Vehicle driving early warning method and device, electronic equipment and storage medium

By identifying the key points of the waist and shoulders of the vehicle driver and calculating the shoulder and waist triangle centroid, the problems of large particle size and misjudgment in the existing technology are solved, and fast and accurate driver sitting posture detection and early warning are achieved, and vehicle safety is improved Effectiveness of driving.

CN119091421AActive Publication Date: 2024-12-06CHONGQING JINKANG NEW ENERGY VEHICLE CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410975872.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-12-06
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

The existing driver's driving motion detection method has a large granularity, and there are problems of inaccurate identification and misjudgment, which affects the accuracy of driving detection and the effectiveness of safe driving of vehicles.

Method used

By collecting the sitting posture images of the vehicle driver, identifying the key points of the waist and shoulders, calculating the center of mass of the shoulder and waist triangle, comparing it with the initial center of mass, generating the center of mass deviation results, detecting whether the sitting posture is abnormal, and warning prompts are made in abnormal situations.

Benefits of technology

It realizes the rapid and accurate identification of the driver's sitting posture, reduces the probability of traffic accidents caused by dangerous driving actions, and improves the effectiveness of safe driving of vehicles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091421A_ABST
    Figure CN119091421A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle driving early warning method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting a sitting posture image of a vehicle driver, recognizing key points in the sitting posture image, determining the mass center of a current sitting posture through employing waist key points and shoulder key points, and carrying out the early warning of the current sitting posture; the current sitting posture mass center is compared with a pre-determined initial sitting posture mass center, a mass center deviation result is generated, whether the sitting posture of the vehicle driver is abnormal or not is detected according to the mass center deviation result, and early warning prompt is given to the vehicle driver in response to the fact that the sitting posture of the vehicle driver is determined to be abnormal. According to the method, the waist and shoulder key points of the driver are intelligently detected through the sitting posture image, the shoulder and waist triangle centroid position of the driver is obtained, the sitting posture centroid is adopted for sitting posture judgment, whether the sitting posture state of the driver is abnormal or not can be rapidly and accurately recognized, the accuracy of driving sitting posture judgment is improved, and driving early warning is automatically conducted; and the effectiveness of vehicle safe driving is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a vehicle driving warning method, device, electronic equipment and storage medium. Background Art

[0002] Vehicles are important means of transportation. While improving the comfort of the driving posture, driving safety is becoming increasingly important. The driver's improper sitting posture may cause safety risks. For example, if the driver makes large movements of the upper body during driving, such as turning the head, leaning sideways, bending over, etc., it may easily cause the vehicle to lose control.

[0003] At present, the judgment of the driver's dangerous driving behavior is mainly through visual detection, such as detecting the driver's head, hands on the steering wheel, etc., or by installing a pressure sensor on the seat to detect the sitting posture according to the change in pressure. However, the existing driving detection method has a large detection granularity, and there are problems of inaccurate recognition and misjudgment, which affects the accuracy of driving detection and further affects the effectiveness of vehicle safe driving. Summary of the invention

[0004] In view of this, the present invention aims to propose a vehicle driving warning method, device, electronic device and storage medium to solve the problem that the current detection method is inaccurate and prone to misjudgment, affecting the accuracy of driving detection, and to achieve automatic and accurate vehicle driving warning.

[0005] According to a first aspect of the present invention, a vehicle driving warning method is provided, the method comprising:

[0006] Collecting a sitting posture image of the vehicle driver, and identifying key points in the sitting posture image; wherein the key points include waist key points and shoulder key points;

[0007] The waist key points and the shoulder key points are used to determine the current sitting posture center of mass, and the current sitting posture center of mass is compared with the predetermined initial sitting posture center of mass to generate a center of mass deviation result;

[0008] Detecting whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result;

[0009] In response to determining that the vehicle driver has an abnormal sitting posture, a warning prompt is given to the vehicle driver.

[0010] Optionally, the collecting of a sitting posture image of the vehicle driver and identifying key points in the sitting posture image, wherein the key points include waist key points and shoulder key points, comprises:

[0011] The vehicle camera is used to collect images of the preset area, and the collected sample images are input into the preset neural network model for training to obtain the key point detection model;

[0012] Acquire the current sitting posture image of the vehicle driver;

[0013] The sitting posture image is recognized by using a key point detection model to determine the waist key points and shoulder key points of the sitting posture image.

[0014] Optionally, the step of using the waist key points and the shoulder key points to determine the current sitting posture center of mass, comparing the current sitting posture center of mass with a predetermined initial sitting posture center of mass, and generating a center of mass deviation result includes:

[0015] Using the waist key points and the shoulder key points to generate a shoulder-waist triangle;

[0016] Calculating the center of mass of the shoulder-waist triangle, and determining the center of mass of the shoulder-waist triangle as the center of mass of the current sitting posture;

[0017] Taking the predetermined initial sitting posture center of mass as the coordinate origin, constructing a rectangular coordinate system, and determining the coordinates of the current sitting posture center of mass;

[0018] The coordinate distance between the initial sitting posture center of mass and the current sitting posture center of mass is calculated, and the horizontal distance and vertical distance of the center of mass coordinates are determined as the center of mass deviation result.

[0019] Optionally, detecting whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result includes:

[0020] Pre-calibrate a first threshold in the horizontal direction and a second threshold in the vertical direction based on an actual vehicle;

[0021] If the horizontal distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is less than or equal to a first threshold, and the vertical distance is less than or equal to a second threshold, then it is determined that the sitting posture of the vehicle driver is normal;

[0022] Otherwise, it is determined that the sitting posture of the vehicle driver is abnormal.

