Driving training student assisting method and system

Abstract

The embodiment of the invention provides a driving training student assisting method and system. The problem that improper driving visual field learning efficiency and safety are affected can be solved. The method comprises the following steps: acquiring environment image data of a current vehicle through a visual sensor under the condition of monitoring that a student exists in a driving position; based on a current vehicle structure, ideal driving view image data of a driver is cut from the environment image data; and displaying the ideal driving visual field image data in a vehicle-mounted display of the current vehicle or an intelligent terminal under the jurisdiction of the student, so that the student adjusts a seat until the actual driving visual field of the student is aligned with the ideal driving visual field image data.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a method and system for assisting driving training students. Background Art

[0002] In driving test training, the difference in driving vision has an important impact on the learning efficiency and safety of students. Driving vision refers to the road environment that a driver can clearly perceive and observe during driving, including the coverage of the front vision, side vision, and rear vision. The factors affecting vision include the body structure (such as A-pillar occlusion), seat height, rearview mirror adjustment, environmental lighting, the observation habits of students, and psychological factors (such as nervousness). Improper driving vision affects both learning efficiency and safety. Summary of the Invention

[0003] The embodiments of this application provide a method and system for assisting driving training students, which can solve the problem that improper driving vision affects both learning efficiency and safety.

[0004] The first aspect of the embodiments of this application provides a method for assisting driving training students, including:

[0005] When it is detected that there is a student in the driver's seat, obtain the environmental image data of the current vehicle through a visual sensor;

[0006] Cut out the ideal driving vision image data of the driver from the environmental image data based on the current vehicle structure;

[0007] Display the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the student, so that the student can adjust the seat until aligning his actual driving vision with the ideal driving vision image data.

[0008] Optionally, it further includes:

[0009] Collect the student image data of the driver's seat;

[0010] Analyze and predict the current theoretical driving vision image data of the student based on the student image data;

[0011] Display the theoretical driving vision image data and the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the student at the same time, so that the student can adjust the seat until aligning his actual driving vision with the ideal driving vision image data.

[0012] Optionally, the analyzing and predicting the current theoretical driving vision image data of the student based on the student image data includes:

[0013] Analyze the positional relationship between the head image of the trainee image data and the fixed reference point of the driver's seat;

[0014] Predict the current theoretical driving vision image data of the trainee based on the positional relationship.

[0015] Optionally, it further includes:

[0016] Collect the trainee image data of the driver's seat;

[0017] Analyze and predict the current theoretical driving vision image data of the trainee based on the trainee image data;

[0018] Automatically adjust the seat based on the theoretical driving vision image data and the ideal driving vision image data until the theoretical driving vision image data of the trainee is aligned with the ideal driving vision image data.

[0019] Optionally, it further includes:

[0020] After simultaneously displaying the theoretical driving vision image data and the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, start timing;

[0021] Collect the periodic trainee image data of the driver's seat again after a preset time;

[0022] Analyze and predict the current periodic theoretical driving vision image data of the trainee based on the periodic trainee image data;

[0023] In the case where the periodic theoretical driving vision image data and the ideal driving vision image data still do not match, automatically adjust the seat until the theoretical driving vision image data of the trainee is aligned with the ideal driving vision image data.

[0024] Optionally, it further includes:

[0025] Before monitoring that the theoretical driving vision image data is aligned with the ideal driving vision image data, keep the vehicle in a stopped or turned-off state.

[0026] The second aspect of the embodiments of the present application provides a driving training trainee assistance device, including:

[0027] A monitoring unit, configured to obtain the environmental image data of the current vehicle through a visual sensor when it is monitored that there is a trainee in the driver's seat;

[0028] A cutting unit, configured to cut out the ideal driving vision image data of the driver from the environmental image data based on the structure of the current vehicle;

[0029] An alignment unit for displaying the ideal driving vision image data on an in-vehicle display of the current vehicle or an intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until his actual driving vision is aligned with the ideal driving vision image data.

[0030] In a third aspect of the embodiments of the present application, an electronic system is provided, including a memory and a processor. When the processor executes a computer program stored in the memory, the steps of the above-mentioned driving training trainee assistance method are implemented.

[0031] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned driving training trainee assistance method are implemented.

[0032] In summary, for the driving training trainee assistance method provided by the embodiments of the present application, when it is detected that there is a trainee in the driver's seat, environmental image data of the current vehicle is obtained through a vision sensor; based on the structure of the current vehicle, ideal driving vision image data of the driver is cut out from the environmental image data; the ideal driving vision image data is displayed on an in-vehicle display of the current vehicle or an intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until his actual driving vision is aligned with the ideal driving vision image data. During driving training, the same vehicle is used alternately by multiple trainees, and there are obvious differences in the height, driving posture, and seat habits of each trainee. This results in huge differences in the actual driving vision observed by different trainees. Especially for trainees with insufficient driving experience, lacking the experience of correctly adjusting the seat or posture, it is very difficult to achieve the ideal driving vision by themselves. This situation not only reduces the learning efficiency but also increases the safety risk. Therefore, an assistance method is needed to help trainees quickly and accurately adjust the seat and driving posture to ensure that their actual driving vision meets the ideal standard. Thus, without the need for experience guidance, trainees can quickly and accurately adjust their vision to the best state by simply and repeatedly comparing their actual vision with the standard display image. This method reduces the need for coaches to provide repeated manual guidance, greatly improving the training efficiency. After the trainee's actual vision is adjusted to the best state, they can clearly perceive the position of the road surface, pedestrians, and other vehicles, significantly reducing the observation blind spots or misjudgments caused by vision differences and ensuring driving safety. This method does not rely on complex vision comparison and superimposed display technologies, but only displays the ideal driving vision image alone, with intuitive and simple operation, reducing the learning and usage costs of trainees. Since the driving vision template is a standard template predefined by the vehicle manufacturer, it can ensure the unity of the driving vision standards for different trainees, facilitating the formation of standardized driving vision habits and improving the overall standardization level of driving training.

