Safety belt detection device and safety belt wearing identification system and method

Abstract

The invention relates to a safety belt detection device, a safety belt wearing identification system and a safety belt wearing identification method, relates to the technical field of vehicles, and is used for guaranteeing the accuracy of safety belt wearing identification while reducing the hardware cost. The safety belt detection device comprises a plurality of detection branches which are connected in parallel, each detection branch corresponds to a safety belt lock catch on a seat, a first resistor and a switch are arranged on each detection branch, and the switches on the detection branches are closed when the safety belt lock catches are inserted; the first end of the second resistor is connected with a first reference voltage end, the second end of the second resistor is connected with the first ends of the plurality of detection branches, the second ends of the plurality of detection branches are connected with a second reference voltage end, and the voltage of the first reference voltage end is higher than that of the second reference voltage end; and the acquisition device is used for acquiring an electrical parameter signal at the second end of the second resistor, so that the hardware cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, specifically to a seat belt detection device, a seat belt wearing recognition system, and a method. Background Technology

[0002] In recent years, with continuous economic development and a sustained increase in vehicle ownership, the frequency of vehicle use has significantly increased, making road traffic safety issues increasingly prominent. Against this backdrop, seatbelt recognition, as a core component of active safety systems, has become a crucial line of defense for protecting the lives of drivers and passengers.

[0003] In related technologies, seatbelt wearing is detected using buckle sensors. However, buckle sensors mostly employ mechanical switches and matching independent wiring harnesses, which are costly. Furthermore, mechanical switches have a high rate of contact failure, which can negatively impact the stability of seatbelt wearing recognition. Therefore, improving the overall performance of seatbelt recognition is a pressing issue that needs to be addressed. Summary of the Invention

[0004] This invention provides a seat belt detection device, a seat belt wearing recognition system and method to solve the problem of poor overall performance of seat belt recognition function in related technologies.

[0005] In a first aspect, a seatbelt detection device is provided, comprising: a plurality of detection branches 10 connected in parallel, each detection branch corresponding to a seatbelt buckle on a seat, each detection branch being provided with a first resistor and a switch, the switch on the detection branch being closed when the seatbelt buckle is inserted; a second resistor, the first end of the second resistor being connected to a first reference voltage terminal, the second end of the second resistor being connected to the first end of the plurality of detection branches, the second end of the plurality of detection branches being connected to a second reference voltage terminal, the voltage of the first reference voltage terminal being higher than the voltage of the second reference voltage terminal; and a data acquisition device for acquiring electrical parameter signals at the second end of the second resistor.

[0006] The beneficial effects of this invention are as follows: By employing a parallel structure of multiple independent detection branches, a fault in one branch does not affect other branches, effectively ensuring the stable operation of seat belt detection. Each detection branch corresponds to a seat belt buckle and is equipped with a switch, providing a one-to-one correspondence and clearly defined switch status. The second resistor and multiple detection branches form a voltage divider circuit. By acquiring the electrical parameter signal at the second terminal of the second resistor through a data acquisition device, the seat belt detection device can accurately determine whether the seat belt is inserted or removed. Therefore, during seat belt wearing detection, the seat belt status can be directly determined, improving detection accuracy and reliability. This seat belt detection device has a simple structural design, reducing hardware costs and thus improving the overall performance of the seat belt recognition function.

[0007] Furthermore, the resistance values ​​of the first resistors on the different detection branches mentioned above are different.

[0008] Based on the above technical means, by setting different resistance values ​​for the first resistor on different detection branches, it is possible to accurately identify the seat corresponding to the change in seat belt status, thereby improving the reliability and anti-interference capability of seat belt detection.

[0009] Furthermore, the aforementioned acquisition device is adapted to be connected to a vehicle controller, and the acquisition device is configured to send electrical parameter signals to the vehicle controller; the vehicle controller is configured to determine the seat in the vehicle where the seat belt buckle is inserted based on the resistance value of the second resistor (20), the potential difference between the first reference voltage and the second reference voltage, the electrical parameter signals, and the resistance value of the first resistor (101) on each detection branch (10).

[0010] Based on the above technical means, by using the resistance value of the second resistor, the potential difference between the first and second reference voltages, electrical parameter signals, and the resistance value of the first resistor on each detection branch, the seat buckle can be accurately identified. This ensures that the seat belt usage status can be accurately identified in complex scenarios, avoiding misjudgments and omissions, providing an effective basis for subsequent warnings, and improving vehicle driving safety.

[0011] In a second aspect, a seatbelt wearing recognition system is provided, comprising: a camera for capturing images inside a vehicle; a seatbelt detection device as described in the first aspect; and a vehicle controller connected to the camera and the seatbelt detection device, respectively. The vehicle controller is configured to: in response to determining that a seatbelt buckle on a target seat is engaged based on electrical parameter signals from the seatbelt detection device, acquire multiple images inside the vehicle captured by the camera within a preset historical time period; and determine a seatbelt wearing detection result based on the multiple images inside the vehicle, the seatbelt wearing detection result being used to indicate whether the occupant is correctly wearing a seatbelt in the target seat.

[0012] The beneficial effects of this invention are as follows: by acquiring in-vehicle images based on the electrical parameter signals of the seat belt detection device when the seat belt buckle is inserted, and performing depth verification based on the in-vehicle images to determine the seat belt wearing status, various unsafe seat belt wearing behaviors can be detected in a timely manner, thereby improving the accuracy and reliability of seat belt wearing detection results.

[0013] Furthermore, the vehicle controller is configured to determine the seatbelt wearing detection result based on multiple in-vehicle images, including: identifying whether an occupant is in the target seat based on the multiple in-vehicle images; in response to identifying that an occupant is in the target seat, determining the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seatbelt and the occupant's body based on the multiple in-vehicle images; wherein, the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle; and determining the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body.

[0014] Based on the aforementioned technical means, identifying whether there is an occupant in the target seat can help to promptly detect whether the seat belt is incorrectly fastened; dual verification of the occupant's hand movements and the relative positional relationship between the seat belt and the occupant's body can determine the seat belt wearing detection results, thereby improving the accuracy and reliability of seat belt wearing detection and effectively avoiding misjudgments or omissions caused by a single detection factor.

[0015] Furthermore, the vehicle controller is configured to determine the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt and the occupant's body based on multiple in-vehicle images, including: determining the positional information of the occupant's area in the in-vehicle images based on the deployment position of the camera in the vehicle and the deployment position of the target seat in the vehicle; segmenting the region image from the in-vehicle images based on the positional information of the occupant's area in the in-vehicle images; and determining the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt and the occupant's body based on the respective region images of the multiple in-vehicle images.

[0016] Based on the above technical means, the acquired in-vehicle images are analyzed for occupant position and segmented to obtain regional images. Based on the acquired regional images, the hand movements of the occupant in the target seat and the positional relationship between the seat belt and the occupant are determined. This can reduce the interference of irrelevant information and thus improve the accuracy of the relative positional relationship.

[0017] Furthermore, the vehicle controller is configured to determine the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body. This includes: determining that the occupant in the target seat is correctly wearing the seatbelt if the hand movement detection result indicates that the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle, and the relative positional relationship between the seatbelt and the occupant's body meets the correct wearing conditions; and determining that the occupant in the target seat is not correctly wearing the seatbelt if the hand movement detection result indicates that the occupant has not made a hand movement to insert the seatbelt into the seatbelt buckle, and / or the relative positional relationship between the seatbelt and the occupant's body does not meet the correct wearing conditions. The correct wearing conditions include: the seatbelt passes through the occupant's body, and the distance between the seatbelt and the occupant's body surface does not exceed a preset distance threshold.

[0018] Based on the aforementioned technical methods, relying solely on single hand gesture detection to determine whether an occupant is wearing a seatbelt, or on seatbelt position detection, is susceptible to interference from movements, vehicle shaking, and objects pressing against the seatbelt, leading to detection errors. Adopting a multi-factor verification approach, considering whether the occupant has inserted the seatbelt into the buckle, whether the seatbelt passes through the body, and whether the distance between the seatbelt and the occupant's body exceeds a certain threshold, can significantly reduce errors caused by single factors, improve detection reliability and accuracy, and provide strong protection for vehicle safety management and occupant safety.

