In-vehicle left object recognition method and device, automobile, and storage medium

Abstract

The present disclosure relates to the technical field of vehicle safety management, and discloses an in-vehicle left object identification method and device, an automobile and a storage medium. The method comprises: in response to a driver's off-vehicle behavior, obtaining a total pressure index, a pressure change index and a pressure distribution index on a passenger seat based on pressure data on the passenger seat collected within a preset collection time length; determining a first comparison result of the total pressure index and a pressure threshold; when it is determined that there is a left object in the vehicle based on the first comparison result, determining a second comparison result of the pressure change index and a change index threshold; when it is determined that the left object is a living body based on the second comparison result, sending reminder information indicating that a living body is left in the vehicle; and when it is unable to determine that the left object is a living body based on the second comparison result, identifying the type of the left object based on the total pressure index and the pressure distribution index, and sending the reminder information based on the type of the left object. The above method can improve the accuracy of in-vehicle left object identification.

Description

Technical Field

[0001] This disclosure relates to the technical field of vehicle safety management, such as a method, device, vehicle, and storage medium for identifying objects left in a vehicle. Background Technology

[0002] In recent years, accidents such as suffocation and heatstroke caused by children or pets being locked inside cars due to user negligence have become increasingly common, seriously threatening lives. Furthermore, passengers frequently forget items in daily life. If the car interior is in a high-temperature environment, items left inside, such as mobile phones and portable power banks, may even spontaneously combust, further increasing safety hazards. Therefore, there is a need for car users to categorize and identify items left inside their vehicles and to implement safety risk warnings.

[0003] In existing technologies, a common method involves collecting pressure values ​​from the seat cushion and backrest to create a body pressure distribution map, which is then compared to a pre-defined standard body pressure distribution map. Based on this comparison, the system can determine the type of object left in the seat. While this method can classify objects left in the vehicle to some extent, its classification accuracy is highly dependent on the universality of the pre-defined body pressure distribution map. The accuracy of the classification results is limited by sample size and data quality; insufficient samples or data bias may increase the classification error rate, affecting the reliability of the system.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0006] This disclosure provides a method, device, vehicle, and storage medium for identifying objects left in a vehicle, which can improve the reliability of the identification process and the accuracy of the classification results, and help to effectively remind people leaving the vehicle to be cautious about leaving living beings or items that pose a safety hazard inside the vehicle.

[0007] According to a first aspect of this disclosure, a method for identifying objects left behind in a vehicle is provided, comprising:

[0008] In response to the driver's departure from the vehicle, based on the pressure data collected on the passenger seats within a preset collection period, the total pressure index, pressure change index, and pressure distribution index on the passenger seats are obtained.

[0009] Determine the first comparison result between the total pressure index and the pressure threshold;

[0010] When it is determined that there are residual objects in the vehicle based on the first comparison result, the second comparison result between the pressure change index and the change index threshold is further determined.

[0011] When the second comparison result determines that the object left behind is a living being, a reminder message is sent to indicate that a living being has been left inside the vehicle.

[0012] If the second comparison result fails to determine that the abandoned object is a living organism, the type of abandoned object is identified based on the total pressure index and pressure distribution index, and a reminder message is sent based on the type of abandoned object.

[0013] In some embodiments, the first comparison result is used to indicate the magnitude relationship between the total pressure index and the pressure threshold; when it is determined that there is a residual object in the vehicle based on the first comparison result, a second comparison result between the pressure change index and the change index threshold is further determined, including: when the first comparison result is that the total pressure index is greater than the pressure threshold, it is determined that there is a residual object in the vehicle, and a second comparison result between the pressure change index and the change index threshold is further determined.

[0014] In some embodiments, the second comparison result is used to indicate the magnitude relationship between the pressure change index and the change index threshold; when it is determined that the object left behind is a living being based on the second comparison result, a reminder message is sent to indicate that a living being left behind in the vehicle, including: when the second comparison result is that the pressure change index is greater than the change index threshold, the object left behind is determined to be a living being, and a reminder message is sent to indicate that a living being left behind in the vehicle.

[0015] In some embodiments, when the second comparison result fails to determine that the remaining object is a living organism, the type of the remaining object is identified based on the total pressure index and the pressure distribution index, and a reminder message is sent based on the type of the remaining object, including: when the second comparison result is that the pressure change index is not greater than the change index threshold, the type of the remaining object is identified based on the total pressure index and the pressure distribution index, and a corresponding reminder message is sent based on the type of the remaining object.

[0016] In some embodiments, the total pressure index is the average of the total pressure at each sampling time point within the sampling period.

[0017] In some embodiments, the passenger seat includes multiple zones, and the pressure change index is obtained based on the pressure change parameters of each zone during the sampling period.

[0018] In some embodiments, each partition has a corresponding weighting coefficient, and the pressure change index is the weighted average of the pressure change parameters of each partition during the sampling period.

[0019] In some embodiments, the pressure change parameter for each partition during the sampling period is used to characterize the change in the pressure ratio of the partition to the total pressure during the sampling period.

[0020] In some embodiments, the pressure change parameter for each partition during the sampling period is the square root of the rate of change of the ratio of the pressure in that partition to the total pressure during the sampling period.

[0021] In some embodiments, identifying the type of legacy object based on the total stress index and the stress distribution index includes: inputting the total stress index and the stress distribution index into a trained identification model, and outputting the type of legacy object based on the identification model.

[0022] In some embodiments, the passenger seat includes multiple zones, and the pressure distribution index includes at least one of the following: the size parameter of the contact area between the passenger seat and the object, the pressure parameter on the passenger seat, the pressure ratio of the pressure in each zone of the passenger seat to the total pressure, and the number of zones on the passenger seat for which pressure data exists.

[0023] In some embodiments, after determining the first comparison result between the total pressure index and the pressure threshold, the method further includes: ending the identification process when it is determined, based on the first comparison result, that no object remains in the vehicle.