[0033] Accordingly, the driving training trainee assistance device, electronic system, and computer-readable storage medium provided by the embodiments of the present invention also have the above technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a schematic flowchart of a possible driving training trainee assistance method provided by an embodiment of the present application;

[0035] Figure 2 is a schematic structural block diagram of a possible driving training trainee assistance device provided by an embodiment of the present application;

[0036] Figure 3 is a schematic hardware structure diagram of a possible driving training trainee assistance device provided by an embodiment of the present application;

[0037] Figure 4 is a schematic structural block diagram of a possible electronic system provided by an embodiment of the present application;

[0038] Figure 5 is a schematic structural block diagram of a possible computer-readable storage medium provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] Embodiments of the present application provide a driving training trainee assistance method and system, which can solve the problem that both the learning efficiency and safety of improper driving vision are affected.

[0040] The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and above-mentioned drawings of the present application are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0041] Please refer to Figure 1 , which is a flowchart of a driving training trainee assistance method provided by an embodiment of the present application, and specifically may include: S110 - S130.

[0042] S110. When it is detected that there is a trainee in the driver's seat, obtain the environmental image data of the current vehicle through a vision sensor.

[0043] S120. Cut out the ideal driving vision image data of the driver from the environmental image data based on the current vehicle structure.

[0044] S130. Display the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until aligning his actual driving vision with the ideal driving vision image data.

[0045] It can be understood that first, a vision sensor (such as a front camera) is installed in the driver's seat of the vehicle to capture the environmental image data in real time. According to the vehicle structure characteristics, the system presets a standardized "ideal driving vision range" (such as a visual range with the standard driver position as a reference). When it is detected that a trainee sits in the driver's seat, the system automatically captures the current environmental image, and crops and processes the image through a pre-determined ideal driving vision template to generate "ideal driving vision image data" that only contains the ideal driver's vision area. This data is separately displayed on the in-vehicle display or the trainee's intelligent terminal to guide the trainee to make autonomous seat and posture adjustments. During the seat adjustment process, the trainee only repeatedly observes his actual driving vision and makes a visual comparison with the separately displayed ideal driving vision image until the two match highly.

[0046] Exemplarily, a pressure sensor is installed under the driver's seat of the vehicle, or a vision sensor (driver monitoring camera) is set inside the vehicle to detect in real time whether there is a trainee sitting in the driver's seat. When it is detected that there is a trainee in the driver's seat (for example, the pressure sensed by the pressure sensor is greater than the set threshold, and the vision sensor recognizes that there is a face in the driver's seat), the system immediately starts the driving vision assistance adjustment program, and at the same time, a prompt appears on the in-vehicle display or the trainee's intelligent terminal device: "Loading the ideal driving vision image for you, please wait."

[0047] Exemplarily, after confirming that a trainee sits in the driver's seat, the vision sensor installed in front of the vehicle (usually located in the central area along the upper edge of the vehicle's front windshield) is immediately activated to capture the environmental image data directly in front of the current vehicle in real time. The collected environmental image data clearly presents the features such as the road, lane lines, road signs, traffic lights, vehicles in front, and environmental features on both sides of the road (such as curbs, railings) in front of the current vehicle, so as to ensure that the reference objects in the driving vision area can be accurately identified in the next step.

[0048] Exemplarily, the system automatically performs precise regional cutting on the collected environmental image data based on the standard driving vision range preset by the vehicle manufacturer (usually the road area in front that the driver can comfortably observe in the standard sitting position, such as the visible range between the A-pillars, the standard road surface display range). During specific implementation, an image template is predefined (such as a rectangular or fan-shaped area with specific coordinates as a reference), and this template clearly indicates the position and range of the driver's ideal vision in the environmental image (for example, a standard driver should be able to see the center line of the road, the left and right lane lines, and the center point of the traffic signal ahead). The system automatically completes the cropping of the real-time captured environmental image data according to this template, generating image data that only contains the ideal driving vision area.

[0049] Exemplarily, the ideal driving vision image data generated in the previous step is separately displayed on a display device in the vehicle (such as the center control screen, the instrument panel liquid crystal screen) or on a smart terminal device carried by the trainee (such as a dedicated APP on a mobile phone or a tablet). At this time, the trainee can intuitively see the separately presented ideal driving vision image (this image is standardized and not affected by actual seat or posture differences). The trainee visually compares the actual driving vision scene he observes with the separately displayed ideal driving vision image repeatedly (such as comparing the visible range of the road surface, the clarity of the lane lines, the position relationship between the traffic signal ahead and the actual vision), and independently adjusts the seat height, front-back position, backrest angle or his own sitting posture until his actual vision is completely consistent with the ideal vision displayed on the screen (for example, the position of the traffic light or lane line ahead achieves visual matching). After completing the adjustment, the trainee independently determines that the vision has reached the standard and can then enter the formal driving training session.

