A method, device and electronic equipment for detecting a sitting posture of a vehicle occupant

Abstract

The application provides a detection method and device for a vehicle occupant sitting posture and an electronic device. The application accurately determines a plurality of effective perception sensors corresponding to a correct posture of an occupant on a seat through a half-body image of the occupant and a seat posture in a plurality of perception sensors of the seat. When a double-knee image in the half-body image and data values respectively collected by the plurality of effective perception sensors satisfy a preset normal condition, it is determined that the whole-body sitting posture of the occupant is correct. The plurality of effective perception sensors that can be used for detection are accurately determined according to the body shape of the occupant and the seat posture, and the influence of invalid data on the detection result is reduced. Meanwhile, the data values respectively collected by the double-knee image and the plurality of effective perception sensors are used as the basis for detection, the whole body is ensured to be in detection, so that the whole body is in a correct sitting posture, the accuracy of the detection sitting posture is improved, the occupant is always in a safe and healthy sitting posture, and the damage degree of the occupant caused by an accident is reduced.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method, apparatus, medium, and electronic device for detecting the seating posture of vehicle occupants. Background Technology

[0002] When driving for extended periods, passengers are prone to fatigue, often leading to unhealthy sitting postures (such as crossing legs or slouching). Maintaining an unhealthy posture for a prolonged period can damage the body, affecting not only physical health (such as causing lumbar and cervical spondylosis) but also increasing the risk of serious injury in accidents. To address this, some related technologies have proposed methods for detecting passenger posture. These methods use multiple pressure sensors mounted on the seat to collect pressure values ​​from the passenger. By analyzing the differences in pressure values ​​from these sensors, the system determines whether the passenger's upper body posture is correct and alerts them to adjust their posture.

[0003] However, each occupant's height and weight vary, and the technology cannot effectively distinguish the impact of seat posture on the correct sitting posture, resulting in inaccurate posture detection. Furthermore, incorrect lower limb posture fails to provide effective support during an accident, causing serious injury to the occupant.

[0004] Therefore, this application provides a method for detecting the seating posture of vehicle occupants to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, medium, and electronic device for detecting the seating posture of vehicle occupants, which can solve at least one of the aforementioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of this application, in a first aspect, this application provides a method for detecting the seating posture of vehicle occupants, comprising:

[0007] Acquire a half-body image of an occupant sitting in a seat and the seat posture, wherein the half-body image includes a complete image of the occupant's head and both knees, and the surface of the seat is provided with multiple sensing sensors;

[0008] Among the multiple sensing sensors, multiple effective sensing sensors are used to determine the correct posture of the occupant on the seat based on the half-body image and the seat posture;

[0009] When the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet the preset normal conditions, it is determined that the occupant's sitting posture is correct.

[0010] Optionally, determining that the occupant's sitting posture is correct when the knee images in the half-body image and the data values ​​collected by the plurality of effective sensing sensors meet preset normal conditions includes:

[0011] The center of gravity area of ​​the seat cushion is determined based on multiple effective sensing sensors installed on the seat cushion, and

[0012] The center of gravity area of ​​the seat back is determined based on multiple effective sensing sensors installed on the seat back.

[0013] When the center of gravity area of ​​the seat cushion and the center of gravity area of ​​the backrest meet the preset normal contact conditions, the positional relationship of the knees is determined based on the position of the knee images in the half-body image.

[0014] When the positional relationship of the two knees meets the preset normal positional relationship conditions, the occupant's sitting posture is determined to be correct.

[0015] Optionally, the determination of the seat cushion's center of gravity region based on multiple effective sensing sensors disposed on the seat cushion includes:

[0016] Based on the multiple effective sensing sensors installed on the seat cushion of the seat, multiple first effective sensing sensors in the left area and multiple second effective sensing sensors in the right area are determined.

[0017] The center of gravity region of the seat cushion is determined based on the data values ​​collected by the multiple first effective sensing sensors in the left area and the data values ​​collected by the multiple second effective sensing sensors in the right area.

[0018] Optionally, determining the seat cushion center of gravity region based on the data values ​​collected by the plurality of first effective sensing sensors in the left region and the data values ​​collected by the plurality of second effective sensing sensors in the right region includes:

[0019] The average value of the left region is obtained based on the data values ​​collected by the multiple first effective sensing sensors in the left region, and

[0020] The average value of the right region is obtained based on the data values ​​collected by the multiple second effective sensing sensors in the right region.

[0021] When the absolute value of the difference between the average value of the left zone and the average value of the right zone is less than or equal to a preset first deviation threshold, the center of gravity region of the seat cushion is determined to be the left zone and the right zone seat cushion.