[0019] Furthermore, the seatbelt wearing recognition system also includes a human-machine interface module, which is connected to the vehicle controller. The vehicle controller is also configured to control the human-machine interface module to issue an alarm message when no occupant is detected in the target seat, or when the seatbelt wearing detection result indicates that the occupant in the target seat is not wearing the seatbelt correctly.

[0020] Based on the aforementioned technical means, by issuing timely warnings when no occupant is detected in the target seat or when the occupant is not wearing a seat belt correctly, the possibility of the occupant wearing the seat belt incorrectly can be effectively avoided, and the occupant can be reminded to wear the seat belt correctly. This helps to reduce the risk of occupant injury in traffic accidents and provides strong protection for the occupant's life safety.

[0021] Thirdly, a seatbelt wearing identification method is provided, comprising: acquiring electrical parameter signals collected by a seatbelt detection device; the seatbelt detection device being the same as the seatbelt detection device described in the first aspect; determining the seat in the vehicle where the seatbelt buckle is inserted based on the electrical parameter signals and the circuit configuration information of the seatbelt detection device; wherein the circuit configuration information includes the resistance value of a second resistor, the potential difference between a first reference voltage and a second reference voltage, and the resistance value of the first resistor on each detection branch.

[0022] The beneficial effects of this invention are as follows: By comprehensively utilizing the circuit configuration information and electrical parameter signals of the seat belt detection device, the seat in the vehicle where the seat belt buckle is engaged can be determined, which can help to carry out seat belt wearing detection for specific seats in the future, and effectively improve the accuracy and reliability of seat belt wearing detection.

[0023] Furthermore, the above method also includes: in response to determining that the seat belt buckle on the target seat is engaged based on the electrical parameter signal of the seat belt detection device, acquiring multiple in-vehicle images captured by the camera within a preset historical time period; determining the seat belt wearing detection result based on the multiple in-vehicle images, the seat belt wearing detection result being used to indicate whether the occupant is wearing the seat belt correctly in the target seat.

[0024] Based on the aforementioned technical means, and using the electrical parameter signals of the seat belt detection device, an in-vehicle image is acquired when the seat belt buckle is confirmed to be inserted. Based on the in-vehicle image, depth verification is performed to determine the seat belt wearing status. This allows for the timely detection of various unsafe seat belt wearing behaviors, thereby improving the accuracy and reliability of seat belt wearing detection results.

[0025] Furthermore, the seatbelt wearing detection result is determined based on multiple in-vehicle images, including: identifying whether an occupant is in the target seat based on multiple in-vehicle images; in response to identifying that an occupant is in the target seat, determining the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seatbelt and the occupant's body based on multiple in-vehicle images; wherein, the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle; and determining the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body.

[0026] Based on the aforementioned technical means, identifying whether there is an occupant in the target seat can help to promptly detect whether the seat belt is incorrectly fastened; dual verification of the occupant's hand movements and the relative position of the seat belt and the occupant's body to determine the seat belt wearing detection result can improve the accuracy and reliability of seat belt wearing detection and effectively avoid misjudgment or omission due to a single detection factor.

[0027] Furthermore, based on multiple in-vehicle images, the detection results of the occupant's hand movements in the target seat and the relative positional relationship between the seat belt and the occupant's body are determined, including: determining the location information of the occupant's area in the in-vehicle images based on the deployment position of the camera and the target seat in the vehicle; segmenting the region image from the in-vehicle images based on the location information of the occupant's area in the in-vehicle images; and determining the detection results of the occupant's hand movements in the target seat and the relative positional relationship between the seat belt and the occupant's body based on the respective region images of the multiple in-vehicle images.

[0028] Based on the above technical means, the acquired in-vehicle images are analyzed for occupant position and segmented to obtain regional images. Based on the acquired regional images, the hand movements of the occupant in the target seat and the positional relationship between the seat belt and the occupant are determined. This can reduce the interference of irrelevant information and thus improve the accuracy of the relative positional relationship.

[0029] Furthermore, based on the hand movement detection results and the relative positional relationship between the seat belt and the occupant's body, the seat belt wearing detection result is determined, including: if the hand movement detection result indicates that the occupant has made a hand movement to insert the seat belt into the seat belt buckle, and the relative positional relationship between the seat belt and the occupant's body meets the correct wearing conditions, the occupant is determined to be wearing the seat belt correctly; if the hand movement detection result indicates that the occupant has not made a hand movement to insert the seat belt into the seat belt buckle, and / or the relative positional relationship between the seat belt and the occupant's body does not meet the correct wearing conditions, the occupant is determined to be not wearing the seat belt correctly; wherein, the correct wearing conditions include: the seat belt passes through the occupant's body, and the distance between the seat belt and the occupant's body surface does not exceed a preset distance threshold.

[0030] Based on the aforementioned technical methods, relying solely on single hand gesture detection to determine whether an occupant is wearing a seatbelt, or on seatbelt position detection, is susceptible to interference from movements, vehicle shaking, and objects pressing against the seatbelt, leading to detection errors. Adopting a multi-factor verification approach, considering whether the occupant has inserted the seatbelt into the buckle, whether the seatbelt passes through the body, and whether the distance between the seatbelt and the occupant's body exceeds a certain threshold, can significantly reduce errors caused by single factors, improve detection reliability and accuracy, and provide strong protection for vehicle safety management and occupant safety.

[0031] Furthermore, the above method also includes issuing an alarm message when no occupant is detected in the target seat, or when the seat belt wearing detection result indicates that the occupant is not wearing the seat belt correctly.

[0032] Based on the aforementioned technical means, by issuing timely warnings when no occupant is detected in the target seat or when the occupant is not wearing a seat belt correctly, the possibility of the occupant wearing the seat belt incorrectly can be effectively avoided, and the occupant can be reminded to wear the seat belt correctly. This helps to reduce the risk of occupant injury in traffic accidents and provides strong protection for the occupant's life safety.

[0033] Fourthly, an electronic device is provided, comprising: a processor and a memory; the memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of the third aspect described above.

[0034] Fifthly, a vehicle is provided, comprising: the seat belt detection device of the first aspect; or the seat belt wearing recognition system of the second aspect; or the electronic device of the fourth aspect.

[0035] In a sixth aspect, a computer-readable storage medium is provided, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method of the third aspect described above.

[0036] In a seventh aspect, a computer program product is provided, comprising computer instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the third aspect.

[0037] The beneficial effects of this invention are:

[0038] (1) By adopting a parallel structure of multiple independent detection branches, a single branch failure does not affect other branches, effectively ensuring the stable operation of seat belt detection. Each detection branch corresponds to a seat belt buckle and is equipped with a switch, providing a one-to-one correspondence and clear switch status. The second resistor and multiple detection branches form a voltage divider circuit. The electrical parameter signal at the second terminal of the second resistor is collected by the acquisition device, enabling the seat belt detection device to accurately determine the seat belt insertion or removal. This allows for a direct determination of the seat belt status during seat belt wearing detection, improving detection accuracy and reliability. The seat belt detection device has a simple structural design, reducing hardware costs and thus improving the overall performance of the seat belt recognition function.

[0039] (2) By setting different resistance values ​​for the first resistor on different detection branches, it is possible to accurately identify the seat corresponding to the change in seat belt status, thereby improving the reliability and anti-interference capability of seat belt detection.

[0040] (3) By using the resistance value of the second resistor, the potential difference between the first reference voltage and the second reference voltage, the electrical parameter signal, and the resistance value of the first resistor on each detection branch, the seat buckle can be accurately identified. This ensures that the seat belt usage can be accurately identified in complex scenarios, avoids misjudgment and missed judgment, provides an effective basis for subsequent warnings, and improves vehicle driving safety.