[0050] Exemplarily, for example: Trainee Wang first sits in the driver's seat. Due to the low seat position, he finds that part of the road surface is blocked by the vehicle instrument panel during actual observation. The system separately displays the ideal driving vision image (clearly showing the complete road surface and the traffic signal ahead). By repeatedly observing the actual vision and comparing it with the ideal vision image, Wang finds that he cannot observe the complete road surface actually, so he independently raises the seat position. After the adjustment, he finds that his actual vision is completely consistent with the ideal vision image on the screen, confirms that the ideal driving vision is achieved, completes the adjustment and enters the next driving training step.

[0051] In summary, the driving training trainee assistance method provided by the above embodiments obtains environmental image data of the current vehicle through a visual sensor when it is detected that there is a trainee in the driver's seat; cuts out the ideal driving vision image data of the driver from the environmental image data based on the structure of the current vehicle; and displays the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until aligning his actual driving vision with the ideal driving vision image data. During the driving training process, the same vehicle is used alternately by multiple trainees, and there are obvious differences in the height, driving posture, and seat habits of each trainee. This results in huge differences in the actual driving vision observed by different trainees. Especially for trainees with insufficient driving experience, lacking the experience of correctly adjusting the seat or posture, it is very difficult to achieve the ideal driving vision by themselves. This situation not only reduces the learning efficiency but also increases the safety risk. Therefore, an assistance method is needed to help trainees quickly and accurately adjust the seat and driving posture to ensure that their actual driving vision meets the ideal standard. Thus, without the need for experience guidance, trainees can quickly and accurately adjust their vision to the best state only by intuitively comparing their actual vision with the standard display image repeatedly. This method reduces the need for coaches to provide repeated manual guidance and greatly improves the training efficiency. After the trainee's actual vision is adjusted to the best state, they can clearly perceive the positions of the road surface, pedestrians, and other vehicles, significantly reducing the observation blind spots or misjudgments caused by vision differences and ensuring driving safety. This method does not rely on complex vision comparison and superimposed display technologies, but only displays the ideal driving vision image alone, with intuitive and simple operations, reducing the learning and usage costs of trainees. Since the driving vision template is a standard template predefined by the vehicle manufacturer, it can ensure the unity of the driving vision standards for different trainees, which is conducive to forming a standardized driving vision habit and improving the overall standardization degree of driving training.

[0052] In one embodiment, it further includes:

[0053] Collecting the trainee image data of the driver's seat;

[0054] Analyzing and predicting the current theoretical driving vision image data of the trainee based on the trainee image data;

[0055] Simultaneously displaying the theoretical driving vision image data and the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until aligning his actual driving vision with the ideal driving vision image data.

[0056] It is understandable that through intelligent vision analysis technology, the "theoretical driving vision image data" of the trainee in the current sitting posture and seat state can be predicted in real time. This "theoretical driving vision" is a simulation image of the actual vision range of the trainee inferred by the system based on the trainee's current posture and vehicle structure. Then, the "theoretical driving vision image data" predicted by the system and the "ideal driving vision image data" preset by the standard are displayed to the trainee at the same time. By intuitively comparing the differences between the trainee's current theoretical driving vision and the ideal driving vision, the trainee can more efficiently guide himself / herself to adjust the posture or seat and quickly achieve the ideal state of the driving vision.

[0057] Exemplarily, after the system collects the image data of the trainee in the driver's seat, real-time analysis is carried out using the technology based on vision analysis and human posture recognition, which can include: image data collection, using the in-vehicle camera to capture the feature image data such as the upper body, head position, line-of-sight direction, body posture, and eye position height of the driver. Image analysis and driving posture modeling, using computer vision algorithms (such as human posture estimation, head orientation recognition algorithm, line-of-sight tracking technology) to analyze the current posture of the driver in real time, such as head angle, eye height, sitting posture height, and distance from the windshield. Predict the theoretical driving vision area, based on the current posture parameters of the driver (such as sitting posture height, head position, head orientation, eye position), combined with the vehicle structure parameters (such as A-pillar position, windshield size, etc.), automatically simulate and generate the vision area that the driver can currently observe theoretically. Further crop the theoretical driving vision image data from the real-time environmental image data. Through intuitive observation, the trainee can easily find the obvious gap between his / her current vision state and the ideal vision. For example, in the ideal vision image data, the traffic light in front is clearly located in the upper-middle area of the vision center; in the theoretical vision image data, due to the insufficient seat height or unreasonable posture of the trainee, part of the traffic light is blocked by the roof edge. The trainee immediately realizes that he / she needs to adjust the seat height upward until his / her actual vision aligns with the ideal vision. Thus, the current driving posture and position of the trainee can be accurately captured in real time, ensuring the accuracy and real-time nature of the subsequent theoretical vision calculation. Using vision analysis technology to accurately predict the real-time vision situation of the trainee enables the trainee to clearly understand the problems (such as blind spots) existing in his / her vision, improving the pertinence and efficiency of the adjustment. The trainee can immediately discover the gap position, gap direction, and specific gap size between his / her current vision and the ideal vision in a simple and intuitive way, avoiding the understanding errors caused by the coach's oral description in traditional teaching and improving the efficiency and accuracy of the trainee's self-adjustment.