[0023] Optionally, in response to determining that the vehicle driver has an abnormal sitting posture, giving a warning prompt to the vehicle driver includes:

[0024] In response to detecting that the driver of the vehicle has an abnormal sitting posture, generating a warning issuing instruction;

[0025] According to the warning instruction, the vehicle computer is controlled to use at least one of voice reminder or text reminder to give a warning to the vehicle driver;

[0026] The number of warning prompts and the time of the warning prompts are recorded.

[0027] Optionally, after recording the number of warning prompts and the time of the warning prompts, the method further includes:

[0028] If the number of warning prompts within a preset period is greater than a preset prompt threshold, a control command is issued to the active pretensioner seat belt;

[0029] The active pre-tensioning seat belt is controlled to perform a tightening or vibration action, and an early warning prompt is given to the vehicle driver.

[0030] Optionally, after giving a warning to the vehicle driver in response to determining that the vehicle driver has an abnormal sitting posture, the method further includes:

[0031] Monitoring the changes in the sitting posture of the driver of the vehicle within a preset period;

[0032] If it is monitored that the sitting posture of the vehicle driver is updated to normal within a preset period, the early warning prompt to the driver is stopped.

[0033] According to a second aspect of the present invention, a vehicle driving warning device is provided, the device comprising:

[0034] An image acquisition module, used to acquire a sitting posture image of the vehicle driver and identify key points in the sitting posture image; wherein the key points include waist key points and shoulder key points;

[0035] A center of mass deviation module, used to determine the center of mass of the current sitting posture using the waist key points and the shoulder key points, compare the position of the center of mass of the current sitting posture with the predetermined initial sitting posture center of mass, and generate a center of mass deviation result;

[0036] A sitting posture detection module, used to detect whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result;

[0037] The early warning prompt module is used to provide an early warning prompt to the vehicle driver in response to determining that the vehicle driver has an abnormal sitting posture.

[0038] According to another aspect of the present invention, there is also provided an electronic device, comprising:

[0039] processor;

[0040] a memory for storing instructions executable by the processor;

[0041] Wherein, the processor is configured to execute the instructions to implement the vehicle driving warning method as described above.

[0042] According to another aspect of the present invention, a 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 vehicle driving warning method as described above are implemented.

[0043] The vehicle driving warning method provided by the embodiment of the present invention collects the sitting posture image of the vehicle driver, identifies the key points in the sitting posture image, uses the waist key points and the shoulder key points to determine the current sitting posture centroid, compares the current sitting posture centroid with the predetermined initial sitting posture centroid, generates the centroid deviation result, detects whether the sitting posture of the vehicle driver is abnormal according to the centroid deviation result, and issues a warning to the vehicle driver in response to determining that the sitting posture of the vehicle driver is abnormal. The embodiment of the present invention intelligently detects the waist and shoulder key points of the driver through the sitting posture image, thereby obtaining the centroid position of the driver's shoulder-waist triangle, and uses the sitting posture centroid to judge the sitting posture, which can quickly and accurately identify whether the driver's sitting posture is abnormal, improve the accuracy of driving posture judgment, and automatically perform driving warning and warning actions when it is detected that the driver is in an abnormal sitting posture, that is, there is a dangerous driving action, thereby reducing the probability of traffic accidents caused by the driver's dangerous driving actions during vehicle driving, and ensuring the effectiveness of vehicle safe driving.

[0044] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0046] Figure 1 is a flow chart of the steps of a vehicle driving warning method provided by an embodiment of the present invention;

[0047] Figure 2 yes Figure 1 A flowchart of step 101 in the vehicle driving warning method provided by an embodiment of the present invention;

[0048] Figure 3 yes Figure 1 A flowchart of step 102 in the vehicle driving warning method provided by an embodiment of the present invention;

[0049] Figure 4 yes Figure 1A flowchart of step 103 in the vehicle driving warning method provided by an embodiment of the present invention;

[0050] Figure 5 is a flowchart of another vehicle driving warning method provided by an embodiment of the present invention;

[0051] Figure 6 is a flow chart of a vehicle driving warning method provided by an embodiment of the present invention;

[0052] Figure 7 is a structural schematic diagram of a vehicle driving warning device provided by an embodiment of the present invention;

[0053] Figure 8 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] To make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can be implemented. The division of the following embodiments is for the convenience of description, and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined and referenced with each other without contradiction.

[0055] Reference Figure 1 , shows a flow chart of the steps of a vehicle driving warning method provided by an embodiment of the present invention, the method may include:

[0056] Step 101, collecting a sitting posture image of the vehicle driver, and identifying key points in the sitting posture image; wherein the key points include waist key points and shoulder key points.

[0057] In an embodiment of the present invention, in order to solve the problem that the current driving detection method has a large detection granularity, inaccurate recognition and easy misjudgment, which affects the accuracy of driving detection and further affects the effectiveness of vehicle safe driving, this embodiment refines the detection granularity and uses the driver's sitting posture centroid to judge the driver's posture. It can quickly and accurately identify whether the driver's sitting posture is abnormal, improve the accuracy of driving posture judgment, and automatically perform driving warnings and warning actions when it is detected that the driver is in an abnormal sitting posture, that is, there is a dangerous driving action, thereby reducing the probability of traffic accidents caused by the driver's dangerous driving actions during vehicle driving and ensuring the effectiveness of vehicle safe driving.