[0041] (4) Based on the electrical parameter signal of the seat belt detection device, the in-vehicle image is acquired when the seat belt buckle is inserted, and the in-vehicle image is used for depth verification to determine the seat belt wearing status. This can promptly detect various unsafe seat belt wearing behaviors and improve the accuracy and reliability of the seat belt wearing detection results.

[0042] (5) By identifying whether there is an occupant in the target seat, it can help to detect whether the seat belt is incorrectly fastened in a timely manner; by double-verifying the occupant's hand movements and the relative positional relationship between the seat belt and the occupant's body, the seat belt wearing test results can be determined, which can improve the accuracy and reliability of seat belt wearing test and effectively avoid misjudgment or omission due to a single detection factor.

[0043] (6) Perform occupant position analysis and image segmentation on the acquired in-vehicle images to obtain regional images. Based on the acquired regional images, determine the hand movement detection results of the occupant in the target seat and the positional relationship between the seat belt of the target seat and the occupant. This can reduce the interference of irrelevant information and thus improve the accuracy of the relative positional relationship.

[0044] (7) Relying solely on single hand gesture detection to determine whether an occupant is wearing a seatbelt, or on seatbelt position detection, is easily affected by factors such as movement, vehicle shaking, and object compression, leading to seatbelt wearing detection errors. Adopting a multi-factor verification method, considering whether the occupant has inserted the seatbelt into the buckle, whether the seatbelt passes through the body, and whether the distance between the seatbelt and the occupant's body exceeds a threshold, can significantly reduce single-factor judgment errors, improve detection reliability and accuracy, and provide strong protection for vehicle safety management and occupant safety.

[0045] (8) By issuing a timely warning when no occupant is detected in the target seat or when the occupant is not wearing a seat belt correctly, the possibility of the occupant fastening the seat belt in the wrong position can be effectively avoided, and the occupant can be reminded to wear the seat belt correctly. This helps to reduce the risk of occupant injury in traffic accidents and provides strong protection for the occupant's life safety.

[0046] (9) By comprehensively utilizing the circuit configuration information and electrical parameter signals of the seat belt detection device, the seat where the seat belt buckle is inserted can be determined, which can help to carry out seat belt wearing tests on specific seats in the future, effectively improving the accuracy and reliability of seat belt wearing tests.

[0047] (10) Based on the electrical parameter signal of the seat belt detection device, the in-vehicle image is acquired when the seat belt buckle is inserted, and the seat belt wearing status is determined by depth verification based on the in-vehicle image. This can promptly detect various unsafe seat belt wearing behaviors and improve the accuracy and reliability of the seat belt wearing detection results.

[0048] (11) By identifying whether there is an occupant in the target seat, it can help to detect whether the seat belt is incorrectly fastened in a timely manner; by verifying the occupant's hand movements and the relative position of the seat belt and the occupant's body, the seat belt wearing test results can be determined, which can improve the accuracy and reliability of seat belt wearing test and effectively avoid misjudgment or omission due to a single detection factor.

[0049] (12) Perform occupant position analysis and image segmentation on the acquired in-vehicle images to obtain regional images. Based on the acquired regional images, determine the hand movement detection results of the occupant in the target seat and the positional relationship between the seat belt of the target seat and the occupant. This can reduce the interference of irrelevant information and thus improve the accuracy of the relative positional relationship.

[0050] (13) Relying solely on single hand gesture detection to determine whether an occupant is wearing a seatbelt, or on seatbelt position detection, is easily affected by factors such as movement, vehicle shaking, and object compression, leading to seatbelt wearing detection errors. Using a multi-factor verification method, considering whether the occupant has inserted the seatbelt into the buckle, whether the seatbelt passes through the body, and whether the distance between the seatbelt and the occupant's body exceeds a threshold, can significantly reduce single-factor judgment errors, improve detection reliability and accuracy, and provide strong protection for vehicle safety management and occupant safety.

[0051] (14) By issuing a timely warning when no occupant is detected in the target seat or when the occupant is not wearing a seat belt correctly, the possibility of the occupant fastening the seat belt in the wrong position can be effectively avoided, and the occupant can be reminded to wear the seat belt correctly. This helps to reduce the risk of occupant injury in traffic accidents and provides strong protection for the life safety of occupants. Attached Figure Description

[0052] Figure 1 This is a schematic diagram of the topology of a seatbelt detection device provided by the present invention;

[0053] Figure 2 This is a schematic diagram of the structure of a seatbelt wearing recognition system provided by the present invention;

[0054] Figure 3 A schematic diagram of a process for detecting the position of an occupant's hand and seatbelt, provided by the present invention;

[0055] Figure 4 A flowchart for seatbelt wearing recognition provided by the present invention;

[0056] Figure 5 A schematic flowchart of a seatbelt wearing recognition method provided by the present invention;

[0057] Figure 6This is a schematic diagram of the composition of a seatbelt wearing recognition device provided by the present invention;

[0058] Figure 7 This is a schematic diagram of the structure of an electronic device provided by the present invention.

[0059] Figure label:

[0060] Seat belt detection device 100; detection branch 10; first resistor 101; switch 102; second resistor 20; data acquisition device 30; camera 201; vehicle controller 202; human-machine interaction module 203. Detailed Implementation

[0061] The following is a detailed description of a call detail record (CDR) data recording method provided by the present invention, with reference to the accompanying drawings.

[0062] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0063] The terms "first" and "second," etc., used in the specification and drawings of this invention are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0064] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0065] It should be noted that in the embodiments of the present invention, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplarily" or "for example" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0066] To facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0067] In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0068] In recent years, with continuous economic development and a sustained increase in vehicle ownership, the frequency of vehicle use has significantly increased, making road traffic safety issues increasingly prominent. Against this backdrop, seatbelt recognition, as a core component of active safety systems, has become a crucial line of defense for protecting the lives of drivers and passengers.

[0069] In related technologies, seatbelt wearing is detected using buckle sensors. However, buckle sensors mostly employ mechanical switches and matching independent wiring harnesses, which are costly. Furthermore, mechanical switches have a high rate of contact failure, which can negatively impact the stability of seatbelt wearing recognition. Therefore, improving the overall performance of seatbelt recognition is a pressing issue that needs to be addressed.

[0070] Based on this, the present invention proposes a seat belt detection device, identification system, method, storage medium, and vehicle, comprising: multiple detection branches 10 connected in parallel, each detection branch 10 corresponding to a seat belt buckle on a seat, each detection branch 10 being provided with a first resistor 101 and a switch 102, the switch 102 on the detection branch 10 being closed when the seat belt buckle is inserted; a second resistor 20, the first end of the second resistor 20 being connected to a first reference voltage terminal, the second end of the second resistor 20 being connected to the first ends of the multiple detection branches 10, the second ends of the multiple detection branches 10 being connected to a second reference voltage terminal, the voltage of the first reference voltage terminal being higher than the voltage of the second reference voltage terminal; and a data acquisition device 30, the data acquisition device 30 being used to acquire electrical parameter signals at the second end of the second resistor 20.

[0071] Therefore, by employing a parallel structure of multiple independent detection branches, a fault in one branch does not affect other branches, effectively ensuring the stable operation of the seatbelt detection. Each detection branch corresponds to a seatbelt buckle and is equipped with a switch, providing a one-to-one correspondence and clearly defined switch status. The second resistor and multiple detection branches form a voltage divider circuit. By acquiring the electrical parameter signal at the second terminal of the second resistor through a data acquisition device, the seatbelt detection device can accurately determine whether the seatbelt is inserted or removed. This allows for a direct assessment of the seatbelt status during seatbelt wearing detection, improving detection accuracy and reliability. The seatbelt detection device features a simple structural design, reducing hardware costs and thus enhancing the overall performance of the seatbelt recognition function.

[0072] The seat belt detection device, identification system, method, storage medium, and vehicle of the present invention will now be described in conjunction with the accompanying drawings.

[0073] The seat belt detection device provided by this invention can be applied to vehicles or seat belt wearing recognition systems in vehicles.

