position falls within the reference range of only one rearview mirror, then the rearview mirror is determined as the target rearview mirror. Of course, if the visual focus position falls in the overlapping area or near the boundary of two reference ranges, the system can make a final decision by combining confidence, historical data, or introducing more detailed priority rules, such as the distance from the center of the range. Obviously, the strategy of this embodiment has the advantages of transparent logic, fast response, and independence from a large amount of training data, and is particularly suitable for scenarios with high requirements for determinism and real-time performance.

[0036] In another embodiment, an intelligent classification strategy based on a pre-trained machine learning model can be used. This strategy takes advantage of machine learning in pattern recognition and complex mapping relationship learning, and can handle more subtle and dynamic intention judgments compared to the previous embodiment. Of course, before that, the system needs to use a large amount of labeled data, such as rearview mirror gaze samples under various driving postures, head poses, and line-of-sight directions, to train a rearview mirror classification model. The model is essentially a support vector machine, random forest, or deep learning network classifier, whose input is the regularized visual focus position feature data, or also includes context features such as head pose and time series information, and the output is the probability or direct classification label belonging to each candidate rearview mirror.

[0037] In the application stage of the model, the system inputs the visual focus position and related features in the current frame or short-term time sequence into the pre-trained rearview mirror classification model. The model outputs a prediction result, such as "left rearview mirror: 85% confidence, right rearview mirror: 10% confidence, interior rearview mirror: 5% confidence". The system then determines the target rearview mirror according to the output result of the model, assuming that the class with the highest confidence is selected as the determined target rearview mirror. The advantage of this strategy is that it can learn the nonlinear and personalized patterns in the driver's gaze habits, has better discrimination ability for ambiguous boundary cases, and has the potential to optimize through continuous learning.

[0038] Those skilled in the art can understand that the matching strategies in the above two embodiments are not mutually exclusive, and can be switched or the results can be fused in actual systems. For example, threshold matching is used when the system is initialized or the interpretation requirement is high; and the machine learning model is enabled when higher adaptive accuracy is pursued.

[0039] Regardless of the strategy used, the common goal is to accurately and robustly map abstract visual focus position data to specific vehicle rearview mirror entities, thereby completing the intention conversion from "where is the driver looking" to "which mirror does the driver want to adjust".

[0040] Step S206, in response to the received adjustment instruction, performing an adjustment operation on the target rearview mirror.

[0041] After determining the target rearview mirror, the above system can enter a state to be adjusted, at which time once the system receives an adjustment instruction from the user, the system can parse the instruction into a specific drive control signal and drive the adjustment mechanism of the target rearview mirror, such as a micro motor, to perform a corresponding angle adjustment action, thereby completing the entire rearview mirror adjustment process.

[0042] The present application provides a multi-modal adjustment instruction triggering method compatible with traditional habits and intuitive interaction.

[0043] In an embodiment, in the case where the adjustment instruction is triggered by manual operation on the in-vehicle adjustment device, the adjustment operation can be performed according to the control signal corresponding to the manual operation. This way continues the user's familiarity with physical manipulation and optimizes it. When the driver triggers the adjustment instruction by operating the dedicated rocker, button or touch slider on the door panel, steering wheel or center console, the system can directly drive the target rearview mirror to perform the adjustment operation according to the control signal corresponding to the manual operation, such as voltage change, digital pulse or coordinate displacement. The advantage is that it provides clear, linear and muscle memory-compliant control feedback, suitable for scenarios that require fine tuning.

[0044] In another embodiment, in the case that the adjustment instruction is triggered by a recognized preset voice instruction, the adjustment operation can be performed according to the voice content of the voice instruction. This way takes advantage of the convenience of natural language interaction to achieve faster adjustment. Specifically, the system continuously listens to or receives voice input after being woken up. When a sentence conforming to the preset voice instruction, such as "adjust a little to the left" or "raise it", is recognized, the specific adjustment direction and amplitude can be parsed according to the semantic content of the voice instruction and converted into a control signal to perform the operation. This way frees the driver's hands, and is particularly suitable for quick adjustment during driving.