[0058] Specifically, in this embodiment, the sitting posture image of the vehicle driver is collected by the in-vehicle camera, and the key points in the sitting posture image are identified through image processing and recognition, especially the waist key points and the shoulder key points. The waist key points and the shoulder key points are important reference points for determining the centroid of the sitting posture, wherein the camera range of the in-vehicle camera at least includes the driver's hips and the body parts above it. It should be noted that the vehicle controller can collect a large number of sitting posture images of the vehicle driver in advance, use the pre-built neural network model, and combine the collected sample images of the driver's sitting posture to perform model training, obtain a human waist and shoulder key point detection model, input the vehicle driver's sitting posture image into the key point detection model, and identify the key points in the sitting posture image, wherein the key points include the waist key points and the shoulder key points.

[0059] It should be noted that in this embodiment, an in-vehicle camera or other image acquisition device can be used to capture the driver's sitting posture image in real time. The in-vehicle camera can be set on the front windshield inside the car. This embodiment does not specifically limit the position of the camera, and it can be any shooting position that can capture the driver's sitting posture, which will not be repeated here.

[0060] Step 102, using the waist key points and the shoulder key points to determine the current sitting posture center of mass, comparing the current sitting posture center of mass with the predetermined initial sitting posture center of mass, and generating a center of mass deviation result.

[0061] In an embodiment of the present invention, the center of mass position of the current sitting posture is calculated based on the identified waist key points and shoulder key points, the center of mass of the current sitting posture is compared with the pre-stored initial sitting posture center of mass, the position deviation between the two is calculated, and the center of mass deviation result is generated.

[0062] Specifically, firstly, the waist key points and shoulder key points are used to generate a shoulder-waist triangle, and the center of mass calculation method is used to calculate the center of mass of the shoulder-waist triangle, and the center of mass of the shoulder-waist triangle is determined as the center of mass of the current sitting posture, and then the predetermined initial sitting posture center of mass is used as the coordinate origin to construct a rectangular coordinate system. The initial sitting posture center of mass is usually determined when the driver adjusts to a safe and standard sitting posture. The coordinates of the current sitting posture center of mass are determined in the current rectangular coordinate system, and the coordinate distance between the initial sitting posture center of mass and the current sitting posture center of mass is calculated, and the horizontal distance and vertical distance of the center of mass coordinates are determined as the center of mass deviation result.

[0063] In this embodiment, the identified waist key points and shoulder key points are used to generate a shoulder-waist triangle. The shoulder-waist triangle is formed based on the actual sitting posture of the driver. The calculation of the center of mass involves the average value of the coordinates of the triangle vertices. The center of mass coordinates are the average value of the coordinates of the three vertices of the triangle. The calculated center of mass of the shoulder-waist triangle is determined as the center of mass of the current sitting posture. In the constructed rectangular coordinate system, the coordinates of the center of mass of the current sitting posture are determined, and the coordinate distance between the initial sitting posture center of mass and the current sitting posture center of mass is calculated. The coordinate distance includes the horizontal distance (X-axis deviation) and the vertical distance (Y-axis deviation). Since the center of mass of the current sitting posture represents the center position of the driver's current sitting posture, the center of mass deviation result reflects the difference between the driver's current sitting posture and the safe sitting posture. When the center of mass of the sitting posture moves or deviates, it can sensitively and quickly identify whether the sitting posture is abnormal, thereby further improving the accuracy of sitting posture detection.

[0064] Step 103: Detect whether the sitting posture of the vehicle driver is abnormal based on the center of mass deviation result.

[0065] In the embodiment of the present invention, whether the sitting posture of the vehicle driver is abnormal is detected according to the horizontal distance (X-axis deviation) and the vertical distance (Y-axis deviation) in the center of mass deviation result. Specifically, if the horizontal distance between the current sitting posture center of mass and the predetermined initial sitting posture center of mass coordinates is less than or equal to the first threshold, and the vertical distance is less than or equal to the second threshold, then it is determined that the sitting posture of the vehicle driver is normal; otherwise, the sitting posture of the vehicle driver is abnormal, which will not be elaborated here.

[0066] Step 104 , in response to determining that the vehicle driver's sitting posture is abnormal, providing a warning prompt to the vehicle driver.

[0067] In an embodiment of the present invention, in response to determining that the vehicle driver's sitting posture is abnormal, a warning prompt is given to the vehicle driver, and the warning prompt includes a voice reminder, a text reminder or a seat belt action warning. Specifically, if it is determined that the vehicle driver's sitting posture is abnormal, a warning instruction is generated to control the vehicle computer to use at least one of the voice reminder or the text reminder to give a warning prompt to the vehicle driver, and the number of warning prompts and the time of the warning prompt are counted. If the number of warning prompts within a preset period is greater than a preset prompt threshold, a control instruction is issued to the active pre-tensioned seat belt to control the active pre-tensioned seat belt to perform a tightening or vibration action, so as to give a warning prompt to the vehicle driver.

[0068] The vehicle driving warning method provided by the embodiment of the present invention collects the sitting posture image of the vehicle driver, identifies the key points in the sitting posture image, uses the waist key points and the shoulder key points to determine the current sitting posture centroid, compares the current sitting posture centroid with the predetermined initial sitting posture centroid, generates the centroid deviation result, detects whether the sitting posture of the vehicle driver is abnormal according to the centroid deviation result, and issues a warning to the vehicle driver in response to determining that the sitting posture of the vehicle driver is abnormal. The embodiment of the present invention intelligently detects the waist and shoulder key points of the driver through the sitting posture image, thereby obtaining the centroid position of the driver's shoulder-waist triangle, and uses the sitting posture centroid to judge the sitting posture, which can quickly and accurately identify whether the driver's sitting posture is abnormal, improve the accuracy of driving posture judgment, and automatically perform driving warning and warning actions when it is detected that the driver is in an abnormal sitting posture, that is, there is a dangerous driving action, thereby reducing the probability of traffic accidents caused by the driver's dangerous driving actions during vehicle driving, and ensuring the effectiveness of vehicle safe driving.