[0074] The vehicles in this invention include, but are not limited to, traditional gasoline-powered vehicles, new energy electric vehicles, and agricultural transport vehicles and construction machinery vehicles used for agricultural operations, among other vehicles of different purposes and power types. The vehicles may have five seats.

[0075] Reference Figure 1 The present invention provides a seat belt detection device 100, comprising:

[0076] Multiple detection branches 10 are connected in parallel. Each detection branch 10 corresponds to a seat belt buckle on a seat. Each detection branch 10 is equipped with a first resistor 101 and a switch 102. The switch 102 on the detection branch 10 is closed when the seat belt buckle is inserted.

[0077] The second resistor 20 has its first end connected to the first reference voltage terminal and its second end connected to the first end of the plurality of detection branches 10. The second end of the plurality of detection branches 10 is connected to the second reference voltage terminal, and the voltage of the first reference voltage terminal is higher than the voltage of the second reference voltage terminal.

[0078] Acquisition device 30 is used to acquire electrical parameter signals at the second terminal of the second resistor 20.

[0079] The seatbelt detection device is a device pre-installed in the vehicle to detect the seatbelt buckle status and output electrical parameter signals.

[0080] Detection branch 10 is an independent circuit branch. Each detection branch 10 is used to detect whether the seat belt buckle on the corresponding target seat is engaged. The first end of detection branch 10 can be a high-voltage end, and the second end of detection branch 10 is the connection point in each detection branch 10 that connects to a second reference voltage terminal, which can be a low-voltage end, such as ground.

[0081] The first resistor 101 is a resistive element installed in each detection branch 10, which acts as a voltage divider in the circuit. When the state of the switch 102 in the detection branch 10 changes, the voltage divider circuit formed by the first resistor 101 enables the acquisition device 30 to detect the change in electrical parameter signal.

[0082] Switch 102 is a component configured in the detection branch 10 to correlate the on / off state with the insertion / removal action of the seatbelt buckle. Switch 102 can be replaced by a buckle sensor.

[0083] In one possible implementation, when the seatbelt buckle is engaged, i.e., when the seatbelt is fastened, the switch 102 on the detection branch 10 is closed, and the circuit is connected.

[0084] In another possible implementation, when the seatbelt buckle is not engaged, i.e., the seatbelt is not fastened, the switch 102 on the detection branch 10 is disconnected, and the circuit is not open.

[0085] The second resistor 20 is installed in the overall circuit. Its first terminal is a connection point to the first reference voltage terminal, which provides a high voltage power supply. The second terminal of the second resistor 20 is a connection point to the first terminals of multiple detection branches 10.

[0086] The acquisition device 30 is used to continuously monitor the electrical parameter signal at the second terminal of the second resistor 20. The electrical parameter signal monitored by the acquisition device 30 changes with the on / off state of the switch 102 in the detection branch 10, thereby reflecting the insertion / removal state of the seat belt buckle.

[0087] The data acquisition device 30 can be a voltage acquisition device or an ammeter.

[0088] When the acquisition device 30 is a voltage acquisition device, the electrical parameter signal monitored by the acquisition device 30 is a voltage signal.

[0089] When the acquisition device 30 is a galvanometer, the electrical parameter signal monitored by the acquisition device 30 is a current signal.

[0090] Therefore, by employing a parallel structure of multiple independent detection branches, a fault in one branch does not affect other branches, effectively ensuring the stable operation of the seatbelt detection. Each detection branch corresponds to a seatbelt buckle and is equipped with a switch, providing a one-to-one correspondence and clearly defined switch status. The second resistor and multiple detection branches form a voltage divider circuit. By acquiring the electrical parameter signal at the second terminal of the second resistor through a data acquisition device, the seatbelt detection device can accurately determine whether the seatbelt is inserted or removed. This allows for a direct assessment of the seatbelt status during seatbelt wearing detection, improving detection accuracy and reliability. The seatbelt detection device features a simple structural design, reducing hardware costs and thus enhancing the overall performance of the seatbelt recognition function.

[0091] In some embodiments, the resistance values ​​of the first resistor 101 on the different detection branches 10 are different. When the resistance values ​​of the first resistor 101 on all detection branches 10 are the same, when multiple seat belt buckles are simultaneously inserted or removed, the electrical parameter signal characteristics generated at the second terminal of the second resistor 20 tend to be similar, making it difficult to locate the specific seat. By setting different resistance values ​​for the first resistor 101 on different detection branches 10, it is possible to accurately identify the seat corresponding to the seat belt status change, thereby improving the reliability and anti-interference capability of seat belt detection.

[0092] In some embodiments, the acquisition device 30 is adapted to be connected to the vehicle controller 202. The acquisition device 30 is configured to send an electrical parameter signal to the vehicle controller 202. The vehicle controller 202 is configured to determine the seat in the vehicle where the seat belt buckle is inserted based on the resistance value of the second resistor (20), the potential difference between the first reference voltage and the second reference voltage, the electrical parameter signal, and the resistance value of the first resistor (101) on each detection branch (10).

[0093] In one possible implementation, when the seatbelt buckle is not engaged, switch 102 in detection branch 10 is open, detection branch 10 is in an open-circuit state, and the resistance of detection branch 10 is infinite. Since the voltage at the second terminal of the second resistor 20 depends on the voltage division between the second resistor 20 and the entire parallel detection branch 10, according to the principle of series voltage division, the voltage value at the second terminal of the second resistor 20 is close to the first reference voltage.

[0094] In another possible implementation, when the seatbelt buckle of a target seat is engaged, the corresponding detection branch 10 switch 102 closes, creating a conductive path. At this time, the voltage at the second terminal of the second resistor 20 drops, and the acquisition device 30 continuously acquires the electrical parameter signal at the second terminal of the second resistor 20. The acquired electrical parameter value is compared with multiple different preset wearing thresholds, each preset threshold uniquely corresponding to a specific seat. By analyzing which preset wearing threshold the electrical parameter value matches, it is determined that the occupant in the corresponding specific seat has a tendency to wear the seatbelt.

[0095] For example, if the electrical parameter value at the second end of the second resistor 20 is less than the preset wearing threshold A and less than the preset wearing threshold B, and the preset wearing threshold A corresponds to the front left seat and the preset wearing threshold B corresponds to the front right seat, it is determined that the seat belt buckles on the front left seat corresponding to the preset wearing threshold A and the front right seat corresponding to the preset wearing threshold B are both inserted.

[0096] The preset wearing threshold is a critical value of electrical parameters calculated in advance based on the resistance value of the first resistor 101 in different detection branches 10 and the circuit principle. It is used to provide a basis for distinguishing seats where the seat belt buckle is inserted.

[0097] Understandably, the vehicle can identify the number of switches 102 open and closed and the corresponding seat positions within the topology of the seat belt detection device based on the electrical parameter signals emitted by the acquisition device 30 (presented in the form of electrical parameter values; that is, if the electrical parameter signal is a voltage signal, it is presented in the form of voltage values; if the electrical parameter signal is a current signal, it is presented in the form of current values), thereby determining the number of seats in the vehicle where the seat belt buckles are engaged.

[0098] Therefore, by using the resistance value of the second resistor, the potential difference between the first and second reference voltages, electrical parameter signals, and the resistance value of the first resistor on each detection branch, accurate identification of seats with seat belt buckles can be achieved. This ensures accurate identification of seat belt usage in complex scenarios, avoids misjudgments and omissions, provides effective basis for subsequent warnings, and improves vehicle driving safety.

[0099] For example, refer to Figure 1 The topology of the seat belt detection device is as follows: the acquisition device 30 is a voltage acquisition device, and the calculation formula for the acquired voltage value is as follows:

[0100]

[0101] Wherein, U0 represents the voltage value acquired by the acquisition device 30; R b R1, R2, R3, R4, and R5 are connected in parallel, representing the equivalent resistance; R0 represents the resistance value of the second resistor 20; U c R1, R2, R3, R4, and R5 represent the voltage at the first reference voltage terminal; R1, R2, R3, R4, and R5 represent the resistance values ​​of the first resistor 101.