[0045] In yet another embodiment, in the case that the adjustment instruction is triggered by a recognized preset head motion, the adjustment operation can be performed according to the adjustment intention corresponding to the head motion, and the recognition of the head motion does not depend on the change of the visual focus position. Specifically, the recognition of the head motion for triggering adjustment is logically decoupled from the determination of the visual focus position of the target rearview mirror. For example, assuming that the system has locked the target rearview mirror through the visual focus position of the driver, the driver does not need to find or touch any physical control, but only needs to make a predefined and obvious head motion, such as quickly nodding twice towards the target rearview mirror, or making a "lifting the chin" motion. When the system recognizes the head motion, it does not depend on or rejudge whether the visual focus position of the driver has changed. This means that when the driver is making the nodding motion, his line of sight can and usually will remain looking in the direction of the target rearview mirror, and this line of sight maintenance behavior will not interfere with the recognition of the head motion, nor will it cause the selected target rearview mirror to change. At this time, the system can independently analyze the data stream from the head posture sensor such as the DMS camera to recognize the specific motion pattern. Once the preset head motion is recognized, the system generates a control signal according to the adjustment intention corresponding to the motion, such as "noding twice" being pre-mapped to "rotating 5 degrees backward", and performs the adjustment operation on the previously locked target rearview mirror that has not been switched due to the change of the line of sight. Obviously, the above embodiment seamlessly maps the selection and adjustment steps to the two physiological motions of the driver's most natural gaze and nod, without moving the line of sight away from the road or the hands away from the steering wheel, thereby ensuring the continuity and safety of driving to the greatest extent, and representing a fundamental progress in the interaction logic of rearview mirror adjustment.

[0046] In summary, the present scheme provides a multi-level human-computer interaction interface that adapts to different scenarios and user preferences by integrating manual, voice, and innovative head motion triggering methods. Among them, the head motion triggering mechanism is the most forward-looking and practical core interaction innovation of the present scheme, because it completely frees the hands, is intuitive to operate, and is safe and reliable.

[0047] In addition, after the identification of the target rearview mirror is completed in the previous step, instead of immediately performing mechanical adjustment, the system can further introduce a human-computer interaction confirmation link. Specifically, after determining the target rearview mirror that the driver intends to adjust according to the visual information, and before performing the adjustment operation on the target rearview mirror, the system outputs voice information for prompting the adjustment of the target rearview mirror.

[0048] The design of the voice information aims to achieve the following two purposes: one is to provide clear operation feedback and confirmation to the driver, and the other is to serve as an additional safety check barrier. Its content can be pre-designed to ensure that the information is clear and unambiguous. For example, the system can broadcast: “Preparation for adjusting the left rearview mirror, please start operation.” Or “Adjusting the right rearview mirror angle for you.” The core elements of the voice information include: the explicit identification of the target rearview mirror and the operation state prompt. The former is used to clearly indicate the object to be adjusted by using direction words such as “left”, “right”, “inside”, etc., so that the driver immediately knows the identification result of the system; the latter is used to inform the driver that the system has entered the state of being ready for adjustment, and can accept specific adjustment instructions, such as operating the rocker, issuing voice instructions, or making head movements, etc.

[0049] Specifically, the voice broadcast provides a short confirmation window for the driver. If the system identification is incorrect, for example, the driver intends to observe the road conditions of the right rearview mirror, but is identified as intending to adjust, the driver can intervene by canceling the operation or repeatedly gazing at the correct rearview mirror after hearing the voice prompt, thereby effectively preventing unintended adjustment caused by misidentification and eliminating safety hazards. In addition, it makes the execution process of the rearview mirror adjustment system visible to the outside, avoiding the driver's doubts or confusion, establishing a clear human-computer communication channel, and improving user experience and trust in automated functions.

[0050] As understood by those skilled in the art, the specific wording, language, tone, and timing of the voice information can be customized according to vehicle models, user preferences, or regional market requirements, and the core function is to provide voice confirmation and prompt before performing physical adjustment.

[0051] Finally, after outputting the voice prompt and entering the state of waiting for adjustment instructions, the present application also introduces a timeout management mechanism to deal with actual situations such as the driver's temporary change of intention or distraction of attention.

[0052] Specifically, the system can start an internal timer at the same time or after issuing the voice prompt. If the system does not receive any valid adjustment instruction, including but not limited to manual operation, voice instruction or preset head movement, etc. within the preset timeout period, it is automatically determined that the current adjustment process is abandoned or no longer necessary by the driver. Subsequently, the system will automatically cancel the entire rearview mirror adjustment process, exit the adjustment state, and optionally output a voice prompt such as "adjustment cancelled", while releasing the relevant computing resources. This mechanism effectively avoids the problem of resource occupation and state suspension caused by indefinite waiting of the system, ensuring that the system can respond to subsequent other tasks or requests in a timely manner.

