Vehicle seat state identification method and system based on multi-source sensing

Abstract

The invention belongs to the technical field of vehicle control, and particularly relates to a vehicle seat state recognition method and system based on multi-source sensing. The identification method comprises the following steps that the pressure sensor collects data and transmits the data to the system; the system judges whether the seat pressure is larger than a set threshold value or not, and if not, the seat is marked as an empty seat; if yes, the sensor detects the temperature within the range of the seat; if not, the passenger is marked, and if not, the luggage is marked; the system encrypts the judgment data to form an encrypted data packet; the information is transmitted to the mobile phone of the vehicle owner and uploaded to the cloud through the mobile phone of the vehicle owner, and then the passenger APP displays the vehicle seat state information. According to the technical scheme, whether passengers or articles exist in the seats or not is judged by placing the sensors on the seats of the passengers, and the number of the passengers capable of being carried by the current vehicle can be displayed in real time through the mobile phone terminal. Passengers and drivers can conveniently judge whether carrying is available or not, travel inconvenience is reduced, communication times are reduced, and efficiency is improved.

Description

Technical Field

[0001] This invention belongs to the field of vehicle control technology, specifically relating to a method and system for vehicle seat status recognition based on multi-source sensing. Background Technology

[0002] In the shared mobility ecosystem, the ambiguity regarding the actual number of users who can ride in a vehicle causes significant problems for both user groups, and existing technical solutions have failed to effectively address this issue.

[0003] (I) The "Passive Carpooling Dilemma" of i-person (introverted users):

[0004] 1) Although users choose non-carpooling services (such as private cars or express cars), the platform / drivers may add carpooling orders during the trip without authorization in order to increase their income, resulting in the actual number of passengers carried by the vehicle exceeding expectations.

[0005] 2) Introverted users face sudden social pressure: they are forced to share small spaces with strangers and lack prior knowledge and choice.

[0006] Existing system defects: The passenger-side APP only displays the order type (such as "express car"), and cannot obtain the current actual number of passengers in the vehicle and the trend of change in real time. Users lack the basis to actively avoid or cancel orders.

[0007] (ii) Risk of "Misjudgment of Carrying Capacity" in Group Travel:

[0008] 1) When multiple people travel together (such as family trips or group activities) and need to book multiple vehicles, the existing system only provides the company category to which the vehicle belongs.

[0009] 2) In real-world scenarios, if passengers already on board are carrying large luggage (such as strollers or camping equipment) or there are non-standard body types (such as those with large builds), the nominal number of seats will not equal the actual number of available seats.

[0010] Consequences: Group passengers arrive to find that the vehicle cannot accommodate all members and luggage, and are forced to be temporarily reassigned to other vehicles, causing travel delays, soaring costs, and a ruined experience. Group pick-up and drop-off at airports / high-speed rail stations can lead to long-term congestion of passengers.

[0011] Visual recognition (such as Tesla's occupant detection) works by using camera image analysis to identify the number and location of occupants. However, radar sensors designed for occupancy detection typically require one sensor per seat. To observe two or more seats with a single radar sensor necessitates a relatively complex radar system with high angular resolution. According to existing technology, this is usually achieved using MIM0 (Multiple-Input Multiple-Output) radar. However, this presents several drawbacks: ① Sensitive to lighting / occlusion: Nighttime conditions, clothing obstructions, and seatback tilt lead to high recognition failure rates. ② Extremely high privacy risks: Continuous in-vehicle camera recording raises strong user resistance and legal compliance issues (such as GDPR). ③ High computational complexity and cost: Requires high-performance AI chips, making widespread adoption in ordinary commercial vehicles difficult. ④ Weak luggage recognition capabilities: Difficult to accurately determine the actual occupancy of seats by luggage. Summary of the Invention

[0012] The purpose of this invention is to provide a vehicle seat state recognition method and system based on multi-source sensing, in order to solve the following technical problems:

[0013] (1) i people do not want to carpool but are forced to: the driver accepts the order privately, and the passenger only finds out that there is an extra stranger when he gets in the car.

[0014] (2) Misjudgment of seating for group travel: 7-seater vehicles can only accommodate 5 people because of luggage taking up seats.