[0024] According to a second aspect of this disclosure, a vehicle in-vehicle object recognition device is provided, comprising:

[0025] The indicator acquisition module is configured to: in response to the driver's departure behavior, acquire the total pressure indicator, pressure change indicator, and pressure distribution indicator of the passenger seat based on the pressure data collected on the passenger seat within a preset collection period;

[0026] The first identification module is configured to: determine a first comparison result between the total pressure index and the pressure threshold; when it is determined that there is a left-behind object in the vehicle based on the first comparison result, continue to determine a second comparison result between the pressure change index and the change index threshold; when it is determined that the left-behind object is a living being based on the second comparison result, send a reminder message indicating that there is a living being left in the vehicle.

[0027] The second identification module is configured to: when the leftover object cannot be determined to be a living organism based on the second comparison result, identify the type of the leftover object based on the total pressure index and the pressure distribution index, and send a reminder message based on the type of the leftover object.

[0028] According to a third aspect of this disclosure, an in-vehicle object recognition device is provided, including a processor and a memory storing program instructions, wherein the processor is configured to execute the in-vehicle object recognition method provided in the first aspect of this disclosure when running the program instructions.

[0029] According to a fourth aspect of this disclosure, an automobile is provided, including an in-vehicle object identification device provided in the second or third aspect of this disclosure, wherein the in-vehicle object identification device is communicatively connected to a pressure sensor in a passenger seat to receive pressure data of the passenger seat collected by the pressure sensor.

[0030] According to a fifth aspect of this disclosure, a storage medium is provided that stores computer program instructions, which, when executed by a processor, perform the in-vehicle object recognition method provided in the first aspect of this disclosure.

[0031] The in-vehicle object identification method, apparatus, vehicle, and storage medium provided in this disclosure can achieve the following technical effects:

[0032] The in-vehicle object identification method provided in this disclosure not only considers total pressure but also combines pressure change indicators and pressure distribution indicators, enabling a more comprehensive description of the characteristics of the abandoned object. This multi-dimensional analysis significantly improves the accuracy and reliability of classification. Specifically, by directly comparing the total pressure indicator and pressure change indicator with their corresponding thresholds, the calculation process is greatly simplified, and the calculation speed and real-time performance are improved. Because a more flexible threshold comparison mechanism is adopted, rather than relying on a fixed preset body pressure distribution map, the dependence on a large amount of high-quality sample data is reduced, lowering the risk of classification errors due to insufficient samples or data bias. In particular, the introduction of the pressure change indicator can better capture the dynamic characteristics of living organisms, thereby effectively distinguishing living organisms from other types of abandoned objects and improving the accuracy of classification results. Furthermore, if the total pressure indicator and pressure change indicator fail to successfully determine whether the abandoned object is a living organism, the comprehensive analysis of the total pressure indicator and pressure distribution indicator is used to further determine the type of abandoned object, improving the reliability of the identification process and the accuracy of the classification results. In addition, the system can send corresponding reminders based on the type of object left behind, effectively reminding people to be careful not to leave living beings or items that pose a safety hazard in the vehicle, thereby preventing dangerous or unexpected situations from occurring.

[0033] The above general description and the description below are exemplary and illustrative only and are not intended to limit this disclosure. Attached Figure Description

[0034] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0035] Figure 1 This is a schematic diagram of the structure of a car seat provided in an embodiment of this disclosure;

[0036] Figure 2 This is a schematic diagram of a pressure sensor provided in an embodiment of this disclosure;

[0037] Figure 3 This is a schematic diagram showing the distribution of pressure values ​​at various collection points in a frame of pressure data provided in this embodiment of the disclosure;

[0038] Figure 4 This is a pressure distribution cloud map of a water bottle on a seat provided in an embodiment of the present disclosure;

[0039] Figure 5 This is a pressure distribution cloud map of an adult on a seat provided in an embodiment of this disclosure;

[0040] Figure 6 This is a schematic diagram of the partitioning of a seat cushion provided in an embodiment of this disclosure;

[0041] Figure 7 This is a flowchart illustrating a method for identifying objects left in a vehicle according to an embodiment of this disclosure;

[0042] Figure 8 This is a flowchart illustrating another method for identifying objects left in a vehicle according to an embodiment of this disclosure;

[0043] Figure 9 This is a schematic diagram of the structure of an in-vehicle object recognition device provided in an embodiment of this disclosure;

[0044] Figure 10 This is a schematic diagram of another in-vehicle object recognition device provided in this embodiment. Detailed Implementation

[0045] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0046] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0047] Unless otherwise stated, the term "multiple" means two or more.

[0048] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0049] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0050] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0051] This disclosure provides an embodiment of a vehicle, such as... Figure 1 As shown, car seats are equipped with pressure sensors that collect pressure data on the seat surface. Combined with... Figure 2 As shown, the pressure sensor can be an array-type flexible pressure sensor, with sampling points arranged in an array. A single frame of pressure data acquired by the pressure sensor includes pressure values ​​from multiple sampling points. Figure 3 This shows the pressure distribution at various sampling points in a frame of pressure data. Different objects exhibit different pressure distributions on the seat. Figure 4 and Figure 5 The pressure distribution cloud maps of a water bottle and an adult on the seat are shown separately. Therefore, the pressure data generated by different objects on the seat are also different.

[0052] Car seats can be divided into driver seats and passenger seats. Here, the driver seat refers to the seat where the driver sits, while passenger seats are all other seats besides the driver's seat. Passenger seats include the front passenger seat and all rear seats. Both driver and passenger seats can be equipped with pressure sensors, or pressure sensors can be installed only in the passenger seats. For example... Figure 1 As shown, when an object is placed on the seat, the pressure sensor can collect data on the pressure exerted by that object on the seat. Specifically, the pressure sensor can be installed in multiple locations on the seat, including the seat cushion, backrest, and armrests. Taking the seat cushion as an example, the pressure sensor can be embedded between the protective layer (such as a leather layer) and the cushioning layer (such as a foam layer). This arrangement not only effectively senses various pressure changes applied to the seat but also ensures the stability and durability of the sensor during daily use.