[0053] Furthermore, to adapt to the dynamic changes of the driver's intention, the present scheme also supports the process of dynamically reselecting the target rearview mirror. That is, before the timeout, if the system detects that the driver's visual guidance features have changed significantly, for example, the driver's gaze shifts from the original locked left rearview mirror area to the right rearview mirror associated area and continues to focus for a certain period of time, the system can automatically interrupt the current waiting process for the original target rearview mirror. Subsequently, the system will determine the target rearview mirror based on the new visual information and update the voice prompt, thereby seamlessly transitioning to a new adjustment process and achieving dynamic adjustment following the natural gaze behavior of the driver.

[0054] Next, taking Figure 3 and Figure 4 as examples, the specific vehicle architecture and determination process involved in rearview mirror adjustment are introduced. First, as shown in Figure 3 , the vehicle can specifically include a steering wheel integrated module, a rearview mirror driving module, and a feedback module. The steering wheel integrated module can be understood as a general term for modules deployed in the vehicle steering wheel, Figure 1 The visual acquisition device, visual information processing device, and adjustment input module of the rearview mirror adjustment device in the vehicle can be in the form of submodules of the steering wheel integrated module, corresponding to the visual acquisition module, visual information processing module, and adjustment input module respectively and deployed in the vehicle steering wheel. At the same time, Figure 1 The rearview mirror driving module in the rearview mirror adjustment device in the vehicle can be independent of the above-mentioned steering wheel integrated module, and further divided into left and right rearview mirror electric driving modules to control the rearview mirror at the corresponding position through the respective motor and control circuit. At the same time, Figure 3 The feedback module in the vehicle can be to broadcast relevant voice information from the visual information processing module through the vehicle-mounted voice system, or to collect the driver's voice information including control instructions and feed back to the visual information processing module to realize additional voice adjustment of the rearview mirror.

[0055] Next, as shown in Figure 4 , the specific steps include: Step S402, the vehicle system activates the rearview mirror adjustment process when detecting that the preset starting condition is met.

[0056] In an embodiment, when the driver starts the vehicle, i.e. the vehicle is powered on, the vehicle state sensor sends the "vehicle powered on" state to the body controller. After the controller detects this signal that meets the preset vehicle state condition, it automatically triggers and activates the total process of the rearview mirror adjustment method, so that the system enters the preparation state.

[0057] Step S404, the vehicle-mounted visual acquisition device acquires image data containing the driver's face.

[0058] In an embodiment, after the system is activated, the camera installed behind the steering wheel or on the instrument panel starts to work as a visual acquisition device, captures and outputs real-time images or video frames containing the driver's face area, providing raw data for subsequent analysis.

[0059] Step S406, the visual analysis system processes the image data to determine the visual focus position of the driver, and determines the target rearview mirror from multiple candidate rearview mirrors according to the visual focus position.

[0060] In an embodiment, after receiving the image from the camera, the vehicle-mounted computing unit in the visual analysis system can analyze the eye and head features in the image by running face detection, gaze tracking and head pose estimation algorithms. For example, the system calculates that the driver's gaze direction and head orientation are stably directed to the left side window area of the vehicle, and finally determines that the visual focus position is "left rearview mirror associated area" through coordinate transformation.

[0061] At this time, the vehicle-mounted computing unit can compare the position in the visual focus position data with the pre-stored position reference range of the left, right and inner rearview mirrors. Since the calculated position falls into the "left reference range", the module determines the "left outer rearview mirror" as the target rearview mirror intended to be adjusted by the driver.

[0062] Step S408, the vehicle-mounted voice system outputs confirmation and operation guidance voice information about the target rearview mirror.

[0063] In an embodiment, after the target is determined, the vehicle-mounted infotainment system or the dedicated voice prompt module can call the speech synthesis function to broadcast prompt information such as "ready to adjust the left rearview mirror, please operate by nodding or joystick", so as to confirm the recognition result to the driver and guide the subsequent operation.

[0064] Step S410, whether the adjustment instruction is input is monitored.

[0065] In one embodiment, the system can activate monitoring to determine whether there are signals from adjustment devices such as steering wheel joysticks and central control buttons; at the same time, it can also additionally monitor the driver's real-time visual focus data obtained from the DMS to determine whether the user has changed the target rearview mirror that they intend to adjust.

[0066] In step S412, the system receives a head movement command.