[0102] In some embodiments, refer to Figure 2 The present invention also provides a seatbelt wearing recognition system, comprising:

[0103] Camera 201 is used to capture images inside the vehicle; seat belt detection device 100; vehicle controller 202 is connected to camera 201 and seat belt detection device 100 respectively.

[0104] The vehicle controller 202 is configured to: in response to determining that the seat belt buckle on the target seat is engaged based on the electrical parameter signal of the seat belt detection device 100, acquire multiple in-vehicle images captured by the camera 201 within a preset historical time period; determine the seat belt wearing detection result based on the multiple in-vehicle images, and the seat belt wearing detection result is used to indicate whether the occupant is wearing the seat belt correctly in the target seat.

[0105] The seatbelt wearing test results include two types: those indicating that the occupant is wearing the seatbelt correctly and those indicating that the occupant is not wearing the seatbelt correctly. Incorrect seatbelt wearing includes either incorrect seatbelt wearing (e.g., a twisted seatbelt, misuse of the seatbelt (e.g., using a seatbelt extender)) or not wearing the seatbelt at all.

[0106] As a core component of in-vehicle visual perception, camera 201 is responsible for collecting images inside the vehicle. Camera 201 is also responsible for triggering historical image retrospective acquisition when the vehicle controller 202 determines a change in the target seat's seatbelt status through the electrical parameter signal of the seatbelt detection device 100, and for transmitting the acquired historical images to the vehicle controller 202 in real time.

[0107] For example, the camera 201 can be a monocular depth camera installed in the rearview mirror area of ​​the vehicle, capturing images of the vehicle interior in real time according to a preset acquisition interval. The rearview mirror area is the junction between the rearview mirror and the roof, and the camera 201 positioned in this area can cover the entire seating area of ​​the vehicle. The preset acquisition interval can be set to 100 milliseconds. The camera 201 can be deployed at any location within the rearview mirror area, which can be the junction between the rearview mirror and the roof.

[0108] In some embodiments, in practical applications, situations may arise such as the seatbelt being mistakenly fastened to another seat or the seatbelt not being properly inserted into the seat buckle (e.g., merely resting on the buckle without being secured). The vehicle controller is configured to determine the seatbelt wearing detection result based on multiple in-vehicle images, including: identifying whether an occupant is present in the target seat based on the multiple in-vehicle images; in response to identifying the presence of an occupant in the target seat, determining the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seatbelt and the occupant's body based on the multiple in-vehicle images; wherein, the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle; and determining the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body.

[0109] Therefore, identifying whether there is an occupant in the target seat can help to detect whether the seat belt is incorrectly fastened in a timely manner; double verification of the occupant's hand movements and the relative position of the seat belt and the occupant's body to determine the seat belt wearing detection result can improve the accuracy and reliability of seat belt wearing detection and effectively avoid misjudgment or omission due to a single detection factor.

[0110] The hand movement detection results are obtained by using convolutional neural network technology to detect key hand points in the region image, analyzing the occupant's hand posture, and determining whether they have made a movement to insert the buckle. Key hand points include, but are not limited to, the wrist, the base of the thumb, the tip of the thumb, the root joints, intermediate joints, and fingertips of the other four fingers.

[0111] As one possible implementation, the relative positional relationship between the seat belt and the occupant's body includes two positions: the seat belt passing through the occupant's body and the seat belt not passing through the occupant's body. The aforementioned determination of the relative positional relationship between the seat belt and the occupant's body at the target seat can be achieved by analyzing information such as the distance and relative position between the center points of the bounding boxes of the seat belt and key body parts (such as the shoulder, waist, and chest). This allows for the determination of the contact status between the seat belt and the key body parts, enabling accurate identification of the relative positional relationship between the seat belt and the occupant's body, and thus determining whether the seat belt passes through the occupant's body.

[0112] For example, such as Figure 3 As shown, the vehicle controller 202 is configured to, in response to detecting the presence of an occupant in a target seat, determine, based on multiple in-vehicle images, the specific steps of determining the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt and the occupant's body, including:

[0113] S301. Based on the deployment location of camera 201 inside the vehicle and the deployment location of the target seat inside the vehicle, determine the location information of the area where the occupant is located in the in-vehicle image.

[0114] The deployment position of the target seat in the vehicle refers to the relative positional relationship between the seats inside the vehicle, including but not limited to the front-to-back distance, left-to-right spacing, and vertical height difference between the seats.

[0115] The location information of the occupant's area in the in-vehicle image includes, but is not limited to, the coordinates and pixel range of the occupant's area in the image. It can be represented by coordinate points in the image (such as the coordinates of the upper left corner and the lower right corner) or by a description of the pixel area.

[0116] As one possible implementation, determining the location of the occupant's area in the in-vehicle image can be achieved as follows: A three-dimensional coordinate system within the vehicle is constructed, clarifying the positions of camera 201 and key points of the target seat within it, and obtaining the intrinsic and extrinsic parameters of camera 201. The spatial points of the target seat are transformed to the coordinate system of camera 201 using the extrinsic parameters, and then projected onto the imaging plane using the intrinsic parameters, with distortion corrected. By repeating this process on multiple key points of the target seat, the corrected pixel coordinates are connected to form a boundary polygon, which represents the location of the occupant's area in the in-vehicle image.

[0117] Among them, the key points of the seat are the core reference points that define the position of the target seat in three-dimensional space and image plane. For example, they can be the center point of the seat cushion, the top end point of the backrest, the connection point between the bottom of the backrest and the seat cushion, etc.

[0118] S302. Based on the location information of the occupant's area in the in-vehicle image, segment the area image from the in-vehicle image.

[0119] The region image can include the occupant's body and objects closely related to the occupant, such as the seat belt. Image segmentation techniques can include thresholding, edge detection, and semantic segmentation.

[0120] S303. Perform human feature detection on the acquired regional image, and determine that there is an occupant in the target seat if human features are detected in the regional image.

[0121] As one possible approach, the specific detection method for human features can be as follows: First, construct a multi-scale feature pyramid; then, use HRNet to jointly detect human key points (such as shoulders, chest, wrists, hips, and head) and perform contour segmentation using an improved model based on DeepLabv3; verify the existence of the human body by analyzing whether the distribution of key points conforms to the "head-torso-limbs" topological structure and analyzing the displacement of human key points in consecutive frames.

[0122] S304. If it is determined that there is an occupant in the target seat, based on the region image, determine the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body.

[0123] In some embodiments, the vehicle controller is configured to determine the hand movement detection results of an occupant in a target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body based on multiple in-vehicle images, including: determining the positional information of the occupant's location area in the in-vehicle images based on the deployment position of the camera in the vehicle and the deployment position of the target seat in the vehicle; segmenting a region image from the in-vehicle images based on the positional information of the occupant's location area in the in-vehicle images; and determining the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt and the occupant's body based on the respective region images of the multiple in-vehicle images.

[0124] Therefore, by performing occupant position analysis and image segmentation on the acquired in-vehicle images, regional images are obtained. Based on the acquired regional images, the hand movement detection results of the occupant in the target seat and the positional relationship between the seat belt and the occupant in the target seat can be determined. This can reduce the interference of irrelevant information and thus improve the accuracy of the relative positional relationship.

[0125] As one possible implementation, after denoising and normalizing the acquired in-vehicle images, the in-vehicle image sequence is divided into sub-image sequences based on a preset sliding window. Using a convolutional neural network, feature mining is performed on each sub-image sequence, and the features are fused with those obtained from image segmentation and seatbelt position detection within the sub-image sequences to obtain comprehensive features. Based on fully connected layers and the comprehensive features, the action category corresponding to the sub-image sequence is determined. The action category determination results of all sub-image sequences are input into a temporal model to determine the occupant's hand movements and the relative positional relationship between the seatbelt and the occupant's body. This temporal model can be a Long Short-Term Memory (LSTM) network or a Transformer model.