[0053] Optionally, embodiments of this disclosure may divide the car seat into multiple zones, with a pressure sensor installed in each zone. For example... Figure 6As shown, the seat cushion can be divided into 5 sections, namely section 1 to section 5. Among them, section 1 to section 3 are the middle area of ​​the seat cushion, and section 4 and section 5 are the side areas of the seat cushion.

[0054] This disclosure provides a vehicle-in-car object identification device (hereinafter referred to as the identification device), which is communicatively connected to a pressure sensor in the passenger seat of the vehicle. The identification device can receive pressure data collected by the pressure sensor from the passenger seat and, after the driver leaves the vehicle, determine whether an object is left inside the vehicle and the type of object based on the pressure data. Here, a left-behind object refers to an object left on the passenger seat after the driver gets out of the vehicle; the left-behind object can be a living or non-living object. When the identification device detects the presence of a left-behind object in the vehicle, it can send a reminder message to a terminal device. Here, the terminal device can be a smartphone, tablet, wearable device (such as a smartwatch, smart glasses, etc.), smart speaker, alarm, voice output device, or warning light, etc. The reminder message can be delivered to the user in various forms, including text messages, voice messages, light prompts, mechanical vibrations, etc., or any combination of these forms.

[0055] In some embodiments, the identification device can be integrated into the vehicle interior. Specifically, the identification device can be part of the onboard computer or a specially configured electronic device with computing capabilities. In this setup, the identification device can communicate directly with pressure sensors and terminal devices. It can directly receive data from the pressure sensors and immediately send an alert to the terminal device when it detects a leftover object in the vehicle. Alternatively, the identification device can also communicate with the terminal device via a cloud server. In this case, the identification device sends the alert to the cloud server, which then forwards it to the terminal device.

[0056] In other embodiments, the identification device can be a cloud server that maintains a communication connection with the onboard computer and terminal devices. In this mode, the onboard computer first receives pressure data from pressure sensors and transmits this data to the cloud server (i.e., the identification device). When the identification device detects a leftover object in the vehicle, it can send an alert message directly to the terminal device.

[0057] In conjunction with the identification device provided in the embodiments of this disclosure, the embodiments of this disclosure provide a method for identifying objects left behind in a vehicle. Figure 7 As shown, the methods for identifying objects left behind in vehicles include:

[0058] S701, the identification device responds to the driver's departure behavior and obtains the total pressure index, pressure change index and pressure distribution index of the passenger seat based on the pressure data collected on the passenger seat within a preset collection period.

[0059] In this embodiment of the disclosure, the criteria for the driver's departure behavior can be set according to actual design needs. For example, the criteria for the driver's departure behavior include: the vehicle is in a parked state and there is no pressure data on the driver's seat. Specifically, when the recognition device detects that the vehicle is in a parked state and the pressure data collected by the pressure sensor on the driver's seat is zero, it determines that the driver has left the vehicle. At this time, the recognition device can obtain the total pressure index, pressure change index, and pressure distribution index on the passenger seat based on the pressure data collected on the passenger seat within a preset collection period.

[0060] In this embodiment of the disclosure, the pressure data collected on the passenger seat within a preset collection period refers to the pressure data collected by the pressure sensor installed on the passenger seat within a specified time period. Specifically, this preset collection period is a specific time period calculated from the start of the driver's departure from the vehicle. For example, the preset collection period can be set to 5 seconds after the driver leaves the vehicle.

[0061] In this embodiment of the disclosure, the pressure sensor continuously collects multiple frames of pressure data on the passenger seat within a preset collection period. The identification device can perform statistical analysis on these pressure data to obtain the total pressure index, pressure change index, and pressure distribution index on the passenger seat.

[0062] In this embodiment of the disclosure, the total pressure index is mainly used to preliminarily determine whether there is any abandoned object. The pressure change index reflects the change in pressure on the passenger seat over time, and is suitable for distinguishing between static objects and dynamic living beings, thus enabling the identification of the presence of living beings. The pressure distribution index reflects the surface pressure distribution on the passenger seat, which helps to identify information such as the shape and location of any abandoned object.

[0063] S702, the identification device determines the first comparison result between the total pressure index and the pressure threshold.

[0064] In this embodiment, the first comparison result is used to indicate the relationship between the total pressure index and the pressure threshold, which is a reference value used to determine whether there are any objects left behind on the passenger seat. Here, based on a large amount of experimental data and actual usage scenarios, the pressure generated on the seat by different types of left-behind objects (such as living beings, items, etc.) can be statistically determined, and a reasonable pressure threshold can be set based on this pressure data. Furthermore, considering the influence of factors such as different vehicle models, seat materials, and passenger weight, the pressure threshold can be dynamically adjusted using machine learning algorithms. For example, data can be continuously collected during vehicle use, and the pressure threshold can be optimized according to the actual situation.

[0065] After the driver leaves the vehicle, pressure data on the passenger seats is first collected, and a total pressure index is calculated. This total pressure index is then compared to a preset pressure threshold to preliminarily determine if any object has been left behind on the passenger seats. If the total pressure index exceeds the threshold, a potential object is considered to be left behind on the passenger seats; otherwise, no object is considered to be left behind.

[0066] S703, when the identification device determines that there is a residual object in the vehicle based on the first comparison result, it continues to determine the second comparison result of the pressure change index and the change index threshold.

[0067] S704, when the identification device determines that the object left behind is a living being based on the second comparison result, it sends a reminder message to indicate that a living being has been left inside the vehicle.