[0015] To solve the above problems, this application provides the following technical solution:

[0016] A method for vehicle seat state recognition based on multi-source sensing includes the following steps:

[0017] S1. Pressure sensor data is acquired and transmitted to the system;

[0018] S2. The system determines whether the seat pressure is greater than the set threshold. If yes, proceed to step S3; otherwise, mark it as an empty seat.

[0019] S3. The sensor detects the temperature within the seat area. If the temperature is >30℃, it is marked as a passenger; otherwise, it is marked as luggage.

[0020] S4. The system encrypts the data marked as empty seats in step S2, passenger data in step S3, and luggage data to form an encrypted data packet.

[0021] S5. The encrypted data packet is transmitted to the vehicle owner's mobile phone and then uploaded to the cloud via the vehicle owner's mobile phone, where it is displayed on the passenger APP to show the vehicle seat status information.

[0022] Furthermore, when a driver accepts a ride-sharing order, the system is activated, including the following steps:

[0023] S11, The pressure sensor detects that the new pressure is greater than the set value;

[0024] S12. The infrared temperature sensor detects the temperature within the seat area. If the temperature is >30℃, it is marked as a new passenger and proceeds to step S13. Otherwise, it is marked as luggage placement and the seat status is updated.

[0025] S13. The driver's mobile phone will sound and light an alarm, and an encrypted data packet will be generated and sent to the cloud. At the same time, a warning message will be pushed to the passenger's APP, allowing the passenger to cancel the order or complain to the platform through the APP.

[0026] Furthermore, the encrypted data packet is transmitted to the car owner's mobile phone via Bluetooth, and then transmitted to the cloud through the data interface of the car owner's mobile phone platform APP.

[0027] Furthermore, the encrypted data packet includes timestamps and sensor module data.

[0028] Furthermore, it also includes a group travel carrying verification process, comprising the following steps:

[0029] S21. Users input their requirements through the APP;

[0030] S22, the volume required for cloud computing to meet user needs;

[0031] S23. Query the vehicle database according to the required capacity and determine whether the actual empty seat capacity is greater than or equal to the capacity required by the user. If yes, proceed to step S24. If no, push the insufficient capacity information to the user and recommend other vehicles at the same time.

[0032] S24. Push vehicle availability information to the user and display a seat heatmap, allowing the user to confirm vehicle use.

[0033] A vehicle seat status recognition system based on multi-source sensing includes a pressure detection module installed under the seat cushion, which outputs an electrical signal proportional to the load.

[0034] An infrared heat source detection module is installed in the seat back to detect radiation from living organisms at 35-42℃.

[0035] The control unit receives signals from the pressure detection module and the infrared heat source detection module and performs detection to identify passengers, luggage, or empty seats.

[0036] The communication module uploads the detection status data of the control unit to the cloud server via the owner's mobile phone.

[0037] Furthermore, the pressure detection module is preferably a flexible piezoresistive film, and the infrared heat source detection module is preferably a non-contact thermopile sensor.

[0038] The beneficial effects of this invention are:

[0039] This technical solution addresses the inconvenience of transportation caused by rising car sales. When the distance is long and there are no shared bicycles available, taxis are the only option, but this can be inconvenient for multiple passengers, especially if the taxi driver is already carrying another passenger. By placing sensors on passenger seats, the solution can determine if a seat is occupied or if there are any items inside. Crucially, the solution allows the driver to display the current number of passengers the vehicle can carry in real time on a mobile app. This facilitates communication between passengers and drivers, reducing inconvenience, minimizing communication, and increasing efficiency. Attached Figure Description

[0040] Figure 1 This is a flowchart of the vehicle seat state recognition method based on multi-source sensing according to the present invention.

[0041] Figure 2 Flowchart for preventing private carpooling in ride-hailing services.

[0042] Figure 3 Flowchart for verifying the capacity of group travel. Detailed Implementation

[0043] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings. The following embodiments are merely exemplary and can only be used to explain and illustrate the technical solution of the present invention, and should not be construed as limiting the technical solution of the present invention.

[0044] This application primarily addresses the following issues: First, when a passenger places an order via a mobile app but doesn't want to share a ride, the driver may accept the order without authorization, leading the passenger to discover a stranger in the car upon boarding. Canceling the order at this point disrupts the passenger's travel time. Second, in group travel, for example, a 7-seater vehicle may only seat 5 people due to luggage taking up space, resulting in misjudgment of seating.