[0022] Optionally, the determination of the center of gravity region of the seat back based on multiple effective sensing sensors disposed on the seat back includes:

[0023] Based on the multiple effective sensing sensors installed on the back of the seat, multiple third effective sensing sensors in the upper area and multiple fourth effective sensing sensors in the lower area are determined.

[0024] The center of gravity region of the chair back is determined based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0025] Optionally, determining the chair back center of gravity region based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region includes:

[0026] The average value of the upper region is obtained based on the data values ​​collected by the multiple third effective sensing sensors in the upper region.

[0027] The average value of the lower region is obtained based on the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0028] When the absolute value of the difference between the average value of the lower region and the average value of the upper region is less than or equal to a preset second deviation threshold, the center of gravity region of the chair back is determined to be the upper region and the lower region.

[0029] Optionally, determining that the occupant's sitting posture is correct when the positional relationship of the two knees meets the preset normal positional relationship conditions includes:

[0030] When the knees can be located in the half-body image, and the angle between the line connecting the knees and the preset horizontal line is less than or equal to a preset deviation angle threshold, the occupant's sitting posture is determined to be correct.

[0031] Optionally, among the plurality of sensing sensors, the plurality of effective sensing sensors corresponding to determining the correct posture of the occupant on the seat based on the half-body image and the seat posture include:

[0032] Determine the frontal back contour and frontal hip contour based on the half-body image;

[0033] The effective back contour is determined based on the frontal back contour and the seat posture, and

[0034] The effective hip contour is determined based on the frontal hip contour and the seat posture.

[0035] The effective back contour is projected onto the back of the seat to determine the back contour area, and

[0036] The effective hip contour is projected onto the seat cushion of the seat to determine the seat cushion contour area;

[0037] Each sensing sensor in the chair back contour region is identified as a valid sensing sensor, and

[0038] Each sensing sensor in the seat cushion contour area is identified as a valid sensing sensor.

[0039] According to a specific embodiment of this application, in a second aspect, this application provides a device for detecting the seating posture of vehicle occupants, comprising:

[0040] Multiple sensing sensors are installed on the surface of the seat;

[0041] Multiple attitude sensors are configured to acquire the seat attitude of the seat;

[0042] A camera is positioned in front of the seat and configured to capture a half-body image of the occupant on the seat, wherein the half-body image includes a complete image of the occupant's head and both knees;

[0043] The processor is configured as follows:

[0044] Acquire a half-body image of the occupant sitting in the seat and the seat posture;

[0045] Based on the half-body image and the seat posture, multiple effective sensing sensors are determined from among the multiple sensing sensors to identify the correct posture of the occupant on the seat.

[0046] When the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet the preset normal conditions, it is determined that the occupant's sitting posture is correct.

[0047] Optionally, determining that the occupant's sitting posture is correct when the knee images in the half-body image and the data values ​​collected by the plurality of effective sensing sensors meet preset normal conditions includes:

[0048] The center of gravity area of ​​the seat cushion is determined based on multiple effective sensing sensors installed on the seat cushion, and

[0049] The center of gravity area of ​​the seat back is determined based on multiple effective sensing sensors installed on the seat back.

[0050] When the center of gravity area of ​​the seat cushion and the center of gravity area of ​​the backrest meet the preset normal contact conditions, the positional relationship of the knees is determined based on the position of the knee images in the half-body image.

[0051] When the positional relationship of the two knees meets the preset normal positional relationship conditions, the occupant's sitting posture is determined to be correct.

[0052] Optionally, the determination of the seat cushion's center of gravity region based on multiple effective sensing sensors disposed on the seat cushion includes:

[0053] Based on the multiple effective sensing sensors installed on the seat cushion of the seat, multiple first effective sensing sensors in the left area and multiple second effective sensing sensors in the right area are determined.

[0054] The center of gravity region of the seat cushion is determined based on the data values ​​collected by the multiple first effective sensing sensors in the left area and the data values ​​collected by the multiple second effective sensing sensors in the right area.

[0055] Optionally, determining the seat cushion center of gravity region based on the data values ​​collected by the plurality of first effective sensing sensors in the left region and the data values ​​collected by the plurality of second effective sensing sensors in the right region includes:

[0056] The average value of the left region is obtained based on the data values ​​collected by the multiple first effective sensing sensors in the left region, and

[0057] The average value of the right region is obtained based on the data values ​​collected by the multiple second effective sensing sensors in the right region.

[0058] When the absolute value of the difference between the average value of the left zone and the average value of the right zone is less than or equal to a preset first deviation threshold, the center of gravity region of the seat cushion is determined to be the left zone and the right zone seat cushion.