[0068] In this embodiment, the second comparison result is used to indicate the relationship between the pressure change index and the change index threshold, which is a reference value used to determine whether the object left on the seat is a living being. Specifically, since living beings exhibit regular breathing movements when asleep, this causes the pressure on the seat contact surface to change periodically. Therefore, by accurately measuring the pressure and setting an appropriate change index threshold, it is possible to distinguish between a sleeping living being and a static object of the same mass. For example, the identification device can distinguish between a sleeping baby and a bag of rice of the same weight. Here, by conducting experiments on the pressure change characteristics of different types of leftover objects (such as living beings, static objects, etc.) in different scenarios, corresponding pressure change data is obtained, and a reasonable change index threshold is set based on this pressure change data. Furthermore, considering the influence of factors such as different vehicle models, seat materials, and the behavior of living beings, the change index threshold can be dynamically adjusted using machine learning algorithms. For example, data can be continuously collected during vehicle use, and the change index threshold can be optimized according to the actual situation.

[0069] When the identification device determines that an object is left in the vehicle based on the first comparison result, it compares the pressure change index with a preset change index threshold to preliminarily determine whether the object left on the passenger seat is a living being. If the pressure change index is greater than the change index threshold, the object is considered to be a living being, and an alert message is sent to the terminal device to indicate that a living being has been left in the vehicle.

[0070] S705, when the identification device fails to determine that the abandoned object is a living organism based on the second comparison result, it identifies the type of abandoned object based on the total pressure index and the pressure distribution index, and sends a reminder message based on the type of abandoned object.

[0071] If the second comparison between the pressure change index and the change index threshold fails to confirm whether the abandoned object is a living organism, the type of abandoned object can be further identified based on the total pressure index and pressure distribution index. Then, an alert message can be sent based on the type of abandoned object. Here, the alert message can be used to indicate the presence of an abandoned object in the vehicle and its type.

[0072] The types of left-behind items can be set according to actual needs. For example, the types of left-behind items may include: toddlers aged 0-6 years old placed in child safety seats, children aged 6-12 years old using booster seats, passengers aged 12 years and older, pet cats, pet dogs, suitcases and bags, water bottles and beverage bottles, mobile phones or power banks, and other items.

[0073] This disclosure provides a method for identifying objects left behind in vehicles in the morning. It considers not only total pressure but also pressure change and pressure distribution indicators, enabling a more comprehensive description of the characteristics of the left-behind objects. This multi-dimensional analysis significantly improves the accuracy and reliability of classification. Specifically, by directly comparing the total pressure and pressure change indicators with their corresponding thresholds, the calculation process is greatly simplified, improving calculation speed and real-time performance. Because a more flexible threshold comparison mechanism is used, rather than relying on a fixed preset body pressure distribution map, the reliance on a large amount of high-quality sample data is reduced, lowering the risk of classification errors due to insufficient samples or data bias. In particular, the introduction of pressure change indicators can better capture the dynamic characteristics of living organisms, thereby effectively distinguishing living organisms from other types of left-behind objects and improving the accuracy of classification results.

[0074] Furthermore, if the total pressure index and pressure change index fail to determine whether the abandoned object is a living being, the system continues to use a comprehensive analysis of the total pressure index and pressure distribution index to further determine the type of abandoned object, improving the reliability of the identification process and the accuracy of the classification results. In addition, the system can send corresponding reminder messages based on the type of abandoned object, effectively reminding occupants to be cautious about leaving living beings or potentially dangerous items inside the vehicle, thereby preventing dangerous or unexpected situations.

[0075] In some embodiments, the passenger seat includes multiple zones, and the pressure distribution index includes at least one of the following: the size parameter of the contact area between the passenger seat and the object, the pressure parameter on the passenger seat, the pressure ratio of the pressure in each zone of the passenger seat to the total pressure, and the number of zones on the passenger seat for which pressure data exists.

[0076] In some embodiments, the dimensional parameters of the contact area between the passenger seat and the object left behind may include the area of ​​the contact area, the length of the contact area, and the width of the contact area.

[0077] In this embodiment of the disclosure, Figure 6 For example, assuming a pressure sensor is only installed on the seat cushion of a passenger seat, a coordinate system XOY can be set up to represent the position information of the cushion. The X-axis is parallel to the length direction of the cushion, and the Y-axis is parallel to the width direction of the cushion. The length of the contact area is defined as the distance between the two farthest pressure data collection points along the Y-axis, and the width of the contact area is defined as the distance between the two farthest pressure data collection points along the X-axis.

[0078] The length of the contact area is denoted as l, and the width of the contact area is denoted as w. The length and width of the contact area can be calculated using formulas 1 and 2:

[0079] l=(x1-x n )d---Formula 1;

[0080] w = (y1 - y n )d---Formula 2.

[0081] y1 is the sequence number of the first pressure data acquisition in the positive Y-axis direction of the pressure sensor. n x1 is the sequence number of the last pressure data acquisition in the positive Y-axis direction of the pressure sensor, and x2 is the sequence number of the first pressure data acquisition in the positive X-axis direction of the pressure sensor. n d represents the sequence number of the last pressure data acquisition point in the positive X-axis direction of the pressure sensor, and d represents the distance between two adjacent acquisition points in the pressure sensor.

[0082] In some embodiments, the sampling time period includes multiple sampling moments, each sampling moment corresponds to a contact area, and the contact areas at each sampling moment may be different.

[0083] In some embodiments, the average area of ​​the contact region at all sampling times within a sampling period can be used as a pressure distribution index.

[0084] In some embodiments, the average length of the contact area at all sampling times within a sampling period can be used as a pressure distribution index.

[0085] In some embodiments, the average width of the contact area at all sampling times within a sampling period can be used as a pressure distribution index.

[0086] In some embodiments, the pressure sensor collects pressure data at various sampling moments within a sampling time period, with the pressure data at each sampling moment serving as a frame of pressure data. Here, a total pressure is obtained based on the frame of pressure data collected at each sampling moment, and the total pressure index is the average of the total pressure at all sampling moments within the sampling time period.

[0087] In this embodiment of the disclosure, the total pressure at a sampling moment is equal to the area of ​​the contact region corresponding to that sampling moment, multiplied by the sum of all pressure values ​​in a frame of pressure data corresponding to that sampling moment. Specifically, the total pressure at a sampling moment is denoted as M, and the total pressure can be calculated using Formula 3:

[0088]

[0089] In Formula 3, N represents the total number of pressure values ​​in a frame of pressure data collected by the pressure sensor at one sampling time, and P... i Let A be the i-th pressure value in a frame of pressure data, where i ranges from 1 to N, and A is the area of ​​the contact region corresponding to a sampling time.