[0058] In one embodiment, the analysis and prediction of the current theoretical driving vision image data of the trainee based on the analysis of the trainee's image data includes:

[0059] Analyze the positional relationship between the head image of the trainee based on the trainee image data and the fixed reference point of the driver's seat;

[0060] Predict the current theoretical driving vision image data of the trainee based on the positional relationship.

[0061] It can be understood that in the current implementation, more refined steps are proposed: analyze using the positional relationship between the trainee's head image and the fixed reference point of the driver's seat, and then realize the prediction of the current theoretical driving vision image data of the trainee. The head position and posture of the driver are the key factors determining the driving vision. By capturing the trainee's head image and determining the precise positional relationship of the head relative to the fixed reference point of the driver's seat (such as a fixed reference point inside the vehicle, a fixed feature point on the A-pillar, rearview mirror, windshield, etc.), the true spatial position, viewing angle, and blind area of the driver's line of sight can be deduced. Based on the above positional relationship data, the system can accurately calculate the driving vision area that the driver currently theoretically sees, and generate a theoretical driving vision image from the trainee's perspective corresponding to the real-time environment image.

[0062] Exemplarily, clear image data of the trainee's head is collected in real time through an in-cabin camera (e.g., located directly in front of the dashboard, on the roof, or in the area of the interior rearview mirror). The position of the camera is clear and fixed, serving as a standard reference point, such as the base of the interior rearview mirror or the center of the vehicle instrument panel. For example, the camera captures the frontal or side image of the trainee's head, including clear facial and head contours. Based on the trainee's head image, key feature points (such as the positions of both eyes, the tip of the nose, and the ears) are extracted using image recognition technology (such as the face key point recognition algorithm). At the same time, the coordinate data of the fixed reference points of the driver's seat (such as the edge of the front windshield, the position of the rearview mirror, and the center of the steering wheel) is known. Through real-time image analysis (such as three-dimensional space coordinate mapping and pose estimation algorithms), the three-dimensional space coordinates (X, Y, and Z axis coordinates) of the trainee's head are clearly obtained, thereby forming the precise position relationship information of the driver's head relative to the fixed reference points of the vehicle. According to the head space position (coordinate data) obtained in the previous step and information such as the driver's line of sight direction and eye height, the system automatically performs line of sight tracking algorithm calculations to simulate the precise position and angle range of the trainee's current line of sight in three-dimensional space. Subsequently, in combination with the vehicle structure (windshield, A-pillar, and vehicle head height), the spatial area range that the trainee can theoretically observe clearly at this time (i.e., the current theoretical driving vision area) is determined. Finally, according to the spatial position of this theoretical driving vision area, the area image is accurately cut out from the real-time captured front environment image, which is the "theoretical driving vision image data". For example, the system analyzes and finds that the trainee's head is relatively rearward and lower, deduces that the current theoretical vision area is lower, and the traffic signal in front may not be within the vision range, so the actual theoretical vision image of the trainee is cropped. The theoretical driving vision image data obtained from the above steps and the preset ideal driving vision image data (standard driver vision range) of the system are simultaneously displayed on the in-vehicle display screen in the current vehicle or the trainee's intelligent terminal. When the trainee adjusts the seat or posture, by repeatedly observing the gap between their own theoretical vision image and the ideal vision image, the trainee gradually adjusts their actual vision to the position state consistent with the ideal vision image. For example, in the ideal vision image, it is clearly shown that "the white stop line in the middle of the road is located in the center of the vision", while in the current theoretical vision image, it shows that half of the stop line is blocked by the edge of the dashboard. The trainee adjusts by raising the seat or moving the seat forward until the theoretical vision image is consistent with the ideal vision image. Thus, accurate posture data is provided, avoiding human perception errors and ensuring the accuracy and reliability of subsequent theoretical vision analysis. It clearly reveals the current actual vision blind area of the trainee, effectively quantifies the trainee's vision difference, and provides a clear visual reference for the trainee. The system realizes the real-time automatic analysis of the theoretical vision image, greatly improving the efficiency and accuracy of the trainee's vision adjustment. The trainee can intuitively see the gap position between their own vision state and the ideal state, and accurately guide their own adjustment. The intuitive comparison avoids the subjective errors that may be caused by the coach's repeated oral guidance in the traditional training mode, and greatly improves the self-learning ability and training quality.

[0063] In one embodiment, it further includes:

[0064] Collect the image data of the trainee in the driver's seat;

[0065] Based on the analysis of the trainee's image data, predict the current theoretical driving vision image data of the trainee;

[0066] Based on the theoretical driving vision image data and the ideal driving vision image data, automatically adjust the seat until the theoretical driving vision image data of the trainee is aligned with the ideal driving vision image data.