[0059] Optionally, the determination of the center of gravity region of the seat back based on multiple effective sensing sensors disposed on the seat back includes:

[0060] Based on the multiple effective sensing sensors installed on the back of the seat, multiple third effective sensing sensors in the upper area and multiple fourth effective sensing sensors in the lower area are determined.

[0061] The center of gravity region of the chair back is determined based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0062] Optionally, determining the chair back center of gravity region based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region includes:

[0063] The average value of the upper region is obtained based on the data values ​​collected by the multiple third effective sensing sensors in the upper region.

[0064] The average value of the lower region is obtained based on the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0065] When the absolute value of the difference between the average value of the lower region and the average value of the upper region is less than or equal to a preset second deviation threshold, the center of gravity region of the chair back is determined to be the upper region and the lower region.

[0066] Optionally, determining that the occupant's sitting posture is correct when the positional relationship of the two knees meets the preset normal positional relationship conditions includes:

[0067] When the knees can be located in the half-body image, and the angle between the line connecting the knees and the preset horizontal line is less than or equal to a preset deviation angle threshold, the occupant's sitting posture is determined to be correct.

[0068] Optionally, among the plurality of sensing sensors, the plurality of effective sensing sensors corresponding to determining the correct posture of the occupant on the seat based on the half-body image and the seat posture include:

[0069] Determine the frontal back contour and frontal hip contour based on the half-body image;

[0070] The effective back contour is determined based on the frontal back contour and the seat posture, and

[0071] The effective hip contour is determined based on the frontal hip contour and the seat posture.

[0072] The effective back contour is projected onto the back of the seat to determine the back contour area, and

[0073] The effective hip contour is projected onto the seat cushion of the seat to determine the seat cushion contour area;

[0074] Each sensing sensor in the chair back contour region is identified as a valid sensing sensor, and

[0075] Each sensing sensor in the seat cushion contour area is identified as a valid sensing sensor.

[0076] According to a specific embodiment of this application, in a third aspect, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle occupant seating posture detection method as described in any of the preceding claims.

[0077] According to a specific embodiment of this application, in a fourth aspect, this application provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the vehicle occupant seating posture detection method as described in any of the preceding claims.

[0078] Compared with the prior art, the above-described solutions of this application have at least the following beneficial effects:

[0079] This application provides a method, apparatus, medium, and electronic device for detecting the sitting posture of a vehicle occupant. This application accurately identifies multiple effective sensors corresponding to the correct posture of the occupant on the seat using a half-body image of the occupant and the seat posture, among multiple sensing sensors on the seat. When the knee images in the half-body image and the data values ​​collected by each of the multiple effective sensing sensors meet preset normal conditions, the occupant's full-body sitting posture is determined to be correct. Accurately identifying multiple effective sensing sensors that can actually be used for detection based on the occupant's body shape and seat posture reduces the impact of invalid data on the detection results. Simultaneously, using the knee images and the data values ​​collected by each of the multiple effective sensing sensors as the basis for detection ensures that the entire body is under detection, thus ensuring the correct sitting posture and improving the accuracy of posture detection. This ensures the occupant is always in a safe and healthy sitting posture, reducing the degree of harm to the occupant in an accident. Attached Figure Description

[0080] Figure 1 A flowchart of a method for detecting the seating posture of vehicle occupants according to an embodiment of this application is shown;

[0081] Figure 2 A unit block diagram of a vehicle occupant seating posture detection device according to an embodiment of this application is shown. Detailed Implementation

[0082] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0083] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0084] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0085] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0086] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0087] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0088] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0089] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0090] The embodiments provided in this application are embodiments of a method for detecting the sitting posture of vehicle occupants.

[0091] The following is combined with Figure 1 The embodiments of this application will be described in detail.

[0092] Step S101: Obtain a half-body image of the occupant sitting in the seat and the seat posture.

[0093] The half-body image includes a complete image of the occupant's head and knees, and the surface of the seat is equipped with multiple sensing sensors.

[0094] The half-body image includes a complete image of the occupant from the knees up. The half-body image can be an image of the occupant in any sitting position on the seat.

[0095] For example, a camera positioned in front of the seat can capture half-body images of the occupant while seated.

[0096] Correct sitting posture is primarily reflected in the upper body and legs. The position of the knees better characterizes the leg posture, simplifying leg recognition. Furthermore, due to the limited space inside the vehicle, half-body images are easier to capture, allowing detection to take into account both upper body and lower limb posture.

[0097] The surface of the seat includes the seat cushion surface and the backrest surface.

[0098] The sensing sensors include pressure sensors and / or distance sensors.

[0099] Step S102: Among the plurality of sensing sensors, determine the plurality of effective sensing sensors corresponding to the correct posture of the occupant on the seat based on the half-body image and the seat posture.