[0090] In some embodiments, the pressure parameters on the passenger seat include at least one of average pressure and peak pressure. The sampling time period includes multiple sampling moments, each corresponding to an average pressure and a peak pressure. The average pressure and peak pressure may be different at different sampling moments.

[0091] The average pressure at a given sampling time is the arithmetic mean of all pressure values ​​collected by the pressure sensor at that time. The peak pressure at a given sampling time is the maximum value among all pressure values ​​collected by the pressure sensor at that time.

[0092] The average pressure at a given moment is represented by P. v The average pressure can be calculated using formula 4:

[0093] In Formula 4, N represents the total number of pressure values ​​collected by the pressure sensor at a single acquisition moment, and P... i Let be the i-th pressure value collected by the pressure sensor at a certain acquisition time, where i can be 1 to N.

[0094] In some embodiments, the average pressure at all sampling times within a sampling period can be used as a pressure distribution index.

[0095] The peak pressure at a given moment is represented by P. max The peak pressure can be calculated using formula 5: P max =max(P1,P2,……,P) N )---Formula 5.

[0096] In Formula 5, N represents the total number of pressure values ​​collected by the pressure sensor at a single acquisition moment, and P... i Let i be the i-th pressure value collected by the pressure sensor at a certain acquisition time, where i can be 1 to N.

[0097] In some embodiments, the average of the peak pressures at all sampling times within a sampling period can be used as a pressure distribution index.

[0098] In this embodiment of the disclosure, if a pressure sensor in a partition collects pressure data, then the partition is considered to have pressure data; otherwise, the partition is considered not to have pressure data. Figure 6 For example, the number of partitions containing pressure data on a passenger seat ranges from 0 to 5. Assuming partitions 1 through 3 contain pressure data, while partitions 4 and 5 do not, then the number of partitions containing pressure data on the passenger seat is 3. Here, if a partition contains pressure data, then that partition can be considered active. The number of partitions containing pressure data on the passenger seat can be defined as the partition activation number, which can be represented as θ.

[0099] In some embodiments, the sampling period includes multiple sampling times, each corresponding to the number of partitions on a passenger seat containing pressure data. The number of partitions containing pressure data on the passenger seat may differ at each sampling time. Here, the average number of partitions containing pressure data on the passenger seat (i.e., the number of active partitions) across all sampling times within the sampling period can be used as a pressure distribution indicator.

[0100] In this embodiment of the disclosure, the sampling time period includes multiple sampling moments. For each partition, each sampling moment generates a pressure ratio between the pressure within that partition and the total pressure. Based on the pressure data collected at each sampling moment within a partition, a pressure within that partition is obtained. Specifically, the pressure of a partition at a sampling moment is equal to the area of ​​the sub-contact region in the partition corresponding to that sampling moment, multiplied by the average pressure value in the partition corresponding to that sampling moment.

[0101] The pressure ratio of a zone at a sampling time to the total pressure at that sampling time can be calculated using Formula 6:

[0102]

[0103] In Formula 6, n is the partition number, and R n P is the ratio of the pressure in partition n at a sampling time to the total pressure at that sampling time. v,n C is the average pressure value in partition n corresponding to a sampling time. n It is the area of ​​the sub-contact region in partition n corresponding to a sampling time, and M is the total pressure at a sampling time.

[0104] In some embodiments, the average pressure ratio corresponding to all sampling times of each partition during the sampling period can be used as a pressure distribution index.

[0105] In some embodiments, the passenger seat includes multiple zones, and the pressure change index is obtained based on the pressure change parameters of each zone during the sampling period.

[0106] In some embodiments, the pressure change parameter for each partition during the sampling period is used to characterize the change in the pressure ratio of that partition to the total pressure during the sampling period. Optionally, the pressure change parameter for each partition during the sampling period is the square root of the rate of change of the pressure ratio of that partition to the total pressure during the sampling period.

[0107] The square root of the rate of change of the pressure ratio within a zone to the total pressure over the sampling period can be calculated using Formula 7:

[0108]

[0109] In Formula 7, n is the partition number, R rms,n R is the square root of the rate of change of the ratio of pressure within partition n to total pressure over the sampling time period, where t represents any sampling moment. n (t) is the pressure ratio of partition n at a sampling time t to the total pressure at sampling time t, where t1 is the first sampling time and t2 is the last sampling time.

[0110] In some embodiments, each partition has a corresponding weighting coefficient.

[0111] The pressure change index is a weighted average of the pressure change parameters for each zone over the sampling period. The weighting coefficient of a zone is related to its location within the passenger seat; for example, a zone located in the center of the seat cushion has a greater weighting coefficient than a zone located on the side of the seat cushion. Figure 6 For example, partitions 1 to 3 are located in the middle area of ​​the seat cushion, and the weight coefficient of these three partitions is 0.25; partitions 4 and 5 are located in the side area of ​​the seat cushion, and the weight coefficient of these two partitions is 0.125.

[0112] The pressure change index can be calculated using formula 8:

[0113]

[0114] In Formula 8, R ω The pressure change index is ω, where n is the partition number, M is the total number of partitions, and ω is the total pressure change index. n R is the weight coefficient of partition n. rms,nIt is the square root of the rate of change of the pressure ratio within partition n to the total pressure over the sampling period.

[0115] Table 1 shows the various metrics obtained from a single frame of stress data for three types of legacy objects: a sitting adult at rest, a sitting adult in an active position, and a thermos.

[0116] Table 1

[0117]

[0118] In some embodiments, the first comparison result is used to indicate the magnitude relationship between the total pressure index and the pressure threshold. When it is determined that there is a residual object in the vehicle based on the first comparison result, a second comparison result between the pressure change index and the change index threshold is further determined, including: if the first comparison result is that the total pressure index is greater than the pressure threshold, it is determined that there is a residual object in the vehicle, and the second comparison result between the pressure change index and the change index threshold is further determined.