[0069] Further, see Figure 2 , showing Figure 1 A flowchart of step 101 in a vehicle driving warning method is provided. The method is basically the same as the vehicle driving warning method provided in the first embodiment of the present invention. Step 101 may include:

[0070] Step 201, use the vehicle camera to collect images of a preset area, input the collected sample images into a preset neural network model for training, and obtain a key point detection model.

[0071] Step 202, obtaining a current sitting posture image of the vehicle driver.

[0072] Step 203: Use a key point detection model to identify the sitting posture image and determine the waist key points and shoulder key points of the sitting posture image.

[0073] It should be noted that, in the embodiment of the present invention, a vehicle camera is used to collect images of a preset area, which is usually the driver's seat area, for capturing the driver's sitting posture image, and the collected sample images are input into a preset neural network model, and the sample images include images of different drivers in different sitting postures. In order to improve the accuracy of key point detection, this embodiment pre-inputs the collected sample images into a preset neural network model for training to obtain a key point detection model, that is, the sample images are trained by the preset neural network model to learn how to identify and locate the key points in the sitting posture image, especially the waist key points and shoulder key points. The trained neural network model can accurately identify the key points in the sitting posture image to form a key point detection model.

[0074] Specifically, the current sitting posture image of the vehicle driver is acquired in real time for real-time monitoring of the driver's sitting posture, and the current sitting posture image is recognized using a trained key point detection model. The key point detection model automatically locates and recognizes the waist key points and shoulder key points in the current sitting posture image, and determines the specific positions of the waist key points and shoulder key points in the current sitting posture image based on the recognition results.

[0075] This embodiment uses a pre-trained key point detection model to identify key points in the driver's sitting posture image in real time, especially the waist and shoulder key points. The accuracy of the waist and shoulder key points is crucial for determining whether the driver's sitting posture is abnormal. The key point detection model is used to automatically monitor and identify the sitting posture key points, thereby improving the accuracy and efficiency of sitting posture monitoring.

[0076] Further, see Figure 3 , showing Figure 1 A flowchart of step 102 in a vehicle driving warning method is provided. The method is basically the same as the vehicle driving warning method provided in the first embodiment of the present invention. Step 102 may include:

[0077] Step 301, using the waist key points and the shoulder key points to generate a shoulder-waist triangle.

[0078] Step 302, calculate the center of mass of the shoulder-waist triangle, and determine the center of mass of the shoulder-waist triangle as the center of mass of the current sitting posture.

[0079] Step 303, using the predetermined initial sitting posture center of mass as the coordinate origin, constructing a rectangular coordinate system, and determining the coordinates of the current sitting posture center of mass.

[0080] Step 304, calculating the coordinate distance between the initial sitting posture center of mass and the current sitting posture center of mass, and determining the horizontal distance and vertical distance of the center of mass coordinates as the center of mass deviation result.

[0081] It should be noted that the embodiment of the present invention uses the identified waist key points and shoulder key points to generate a shoulder-waist triangle, and adopts a centroid calculation method to calculate the centroid of the shoulder-waist triangle. The calculated centroid of the shoulder-waist triangle is determined as the current sitting posture centroid, and the current sitting posture centroid reflects the center position of the driver's current sitting posture. The predetermined initial sitting posture centroid is used as the coordinate origin of the rectangular coordinate system. In the constructed rectangular coordinate system, the coordinates of the current sitting posture centroid are determined. The current sitting posture centroid coordinates are relative to the position of the initial sitting posture centroid (coordinate origin), so as to facilitate the calculation of the coordinate distance between the initial sitting posture centroid and the current sitting posture centroid. The sitting posture distance includes horizontal distance and vertical distance. The calculated horizontal distance and vertical distance are determined as the centroid deviation result, which reflects the difference between the driver's current sitting posture and the safe sitting posture.

[0082] Specifically, based on the key points of the waist and two shoulders, three connecting lines, namely L shoulder 1, L shoulder 2, and L waist, are determined, forming the driver's shoulder-waist triangle. Then, the center of mass of the shoulder-waist triangle is determined, and the xy coordinate system is constructed with the driver's initial normal sitting center of mass position as the relative origin. When there is a certain vehicle speed (such as a vehicle speed ≥ 5km / h), the driver's sitting image is collected in real time. The key point detection model trained in the early stage is used to quickly obtain the driver's current sitting center of mass position, and the current sitting center of mass position is compared with the initial center of mass position to determine the deviation of the driver's sitting posture and whether it is abnormal.

[0083] The embodiment of the present invention accurately calculates the center of mass of the driver's current sitting posture and compares it with the center of mass of the initial sitting posture to determine whether the sitting posture is abnormal. The warning method based on the center of mass deviation can sensitively and fine-grainedly detect changes and abnormalities in the sitting posture, effectively monitor and remind the driver to adjust the sitting posture, and provide timely sitting posture warning to the driver, thereby reducing fatigue and driving errors caused by poor sitting posture and improving driving safety. The calculation and application of the center of mass deviation results further enhance the vehicle driving posture detection and warning effect.

[0084] Further, see Figure 4 , showing Figure 1 A flowchart of step 103 in a vehicle driving warning method is provided. The method is basically the same as the vehicle driving warning method provided in the first embodiment of the present invention. Step 103 may include:

[0085] Step 401 , pre-calibrate a first threshold in the horizontal direction and a second threshold in the vertical direction based on an actual vehicle.