[0067] It can be understood that during the driving training process, since the training vehicle is often shared by multiple trainees, the significant differences in body height and sitting posture habits among trainees result in huge differences in actual driving vision. The traditional method of relying on trainees to adjust the seat by themselves to achieve the best vision is usually not efficient because trainees lack driving experience and it is difficult to correctly and precisely complete the vision adjustment. Therefore, this embodiment is based on automated means and directly adjusts the seat position through intelligent technology to make the driving vision reach the ideal state, significantly improving the efficiency and safety of driving training.

[0068] Exemplarily, the image data of the trainee is obtained in real time through a visual sensor installed in the front of the cab (such as near the interior rearview mirror or the dashboard area). This image data usually includes the frontal and side positions of the trainee's head, the eye height, and the head orientation. The system captures the high-precision image data of the trainee's head in real time for subsequent analysis and calculation of the theoretical driving vision.

[0069] Exemplarily, based on the image data of the trainee's head collected in real time, the system calculates the head position, line-of-sight orientation, and eye position coordinates through visual analysis algorithms (such as pose estimation algorithms and gaze tracking algorithms), and combines the vehicle structure parameters of the driver's seat (windshield size, A-pillar position coordinates, reference position of the seat in the vehicle) to calculate the driving vision area that the current trainee can actually observe theoretically, and crops the corresponding vision area in the environmental image data to generate the current "theoretical driving vision image data".

[0070] Exemplarily, the theoretical driving vision image data obtained in step 2 is compared and analyzed with the "ideal driving vision image data" predefined in the vehicle standard, and the spatial gap (such as height difference, angle difference) between the two image data is calculated. For example, if the front vision shown in the trainee's theoretical driving vision image is significantly lower, while the ideal driving vision image should show a higher vision, the system determines that the seat needs to be adjusted upward by a certain distance to eliminate the vision height gap.

[0071] Exemplarily, after clarifying the gap between the theoretical driving vision and the ideal driving vision, the system converts the gap value into a seat adjustment instruction (such as the vertical height adjustment of the seat, the front-back position adjustment, and the change in the tilt angle of the backrest). The motor system of the vehicle's electric seat automatically and precisely adjusts the seat position according to the instruction. While the seat is being gradually adjusted, the system continuously collects the image data of the driver's head position, recalculates the theoretical driving vision image data, and compares it with the ideal driving vision image data until the real-time theoretical driving vision completely matches the ideal driving vision, at which point the adjustment action stops. For example, when the system first calculates that the trainee's head position is relatively low and the theoretical driving vision is low (unable to see the traffic lights in the distance), the system issues an instruction to automatically drive the seat to rise vertically. As the seat is gradually lifted, the head image is collected again in real time for the calculation and analysis of the theoretical driving vision until the traffic light position appears within the theoretical driving vision, achieving a match with the ideal vision, and the adjustment automatically stops. Thus, through real-time visual image analysis and theoretical driving vision prediction, the system automatically controls the precise adjustment of the seat, significantly reducing the errors and inefficiencies caused by manual adjustment. The driver's vision is automatically and precisely adjusted to the ideal state, effectively reducing the driving risks caused by poor vision and greatly improving the safety and teaching efficiency of driving training. Through the standard ideal vision template and automated seat adjustment, it can ensure that trainees of different heights and body types can reach the unified vision standard, greatly improving the standardization and regularization of training management.

[0072] In one embodiment, it further includes:

[0073] After simultaneously displaying the theoretical driving vision image data and the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, start timing;

[0074] Collect the periodic trainee image data of the driver's seat again after a preset time;

[0075] Analyze and predict the current periodic theoretical driving vision image data of the trainee based on the periodic trainee image data;

[0076] In the case where the periodic theoretical driving vision image data still does not match the ideal driving vision image data, automatically adjust the seat until the theoretical driving vision image data of the trainee is aligned with the ideal driving vision image data.

[0077] It can be understood that, based on the previously provided method for automatically adjusting the driving vision, this new embodiment further emphasizes the vision verification link after the automatic adjustment of the seat. That is, after the theoretical driving vision and the ideal driving vision are simultaneously displayed for the first time, the system automatically starts a timing program. When the set time limit is exceeded, the system checks again whether the current theoretical driving vision of the trainee exactly matches the ideal driving vision. If a gap is still found, secondary automatic adjustment is initiated to ensure that the driving vision is accurate and fully meets the standards. The aim is to further improve the accuracy, stability, and safety of the automatic seat adjustment, ensuring that the actual vision of the trainee remains in the ideal state for a long time.

[0078] Exemplarily, after the system first predicts the theoretical driving vision based on the trainee's image data, it is simultaneously displayed on the in-vehicle display or the trainee's smart terminal together with the ideal driving vision image. Subsequently, the system automatically starts the built-in timing program (for example, starting from 0 and setting the timing duration to 1 minute). During this period, the trainee can observe and compare the two images (theoretical vision and ideal vision) displayed on the screen, and slightly adjust their sitting or postures to ensure that they can more naturally adapt to the current preliminarily adjusted seat state.

[0079] Exemplarily, when the timing reaches the set time limit (for example, after 1 minute), the system automatically starts the internal vision sensor again, re-captures the image data of the trainee's head posture and position, and analyzes and calculates the latest theoretical driving vision image data in the trainee's current posture in real time. This step uses the same vision analysis algorithm as the initial calculation of the theoretical driving vision (such as head posture analysis, eye position, and line-of-sight direction modeling) to ensure accurate real-time capture of the trainee's latest theoretical driving vision state after the posture fine-tuning.