[0119] In some embodiments, after determining the first comparison result between the total pressure index and the pressure threshold, the method further includes: ending the identification process when it is determined, based on the first comparison result, that no object remains in the vehicle. Specifically, when the first comparison result indicates that the total pressure index is not greater than the pressure threshold, it is determined that no object remains in the vehicle, and the identification process ends.

[0120] In some embodiments, the second comparison result is used to indicate the magnitude relationship between the pressure change index and the change index threshold. When it is determined that the object left behind is a living being based on the second comparison result, sending an alert message indicating that a living being left behind in the vehicle includes: when the second comparison result shows that the pressure change index is greater than the change index threshold, determining that the object left behind is a living being, and sending an alert message indicating that a living being left behind in the vehicle.

[0121] In some embodiments, when the second comparison result fails to determine that the remaining object is a living organism, the type of the remaining object is identified based on the total pressure index and the pressure distribution index, and a reminder message is sent based on the type of the remaining object, including: when the second comparison result is that the pressure change index is not greater than the change index threshold, the type of the remaining object is identified based on the total pressure index and the pressure distribution index, and a corresponding reminder message is sent based on the type of the remaining object.

[0122] In conjunction with the identification device provided in the embodiments of this disclosure, the embodiments of this disclosure provide another method for identifying objects left behind in a vehicle, combined with Figure 8 As shown, the methods for identifying objects left behind in vehicles include:

[0123] S801, the identification device responds to the driver's departure behavior and obtains the total pressure index, pressure change index and pressure distribution index of the passenger seat based on the pressure data collected on the passenger seat within a preset collection period.

[0124] S802, the identification device determines whether the total pressure index is greater than the pressure threshold.

[0125] In this embodiment of the disclosure, when the total pressure index is greater than the pressure threshold, S803 is executed; when the total pressure index is not greater than the pressure threshold, it is determined that there is no object left in the vehicle, and the identification process ends.

[0126] S803, the identification device determines that there are leftover objects inside the vehicle.

[0127] S804, the identification device determines whether the pressure change index is greater than the change index threshold.

[0128] In this embodiment of the disclosure, when the second comparison result is that the pressure change index is greater than the change index threshold, S805 is executed; when the second comparison result is that the pressure change index is not greater than the change index threshold, S806 is executed.

[0129] S805, the identification device determines that the object left behind is a living being and sends a reminder message indicating that a living being has been left inside the vehicle.

[0130] S806, the identification device identifies the type of the abandoned object based on the total pressure index and the pressure distribution index, and sends corresponding reminder information based on the type of the abandoned object.

[0131] In some embodiments, identifying the type of legacy object based on the total stress index and the stress distribution index includes: inputting the total stress index and the stress distribution index into a trained identification model, and outputting the type of legacy object based on the identification model.

[0132] In this embodiment of the disclosure, the recognition model can be trained through the following process:

[0133] (1) Set category labels for leftover items. Category labels may include: toddlers aged 0-6 years in child safety seats, children aged 6-12 years using booster seats, passengers aged 12 years and older, pet cats, pet dogs, suitcases and bags, water and beverage bottles, mobile phones or power banks, and other items. These category labels can be denoted as y. i ∈{H0,H1,H2,H3,H4,H5,H6,H7}, where y i This represents the i-th category label.

[0134] (2) For each classification label, obtain the feature vector of the classification label. The feature vector may include the total pressure index and the pressure distribution index. Optionally, the pressure distribution index includes at least one of the following: the size parameter of the contact area between the passenger seat and the abandoned object, the pressure parameter on the passenger seat, the pressure ratio of the pressure in each zone of the passenger seat to the total pressure, and the number of zones on the passenger seat with pressure data.

[0135] Optionally, the pressure distribution indicators include the average area of ​​the contact area at all sampling moments within the sampling period, the average width of the contact area at all sampling moments within the sampling period, the average length of the contact area at all sampling moments within the sampling period, the average average pressure at all sampling moments within the sampling period, the average peak pressure at all sampling moments within the sampling period, the average number of partitions with pressure data on the passenger seat at all sampling moments within the sampling period (i.e., the number of active partitions), and the average pressure ratio of each partition at all sampling moments within the sampling period. The total pressure indicator and the above seven averages are used as the feature vector for the classification label, and the feature vector can be denoted as x. i = (T0; T1; T2; T3; T4; T5; T6; T7), where x i Let represent the feature vector of the i-th classification label.

[0136] Having obtained multiple classification labels and their feature vectors, we can begin constructing the dataset. The dataset can be denoted as D = {(x1,y1),(x2,y2),…,(x...} m ,y m )}, where m is the total number of category labels.

[0137] (3) Construct a recognition model, which can be a multi-class recognition model. The functional expression of the recognition model can be: f(x) i )=α T x i +β, and it should be f:x i →y i In the above function, the parameter α = (α0; α1; ...; α7) is the prediction weight coefficient vector, and the parameter β is the prediction error.

[0138] In this embodiment, α and β can be determined based on dataset D, thereby obtaining a uniquely determined functional expression and completing the construction of the recognition model. Determining α and β includes the following steps:

[0139] (3.1) Substitute the dataset D into f(x) i )=α T x i +β, this substitution process can be represented in matrix form:

[0140]

[0141] (3.2) Remember y = (y1; y2; ...; y m Based on the least squares method to minimize the mean square error, the following equation is obtained:

[0142] Let E ω =(y-Xω) T (y-Xω) and taking the derivative with respect to ω, we get:

[0143] Setting the above equation to 0, we obtain the optimal solution (α) for ε = (α0; α1; ...; α7; β). * ,β * The analytical solution of ) is obtained, thereby fully constructing the recognition model, that is, completing the training process of the recognition model.