[0100] Seat posture determines the passenger's correct sitting posture. Multiple effective sensing sensors corresponding to the passenger's correct sitting posture are determined based on a half-body image. This allows for the accurate identification of the multiple effective sensing sensors that can actually be used for detection, based on the occupant's body shape and seat posture.

[0101] In some specific embodiments, determining the multiple effective sensing sensors corresponding to the correct posture of the occupant on the seat based on the half-body image and the seat posture among the plurality of sensing sensors includes the following steps:

[0102] Step S102-1: Determine the frontal back contour and frontal hip contour based on the half-body image.

[0103] The half-body image is input into the trained contour recognition model, which outputs the frontal back contour and the frontal hip contour. The process of training the contour recognition model is not described in detail in this embodiment, but can be implemented by referring to various methods in the prior art.

[0104] Step S102-2: Determine the effective back contour based on the frontal back contour and the seat posture, and determine the effective hip contour based on the frontal hip contour and the seat posture.

[0105] Based on how people sit, passengers do not rest their entire back against the seat back; only part of their back rests against the seat back. Similarly, passengers do not sit their entire buttocks on the seat cushion; only part of their buttocks rests on the seat cushion.

[0106] Effective back contour refers to the contour of an occupant's back when properly leaning against the seat back.

[0107] Effective hip contour refers to the contour of contact between the buttocks and the seat cushion when an occupant is properly seated.

[0108] Step S102-3: Project the effective back contour onto the back of the seat to determine the back contour area, and project the effective hip contour onto the seat cushion to determine the seat cushion contour area.

[0109] The backrest contour area refers to the area occupied by the seat back when the occupant is properly leaning against it;

[0110] The seat cushion outline area refers to the area occupied by the seat cushion when the occupant is properly seated on the seat cushion.

[0111] Step S102-4: Determine each sensing sensor in the backrest contour area as a valid sensing sensor, and determine each sensing sensor in the seat cushion contour area as a valid sensing sensor.

[0112] In this specific embodiment, the frontal back contour and frontal hip contour are determined using a half-body image. These contours are then combined with the seat posture to determine the effective back contour and effective hip contour. These effective back contours and effective hip contours are then projected onto the chair back and seat cushion, respectively, to determine the chair back contour region and seat cushion contour region. Finally, the effective sensing sensors in the chair back contour region and the effective sensing sensors in the seat cushion contour region are determined based on the occupant's body shape and seat posture. This accurately identifies multiple effective sensing sensors that can actually be used for detection.

[0113] Step S103: When the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet the preset normal conditions, it is determined that the occupant's sitting posture is correct.

[0114] This application embodiment accurately identifies multiple effective sensors corresponding to the occupant's correct posture on the seat using a half-body image and seat posture. When the knee images in the half-body image and the data values ​​collected by each of the multiple effective sensors meet preset normal conditions, the occupant's full-body sitting posture is determined to be correct. Accurately identifying the multiple effective sensors that can actually be used for detection based on the occupant's body shape and seat posture reduces the impact of invalid data on the detection results. Simultaneously, using the knee images and the data values ​​collected by each of the multiple effective sensors as the basis for detection ensures that the entire body is under detection, thus ensuring the correct sitting posture and improving the accuracy of posture detection. This ensures the occupant is always in a safe and healthy sitting posture, reducing the degree of harm to the occupant in an accident.

[0115] In some specific embodiments, determining that the occupant's sitting posture is correct when the knee images in the half-body image and the data values ​​collected by the plurality of effective sensing sensors meet preset normal conditions includes the following steps:

[0116] Step S103-1: Determine the center of gravity region of the seat cushion based on multiple effective sensing sensors installed on the seat cushion, and determine the center of gravity region of the seat back seat cushion based on multiple effective sensing sensors installed on the seat back.

[0117] The center of gravity area of ​​the seat cushion refers to the zone where the occupant's sitting posture has the greatest impact on the data values ​​of the effective sensing sensors on the seat cushion.

[0118] The center of gravity area of ​​the chair back refers to the area where the occupant's sitting posture has the greatest impact on the data values ​​of the effective sensing sensors on the chair back.

[0119] In some specific embodiments, determining the center of gravity region of the seat cushion based on multiple effective sensing sensors disposed on the seat cushion includes the following steps:

[0120] Step S103-1a-1: Based on the multiple effective sensing sensors installed on the seat cushion of the seat, determine multiple first effective sensing sensors in the left area and multiple second effective sensing sensors in the right area.

[0121] For example, based on the distribution area of ​​multiple effective sensing sensors installed on the seat cushion, the area can be divided into a left zone and a right zone. For instance, the area of ​​the left zone may be equal to the area of ​​the right zone, or the number of multiple first effective sensing sensors in the left zone may be equal to the number of multiple second effective sensing sensors in the right zone. Of course, this specific embodiment is not limited to this.