[0080] Exemplarily, the system strictly compares the theoretical driving vision image data obtained from this secondary analysis with the standard ideal driving vision image data, and automatically analyzes whether the two images exactly match.

[0081] If the system analyzes and finds that there are still differences between the two images, for example, the positions of the road ahead or traffic lights do not exactly correspond (there are vertical or horizontal deviations), the system clearly determines that the current seat position has not reached the ideal driving vision state.

[0082] Exemplarily, when it is confirmed that the above-mentioned theoretical driving vision still does not match the ideal vision, the system automatically triggers the second fine adjustment process of the seat. Based on the gap position relationship between the latest calculated theoretical driving vision and the ideal driving vision (for example, the system analyzes that the theoretical vision is still 5 cm lower than the ideal vision), the vehicle seat motor is automatically driven for precise secondary adjustment (such as lifting or fine-tuning the seat) until the latest theoretical driving vision calculated by the system through collecting the head image data of the trainee again completely matches the standard ideal driving vision. After completing the secondary adjustment, the system will prompt the trainee again that the vision has reached the ideal state. Thus, the re-verification and automatic adjustment steps after timing are introduced to effectively solve the problem of the deviation of the vision state caused by the change of the trainee's own posture or nervousness after the initial adjustment of the seat, ensuring the long-term precise stability of the vision. In the initial stage of driving training, the vision fluctuations caused by the trainee's nervousness and unstable posture can be automatically re-confirmed and corrected by this solution, ensuring that the trainee's vision is stably maintained in the ideal state for a long time, significantly reducing the safety risk of driving training. The trainee does not need to manually adjust the seat frequently or be guided by the coach repeatedly. Only through one automatic initial adjustment + timing secondary review and fine adjustment, the seat position can be accurately adjusted, significantly improving the driving training efficiency and enhancing the trainee's training experience.

[0083] According to some embodiments, it further includes:

[0084] Before it is monitored that the theoretical driving vision image data is aligned with the ideal driving vision image data, the stopped state of the vehicle is maintained.

[0085] In one embodiment, it further includes:

[0086] Before it is monitored that the theoretical driving vision image data is aligned with the ideal driving vision image data, the vehicle is kept in the flameout state.

[0087] It can be understood that in actual driving training, driving trainees usually lack driving experience. If the driving seat or posture is not correctly adjusted to the ideal state, starting the vehicle rashly may lead to potential safety risks. Therefore, the above embodiments further propose a safety constraint mechanism, that is: during the automatic or manual adjustment of the driving vision stage, the vehicle will automatically monitor whether the current theoretical driving vision image data of the trainee matches the ideal driving vision image data. Before the system confirms that the two are completely matched, the vehicle starting device or driving function is in a locked or disabled state, so as to forcibly ensure that the trainee can start driving training after reaching a safe and ideal driving vision, ensuring the safety of the training.

[0088] In some examples, images of the traffic environment around the vehicle can be collected in real time through an external vehicle camera. For other vehicles in front of or on the side of the vehicle, the theoretical visual blind area caused by their specific vehicle structure (such as vehicle size, width of A-pillar or C-pillar, etc.) is analyzed. When the trainee's vehicle enters the theoretical blind area of another vehicle, the system monitors the position relationship in real time, immediately generates and sends a prompt message to the trainee to prevent the trainee from staying in the blind area of other vehicles for a long time, so as to effectively reduce the risk of potential collision accidents and improve the safety of the trainee's driving and the effectiveness of driving training. The system first uses an external vehicle environment vision sensor (such as a high-definition camera installed at the front end, side, or outside the rearview mirror of the vehicle) to capture the environmental image data around the trainee's vehicle in real time. The system analyzes and identifies other vehicles in the environmental image in real time, determines the types, brands, and structural data of these vehicles, and calculates the theoretical blind area range of these vehicles in real time based on a pre-stored vehicle structure database (including vehicle model size, pillar width, blind area feature data). After obtaining the theoretical blind area image data of the surrounding vehicles, the system continuously monitors the real-time driving position trajectory of the trainee's vehicle. When the system detects that the vehicle driven by the trainee is entering or has entered the theoretical blind area of another vehicle, it immediately sends a warning prompt message to guide the trainee to adjust the position in time to ensure safe driving.

[0089] Exemplarily, multi-directional vision sensors are installed outside the driver training vehicle, such as high-definition cameras installed at the front bumper or side rearview mirror of the vehicle, to collect traffic environment image information around the vehicle in real time. This environmental image data includes the appearance and structural features of surrounding vehicles (front-end shape, side structure, A-pillar / C-pillar position, vehicle brand logo, vehicle model identification information, etc.), providing data support for the next vehicle type identification and blind area calculation.

[0090] Exemplarily, the system uses vehicle recognition algorithms (such as deep learning image recognition, computer vision vehicle feature recognition model) to accurately identify and classify the vehicle types, brands, and models of other vehicles in the real-time environmental image data. For example, the system identifies the vehicle next to it as an "SUV model or large truck", or a specific brand such as "BMW X5", "Toyota Highlander", etc.