[0144] After training the recognition model, it can be applied to the actual process of identifying objects left inside a vehicle. In the process of identifying objects left inside a vehicle, the obtained total pressure index and pressure distribution index are used as feature vectors and input into the trained recognition model. The type of the object can be obtained according to the input-output mapping table of the recognition model shown in Table 2.

[0145] Table 2

[0146]

[0147] In Table 2, This indicates the overall pressure index. This represents the average area of ​​the contact region at all sampling moments within the sampling period. This represents the average width of the contact area at all sampling moments within the sampling period. This represents the average length of the contact area at all sampling times within the sampling period. This represents the average pressure at all sampling moments within the sampling period. This represents the average peak pressure at all sampling times within the sampling period. This represents the average number of partitions (i.e., the number of active partitions) containing pressure data on passenger seats across all sampling times within the sampling period. This represents the average pressure ratio of partition n across all sampling times within the sampling period.

[0148] Combination Figure 9 As shown, this embodiment of the present disclosure provides a vehicle in-vehicle object recognition device 900, which includes an indicator acquisition module 901, a first recognition module 902, and a second recognition module 903.

[0149] The indicator acquisition module 901 is configured to: in response to the driver's departure behavior, acquire the total pressure indicator, pressure change indicator and pressure distribution indicator of the passenger seat based on the pressure data collected on the passenger seat within a preset collection period.

[0150] The first identification module 902 is configured to: determine a first comparison result between the total pressure index and the pressure threshold; when it is determined that there is a left-behind object in the vehicle based on the first comparison result, continue to determine a second comparison result between the pressure change index and the change index threshold; when it is determined that the left-behind object is a living being based on the second comparison result, send a reminder message indicating that there is a living being left in the vehicle.

[0151] The second identification module 903 is configured to: when the leftover object cannot be determined to be a living organism based on the second comparison result, identify the type of the leftover object based on the total pressure index and the pressure distribution index, and send a reminder message based on the type of the leftover object.

[0152] This disclosure provides a device for identifying objects left in vehicles in the morning. It considers not only total pressure but also pressure change and pressure distribution indicators, enabling a more comprehensive description of the characteristics of left-behind objects. This multi-dimensional analysis significantly improves the accuracy and reliability of classification. Specifically, by directly comparing the total pressure and pressure change indicators with their corresponding thresholds, the calculation process is greatly simplified, improving calculation speed and real-time performance. Because a more flexible threshold comparison mechanism is used, rather than relying on a fixed preset body pressure distribution map, the dependence on a large amount of high-quality sample data is reduced, lowering the risk of classification errors due to insufficient samples or data bias. In particular, the introduction of pressure change indicators can better capture the dynamic characteristics of living organisms, thereby effectively distinguishing living organisms from other types of left-behind objects and improving the accuracy of classification results.

[0153] Furthermore, if the total pressure index and pressure change index fail to determine whether the abandoned object is a living being, the system continues to use a comprehensive analysis of the total pressure index and pressure distribution index to further determine the type of abandoned object, improving the reliability of the identification process and the accuracy of the classification results. In addition, the system can send corresponding reminder messages based on the type of abandoned object, effectively reminding occupants to be cautious about leaving living beings or potentially dangerous items inside the vehicle, thereby preventing dangerous or unexpected situations.

[0154] In some embodiments, the first comparison result is used to indicate the magnitude relationship between the total pressure index and the pressure threshold. The first identification module 902 is configured to: when the first comparison result is that the total pressure index is greater than the pressure threshold, determine that there is a residual object in the vehicle, and continue to determine a second comparison result between the pressure change index and the change index threshold.

[0155] In some embodiments, the second comparison result is used to indicate the magnitude relationship between the pressure change index and the change index threshold. The first identification module 902 is configured to: when the second comparison result shows that the pressure change index is greater than the change index threshold, determine that the abandoned object is a living being, and send a reminder message indicating that a living being has been left in the vehicle.

[0156] In some embodiments, the second identification module 903 is configured to: when the second comparison result is that the pressure change index is not greater than the change index threshold, identify the type of the legacy object based on the total pressure index and the pressure distribution index, and send corresponding reminder information based on the type of the legacy object.

[0157] In some embodiments, the total pressure index is the average of the total pressure at each sampling time point within the sampling period.

[0158] In some embodiments, the passenger seat includes multiple zones, and the pressure change index is obtained based on the pressure change parameters of each zone during the sampling period.

[0159] In some embodiments, each partition has a corresponding weighting coefficient, and the pressure change index is the weighted average of the pressure change parameters of each partition during the sampling period.

[0160] In some embodiments, the pressure change parameter for each partition during the sampling period is used to characterize the change in the pressure ratio of the partition to the total pressure during the sampling period.

[0161] In some embodiments, the pressure change parameter for each partition during the sampling period is the square root of the rate of change of the ratio of the pressure in that partition to the total pressure during the sampling period.

[0162] In some embodiments, the second identification module 903 is configured to: input the total pressure index and the pressure distribution index into the trained identification model, and output the type of the legacy object based on the identification model.

[0163] In some embodiments, the passenger seat includes multiple zones, and the pressure distribution index includes at least one of the following: the size parameter of the contact area between the passenger seat and the object, the pressure parameter on the passenger seat, the pressure ratio of the pressure in each zone of the passenger seat to the total pressure, and the number of zones on the passenger seat for which pressure data exists.

[0164] In some embodiments, the first identification module 902 is configured to: after determining the first comparison result between the total pressure index and the pressure threshold, further include: ending the identification process when it is determined based on the first comparison result that there is no object left in the vehicle.

[0165] Combination Figure 10As shown, this disclosure provides another in-vehicle object recognition device 1000, which includes a processor 1001 and a memory 1002 for predicting air outlet temperature. Optionally, the in-vehicle temperature prediction device 1000 may further include a communication interface 1003 and a bus 1004. The processor 1001, communication interface 1003, and memory 1002 can communicate with each other via the bus 1004. The communication interface 1003 can be used for information transmission. The processor 1001 can call logical instructions in the memory 1002 to execute the in-vehicle object recognition method of the above embodiment.

