WO2024083215A1

WO2024083215A1 - In-cabin detection method, in-cabin detection apparatus, computer program product and motor vehicle

Info

Publication number: WO2024083215A1
Application number: PCT/CN2023/125612
Authority: WO
Inventors: 赵辉; 商朗
Original assignee: 法雷奥汽车内部控制（深圳）有限公司
Priority date: 2022-10-21
Filing date: 2023-10-20
Publication date: 2024-04-25
Also published as: CN117917586A

Abstract

An in-cabin detection method, comprising: sending a detection sending wave into a cabin by means of an ultrasonic sensing unit, and receiving a detection return wave; determining in-cabin feature data according to the received detection return wave; and on the basis of detection reference data and the in-cabin feature data, determining whether a target object is present in the cabin, wherein the detection reference data is configured to correspond to a reference return wave received by the ultrasonic sensing unit when no target object is present in the cabin. Thus, the in-cabin detection method can determine whether a target object is present in a cabin, whilst ensuring privacy protection and relatively low costs.

Description

In-cabin detection method, in-cabin detection device, computer program product and motor vehicle

Technical Field

The present disclosure relates to the field of motor vehicles, and more particularly to an in-cabin detection method, an in-cabin detection device, a computer program product, and a motor vehicle.

Background technique

With the significant increase in demand for advanced driver assistance systems (ADAS) and autonomous driving in motor vehicles and the widespread application of related technologies, more and more driver assistance systems (such as assisted parking systems, automatic parking systems, wading detection systems, driver monitoring systems (DMS) and occupant monitoring systems, etc.) are widely used in motor vehicles. Here, ultrasonic sensors have simple principles and low costs. They can realize ultrasonic ranging and speed measurement functions with a small amount of calculation. They are particularly suitable for use in low-speed maneuvering systems of motor vehicles, such as assisted parking systems.

Driver monitoring systems and occupant monitoring systems are usually implemented by arranging millimeter-wave radars (In Cabin Radar) and cameras in the cabin of a motor vehicle to achieve safety reminder functions such as detecting whether target objects such as babies and pets are forgotten in the vehicle, whether unauthorized persons have entered the cabin of the motor vehicle, etc.

However, for the visual technology solutions using cameras, there are many hidden dangers in terms of privacy protection. And for the technical solutions using millimeter-wave radar, millimeter-wave radar itself has defects such as high cost. And in order to achieve better target separation in the cabin, the frequency band of millimeter-wave radar used in the cabin of motor vehicles is usually, for example, 57-64GHz, and the power is usually higher than that of mobile phones. Therefore, in order to meet regulatory requirements, for example, the FCC (Federal Communications Commission) and other institutions are required to conduct certification and approval in terms of electromagnetic safety, resulting in additional costs in terms of certification, such as fees and processes.

Therefore, there is a need for an in-cabin detection method, an in-cabin detection device, a computer program product, and a motor vehicle. The method can use an ultrasonic sensor with advantages in privacy protection and cost, and can detect a target object in the cabin at a low cost without the need for cumbersome electromagnetic safety certification, so as to issue a safety reminder when necessary according to the use scenario of the in-cabin detection.

Public Content

In view of the above problems, the present disclosure proposes an in-cabin detection method, an in-cabin detection device, a computer program product, and a motor vehicle. According to the in-cabin detection method, the in-cabin detection device, the computer program product, and the motor vehicle of the present disclosure, it is possible to determine whether there is a target object in the cabin while ensuring privacy protection and at a low cost.

In the sense of the present disclosure, a motor vehicle can be any vehicle. Preferred motor vehicles are, for example, automobiles, rail vehicles. Particularly preferred are automobiles, for example passenger cars or trucks.

According to one aspect of the present disclosure, a method for in-cabin detection is proposed, comprising: sending a detection transmission wave into the cabin by means of an ultrasonic sensing unit, and receiving a detection return wave; determining in-cabin characteristic data based on the received detection return wave; judging whether there is a target object in the cabin based on the detection reference data and the in-cabin characteristic data; wherein the detection reference data is configured to correspond to the reference return wave received by the ultrasonic sensing unit when there is no target object in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed herein, the in-cabin characteristic data is configured as an envelope curve for characterizing the detection return wave, and the detection reference data is configured as an envelope curve for characterizing the reference return wave; wherein, based on the detection reference data and the in-cabin characteristic data, judging whether there is a target object in the cabin includes: when the envelope curve represented by the in-cabin characteristic data is inconsistent with the envelope curve represented by the detection reference data, judging that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed herein, the in-cabin characteristic data is configured to include a flight time determined based on the detection return wave, and the detection reference data is configured to include a flight time determined based on the reference return wave; wherein, based on the detection reference data and the in-cabin characteristic data, judging whether there is a target object in the cabin includes: when the flight time included in the in-cabin characteristic data is less than the flight time included in the detection reference data, judging that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed in the present invention, the in-cabin characteristic data is further configured to include a detection return wave peak value determined based on the detection return wave, and the detection reference data is configured to include a reference return wave peak value determined based on the reference return wave; wherein, based on the detection reference data and the in-cabin characteristic data, judging whether there is a target object in the cabin includes: when the detection return wave peak value included in the in-cabin characteristic data is smaller than the reference return wave peak value included in the detection reference data, judging that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed herein, when the flight time included in the in-cabin characteristic data is less than or equal to 0.9 times the flight time included in the detection reference data, it is judged that a target object exists in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed herein, the in-cabin detection method further includes: sending detection transmission waves into the cabin multiple times, and receiving detection return waves multiple times, wherein the in-cabin characteristic data is configured to include a discrete degree of flight time determined according to the detection return wave, and the detection reference data is configured to include a discrete degree of flight time determined according to the reference return wave; wherein, based on the detection reference data and the in-cabin characteristic data, judging whether there is a target object in the cabin includes: when the discrete degree included in the in-cabin characteristic data is greater than the discrete degree included in the detection reference data, judging that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed herein, the in-cabin detection method further includes: when a discrete degree included in the in-cabin characteristic data is greater than a target object motion threshold, determining that a target object in the cabin is in motion.