[0091] Exemplarily, based on a standard structure database corresponding to the built-in pre-stored vehicle type or model (such as the typical driver's blind spot size parameters of various vehicle models, including pillar thickness, vehicle body length, and rearview mirror position parameters), the system accurately calculates the theoretical blind spot area corresponding to the surrounding moving vehicles (such as the oblique rear blind spots on both sides of the vehicle, the front A-pillar blind spot, the right-turn blind spot, etc.). Based on the specific vehicle structure data identified currently, the system maps and determines the specific positions and ranges of these blind spots in the road space in real time. For example, when the system identifies that the vehicle moving ahead is an SUV model, according to the size characteristics of the A-pillar and side rearview mirrors of the SUV model, it calculates and marks the theoretical blind spot range in the areas behind both sides of the vehicle.

[0092] Exemplarily, during the real-time driving process, the system simultaneously collects the position trajectory data of the vehicle driven by the trainee (implemented through GPS, in-vehicle sensors, or visual positioning algorithms), and precisely compares and analyzes it with the theoretical blind spot position data of other vehicles in real time to determine whether the trainee's vehicle is driving into or has entered the theoretical blind spot of other vehicles.

[0093] Exemplarily, when the system analyzes and monitors in real time that the vehicle driven by the trainee has driven into the theoretical blind spot of other vehicles, it immediately automatically generates visual or audible warning prompt messages (such as "Attention: Currently in the right blind spot of the vehicle ahead, please adjust your position in time"), and timely reminds the trainee to quickly adjust the driving trajectory, speed, or position through the in-vehicle display screen or voice broadcast, so as to avoid staying in the blind spot of other vehicles for a long time and reduce the potential collision risk. Thus, by monitoring and prompting the dangerous state of the trainee entering the theoretical blind spot of other vehicles in real time, it can effectively prevent accidental collision accidents in the blind spot caused by the trainee's lack of experience or cognitive defects, and ensure the safety of driving training. Through real-time prompts, the trainee can gradually master the good driving habit of avoiding the blind spots of other vehicles, cultivate driving safety awareness, and improve the safety skills of actual road driving. Based on accurate vehicle type identification and real-time blind spot calculation, more accurate and personalized safety prompts are provided, avoiding traditional general safety prompt methods, and effectively improving the accuracy and timeliness of safety prompt effects.

[0094] Please refer to Figure 2 , an embodiment of the driving training trainee assistance device in the embodiment of the present application may include:

[0095] A monitoring unit 201, configured to obtain the environmental image data of the current vehicle through a visual sensor when it monitors that there is a trainee in the driver's seat;

[0096] A cutting unit 202, configured to cut out the ideal driving vision image data of the driver from the environmental image data based on the current vehicle structure;

[0097] An alignment unit 203 is configured to display the ideal driving vision image data on an in-vehicle display of the current vehicle or a smart terminal under the jurisdiction of the trainee, so that the trainee adjusts the seat until his / her actual driving vision is aligned with the ideal driving vision image data.

[0098] In summary, for the driving training trainee assistance device provided in the above embodiment, when it is detected that there is a trainee in the driver's seat, the environmental image data of the current vehicle is acquired through a vision sensor; the ideal driving vision image data of the driver is cut out from the environmental image data based on the structure of the current vehicle; the ideal driving vision image data is displayed on an in-vehicle display of the current vehicle or a smart terminal under the jurisdiction of the trainee, so that the trainee adjusts the seat until his / her actual driving vision is aligned with the ideal driving vision image data. During the driving training process, the same vehicle is used alternately by multiple trainees, and there are obvious differences in the heights, driving postures, and seat habits of each trainee. This results in huge differences in the actual driving visions observed by different trainees. Especially for trainees with insufficient driving experience, lacking the experience of correctly adjusting the seat or posture, it is very difficult to achieve the ideal driving vision by themselves. This situation not only reduces the learning efficiency but also increases the safety risk. Therefore, an auxiliary method is needed to help trainees quickly and accurately adjust the seat and driving posture to ensure that their actual driving vision meets the ideal standard. Thus, the trainee can quickly and accurately adjust the vision to the best state without the need for experience guidance, only by intuitively comparing his / her actual vision with the standard display image repeatedly. This method reduces the need for coaches to repeatedly provide manual guidance, greatly improving the training efficiency. After the trainee's actual vision is adjusted to the best state, the trainee can clearly perceive the positions of the road surface, pedestrians, and other vehicles, significantly reducing the observation blind spots or misjudgments caused by vision differences and ensuring driving safety. This method does not rely on complex vision comparison and superimposed display technologies, only displays the ideal driving vision image alone, with intuitive and simple operation, reducing the learning and usage costs of trainees. Since the driving vision template is a standard template predefined by the vehicle manufacturer, it can ensure the unity of the driving vision standards for different trainees, is conducive to forming a standardized driving vision habit, and improves the overall standardization degree of driving training.

[0099] Above Figure 2 The driving training trainee assistance device in the embodiments of the present application has been described from the perspective of modular functional entities. Next, the driving training trainee assistance device in the embodiments of the present application will be described in detail from the perspective of hardware processing. Please refer to Figure 3 An embodiment of the driving training trainee assistance device 300 in the embodiments of the present application includes:

[0100] An input device 301, an output device 302, a processor 303, and a memory 304, where the number of processors 303 can be one or more. Figure 3Take a processor 303 as an example. In some embodiments of the present application, the input device 301, the output device 302, the processor 303, and the memory 304 may be connected by a bus or other means, where, Figure 3 Take the connection by bus as an example.