[0126] The preset sliding window is the set time length for extracting sub-image sequences from the image sequence, which determines the time span of the images contained in each sub-image sequence.

[0127] For example, assuming a preset historical time period of 3 seconds and a preset sliding window of 1 second, in response to the electrical parameter signal of the seat belt detection device 100, the vehicle controller 202 obtains multiple in-vehicle images captured by the camera 201 within the previous 3 seconds from the vehicle database and constructs a target in-vehicle image sequence.

[0128] The target vehicle interior image sequence is divided using a preset sliding window to obtain three target sub-image sequences. Each target sub-image sequence represents a set of vehicle interior images captured by camera 201 within a continuous 1-second time period.

[0129] Convolutional neural networks are used to extract features layer by layer from images in each sub-image sequence. Through operations such as convolutional layers and pooling layers, they automatically learn the spatiotemporal features in the images, such as the shape, orientation and position of the seat belt, the spatial features of the relative position of the seat belt and the occupant, the temporal features of the positional relationship changing over time, the occupant's body contour, and the morphology and trajectory features of the occupant's hand movements.

[0130] In some embodiments, relying solely on the occupant's hand gesture of inserting the seatbelt into the buckle to determine seatbelt wearing has vulnerabilities: objects like buckles may be mistakenly inserted into the buckle. Similarly, relying solely on the seatbelt passing through the occupant's body also has problems: abnormal seatbelt passage or involuntary wearing may occur. The vehicle controller is configured to determine seatbelt wearing detection results based on hand gesture detection results and the relative positional relationship between the seatbelt and the occupant's body, including: determining that the occupant in the target seat is correctly wearing the seatbelt if the hand gesture detection results indicate that the occupant has made a hand gesture of inserting the seatbelt into the buckle and the relative positional relationship between the seatbelt and the occupant's body meets the correct wearing conditions; and determining that the occupant in the target seat is not correctly wearing the seatbelt if the hand gesture detection results indicate that the occupant has not made a hand gesture of inserting the seatbelt into the buckle and / or the relative positional relationship between the seatbelt and the occupant's body does not meet the correct wearing conditions. The correct wearing conditions include: the seatbelt passing through the occupant's body and the distance between the seatbelt and the occupant's body surface not exceeding a preset distance threshold.

[0131] As one possible implementation, if the occupant does not make any hand movements to insert the seat belt into the seat belt buckle and the seat belt does not pass through the occupant's body, it is determined that the current occupant is not wearing a seat belt.

[0132] As another possible implementation, if the occupant makes a hand motion to insert the seat belt into the seat belt buckle, and the seat belt does not pass through the occupant's body, it can be determined that the current occupant is not wearing a seat belt.

[0133] As another possible implementation, if the occupant does not perform any hand movements to insert the seat belt into the seat belt buckle, the seat belt passes through the occupant's body, and the distance between the seat belt and the center point of the occupant's preset body part does not exceed a preset distance threshold, it is determined that the current occupant is not wearing a seat belt.

[0134] As another possible implementation, if the occupant does not perform any hand movements to insert the seat belt into the seat belt buckle, the seat belt passes through the occupant's body, and the distance between the seat belt and the center point of the occupant's preset body part exceeds a preset distance threshold, it is determined that the current occupant is not wearing a seat belt.

[0135] As another possible implementation, if the occupant makes a hand motion to insert the seat belt into the seat belt buckle, the seat belt passes through the occupant's body, and the distance between the seat belt and the center point of a preset part of the occupant exceeds a preset distance threshold, it is determined that the current occupant is not wearing a seat belt.

[0136] Therefore, relying solely on single hand gesture detection to determine whether an occupant is wearing a seatbelt, or on seatbelt position detection, is easily affected by factors such as movement, vehicle shaking, and pressure from objects, leading to seatbelt detection errors. Adopting a multi-factor verification method, considering whether the occupant's hand gestures insert the seatbelt into the buckle, whether the seatbelt passes through the body, and whether the distance between the seatbelt and the occupant's body exceeds a certain threshold, can significantly reduce errors caused by single factors, improve detection reliability and accuracy, and provide strong protection for vehicle safety management and occupant safety.

[0137] It should be noted that the hand gesture detection results include both hand gestures that indicate the occupant is inserting the seat belt into the seat belt buckle and hand gestures that do not indicate the occupant is inserting the seat belt into the seat belt buckle (such as adjusting clothing or adjusting the seat).

[0138] The relative position of the seat belt to the occupant's body refers to situations where the seat belt does not cross the occupant's body. This means that the seat belt does not form an effective restraint connection with the occupant's critical body parts, that is, the seat belt does not cross the critical body parts of the occupant's body in the correct way. For example, the seat belt does not contact any critical body parts at all, or the seat belt is knotted or wrapped around the shoulder or chest. Critical body parts include, but are not limited to, the shoulder, chest, waist, and hip areas.

[0139] The preset center point can be the center point of the bounding box of a critical body part; the preset distance threshold is a critical value set according to the safe and reasonable distance range between the vehicle seat belt and the critical body parts when the seat belt is worn normally.

[0140] For example, the specific method for obtaining the distance between the seat belt and the center point of the preset part of the occupant can be as follows: First, obtain the coordinate position of the specific reference point of the seat belt (a fixed feature point on the seat belt set in advance) in the image; then, based on the transformation relationship between the image coordinate system and the actual physical space (this transformation relationship can be determined by the calibration work performed in advance inside the vehicle), convert the coordinates of the specific reference point of the seat belt and the center point of the preset part in the image into coordinates in the actual physical space, and then calculate it using a distance calculation formula (such as the Euclidean distance formula).

[0141] For example, if an occupant makes a hand motion to insert the seat belt into the seat belt buckle, the seat belt passes through the occupant's body, and the distance between the seat belt and the center point of a preset part of the occupant exceeds a preset distance threshold, it can be determined that the seat belt is being used fraudulently (e.g., using a seat belt extender).

[0142] Therefore, by detecting whether the occupant makes a hand motion to insert the seat belt into the seat belt buckle, it can be identified whether the occupant intends to wear the seat belt. By detecting whether the seat belt passes through the occupant's body and whether the distance between the seat belt and the occupant's body exceeds a threshold, it can be confirmed whether the occupant has correctly worn the seat belt.

[0143] In some embodiments, refer to Figure 2 The seat belt wearing recognition system also includes a human-machine interaction module 203, which is connected to the vehicle controller 202. The vehicle controller 202 is also configured to control the human-machine interaction module 203 to issue an alarm message when there is no occupant in the target seat or the seat belt wearing detection result indicates that the occupant in the target seat is not wearing the seat belt correctly.

[0144] Therefore, by issuing timely warnings when no occupant is detected in the target seat or when the occupant is not wearing a seatbelt correctly, the possibility of occupants wearing seatbelts incorrectly can be effectively avoided, and occupants can be reminded to wear seatbelts correctly. This helps to reduce the risk of occupant injury in traffic accidents and provides strong protection for occupant safety.

[0145] The human-computer interaction module 203 is responsible for real-time monitoring and analysis of seat belt wearing status information. It is used to issue alarm information when it detects that the occupant is not wearing a seat belt, and to provide a function for recording malfunction events.

[0146] The malfunction event logging function records malfunction events to the vehicle log for later querying and analysis. Malfunction events refer to seat belt wearing recognition errors caused by interference factors, such as misjudging that the seat belt is worn or misjudging that the seat belt is not worn. Recording malfunction events helps in subsequent troubleshooting and repair, thereby improving the stability and accuracy of seat belt wearing recognition.

[0147] The alarm information is a notification signal sent by the human-machine interface module 203 when it detects that an occupant is not wearing a seatbelt. This notification signal is used to trigger subsequent alarm actions to remind the occupant to wear a seatbelt. The alarm information includes, but is not limited to, the timestamp of the alarm message and the specific seat location of the occupant who is not wearing a seatbelt.