[0067] In one embodiment, assuming that during the monitoring process in step S410, after hearing the voice prompt, the driver does not operate the joystick but instead naturally nods twice quickly towards the left rearview mirror. The in-vehicle camera captures this action, and the action recognition algorithm can determine that the action conforms to the preset "double nod" adjustment trigger pattern, and this recognition process is independent of the current stable visual focus orientation determination. The system then interprets this head action as an adjustment command for the selected target, namely the left rearview mirror.

[0068] Step S414: The system received the adjustment command and timed out.

[0069] In one embodiment, the system confirms that no adjustment command has been received for a preset waiting time. At this point, step S404 can be re-executed.

[0070] In step S416, the rearview mirror control unit drives the adjustment motor of the target rearview mirror to perform angle adjustment.

[0071] In one embodiment, the rearview mirror control unit receives a control command from step S412 containing a specific adjustment intention, such as "rotate backward by 5 degrees," which is preset in the system. Subsequently, the unit generates a corresponding drive signal to control the operation of the micro motor inside the left exterior rearview mirror, driving the lens to rotate to the specified angle, thereby completing this intelligent adjustment.

[0072] Figure 5 This is a schematic structural diagram of an electronic device according to an exemplary embodiment. Please refer to... Figure 5 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile storage, and may also include other necessary hardware. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it, forming a vehicle-based rearview mirror adjustment device at the logical level. Of course, besides software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution entity of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0073] Figure 6 This application illustrates a block diagram of a vehicle rearview mirror adjustment device according to an embodiment. Please refer to... Figure 6The device includes: The visual information acquisition unit 602 is used to acquire the visual information of the driver of the vehicle, and the visual information is used to characterize the driver's visual focus orientation. The target rearview mirror determination unit 604 determines the target rearview mirror in the vehicle that the driver intends to adjust based on the visual information. The adjustment operation execution unit 606 is used to perform an adjustment operation on the target rearview mirror in response to a received adjustment command.

[0074] Optionally, the visual information acquisition unit 602 is specifically used for: Acquire an image containing the driver's face; The image is subjected to visual analysis processing to obtain visual information that characterizes the orientation of the visual focus.

[0075] Optionally, the visual information acquisition unit 602 is specifically used for: Determine the driver's line of sight and / or head orientation based on the image; The visual information is determined based on the direction of the gaze and / or the orientation of the head.

[0076] Optionally, the visual information acquisition unit 602 is specifically used for: If only the direction of the line of sight is obtained, the orientation of the visual focus is determined based on the direction of the line of sight; If only the head orientation is known, the visual focus orientation is determined based on the head orientation; When the direction of the gaze and the direction of the head are obtained simultaneously, and the two are pointing in the same direction, the location of the visual focus is determined according to the direction of the gaze or the direction of the head. When both the line of sight and the head orientation are obtained simultaneously, but the two are not aligned, the location of the visual focus is determined based on the line of sight.

[0077] Optionally, the adjustment operation execution unit 606 is specifically used for: When the adjustment command is triggered by manual operation of the in-vehicle adjustment device, the adjustment operation is executed according to the control signal corresponding to the manual operation. When the adjustment command is triggered by a recognized preset head movement, the adjustment operation is performed according to the adjustment intention corresponding to the head movement. The recognition of the head movement does not depend on the change of the visual focus position. When the adjustment command is triggered by a recognized preset voice command, the adjustment operation is performed according to the voice content of the voice command.

[0078] Optionally, the target rearview mirror determining unit 604 is specifically used for: According to a preset matching strategy, a target rearview mirror that matches the visual focus orientation is determined from at least two candidate rearview mirrors of the vehicle.

[0079] Optionally, the preset matching strategy includes any of the following: The visual focus direction is matched with the preset direction reference range corresponding to each candidate rearview mirror to determine the target rearview mirror; The visual focus orientation is input into a pre-trained rearview mirror classification model, and the target rearview mirror is determined based on the output of the model.

[0080] Optionally, before acquiring the driver's visual information of the vehicle, the device further includes: The condition judgment unit is used to determine whether the preset rearview mirror adjustment start conditions are met.

[0081] Optionally, the rearview mirror adjustment activation conditions include one or a combination of the following conditions: Received the adjustment start command actively triggered by the driver; The vehicle status conditions are detected to be met, including at least one of the following: the vehicle is powered on, the driver is seated, or the gear is switched. Based on the driver's visual focus location information obtained from other vehicle systems, it is determined that the driver's visual focus remains on the location area associated with any rearview mirror for a preset duration.