[0045] This application provides a vehicle seat status recognition system based on multi-source sensing, including:

[0046] The pressure detection module is located under the seat cushion and outputs an electrical signal proportional to the load. Preferably, the pressure detection module uses a flexible piezoresistive diaphragm (model FSR402) with a range of 0-100kg and a linear error of ±5%. The piezoresistive diaphragm is adhered to the interlayer between the seat foam and the fabric.

[0047] Infrared heat source detection module: located on the seat back, detects biological radiation at 35-42℃; preferably, the infrared heat source detection module adopts a non-contact thermopile sensor (model MLX90614), with a temperature measurement accuracy of ±0.5℃. The infrared sensor is embedded under the headrest (10-15cm away from the back of the seated passenger).

[0048] Control unit: Used to receive signals from the pressure detection module and infrared heat source detection module mentioned above and execute:

[0049] if (pressure_val > P_thresh && temp_val > 30.0)

[0050] status = HUMAN; / / Identified as a passenger

[0051] else if (pressure_val > P_thresh && temp_val <= 30.0)

[0052] status = LUGGAGE; / / Recognized as luggage

[0053] else

[0054] status = EMPTY; / / Empty seat.

[0055] Communication module: Uploads the status data determined by the control unit to the cloud server via the vehicle owner's mobile phone.

[0056] like Figure 1 As shown, this application provides a vehicle seat state recognition method based on multi-source sensing, including the following steps:

[0057] S1. The pressure sensor acquires data and transmits it to the control unit;

[0058] S2. The control unit determines whether the pressure of each seat in the vehicle is greater than a set threshold. If so, proceed to step S3; otherwise, mark it as an empty seat.

[0059] The technical solution of this application also includes the problem that there are occupants in the vehicle but they are not sitting in the correct seat position, which leads to inaccurate data detected by the pressure sensor. Therefore, under normal circumstances, after the system is activated, even if the pressure detected by the pressure sensor is not greater than the set threshold, it will not be directly marked as an empty seat. Instead, the infrared temperature sensor will be activated to detect the temperature data of the space outside the driver's area.

[0060] S3. The sensor detects the temperature within the seat area. If the temperature is >30℃, it is marked as an occupant; otherwise, it is marked as luggage. To ensure the accuracy of detection within the vehicle, the detection range of all non-contact thermopile sensors in the vehicle needs to basically cover all spaces in the vehicle, including the trunk space, to improve vehicle safety.

[0061] S4. The system encrypts the data marked as empty seats in step S2, passenger data in step S3, and baggage data to form an encrypted data packet; in this application, the encrypted data packet needs to include timestamp + sensor data.

[0062] S5. The encrypted data packet is transmitted to the driver's mobile phone and then uploaded to the cloud via the driver's phone. The passenger's app then displays the vehicle seat status information. In this embodiment, to ensure the accuracy of the information received by the passenger and to prevent the driver from privately controlling their phone to prevent data from being uploaded to the cloud, the following methods can be used: The data packet is directly transmitted to the driver's mobile phone via Bluetooth or other means through a communication module, and then transmitted to the platform via the driver's dispatch platform app data interface. If the driver turns off Bluetooth, the platform determines that it does not know the driver's actual information and directly suggests that the passenger cancel the order. Another method is to integrate the system's control unit into the vehicle's ECU, with the ECU's communication module transmitting the encrypted data packet to the cloud. Other similar methods are also acceptable.

[0063] like Figure 2 As shown, this application also provides a vehicle seat status recognition method based on multi-source sensing, which activates the system when a driver accepts a ride-sharing order, including the following steps:

[0064] S11, The pressure sensor detects a new pressure > the set value; especially after the driver has accepted the order, within the time range from the passenger's location, the system continuously collects the pressure data detected by the pressure sensor and compares it with the set value. In this embodiment, the set value of 5 kg is used as the initial judgment condition, which also includes the aforementioned handling method when the passenger is not sitting in the correct position of the seat, resulting in inaccurate detection.