[0166] Furthermore, the logic instructions in the aforementioned memory 1002 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0167] The memory 1002, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 1001 executes functional applications and data processing by running the program instructions / modules stored in the memory 1002, thereby implementing the in-vehicle object recognition method in the above embodiments.

[0168] The memory 1002 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 1002 may include high-speed random access memory and may also include non-volatile memory.

[0169] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the above-described method for identifying objects left behind in a vehicle.

[0170] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., and other media capable of storing program code.

[0171] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0172] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to fall within the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0173] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0174] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for identifying objects left behind in a vehicle, characterized in that, include: In response to the driver's departure from the vehicle, based on the pressure data collected on the passenger seats within a preset collection period, the total pressure index, pressure change index, and pressure distribution index on the passenger seats are obtained. Determine the first comparison result between the total pressure index and the pressure threshold; When it is determined that there are residual objects in the vehicle based on the first comparison result, the second comparison result between the pressure change index and the change index threshold is further determined. When the second comparison result determines that the object left behind is a living being, a reminder message is sent to indicate that a living being has been left inside the vehicle. If the second comparison result fails to determine that the abandoned object is a living organism, the type of abandoned object is identified based on the total pressure index and pressure distribution index, and a reminder message is sent based on the type of abandoned object.

2. The method for identifying objects left in a vehicle according to claim 1, characterized in that, The first comparison result is used to indicate the relationship between the total pressure index and the pressure threshold. When it is determined that there is a residual object in the vehicle based on the first comparison result, the second comparison result of the pressure change index and the change index threshold is further determined, including: when the first comparison result is that the total pressure index is greater than the pressure threshold, it is determined that there is a residual object in the vehicle, and the second comparison result of the pressure change index and the change index threshold is further determined.

3. The method for identifying objects left in a vehicle according to claim 1, characterized in that, The second comparison result is used to indicate the relationship between the pressure change index and the change index threshold. When the object left behind is determined to be a living being based on the second comparison result, a reminder message is sent to indicate that a living being has been left behind in the vehicle, including: when the second comparison result is that the pressure change index is greater than the change index threshold, the object left behind is determined to be a living being, and a reminder message is sent to indicate that a living being has been left behind in the vehicle.

4. The method for identifying objects left in a vehicle according to claim 3, characterized in that, If the second comparison result fails to determine that the remaining object is a living organism, the type of the remaining object is identified based on the total pressure index and the pressure distribution index, and a reminder message is sent based on the type of the remaining object. This includes: if the second comparison result shows that the pressure change index is not greater than the change index threshold, the type of the remaining object is identified based on the total pressure index and the pressure distribution index, and a corresponding reminder message is sent based on the type of the remaining object.

5. The method for identifying objects left in a vehicle according to claim 1, characterized in that, The total pressure index is the average total pressure at each sampling moment within the sampling period.

6. The method for identifying objects left in a vehicle according to claim 1, characterized in that, The passenger seat consists of multiple zones, and the pressure change index is obtained based on the pressure change parameters of each zone during the sampling period.

7. The method for identifying objects left in a vehicle according to claim 6, characterized in that, Each partition has a corresponding weighting coefficient, and the pressure change index is the weighted average of the pressure change parameters of each partition during the sampling period.

8. The method for identifying objects left in a vehicle according to claim 6, characterized in that, The pressure change parameter for each zone during the sampling period is used to characterize the change in the pressure ratio of that zone to the total pressure during the sampling period.

9. The method for identifying objects left in a vehicle according to claim 8, characterized in that, The pressure change parameter for each zone during the sampling period is the square root of the rate of change of the ratio of the pressure in that zone to the total pressure during the sampling period.

10. The method for identifying objects left in a vehicle according to claim 1, characterized in that, Identifying the type of legacy object based on total stress index and stress distribution index includes: inputting the total stress index and stress distribution index into a trained identification model, and outputting the type of legacy object based on the identification model.

11. The method for identifying objects left in a vehicle according to claim 1, characterized in that, The passenger seat comprises multiple zones, and the pressure distribution indicators include at least one of the following: the size parameters of the contact area between the passenger seat and the object, the pressure parameters on the passenger seat, the pressure ratio of each zone on the passenger seat to the total pressure, and the number of zones on the passenger seat with pressure data.

12. The method for identifying objects left in a vehicle according to any one of claims 1 to 11, characterized in that, After determining the first comparison result between the total pressure index and the pressure threshold, the process also includes: ending the identification process when it is determined, based on the first comparison result, that there are no left objects inside the vehicle.

13. A device for identifying objects left behind in a vehicle, characterized in that, include: The indicator acquisition module is configured to: in response to the driver's departure behavior, acquire the total pressure indicator, pressure change indicator, and pressure distribution indicator of the passenger seat based on the pressure data collected on the passenger seat within a preset collection period; The first identification module is configured to: determine a first comparison result between the total pressure index and the pressure threshold; when it is determined that there is a left-behind object in the vehicle based on the first comparison result, continue to determine a second comparison result between the pressure change index and the change index threshold; when it is determined that the left-behind object is a living being based on the second comparison result, send a reminder message indicating that there is a living being left in the vehicle. The second identification module is configured to: when the leftover object cannot be determined to be a living organism based on the second comparison result, identify the type of the leftover object based on the total pressure index and the pressure distribution index, and send a reminder message based on the type of the leftover object.

14. A device for identifying objects left behind in a vehicle, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the in-vehicle object identification method as described in any one of claims 1 to 12 when running program instructions.

15. An automobile, comprising an in-vehicle object identification device as described in claim 13 or 14, wherein the in-vehicle object identification device is communicatively connected to a pressure sensor in a passenger seat to receive pressure data of the passenger seat collected by the pressure sensor.

16. A storage medium, characterized in that, The storage medium stores computer program instructions, which, when executed by a processor, perform the in-vehicle object identification method as described in any one of claims 1 to 12.

Images