[0122] Step S103-1a-2: Determine the center of gravity region of the seat cushion based on the data values ​​collected by the multiple first effective sensing sensors in the left region and the data values ​​collected by the multiple second effective sensing sensors in the right region.

[0123] In some specific embodiments, determining the center of gravity region of the seat cushion based on the data values ​​collected by the plurality of first effective sensing sensors in the left region and the data values ​​collected by the plurality of second effective sensing sensors in the right region includes the following steps:

[0124] Step S103-1a-2-1: Obtain the average value of the left region based on the data values ​​collected by the multiple first effective sensing sensors in the left region, and obtain the average value of the right region based on the data values ​​collected by the multiple second effective sensing sensors in the right region.

[0125] Step S103-1a-2-2a: When the absolute value of the difference between the average value of the left area and the average value of the right area is less than or equal to a preset first deviation threshold, the center of gravity area of ​​the seat cushion is determined to be the left area and the right area.

[0126] The center of gravity area of ​​the seat cushion is defined as the left and right zones. This can be understood as the occupant sitting stably on the backrest and seat cushion with their center of gravity between the left and right zones. This arrangement helps the occupant maintain stability while sitting on the seat cushion.

[0127] In this specific embodiment, when the absolute value of the difference between the average value of the left area and the average value of the right area is less than or equal to a preset first deviation threshold, it is determined that the influence of the occupant's sitting posture on the data values ​​collected by the multiple first effective sensing sensors in the left area of ​​the seat cushion is similar to the influence of the data values ​​collected by the multiple second effective sensing sensors in the right area, so as to avoid the influence of the slight left and right swaying of the occupant's body on the detection results.

[0128] Further, in step S103-1a-2-2b, when the absolute value of the difference between the average value of the left area and the average value of the right area is greater than a preset first deviation threshold, and when the average value of the left area is greater than the average value of the right area, the center of gravity region of the seat cushion is determined to be the left area.

[0129] Further, in step S103-1a-2-2c, when the absolute value of the difference between the average value of the left area and the average value of the right area is greater than a preset first deviation threshold, and when the average value of the left area is less than the average value of the right area, the center of gravity area of ​​the seat cushion is determined to be the right area.

[0130] Steps S103-1a-2-2a, S103-1a-2-2b, and S103-1a-2-2c simply indicate that there are three steps, not the order in which they are executed.

[0131] In some specific embodiments, determining the center of gravity region of the seat back based on multiple effective sensing sensors disposed on the seat back includes the following steps:

[0132] Step S103-1b-1: Based on the multiple effective sensing sensors installed on the back of the seat, determine the multiple third effective sensing sensors in the upper area and the multiple fourth effective sensing sensors in the lower area.

[0133] For example, based on the distribution area of ​​multiple effective sensing sensors installed on the back of the seat, the area can be divided into an upper region and a lower region. For instance, the area of ​​the upper region may be equal to the area of ​​the lower region, or the number of multiple third effective sensing sensors in the upper region may be equal to the number of multiple fourth effective sensing sensors in the lower region. Of course, this specific embodiment is not limited to this.

[0134] Step S103-1b-2: Determine the center of gravity region of the chair back based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0135] In some specific embodiments, determining the center of gravity region of the chair back based on the data values ​​collected by the plurality of third effective sensing sensors in the upper region and the data values ​​collected by the plurality of fourth effective sensing sensors in the lower region includes the following steps:

[0136] Step S103-1b-2-1: Obtain the average value of the upper region based on the data values ​​collected by the multiple third effective sensing sensors in the upper region, and obtain the average value of the lower region based on the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0137] Step S103-1b-2-2a: When the absolute value of the difference between the average value of the lower region and the average value of the upper region is less than or equal to a preset second deviation threshold, the center of gravity region of the chair back is determined to be the upper region and the lower region.

[0138] The center of gravity area of ​​the chair back is defined as the upper and lower sections. This means that when the occupant leans comfortably against the chair back, the backrest fully supports their upper body. This allows the occupant to fully extend their upper body, preventing hunching and promoting their health. Furthermore, in the event of an accident, the chair back provides support to the occupant's upper body, reducing the risk of injury.

[0139] In this specific embodiment, when the absolute value of the difference between the average value of the lower area and the average value of the upper area is less than or equal to a preset second deviation threshold, it is determined that the influence of the occupant's sitting posture on the data values ​​collected by the multiple third effective sensing sensors in the upper area of ​​the backrest is similar to the influence of the data values ​​collected by the multiple fourth effective sensing sensors in the lower area, thus avoiding the influence of slight back-and-forth swaying of the occupant's body on the detection results.