[0086] It should be noted that the first threshold in the horizontal direction and the second threshold in the vertical direction can be calibrated through preliminary neural network training and actual vehicle calibration, wherein the first threshold is the allowable error value of the sitting posture center of mass in the horizontal direction, and the second threshold is the allowable error value of the sitting posture center of mass in the vertical direction, and is set according to actual driver characteristics and vehicle driving seat settings, which will not be elaborated here.

[0087] Step 402: If the horizontal distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is less than or equal to a first threshold, and the vertical distance is less than or equal to a second threshold, it is determined that the sitting posture of the vehicle driver is normal.

[0088] Step 403: otherwise, determine that the sitting posture of the vehicle driver is abnormal.

[0089] In the embodiment of the present invention, if the driver's sitting posture deviates too much in the horizontal direction, it may affect the driver's observation of the vehicle's surroundings and increase driving risks. If the driver's sitting posture deviates too much in the vertical direction, it may cause the driver's line of sight to deviate from the road ahead, which also increases driving risks. If the horizontal distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is less than or equal to the first threshold, and the vertical distance is less than or equal to the second threshold, it is determined that the vehicle driver's sitting posture is normal. Otherwise, if the horizontal distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is greater than the first threshold, it is determined that the driver's sitting posture is abnormal, with obvious left and right deviations, such as: the driver's upper body has obvious leaning movements toward the co-pilot or door direction, turning the head backward, etc.; if the vertical distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is greater than the second threshold, it is determined that the driver's sitting posture is abnormal, with obvious up and down deviations, such as: the driver has stood up, leaned back or bent over.

[0090] The embodiment of the present invention accurately determines whether the driver's sitting posture is abnormal based on the horizontal and vertical distances between the current sitting posture center of mass and the initial sitting posture center of mass, which helps to promptly discover the driver's bad sitting posture and prompt the driver to adjust the sitting posture through early warning prompts, thereby improving driving safety.

[0091] Specifically, in response to determining that the vehicle driver has an abnormal sitting posture, the step of providing an early warning prompt to the vehicle driver includes:

[0092] Firstly, in response to detecting an abnormal sitting posture of the vehicle driver, a warning instruction is generated.

[0093] Secondly, according to the warning instruction, the vehicle computer is controlled to use at least one of voice reminder or text reminder to give a warning to the vehicle driver.

[0094] Secondly, record the number of warning prompts and the time of the warning prompts.

[0095] It should be noted that in the above steps, in response to detecting an abnormal sitting posture of the vehicle driver, a warning instruction is generated, and the warning instruction is sent to the vehicle display screen or voice equipment, and the vehicle computer is controlled to use at least one of voice reminders or text reminders to give a warning prompt to the vehicle driver. In order to further monitor the abnormal sitting posture of the driver, the number of warning prompts and the time of the warning prompts are recorded, so as to facilitate the statistics of the driver's sitting posture warning situation within the monitoring period and to provide timely and effective driving warnings.

[0096] For example, when it is detected that the driver is in an abnormal sitting posture, a prompt "There is a dangerous driving action, please drive safely" can be displayed on the large screen of the car or the LCD instrument; the prompt can also be given through the in-vehicle voice prompt or instrument alarm sound; each prompt is separated by a period of time (such as 1 minute), and if the normal sitting posture is restored before the next prompt, the prompt will be terminated until the abnormal sitting posture is detected again.

[0097] When the present embodiment detects an abnormal sitting posture of the driver, it promptly issues an early warning prompt and reminds the driver to adjust his sitting posture through voice or text. At the same time, the number and time of the early warning prompts are recorded for subsequent analysis and evaluation. It can effectively monitor and remind the driver to adjust his sitting posture, thereby improving driving safety and comfort.

[0098] Specifically, after recording the number of warning prompts and the time of the warning prompts, the step further includes:

[0099] If the number of warning prompts within a preset period is greater than a preset prompt threshold, a control command is issued to the active pretensioner seat belt;

[0100] The active pre-tensioning seat belt is controlled to perform a tightening or vibration action, and an early warning prompt is given to the vehicle driver.

[0101] In the embodiment of the present invention, the active pre-tensioning seat belt is also called the motor-controlled pre-tensioning seat belt, which relies on the servo motor to complete the pre-tensioning work of the seat belt in the first time, and can also perform actions such as tightening or vibrating in non-collision scenarios. Specifically, the number of warning prompts is monitored within a preset period, and the monitored number of warning prompts is compared with the preset prompt threshold. The preset period can be a preset time period, such as every ten minutes, every hour or every trip. The preset prompt threshold is the set number of times. The preset period and the preset prompt threshold are set according to actual driving needs, and the specific values ​​are not limited here.

[0102] In this embodiment, if the number of warning prompts within a preset period is greater than a preset prompt threshold, a control instruction is sent to the active pre-tensioned seat belt. The control instruction is used to trigger the seat belt to issue a warning prompt, thereby controlling the active pre-tensioned seat belt to perform an action. Specifically, the active pre-tensioned seat belt is controlled to perform a tightening or vibrating action. The tightening action can be to quickly tighten the seat belt through the seat belt pre-tensioning device to remind the driver to pay attention to the sitting posture. The vibration action can be that the vibration device integrated in the seat belt vibrates to physically remind the driver.

[0103] It should be noted that if the number of warning prompts within the preset period is greater than the preset prompt threshold, a control instruction is sent to the active pre-tensioned seat belt to control the active pre-tensioned seat belt to perform tightening or vibration actions, and give a warning prompt to the vehicle driver. For example, if the driver is prompted that the abnormal sitting posture continuously exceeds the preset prompt threshold, for example, the number of prompts is greater than 3 times within three minutes, and the driver is still in the abnormal sitting posture, the motor-controlled pre-tensioned seat belt is controlled to tighten or vibrate the seat belt to serve as a warning. The tightening force of the seat belt should not be too large, and the duration should not be too long. It is recommended to be less than or equal to 30s.