[0148] As one possible way to achieve this, refer to Figure 2 The seatbelt wearing recognition system also includes: the vehicle controller 202 is further configured to control the human-machine interface module 203 to issue an alarm message when there is an occupant in any of the seats other than the target seat.

[0149] Therefore, by promptly issuing an alarm when there are occupants in seats other than the target seat (i.e., when no occupant is detected in a seat with the seatbelt buckle engaged), the dynamic monitoring of seatbelt wearing status for all occupants in the vehicle can be further strengthened, providing strong protection for the safety of occupants.

[0150] As another possible way to achieve this, refer to Figure 4 If no change in the electrical parameter signal of the seat belt detection device is detected, no seat belt not-worn warning will be issued. If a change in the electrical parameter signal of the seat belt detection device is detected, image acquisition will be performed. Based on the acquired image, occupant hand movements and seat belt position will be identified. A judgment will be made regarding whether the seat belt is being worn based on the identification results. If the seat belt is not being worn correctly, the occupant will be prompted to wear the seat belt; otherwise, no prompt will be given.

[0151] In some embodiments, the executing entity of the seat belt wearing recognition method provided by the present invention may be a seat belt wearing recognition device. The seat belt wearing recognition device may be deployed in an electronic device. The electronic device may be a server cluster composed of multiple servers, a single server, a computer, or any device or equipment with seat belt wearing recognition function, such as a processor or processing chip in a server or computer. The embodiments of the present invention do not limit this.

[0152] In some embodiments, reference Figure 5 The present invention also provides a seat belt wearing recognition method, comprising:

[0153] S501. Acquire the electrical parameter signals collected by the seat belt detection device. The seat belt detection device is the aforementioned seat belt detection device 100.

[0154] S502. Based on electrical parameter signals and the circuit configuration information of the seat belt detection device, determine the seat in the vehicle where the seat belt buckle is engaged; wherein, the circuit configuration information includes the resistance value of the second resistor, the potential difference between the first reference voltage and the second reference voltage, and the resistance value of the first resistor on each detection branch.

[0155] Therefore, by comprehensively utilizing the circuit configuration information and electrical parameter signals of the seat belt detection device, the seat in the vehicle where the seat belt buckle is engaged can be determined, which can help to conduct seat belt wearing tests on specific seats in the future, effectively improving the accuracy and reliability of seat belt wearing tests.

[0156] In some embodiments, the method further includes: in response to determining that the seat belt buckle on the target seat is engaged based on the electrical parameter signal of the seat belt detection device, acquiring multiple in-vehicle images captured by the camera within a preset historical time period; determining a seat belt wearing detection result based on the multiple in-vehicle images, the seat belt wearing detection result being used to indicate whether the occupant is wearing the seat belt correctly in the target seat.

[0157] In some embodiments, determining a seatbelt wearing detection result based on multiple in-vehicle images includes: identifying whether an occupant is present in a target seat based on the multiple in-vehicle images; in response to identifying that an occupant is present in the target seat, determining the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seatbelt and the occupant's body based on the multiple in-vehicle images; wherein the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle; and determining the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body.

[0158] In some embodiments, determining the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body based on multiple in-vehicle images includes: determining the positional information of the occupant's area in the in-vehicle images based on the deployment position of the camera in the vehicle and the deployment position of the target seat in the vehicle; segmenting a region image from the in-vehicle images based on the positional information of the occupant's area in the in-vehicle images; and determining the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body based on the respective region images of the multiple in-vehicle images.

[0159] In some embodiments, the seatbelt wearing detection result is determined based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body. This includes: determining that the occupant is correctly wearing the seatbelt if the hand movement detection result indicates that the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle, and the relative positional relationship between the seatbelt and the occupant's body meets the correct wearing conditions; and determining that the occupant is not correctly wearing the seatbelt if the hand movement detection result indicates that the occupant has not made a hand movement to insert the seatbelt into the seatbelt buckle, and / or the relative positional relationship between the seatbelt and the occupant's body does not meet the correct wearing conditions. The correct wearing conditions include: the seatbelt passes through the occupant's body, and the distance between the seatbelt and the occupant's body surface does not exceed a preset distance threshold.

[0160] In some embodiments, the method further includes issuing an alarm message when no occupant is detected in the target seat, or when the seat belt wearing detection result indicates that the occupant is not wearing the seat belt correctly.

[0161] In some embodiments, reference Figure 6 The present invention also provides a seat belt wearing recognition device 600, comprising:

[0162] The signal acquisition module 601 is used to acquire the electrical parameter signals collected by the seat belt detection device 100.

[0163] Seat recognition module 602: used to determine the seat in the vehicle where the seat belt buckle is inserted based on electrical parameter signals and circuit configuration information of seat belt detection device 100; wherein, the circuit configuration information includes the resistance value of the second resistor, the potential difference between the first reference voltage and the second reference voltage, and the resistance value of the first resistor on each detection branch.

[0164] The seatbelt wearing detection module 603 is used to determine that the seatbelt buckle on the target seat is engaged in response to the electrical parameter signal of the seatbelt detection device 100, and to acquire multiple in-vehicle images captured by the camera 201 within a preset historical time period; and to determine the seatbelt wearing detection result based on the multiple in-vehicle images, which is used to indicate whether the occupant is wearing the seatbelt correctly in the target seat.

[0165] In some embodiments, the seatbelt wearing detection module 603 is specifically used to identify whether an occupant is in a target seat based on multiple in-vehicle images; in response to identifying that an occupant is in the target seat, it determines the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seatbelt and the occupant's body based on the multiple in-vehicle images; wherein, the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seatbelt into the seatbelt buckle; and the seatbelt wearing detection result is determined based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body.

[0166] In some embodiments, the wear detection module 603 is further configured to determine the location information of the occupant's area in the in-vehicle image based on the deployment location of the camera in the vehicle and the deployment location of the target seat in the vehicle; segment the area image from the in-vehicle image based on the location information of the occupant's area in the in-vehicle image; and determine the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body based on the respective area images of multiple in-vehicle images.

[0167] In some embodiments, the wearing detection module 603 is further configured to determine that the occupant is correctly wearing the seat belt when the hand movement detection result indicates that the occupant has made a hand movement to insert the seat belt into the seat belt buckle, and the relative positional relationship between the seat belt and the occupant's body meets the correct wearing conditions; and to determine that the occupant is not correctly wearing the seat belt when the hand movement detection result indicates that the occupant has not made a hand movement to insert the seat belt into the seat belt buckle, and / or the relative positional relationship between the seat belt and the occupant's body does not meet the correct wearing conditions; wherein, the correct wearing conditions include: the seat belt passes through the occupant's body, and the distance between the seat belt and the occupant's body surface does not exceed a preset distance threshold.

[0168] In some embodiments, the seatbelt detection module 603 is further configured to issue an alarm message when no occupant is detected in the target seat, or when the seatbelt detection result indicates that the occupant is not wearing the seatbelt correctly.

[0169] When implementing the functions of the integrated modules described above in hardware, this embodiment of the invention provides a possible structural diagram of the electronic device involved in the above embodiments. For example... Figure 7 As shown, the electronic device 700 includes: a processor 702, a communication interface 703, and a bus 704. Optionally, the electronic device 700 may also include a memory 701.

[0170] Processor 702 may implement or execute various exemplary logic blocks, modules, and circuits described in connection with the present invention disclosure. Processor 702 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in connection with the present invention disclosure. Processor 702 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0171] The communication interface 703 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0172] The memory 701 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0173] In one possible implementation, the memory 701 can exist independently of the processor 702. The memory 701 can be connected to the processor 702 via a bus 704 and is used to store instructions or program code. When the processor 702 calls and executes the instructions or program code stored in the memory 701, it can implement the vehicle light control method provided in this embodiment of the invention.

[0174] In another possible implementation, the memory 701 can also be integrated with the processor 702.