[0140] Further, in step S103-1b-2-2b, when the difference between the average value of the lower region and the average value of the upper region is greater than a preset second deviation threshold, the center of gravity region of the chair back is determined to be the lower region.

[0141] Further, in step S103-1b-2-2c, when the difference between the average value of the upper region and the average value of the lower region is greater than a preset second deviation threshold, the center of gravity region of the chair back is determined to be the upper region.

[0142] Further, in step S103-1b-2-2d, when both the lower region average value and the lower region average value are less than a preset leaning threshold, the chair back center of gravity region is determined to be the no-lean region.

[0143] Steps S103-1b-2-2a, S103-1b-2-2b, S103-1b-2-2c, and S103-1b-2-2d simply indicate that there are four steps, not the order in which they are executed.

[0144] Step S103-2: When the center of gravity area of ​​the seat cushion and the center of gravity area of ​​the backrest meet the preset normal contact conditions, the positional relationship of the two knees is determined based on the position of the two knee images in the half-body image.

[0145] The default normal contact conditions are: the center of gravity areas of the seat cushion are the left and right areas, and the center of gravity areas of the chair back are the upper and lower areas.

[0146] Step S103-3: When the positional relationship of the two knees meets the preset normal positional relationship conditions, it is determined that the occupant's sitting posture is correct.

[0147] In some specific embodiments, determining that the occupant's sitting posture is correct when the positional relationship of the two knees meets a preset normal positional relationship condition includes:

[0148] Step S103-3a: When the knees can be located in the half-body image and the angle between the line connecting the knees and the preset horizontal line is less than or equal to the preset deviation angle threshold, the occupant's sitting posture is determined to be correct.

[0149] In this specific embodiment, the knees can be located in the half-body image, indicating that the center positions of both knees are facing forward of the seat; the angle between the line connecting the knees and the preset horizontal line is less than or equal to a preset deviation angle threshold, ensuring that both feet are at the same height (e.g., on the floor). In the event of an accident, this facilitates the knee joints to quickly mobilize the legs and feet to support the body, preventing the body from lunging forward and causing damage to the chest cavity.

[0150] This application also provides an apparatus embodiment that follows the above embodiments, used to implement the method steps described in the above embodiments. The interpretation of the same names is the same as that in the above embodiments, and the same technical effects are achieved. Therefore, it will not be repeated here.

[0151] like Figure 2 As shown, this application provides a vehicle occupant seating posture detection device 200, comprising:

[0152] Multiple sensing sensors 201 are disposed on the surface of the seat;

[0153] Multiple attitude sensors 202 are configured to collect the seat attitude of the seat;

[0154] Camera 203 is located in front of the seat and configured to capture half-body images of the occupant on the seat, wherein the half-body images include complete images of the occupant's head and both knees;

[0155] Processor 204, configured as follows:

[0156] Acquire a half-body image of the occupant sitting in the seat and the seat posture;

[0157] Based on the half-body image and the seat posture, multiple effective sensing sensors are determined from among the multiple sensing sensors to identify the correct posture of the occupant on the seat.

[0158] When the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet the preset normal conditions, it is determined that the occupant's sitting posture is correct.

[0159] Optionally, determining that the occupant's sitting posture is correct when the knee images in the half-body image and the data values ​​collected by the plurality of effective sensing sensors meet preset normal conditions includes:

[0160] The center of gravity area of ​​the seat cushion is determined based on multiple effective sensing sensors installed on the seat cushion, and

[0161] The center of gravity area of ​​the seat back is determined based on multiple effective sensing sensors installed on the seat back.

[0162] When the center of gravity area of ​​the seat cushion and the center of gravity area of ​​the backrest meet the preset normal contact conditions, the positional relationship of the knees is determined based on the position of the knee images in the half-body image.

[0163] When the positional relationship of the two knees meets the preset normal positional relationship conditions, the occupant's sitting posture is determined to be correct.

[0164] Optionally, the determination of the seat cushion's center of gravity region based on multiple effective sensing sensors disposed on the seat cushion includes:

[0165] Based on the multiple effective sensing sensors installed on the seat cushion of the seat, multiple first effective sensing sensors in the left area and multiple second effective sensing sensors in the right area are determined.

[0166] The center of gravity region of the seat cushion is determined based on the data values ​​collected by the multiple first effective sensing sensors in the left area and the data values ​​collected by the multiple second effective sensing sensors in the right area.

[0167] Optionally, determining the seat cushion center of gravity region based on the data values ​​collected by the plurality of first effective sensing sensors in the left region and the data values ​​collected by the plurality of second effective sensing sensors in the right region includes:

[0168] The average value of the left region is obtained based on the data values ​​collected by the multiple first effective sensing sensors in the left region, and

[0169] The average value of the right region is obtained based on the data values ​​collected by the multiple second effective sensing sensors in the right region.