[0101] Among them, by invoking the operation instructions stored in the memory 304, the processor 303 is used to execute the above steps.

[0102] By invoking the operation instructions stored in the memory 304, the processor 303 is also used to execute Figure 1 any one of the corresponding embodiments.

[0103] Please refer to Figure 4 , Figure 4 , which is a schematic diagram of an embodiment of an electronic system provided by an embodiment of the present application.

[0104] As Figure 4 shown, an embodiment of the present application provides an electronic system, including a memory 410, a processor 420, and a computer program 411 stored on the memory 420 and executable on the processor 420. When the processor 420 executes the computer program 411, the above steps are implemented.

[0105] In the specific implementation process, when the processor 420 executes the computer program 411, it can implement Figure 1 any one of the corresponding embodiments.

[0106] Since the electronic system introduced in this embodiment is the device adopted for implementing a driving training student auxiliary device in an embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation manner and various variations of the electronic system in this embodiment. Therefore, the specific implementation of how this electronic system implements the method in the embodiment of the present application will not be described in detail here. As long as the device adopted by those skilled in the art to implement the method in the embodiment of the present application belongs to the scope protected by the present application.

[0107] Please refer to Figure 5 , Figure 5 , which is a schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present application.

[0108] As Figure 5 shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 511 is stored. When the computer program 511 is executed by a processor, the above steps are implemented.

[0109] In the specific implementation process, when the computer program 511 is executed by a processor, it can implement Figure 1Any implementation mode in the corresponding embodiment.

[0110] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0113] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0115] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions run on a processing device, the processing device is caused to execute the process in the driving training trainee assistance method in the corresponding embodiment as Figure 1 the process in the corresponding embodiment of the driving training trainee assistance method.

[0116] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, a computer, a server, or a data center to another website, a computer, a server, or a data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0117] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0118] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other may be indirect couplings or communication connections through some interfaces, devices, or units, and may be in an electrical, mechanical, or other form.

[0119] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in various embodiments of the present application may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0121] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this 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 enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0122] As mentioned above, the above embodiments are only used to illustrate the technical solution of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of the present application.

Claims

1. A driving training student assistance method, characterized in that, including: When it is detected that there is a trainee in the driver's seat, obtaining environmental image data of the current vehicle through a vision sensor; Based on the current vehicle structure, cutting out the ideal driving vision image data of the driver from the environmental image data; Displaying the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until aligning his own actual driving vision with the ideal driving vision image data.

2. The method according to claim 1, characterized in that, It also includes: Collecting trainee image data of the driver's seat; Analyzing and predicting the current theoretical driving vision image data of the trainee based on the trainee image data; Simultaneously displaying the theoretical driving vision image data and the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until aligning his own actual driving vision with the ideal driving vision image data.

3. The method according to claim 2, wherein The analyzing and predicting the current theoretical driving vision image data of the trainee based on the trainee image data includes: Analyzing the positional relationship between the head image of the trainee based on the trainee image data and the fixed reference point of the driver's seat; Predicting the current theoretical driving vision image data of the trainee based on the positional relationship.

4. The method according to claim 1, characterized in that, It also includes: Collecting trainee image data of the driver's seat; Analyzing and predicting the current theoretical driving vision image data of the trainee based on the trainee image data; Automatically adjusting the seat based on the theoretical driving vision image data and the ideal driving vision image data until aligning the theoretical driving vision image data of the trainee with the ideal driving vision image data.

5. The method according to claim 2, characterized in that, It also includes: After simultaneously displaying the theoretical driving vision image data and the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, starting to time; Collecting the stage trainee image data of the driver's seat again after a preset time; Analyzing and predicting the current stage theoretical driving vision image data of the trainee based on the stage trainee image data; In the case that the stage theoretical driving vision image data and the ideal driving vision image data still do not match, automatically adjusting the seat until aligning the theoretical driving vision image data of the trainee with the ideal driving vision image data.

6. The method according to any one of claims 2-5, characterized in that, It also includes: Keeping the vehicle in a stopped state before it is detected that the theoretical driving vision image data and the ideal driving vision image data are aligned.

7. The method according to any one of claims 2-5, characterized in that, It also includes: Keeping the vehicle in an off state before it is detected that the theoretical driving vision image data and the ideal driving vision image data are aligned.

8. An auxiliary device for driving training students, characterized in that, including: A monitoring unit, configured to obtain environmental image data of the current vehicle through a vision sensor when it is detected that there is a trainee in the driver's seat; A cutting unit, configured to cut out the ideal driving vision image data of the driver from the environmental image data based on the current vehicle structure; An aligning unit, configured to display the ideal driving vision image data on the in-vehicle display of the current vehicle or the intelligent terminal under the jurisdiction of the trainee, so that the trainee can adjust the seat until aligning his own actual driving vision with the ideal driving vision image data.

9. An electronic system includes a memory and a processor, characterized in that, When the processor is used to execute a computer program stored in a memory, the steps of the driving training trainee assistance method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the driving training trainee assistance method according to any one of claims 1 to 7 are implemented.

Images