[0065] S12. The infrared temperature sensor detects the temperature within the seat area. If the temperature is >30℃, it is marked as a new passenger and proceeds to step S13. Otherwise, it is marked as luggage placement and the seat status is updated. This application also includes infrared temperature sensors to perform comprehensive temperature detection of the vehicle's passenger space.

[0066] S13. The driver's mobile phone will sound and light an alarm, and an encrypted data packet will be generated and sent to the cloud. At the same time, a warning message will be pushed to the passenger's APP, allowing the passenger to cancel the order or complain to the platform through the APP.

[0067] like Figure 3 As shown, it also includes a group travel carrying verification process, which includes the following steps:

[0068] S21. Users input their requirements through the APP.

[0069] S22, the volume required for cloud computing user-required content.

[0070] S23. Query the vehicle database based on the required capacity and determine whether the actual empty seat capacity is greater than or equal to the capacity required by the user. If yes, proceed to step S24. If no, push the insufficient capacity information to the user and recommend other vehicles at the same time.

[0071] S24. Push vehicle availability information to the user and display a seat heatmap, allowing the user to confirm vehicle use.

[0072] This technical solution allows for a two-way selection process between taxis and passengers, facilitating the determination of the number of passengers that can be accommodated.

[0073] The above are preferred embodiments of the present invention. The basic principles and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are only illustrative of the principles of the present invention. Various changes and modifications can be made to the present invention without departing from the spirit and scope of the present invention. All such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-source sensing based vehicle seat state recognition method, characterized in that, Comprising the following steps: S1, pressure sensor data acquisition and transmission to the system; S2, the system determines whether the seat pressure is greater than the set threshold, if yes, go to step S3, if not, mark as empty seat; S3, the sensor detects the temperature in the seat range, if the temperature > 30℃, mark as passenger, if not, mark as luggage; S4, the system encrypts the empty seat data marked in step S2, the passenger data marked in step S3 and the luggage data to form an encrypted data packet; S5, the encrypted data packet is transmitted to the owner's mobile phone, and uploaded to the cloud through the owner's mobile phone, and the passenger APP displays the vehicle seat state information.

2. The multi-source sensor-based vehicle seat state recognition method according to claim 1, characterized in that, The driver activates the system when he accepts the carpooling order, comprising the following steps: S11, the pressure sensor detects the new pressure > the set value; S12, the infrared temperature sensor detects the temperature in the seat range, if the temperature > 30℃, mark as new passenger, go to step S13, if not, mark as luggage, update the seat state; S13, the owner's mobile phone sound and light alarm, at the same time generate an encrypted data packet and send it to the cloud, and at the same time push the warning information to the passenger APP, which is cancelled by the passenger through the APP or complained to the platform.

3. The multi-source sensor-based vehicle seat state recognition method according to claim 1 or 2, characterized in that, The encrypted data packet is transmitted to the owner's mobile phone through Bluetooth, and transmitted to the cloud through the data interface of the owner's mobile phone platform APP.

4. The multi-source sensor-based vehicle seat state recognition method according to claim 3, characterized in that, The encrypted data packet includes timestamp + sensor module data.

5. The multi-source sensor-based vehicle seat state recognition method of claim 1, wherein, It also includes a group travel bearing verification process, comprising the following steps: S21, the user inputs the demand content through the APP; S22, the cloud calculates the volume required by the user's demand content; S23, query the vehicle database according to the required volume, and determine whether the actual empty seat volume ≥ the volume required by the user, if yes, go to step S24, if not, push the insufficient capacity information to the user, and at the same time recommend other vehicles; S24, push the vehicle available information to the user, and display the seat heat map, and confirm the use of the vehicle by the user.

6. A multi-source sensing based vehicle seat state recognition system, characterized in that, The pressure detection module is arranged below the seat cushion, and outputs an electrical signal proportional to the load; The infrared heat source detection module is arranged on the seat back, and detects the radiation of 35-42℃ living organisms; The control unit receives the signals of the pressure detection module and the infrared heat source detection module and performs passenger, luggage or empty seat detection; The communication module uploads the detection state data of the control unit to the cloud server through the owner's mobile phone.

7. The multi-source sensor based vehicle seat state recognition system of claim 6, wherein, The pressure detection module is preferably a flexible piezoresistive film, and the infrared heat source detection module is preferably a non-contact thermopile sensor.

Images