[0082] Optionally, the device further includes: The voice prompt unit is used to output voice information to prompt the adjustment of the target rearview mirror after determining the target rearview mirror that the driver intends to adjust in the vehicle based on the visual information and before performing the adjustment operation on the target rearview mirror.

[0083] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0084] Based on the same concept as the methods described above, this application also provides a computer-readable storage medium having computer instructions stored thereon that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0085] Based on the same concept as the methods described above, this application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0086] The embodiments of the subject matter and functional operation described in this application can be implemented in: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this application and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this application can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0087] The processing and logic flow described in this application can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGA (Field-Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit)—and the device can also be implemented as dedicated logic circuitry.

[0088] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a GPS receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0089] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0090] While this application contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily used to describe features of specific embodiments of a particular invention. Certain features described in the multiple embodiments of this application may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0091] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0092] Therefore, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the figures are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0093] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for adjusting a vehicle's rearview mirror, characterized in that, include: Acquire the driver's visual information of the vehicle, the visual information being used to characterize the driver's visual focus orientation; The target rearview mirror in the vehicle that the driver intends to adjust is determined based on the visual information; In response to the received adjustment command, the target rearview mirror is adjusted.

2. The method according to claim 1, characterized in that, The acquisition of the driver's visual information includes: Acquire an image containing the driver's face; The image is subjected to visual analysis processing to obtain visual information that characterizes the orientation of the visual focus.

3. The method according to claim 2, characterized in that, The step of performing visual analysis processing on the image to obtain visual information characterizing the orientation of the visual focus includes: Determine the driver's line of sight and / or head orientation based on the image; The visual information is determined based on the direction of the gaze and / or the orientation of the head.

4. The method according to claim 3, characterized in that, The step of determining the visual focal point orientation as the visual information based on the gaze direction and / or the head orientation includes: If only the direction of the line of sight is obtained, the orientation of the visual focus is determined based on the direction of the line of sight; If only the head orientation is known, the visual focus orientation is determined based on the head orientation; When the direction of the gaze and the direction of the head are obtained simultaneously, and the two are pointing in the same direction, the location of the visual focus is determined according to the direction of the gaze or the direction of the head. When both the line of sight and the head orientation are obtained simultaneously, but the two are not aligned, the location of the visual focus is determined based on the line of sight.

5. The method according to claim 1, characterized in that, The adjustment operation on the target rearview mirror includes: When the adjustment command is triggered by manual operation of the in-vehicle adjustment device, the adjustment operation is executed according to the control signal corresponding to the manual operation. When the adjustment command is triggered by a recognized preset head movement, the adjustment operation is performed according to the adjustment intention corresponding to the head movement. The recognition of the head movement does not depend on the change of the visual focus position. When the adjustment command is triggered by a recognized preset voice command, the adjustment operation is performed according to the voice content of the voice command.

6. The method according to claim 1, characterized in that, Determining the target rearview mirror in the vehicle that the driver intends to adjust based on the visual information includes: According to a preset matching strategy, a target rearview mirror that matches the visual focus orientation is determined from at least two candidate rearview mirrors of the vehicle.

7. The method according to claim 6, characterized in that, The preset matching strategy includes any of the following: The visual focus direction is matched with the preset direction reference range corresponding to each candidate rearview mirror to determine the target rearview mirror; The visual focus orientation is input into a pre-trained rearview mirror classification model, and the target rearview mirror is determined based on the output of the model.

8. The method according to claim 1, characterized in that, Before acquiring the driver's visual information of the vehicle, the method further includes: Determine if the preset conditions for starting the rearview mirror adjustment are met.

9. The method according to claim 8, characterized in that, The conditions for activating the rearview mirror adjustment include one or a combination of the following: Received the adjustment start command actively triggered by the driver; The vehicle status conditions are detected to be met, including at least one of the following: the vehicle is powered on, the driver is seated, or the gear is switched. Based on the driver's visual focus location information obtained from other vehicle systems, it is determined that the driver's visual focus remains on the location area associated with any rearview mirror for a preset duration.

10. The method according to claim 1, characterized in that, The method further includes: After determining the target rearview mirror that the driver intends to adjust in the vehicle based on the visual information, and before performing the adjustment operation on the target rearview mirror, voice information is output to prompt the driver to adjust the target rearview mirror.

11. A computer-readable storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 10.

12. A computer program product, characterized in that, Includes a computer program / instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 10.

Images