[0170] When the absolute value of the difference between the average value of the left zone and the average value of the right zone is less than or equal to a preset first deviation threshold, the center of gravity region of the seat cushion is determined to be the left zone and the right zone seat cushion.

[0171] Optionally, the determination of the center of gravity region of the seat back based on multiple effective sensing sensors disposed on the seat back includes:

[0172] Based on the multiple effective sensing sensors installed on the back of the seat, multiple third effective sensing sensors in the upper area and multiple fourth effective sensing sensors in the lower area are determined.

[0173] The center of gravity region of the chair back is determined based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0174] Optionally, determining the chair back center of gravity region based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region includes:

[0175] The average value of the upper region is obtained based on the data values ​​collected by the multiple third effective sensing sensors in the upper region.

[0176] The average value of the lower region is obtained based on the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

[0177] When the absolute value of the difference between the average value of the lower region and the average value of the upper region is less than or equal to a preset second deviation threshold, the center of gravity region of the chair back is determined to be the upper region and the lower region.

[0178] Optionally, determining that the occupant's sitting posture is correct when the positional relationship of the two knees meets the preset normal positional relationship conditions includes:

[0179] When the knees can be located in the half-body image, and the angle between the line connecting the knees and the preset horizontal line is less than or equal to a preset deviation angle threshold, the occupant's sitting posture is determined to be correct.

[0180] Optionally, among the plurality of sensing sensors, the plurality of effective sensing sensors corresponding to determining the correct posture of the occupant on the seat based on the half-body image and the seat posture include:

[0181] Determine the frontal back contour and frontal hip contour based on the half-body image;

[0182] The effective back contour is determined based on the frontal back contour and the seat posture, and

[0183] The effective hip contour is determined based on the frontal hip contour and the seat posture.

[0184] The effective back contour is projected onto the back of the seat to determine the back contour area, and

[0185] The effective hip contour is projected onto the seat cushion of the seat to determine the seat cushion contour area;

[0186] Each sensing sensor in the chair back contour region is identified as a valid sensing sensor, and

[0187] Each sensing sensor in the seat cushion contour area is identified as a valid sensing sensor.

[0188] This application embodiment accurately identifies multiple effective sensors corresponding to the occupant's correct posture on the seat using a half-body image and seat posture. When the knee images in the half-body image and the data values ​​collected by each of the multiple effective sensors meet preset normal conditions, the occupant's full-body sitting posture is determined to be correct. Accurately identifying the multiple effective sensors that can actually be used for detection based on the occupant's body shape and seat posture reduces the impact of invalid data on the detection results. Simultaneously, using the knee images and the data values ​​collected by each of the multiple effective sensors as the basis for detection ensures that the entire body is under detection, thus ensuring the correct sitting posture and improving the accuracy of posture detection. This ensures the occupant is always in a safe and healthy sitting posture, reducing the degree of harm to the occupant in an accident.

[0189] This embodiment provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method steps described in the above embodiment.

[0190] This application provides a non-volatile computer storage medium storing computer-executable instructions that can perform the steps described in the above embodiments.

[0191] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0192] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting the seating posture of vehicle occupants, characterized in that, include: Acquire a half-body image of an occupant sitting in a seat and the seat posture, wherein the half-body image includes a complete image of the occupant's head and both knees, and the surface of the seat is provided with multiple sensing sensors; Among the multiple sensing sensors, multiple effective sensing sensors are used to determine the correct posture of the occupant on the seat based on the half-body image and the seat posture; When the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet the preset normal conditions, it is determined that the occupant's sitting posture is correct. The step of determining that the occupant's sitting posture is correct when the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet preset normal conditions includes: The center of gravity area of ​​the seat cushion is determined based on multiple effective sensing sensors installed on the seat cushion, and The center of gravity area of ​​the seat back is determined based on multiple effective sensing sensors installed on the seat back. When the center of gravity area of ​​the seat cushion and the center of gravity area of ​​the backrest meet the preset normal contact conditions, the positional relationship of the knees is determined based on the position of the knee images in the half-body image. When the positional relationship of the two knees meets the preset normal positional relationship conditions, it is determined that the occupant's sitting posture is correct; Among the plurality of sensing sensors, the effective sensing sensors that determine the correct posture of the occupant on the seat based on the half-body image and the seat posture include: Determine the frontal back contour and frontal hip contour based on the half-body image; The effective back contour is determined based on the frontal back contour and the seat posture, and The effective hip contour is determined based on the frontal hip contour and the seat posture. The effective back contour is projected onto the back of the seat to determine the back contour area, and The effective hip contour is projected onto the seat cushion of the seat to determine the seat cushion contour area; Each sensing sensor in the chair back contour region is identified as a valid sensing sensor, and Each sensing sensor in the seat cushion contour area is identified as a valid sensing sensor.