[0104] This embodiment can provide a stronger warning prompt through the active pre-tensioned seat belt when it is detected that the driver's sitting posture is abnormal and the number of warning prompts is too many. This warning method directly acts on the driver through physical feedback (such as tightening or vibration), which can more effectively attract the driver's attention, prompting him to adjust his sitting posture and improve driving safety.

[0105] Reference Figure 5 , shows a flow chart of steps of another vehicle driving warning method provided by an embodiment of the present invention, which method is basically the same as the vehicle driving warning method provided by the first embodiment of the present invention, except that the method may further include:

[0106] Step 101, collecting a sitting posture image of the vehicle driver, and identifying key points in the sitting posture image; wherein the key points include waist key points and shoulder key points.

[0107] Step 102, using the waist key points and the shoulder key points to determine the current sitting posture center of mass, comparing the current sitting posture center of mass with the predetermined initial sitting posture center of mass, and generating a center of mass deviation result.

[0108] Step 103: Detect whether the sitting posture of the vehicle driver is abnormal based on the center of mass deviation result.

[0109] Step 104 , in response to determining that the vehicle driver's sitting posture is abnormal, providing a warning prompt to the vehicle driver.

[0110] The above steps 101 to 104 are described in the foregoing description and will not be repeated here.

[0111] Step 105, monitoring the changes in the sitting posture of the vehicle driver within a preset period.

[0112] Step 106: If it is monitored that the sitting posture of the vehicle driver is updated to normal within the preset period, the warning prompt to the driver is stopped.

[0113] In an embodiment of the present invention, changes in the sitting posture of the vehicle driver are monitored in real time within a preset period. The preset period can be a fixed time period, such as every minute, every hour or each trip. Similarly, by analyzing the deviation between the current sitting posture center of mass and the initial sitting posture center of mass, it can be determined whether the driver's sitting posture has changed. If it is monitored that the sitting posture of the vehicle driver is updated to normal within the preset period, that is, the deviation between the current sitting posture center of mass and the initial sitting posture center of mass is within the preset threshold range, it is determined that the driver's sitting posture has been adjusted to a normal state. In response to the sitting posture returning to normal, the early warning prompt to the driver is stopped, and the driver is no longer reminded by voice, text or tightening the seat belt.

[0114] Compared with the prior art, the embodiments of the present invention achieve the beneficial effects brought by the first embodiment. Since frequent warning prompts may cause reminder fatigue to the driver, stopping the warning prompts helps to keep the driver's attention focused. When it is monitored that the driver's sitting posture has returned to normal, the warning prompts can be stopped in time to avoid unnecessary interference and reminder fatigue. The dynamically adjusted warning mechanism helps to improve the driver's comfort and driving experience, and also reflects the intelligence of vehicle driving warning.

[0115] In order to facilitate those skilled in the art to fully understand the above vehicle driving warning method, refer to Figure 6 , Figure 6 : is a flow chart of a vehicle driving warning method provided by an embodiment of the present invention, which shows the overall process of the vehicle driving warning provided by an embodiment of the present invention, specifically including:

[0116] S501, determining the initial sitting posture center of mass of the vehicle driver in normal driving;

[0117] In this embodiment, an ideal sitting posture or a safe sitting posture image is used to determine the initial sitting posture center of mass for normal driving of the vehicle driver. Specifically, the identified waist key points and shoulder key points are used to generate a shoulder-waist triangle, and the center of mass calculation method is used to calculate the center of mass of the shoulder-waist triangle. The calculated center of mass of the shoulder-waist triangle is determined as the initial sitting posture center of mass for normal driving of the vehicle driver.

[0118] S502, the vehicle camera collects a real-time sitting posture image of the driver;

[0119] S503, detecting shoulder key points, waist key points, and the center of mass of the current sitting posture;

[0120] Specifically, the current sitting posture image of the vehicle driver is obtained in real time and input into the trained key point detection model to recognize the current sitting posture image, automatically locate and identify the waist key points and shoulder key points in the current sitting posture image, and determine the specific positions of the waist key points and shoulder key points in the current sitting posture image based on the recognition results, and further determine the current sitting posture center of mass.

[0121] S504, determining whether the driver's sitting posture is abnormal;

[0122] S505, if the horizontal distance between the current sitting posture centroid and the initial sitting posture centroid coordinates is less than or equal to the first threshold, and the vertical distance is less than or equal to the second threshold, the driver's sitting posture is normal;

[0123] S506, the driver's sitting posture is abnormal;

[0124] It should be noted that if the horizontal distance between the current sitting posture center of mass and the predetermined initial sitting posture center of mass coordinates is greater than the first threshold, the driver's sitting posture is judged to be abnormal with obvious left and right deviations; if the vertical distance between the current sitting posture center of mass and the predetermined initial sitting posture center of mass coordinates is greater than the second threshold, the driver's sitting posture is judged to be abnormal with obvious up and down deviations.

[0125] S507, voice and text prompt;

[0126] S508, seat belt warning reminder;

[0127] S509, stop the warning prompt.

[0128] It should be noted that in the above steps, if it is determined that the sitting posture of the vehicle driver is abnormal, the vehicle computer is controlled to use at least one of voice reminders or text reminders to give a warning to the vehicle driver, and the number of warning reminders and the time of the warning reminders are counted. If the number of warning reminders within the preset period is greater than the preset reminder threshold, the active pre-tensioning seat belt is controlled to tighten or vibrate, and the vehicle driver is warned. After the driver resumes a safe sitting posture, the warning reminder is stopped.