[0175] The 704 bus can be an extended industry standard architecture (EISA) bus, etc. The 704 bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0176] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0177] This invention also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. The program can be stored in the computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be any of the foregoing embodiments or memory. The computer-readable storage medium can also be an external storage device of the service invocation device, such as a pluggable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the service invocation device. Further, the computer-readable storage medium can include both internal storage units of the service invocation device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the service invocation device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0178] This invention also provides a computer program product comprising a computer program that, when run on a computer, causes the computer to execute any of the security identification methods provided in the above embodiments.

[0179] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A seatbelt detection device, characterized in that, include: Multiple detection branches (10) are connected in parallel, each detection branch (10) corresponds to a seat belt buckle on a seat, each detection branch (10) is provided with a first resistor (101) and a switch (102), and the switch (102) on the detection branch (10) is closed when the seat belt buckle is inserted; The second resistor (20) has its first end connected to the first reference voltage terminal and its second end connected to the first end of the plurality of detection branches (10). The second end of the plurality of detection branches (10) is connected to the second reference voltage terminal. The voltage of the first reference voltage terminal is higher than the voltage of the second reference voltage terminal. Acquisition device (30) is used to acquire electrical parameter signals at the second end of the second resistor (20).

2. The seat belt detection device according to claim 1, characterized in that, The resistance values ​​of the first resistor (101) on the different detection branches (10) are different.

3. The seat belt detection device according to claim 2, characterized in that, The acquisition device (30) is adapted to connect to a vehicle controller, and the acquisition device (30) is configured to send the electrical parameter signal to the vehicle controller; The vehicle controller is configured to determine the seat in the vehicle where the seatbelt buckle is engaged, based on the resistance value of the second resistor (20), the potential difference between the first reference voltage and the second reference voltage, the electrical parameter signal, and the resistance value of the first resistor (101) on each detection branch (10).

4. A seatbelt wearing recognition system, characterized in that, The seatbelt wearing recognition system includes: A camera (201) is used to capture images inside the vehicle; The seat belt detection device (100) as described in any one of claims 1 to 3; A vehicle controller (202) is connected to the camera (201) and the seatbelt detection device (100) respectively; the vehicle controller (202) is configured to: In response to determining that the seat belt buckle on the target seat is engaged based on the electrical parameter signal of the seat belt detection device (100), multiple in-vehicle images captured by the camera (201) within a preset historical time period are acquired; The seat belt wearing detection result is determined based on the multiple in-vehicle images, and the seat belt wearing detection result is used to indicate whether the occupant is wearing the seat belt correctly in the target seat.

5. The seatbelt wearing recognition system according to claim 4, characterized in that, The vehicle controller (202) is configured to determine the seatbelt wearing detection result based on the plurality of in-vehicle images, including: Based on the multiple in-vehicle images, identify whether there is an occupant in the target seat; In response to the detection of an occupant in the target seat, based on the multiple in-vehicle images, the system determines the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body; wherein, the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seat belt into the seat belt buckle; Based on the hand movement detection results and the relative positional relationship between the seat belt and the occupant's body, the seat belt wearing detection result is determined.

6. The seatbelt wearing recognition system according to claim 5, characterized in that, The vehicle controller (202) is configured to determine, based on the plurality of in-vehicle images, the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body, including: Based on the deployment location of the camera inside the vehicle and the deployment location of the target seat inside the vehicle, the location information of the area where the occupant is located in the in-vehicle image is determined; Based on the location information of the occupant's area in the in-vehicle image, a region image is segmented from the in-vehicle image; Based on the respective region images of the multiple in-vehicle images, the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body are determined.

7. The seatbelt wearing recognition system according to claim 5, characterized in that, The vehicle controller (202) is configured to determine the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body, including: If the hand movement detection result indicates that the occupant has made a hand movement to insert the seat belt into the seat belt buckle, and the relative positional relationship between the seat belt and the occupant's body meets the correct wearing conditions, then it is determined that the occupant in the target seat is wearing the seat belt correctly. If the hand movement detection result indicates that the occupant does not perform any hand movements to insert the seat belt into the seat belt buckle, and / or the relative positional relationship between the seat belt and the occupant's body does not meet the conditions for proper wearing, it is determined that the occupant in the target seat is not wearing the seat belt correctly. The correct wearing conditions include: the seat belt passes through the occupant's body, and the distance between the seat belt and the occupant's body surface does not exceed a preset distance threshold.

8. The seatbelt wearing recognition system according to claim 5, characterized in that, The seatbelt wearing recognition system also includes: Human-computer interaction module (203), which is connected to the vehicle controller (202); The vehicle controller (202) is also configured to: control the human-machine interaction module to issue an alarm message when no occupant is detected in the target seat, or when the seat belt wearing detection result indicates that the occupant in the target seat is not wearing the seat belt correctly.

9. A method for recognizing seatbelt wearing, characterized in that, The method includes: Acquire electrical parameter signals collected by the seat belt detection device; the seat belt detection device is the seat belt detection device as described in any one of claims 1 to 3; Based on the electrical parameter signals and the circuit configuration information of the seat belt detection device, the seat in the vehicle where the seat belt buckle is engaged is determined; wherein, the circuit configuration information includes the resistance value of the second resistor, the potential difference between the first reference voltage and the second reference voltage, and the resistance value of the first resistor on each detection branch.

10. The method according to claim 9, characterized in that, The method further includes: In response to determining that the seatbelt buckle on the target seat is engaged based on the electrical parameter signal of the seatbelt detection device, multiple in-vehicle images captured by the camera within a preset historical time period are acquired; The seat belt wearing detection result is determined based on the multiple in-vehicle images, and the seat belt wearing detection result is used to indicate whether the occupant is wearing the seat belt correctly in the target seat.

11. The method according to claim 10, characterized in that, The determination of seatbelt wearing detection results based on the multiple in-vehicle images includes: Based on the multiple in-vehicle images, identify whether there is an occupant in the target seat; In response to the detection of an occupant in the target seat, based on the multiple in-vehicle images, the system determines the hand movement detection result of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body; wherein, the hand movement detection result is used to characterize whether the occupant has made a hand movement to insert the seat belt into the seat belt buckle; Based on the hand movement detection results and the relative positional relationship between the seat belt and the occupant's body, the seat belt wearing detection result is determined.

12. The method according to claim 11, characterized in that, The step of determining the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body based on the in-vehicle image includes: Based on the deployment location of the camera inside the vehicle and the deployment location of the target seat inside the vehicle, the location information of the occupant's area in the in-vehicle image is determined; Based on the location information of the occupant's area in the in-vehicle image, a region image is segmented from the in-vehicle image; Based on the respective region images of the multiple in-vehicle images, the hand movement detection results of the occupant in the target seat and the relative positional relationship between the seat belt of the target seat and the occupant's body are determined.

13. The method according to claim 10, characterized in that, The determination of the seatbelt wearing detection result based on the hand movement detection result and the relative positional relationship between the seatbelt and the occupant's body includes: If the hand movement detection result indicates that the occupant has made a hand movement to insert the seat belt into the seat belt buckle, and the relative positional relationship between the seat belt and the occupant's body meets the correct wearing conditions, then it is determined that the occupant is wearing the seat belt correctly. If the hand movement detection result indicates that the occupant does not perform any hand movements to insert the seat belt into the seat belt buckle, and / or the relative positional relationship between the seat belt and the occupant's body does not meet the conditions for proper wearing, it is determined that the occupant is not wearing the seat belt correctly. The correct wearing conditions include: the seat belt passes through the occupant's body, and the distance between the seat belt and the occupant's body surface does not exceed a preset distance threshold.

14. The method according to claim 11, characterized in that, The method further includes: If no occupant is detected in the target seat, or if the seatbelt wearing detection result indicates that the occupant is not wearing the seatbelt correctly, an alarm message will be issued.

15. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method as described in claim 9.

16. A vehicle, characterized in that, The vehicle includes a seatbelt detection device as described in any one of claims 1 to 3; or a seatbelt wearing recognition system as described in any one of claims 4 to 8; or an electronic device as described in claim 15.

Images