2. The method according to claim 1, characterized in that, The determination of the seat cushion's center of gravity region based on multiple effective sensing sensors installed on the seat cushion includes: Based on the multiple effective sensing sensors installed on the seat cushion of the seat, multiple first effective sensing sensors in the left area and multiple second effective sensing sensors in the right area are determined. The center of gravity region of the seat cushion is determined based on the data values ​​collected by the multiple first effective sensing sensors in the left area and the data values ​​collected by the multiple second effective sensing sensors in the right area.

3. The method according to claim 2, characterized in that, The determination of the seat cushion center of gravity region based on the data values ​​collected by the multiple first effective sensing sensors in the left area and the data values ​​collected by the multiple second effective sensing sensors in the right area includes: The average value of the left region is obtained based on the data values ​​collected by the multiple first effective sensing sensors in the left region, and The average value of the right region is obtained based on the data values ​​collected by the multiple second effective sensing sensors in the right region. When the absolute value of the difference between the average value of the left zone and the average value of the right zone is less than or equal to a preset first deviation threshold, the center of gravity region of the seat cushion is determined to be the left zone and the right zone seat cushion.

4. The method according to claim 1, characterized in that, The determination of the center of gravity region of the seat back based on multiple effective sensing sensors installed on the seat back includes: Based on the multiple effective sensing sensors installed on the back of the seat, multiple third effective sensing sensors in the upper area and multiple fourth effective sensing sensors in the lower area are determined. The center of gravity region of the chair back is determined based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region.

5. The method according to claim 4, characterized in that, The determination of the chair back center of gravity region based on the data values ​​collected by the multiple third effective sensing sensors in the upper region and the data values ​​collected by the multiple fourth effective sensing sensors in the lower region includes: The average value of the upper region is obtained based on the data values ​​collected by the multiple third effective sensing sensors in the upper region. The average value of the lower region is obtained based on the data values ​​collected by the multiple fourth effective sensing sensors in the lower region. When the absolute value of the difference between the average value of the lower region and the average value of the upper region is less than or equal to a preset second deviation threshold, the center of gravity region of the chair back is determined to be the upper region and the lower region.

6. The method according to claim 1, characterized in that, Determining that the occupant's sitting posture is correct when the positional relationship of the two knees meets the preset normal positional relationship conditions includes: When the knees can be located in the half-body image, and the angle between the line connecting the knees and the preset horizontal line is less than or equal to a preset deviation angle threshold, the occupant's sitting posture is determined to be correct.

7. A device for detecting the seating posture of vehicle occupants, characterized in that, include: Multiple sensing sensors are installed on the surface of the seat; Multiple attitude sensors are configured to acquire the seat attitude of the seat; A camera is positioned in front of the seat and configured to capture a half-body image of the occupant on the seat, wherein the half-body image includes a complete image of the occupant's head and both knees; The processor is configured as follows: Acquire a half-body image of the occupant sitting in the seat and the seat posture; Based on the half-body image and the seat posture, multiple effective sensing sensors are determined from among the multiple sensing sensors to identify the correct posture of the occupant on the seat. When the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet the preset normal conditions, it is determined that the occupant's sitting posture is correct. The step of determining that the occupant's sitting posture is correct when the knee images in the half-body image and the data values ​​collected by the multiple effective sensing sensors meet preset normal conditions includes: The center of gravity area of ​​the seat cushion is determined based on multiple effective sensing sensors installed on the seat cushion, and The center of gravity area of ​​the seat back is determined based on multiple effective sensing sensors installed on the seat back. When the center of gravity area of ​​the seat cushion and the center of gravity area of ​​the backrest meet the preset normal contact conditions, the positional relationship of the knees is determined based on the position of the knee images in the half-body image. When the positional relationship of the two knees meets the preset normal positional relationship conditions, it is determined that the occupant's sitting posture is correct; Among the plurality of sensing sensors, the effective sensing sensors that determine the correct posture of the occupant on the seat based on the half-body image and the seat posture include: Determine the frontal back contour and frontal hip contour based on the half-body image; The effective back contour is determined based on the frontal back contour and the seat posture, and The effective hip contour is determined based on the frontal hip contour and the seat posture. The effective back contour is projected onto the back of the seat to determine the back contour area, and The effective hip contour is projected onto the seat cushion of the seat to determine the seat cushion contour area; Each sensing sensor in the chair back contour region is identified as a valid sensing sensor, and Each sensing sensor in the seat cushion contour area is identified as a valid sensing sensor.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

Images