[0129] The embodiment of the present invention intelligently detects the key points of the driver's waist and shoulders through the sitting posture image, thereby obtaining the center of mass position of the driver's shoulder-waist triangle, and uses the sitting posture center of mass to judge the sitting posture, which can quickly and accurately identify whether the driver's sitting posture is abnormal, improve the accuracy of driving posture judgment, and automatically perform driving warning and alert actions when it is detected that the driver is in an abnormal sitting posture, that is, there is a dangerous driving action, thereby reducing the probability of traffic accidents caused by the driver's dangerous driving actions during vehicle driving, and ensuring the effectiveness of safe vehicle driving.

[0130] Reference Figure 7 , shows a schematic structural diagram of a vehicle driving warning device provided by an embodiment of the present invention, the device comprising:

[0131] The image acquisition module 601 is used to acquire a sitting posture image of the vehicle driver and identify key points in the sitting posture image; wherein the key points include waist key points and shoulder key points;

[0132] A center of mass deviation module 602 is used to determine the center of mass of the current sitting posture using the waist key points and the shoulder key points, compare the position of the center of mass of the current sitting posture with the predetermined initial sitting posture center of mass, and generate a center of mass deviation result;

[0133] A sitting posture detection module 603 is used to detect whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result;

[0134] The early warning prompt module 604 is used to provide an early warning prompt to the vehicle driver in response to determining that the vehicle driver's sitting posture is abnormal.

[0135] Furthermore, the image acquisition module 601 includes:

[0136] The training submodule is used to collect images of a preset area using a vehicle camera, input the collected sample images into a preset neural network model for training, and obtain a key point detection model;

[0137] An acquisition submodule is used to acquire a current sitting posture image of the vehicle driver;

[0138] The recognition submodule is used to recognize the sitting posture image by using a key point detection model, and determine the waist key points and shoulder key points of the sitting posture image.

[0139] Furthermore, the centroid deviation module 602 includes:

[0140] A first generation submodule is used to generate a shoulder-waist triangle by using the waist key points and the shoulder key points;

[0141] A first calculation submodule is used to calculate the mass center of the shoulder-waist triangle, and determine the mass center of the shoulder-waist triangle as the mass center of the current sitting posture;

[0142] A first determination submodule is used to construct a rectangular coordinate system using a predetermined initial sitting posture mass center as a coordinate origin, and determine the coordinates of the current sitting posture mass center;

[0143] The second calculation submodule is used to calculate the coordinate distance between the initial sitting posture center of mass and the current sitting posture center of mass, and determine the horizontal distance and vertical distance of the center of mass coordinates as the center of mass deviation result.

[0144] Furthermore, the sitting posture detection module 603 includes:

[0145] A calibration submodule, used to calibrate a first threshold in the horizontal direction and a second threshold in the vertical direction in advance according to an actual vehicle;

[0146] a second determination submodule, for determining that the sitting posture of the vehicle driver is normal if the horizontal distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is less than or equal to a first threshold value, and the vertical distance is less than or equal to a second threshold value;

[0147] The third determining submodule is used to determine that the sitting posture of the vehicle driver is abnormal otherwise.

[0148] Furthermore, the early warning module 604 includes:

[0149] A second generating submodule is used for generating a warning issuing instruction in response to detecting that the sitting posture of the vehicle driver is abnormal;

[0150] The first warning submodule is used to control the vehicle computer to use at least one of voice reminder or text reminder to give a warning prompt to the vehicle driver according to the warning instruction;

[0151] The recording submodule is used to record the number of warning prompts and the time of the warning prompts.

[0152] Furthermore, the early warning module 604 also includes:

[0153] A sending submodule, used for sending a control instruction to the active pretensioner seat belt if the number of warning prompts within a preset period is greater than a preset prompt threshold;

[0154] The second warning submodule is used to control the active pre-tensioning seat belt to perform a tightening or vibration action to give a warning prompt to the vehicle driver.

[0155] Furthermore, the device also includes:

[0156] A sitting posture monitoring module, used to monitor changes in the sitting posture of the vehicle driver within a preset period;

[0157] The stop warning module is used to stop issuing warning prompts to the vehicle driver if it is monitored that the vehicle driver's sitting posture is updated to normal within a preset period.

[0158] The vehicle driving warning device provided by the embodiment of the present invention collects the sitting posture image of the vehicle driver, identifies the key points in the sitting posture image, uses the waist key points and the shoulder key points to determine the current sitting posture centroid, compares the current sitting posture centroid with the predetermined initial sitting posture centroid, generates the centroid deviation result, detects whether the sitting posture of the vehicle driver is abnormal according to the centroid deviation result, and issues a warning to the vehicle driver in response to determining that the sitting posture of the vehicle driver is abnormal. The embodiment of the present invention intelligently detects the waist and shoulder key points of the driver through the sitting posture image, thereby obtaining the centroid position of the driver's shoulder-waist triangle, and uses the sitting posture centroid to judge the sitting posture, which can quickly and accurately identify whether the driver's sitting posture is abnormal, improve the accuracy of driving posture judgment, and automatically performs driving warning and warning actions when it is detected that the driver is in an abnormal sitting posture, that is, there is a dangerous driving action, thereby reducing the probability of traffic accidents caused by the driver's dangerous driving actions during vehicle driving, and ensuring the effectiveness of vehicle safe driving.

[0159] Reference Figure 8 , an embodiment of the present invention further provides an electronic device, such as Figure 8 As shown, it includes a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704.

[0160] Memory 703, used for storing computer programs;

[0161] The processor 701 is used to execute the program stored in the memory 703 to implement the following steps:

[0162] Collecting a sitting posture image of the vehicle driver, and identifying key points in the sitting posture image; wherein the key points include waist key points and shoulder key points;

[0163] The waist key points and the shoulder key points are used to determine the current sitting posture center of mass, and the current sitting posture center of mass is compared with the predetermined initial sitting posture center of mass to generate a center of mass deviation result;

[0164] Detecting whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result;

[0165] In response to determining that the vehicle driver has an abnormal sitting posture, a warning prompt is given to the vehicle driver.

[0166] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0167] The communication interface is used for communication between the above terminal and other devices.

[0168] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0169] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0170] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the vehicle driving warning method described in any of the above embodiments.

[0171] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can 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 can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0172] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0173] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0174] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A vehicle driving warning method, characterized in that: The method comprises: Collecting a sitting posture image of the vehicle driver, and identifying key points in the sitting posture image; wherein the key points include waist key points and shoulder key points; The waist key points and the shoulder key points are used to determine the current sitting posture center of mass, and the current sitting posture center of mass is compared with the predetermined initial sitting posture center of mass to generate a center of mass deviation result; Detecting whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result; In response to determining that the vehicle driver has an abnormal sitting posture, a warning prompt is given to the vehicle driver.

2. The method according to claim 1, characterized in that: The step of collecting a sitting posture image of the vehicle driver and identifying key points in the sitting posture image, wherein the key points include waist key points and shoulder key points, includes: The vehicle camera is used to collect images of the preset area, and the collected sample images are input into the preset neural network model for training to obtain the key point detection model; Acquire the current sitting posture image of the vehicle driver; The sitting posture image is recognized by using a key point detection model to determine the waist key points and shoulder key points of the sitting posture image.

3. The method according to claim 1, characterized in that The method of using the waist key points and the shoulder key points to determine the current sitting posture center of mass, comparing the current sitting posture center of mass with the predetermined initial sitting posture center of mass, and generating a center of mass deviation result includes: Using the waist key points and the shoulder key points to generate a shoulder-waist triangle; Calculating the center of mass of the shoulder-waist triangle, and determining the center of mass of the shoulder-waist triangle as the center of mass of the current sitting posture; Taking the predetermined initial sitting posture center of mass as the coordinate origin, constructing a rectangular coordinate system, and determining the coordinates of the current sitting posture center of mass; The coordinate distance between the initial sitting posture center of mass and the current sitting posture center of mass is calculated, and the horizontal distance and vertical distance of the center of mass coordinates are determined as the center of mass deviation result.

4. The method according to claim 1, characterized in that: The detecting whether the sitting posture of the vehicle driver is abnormal according to the mass center deviation result includes: Pre-calibrate a first threshold in the horizontal direction and a second threshold in the vertical direction based on an actual vehicle; If the horizontal distance between the current sitting posture centroid and the predetermined initial sitting posture centroid coordinates is less than or equal to a first threshold, and the vertical distance is less than or equal to a second threshold, then it is determined that the sitting posture of the vehicle driver is normal; Otherwise, it is determined that the sitting posture of the vehicle driver is abnormal.

5. The method according to claim 1, characterized in that In response to determining that the vehicle driver has an abnormal sitting posture, giving an early warning to the vehicle driver includes: In response to detecting that the driver of the vehicle has an abnormal sitting posture, generating a warning issuing instruction; According to the warning instruction, the vehicle computer is controlled to use at least one of voice reminder or text reminder to give a warning to the vehicle driver; The number of warning prompts and the time of the warning prompts are recorded.

6. The method according to claim 5, characterized in that After recording the number of warning prompts and the time of the warning prompts, the method further includes: If the number of warning prompts within a preset period is greater than a preset prompt threshold, a control command is issued to the active pretensioner seat belt; The active pre-tensioning seat belt is controlled to perform a tightening or vibration action, and an early warning prompt is given to the vehicle driver.

7. The method according to claim 1, characterized in that After the driver of the vehicle is given an early warning in response to determining that the driver of the vehicle has an abnormal sitting posture, the method further includes: Monitoring the changes in the sitting posture of the driver of the vehicle within a preset period; If it is monitored that the sitting posture of the vehicle driver is updated to normal within a preset period, the early warning prompt to the vehicle driver is stopped.

8. A vehicle driving warning device, characterized in that: The device comprises: An image acquisition module, used to acquire a sitting posture image of the vehicle driver and identify key points in the sitting posture image; wherein the key points include waist key points and shoulder key points; A center of mass deviation module, used to determine the center of mass of the current sitting posture using the waist key points and the shoulder key points, compare the position of the center of mass of the current sitting posture with the predetermined initial sitting posture center of mass, and generate a center of mass deviation result; A sitting posture detection module, used to detect whether the sitting posture of the vehicle driver is abnormal according to the center of mass deviation result; The early warning prompt module is used to provide an early warning prompt to the vehicle driver in response to determining that the vehicle driver has an abnormal sitting posture.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the instructions to implement the vehicle driving warning method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle driving warning method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Posture-based examination cheating detection method

    CN110781762A

  • Human body key point stabilizing method based on hierarchical filtering

    CN113505735A

  • Driving sitting posture recognition method and device and computer readable storage medium

    CN115709720A

  • Three-dimensional object modelling fitting & tracking.

    EP2674913A1

  • System, multi-utility device and method to monitor vehicles for road saftey

    WO2021014464A1