According to a more detailed implementation of the in-cabin detection method disclosed in the present invention, the in-cabin characteristic data is configured to include a detection transmission wave reverberation duration determined based on the detection transmission wave, and the detection reference data is configured to include a reference transmission wave reverberation duration determined based on the reference transmission wave, wherein based on the detection reference data and the in-cabin characteristic data, judging whether there is a target object in the cabin includes: when the detection transmission wave reverberation duration included in the in-cabin characteristic data is greater than the reference transmission wave reverberation duration included in the detection reference data, judging that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed in the present invention, the in-cabin detection method also includes: in the case of judging that there is a target object in the cabin, at a first moment, sending a first plurality of transmission waves in sequence with the help of the ultrasonic sensing unit, respectively determining a first plurality of reverberation durations corresponding to the first plurality of transmission waves, and determining a first discrete degree of the first plurality of reverberation durations; at a second moment after the first moment, sending a second plurality of transmission waves in sequence with the help of the ultrasonic sensing unit, respectively determining a second plurality of reverberation durations corresponding to the second plurality of transmission waves, and determining a second discrete degree of the second plurality of reverberation durations; and judging the distance from the target object according to the relationship between the first discrete degree and the second discrete degree: when the discrete degree becomes larger, judging that the target object is close to the ultrasonic sensing unit; when the discrete degree becomes smaller, judging that the target object is far away from the ultrasonic sensing unit.

According to a more detailed embodiment of the in-cabin detection method disclosed in the present invention, the detection reference The data is determined during factory commissioning, and/or the detection reference data is updated based on cabin feature data determined when no target object exists in the cabin.

According to a more detailed implementation of the in-cabin detection method disclosed herein, the in-cabin detection method also includes: when the motor vehicle on which the in-cabin detection device is installed is started, a reference transmission wave is sent and a reference return wave is received by means of the ultrasonic sensing unit; and the detection reference data is determined based on the reference return wave received by the ultrasonic sensing unit.

In addition, according to the second aspect of the present disclosure, a cabin detection device is proposed, including: an ultrasonic sensing unit, which is configured to send detection transmission waves into the cabin and/or receive detection return waves; a storage unit, which is configured to store detection reference data; an object detection unit, which is configured to determine cabin characteristic data based on the detection return waves received by the ultrasonic sensing unit; wherein the object detection unit is also configured to judge whether there is a target object in the cabin based on the detection reference data and the cabin characteristic data; wherein the detection reference data is configured to correspond to the reference return wave received by the ultrasonic sensing unit when there is no target object in the cabin.

According to a more detailed implementation of the in-cabin detection device disclosed herein, the in-cabin characteristic data is configured as an envelope curve for characterizing the detection return wave, and the detection reference data is configured as an envelope curve for characterizing the reference return wave; wherein the object detection unit is further configured to: when the envelope curve represented by the in-cabin characteristic data is inconsistent with the envelope curve represented by the detection reference data, determine that there is a target object in the cabin.

According to a more detailed embodiment of the in-cabin detection device disclosed in the present invention, the in-cabin characteristic data is configured to include a flight time determined based on the detection return wave, and the detection reference data is configured to include a flight time determined based on the reference return wave; wherein the object detection unit is further configured to: when the flight time included in the in-cabin characteristic data is less than the flight time included in the detection reference data, determine that there is a target object in the cabin.

According to a more detailed embodiment of the in-cabin detection device disclosed in the present invention, the in-cabin characteristic data is further configured to include a detection return wave peak value determined based on the detection return wave, and the detection reference data is configured to include a reference return wave peak value determined based on the reference return wave; wherein the object detection unit is further configured to: when the detection return wave peak value included in the in-cabin characteristic data is smaller than the reference return wave peak value included in the detection reference data, determine that there is a target object in the cabin.

According to a more detailed embodiment of the in-cabin detection device of the present disclosure, the object detection unit is further configured to: when the flight time included in the in-cabin feature data is less than or equal to 0.9 times In the case of the flight time included in the detection reference data, it is determined that there is a target object in the cabin.

According to a more detailed embodiment of the in-cabin detection device disclosed in the present invention, the ultrasonic sensing unit is further configured to send detection transmission waves into the cabin multiple times and/or receive detection return waves multiple times, the in-cabin characteristic data is configured to include the discrete degree of flight time determined according to the detection return wave, and the detection reference data is configured to include the discrete degree of flight time determined according to the reference return wave; wherein the object detection unit is further configured to: when the discrete degree included in the in-cabin characteristic data is greater than the discrete degree included in the detection reference data, determine that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection device disclosed herein, the object detection unit is further configured to determine that a target object in the cabin is in motion when a discrete degree included in the in-cabin characteristic data is greater than a target object motion threshold.

According to a more detailed implementation of the in-cabin detection device disclosed in the present invention, the in-cabin characteristic data is configured to include a detection transmission wave reverberation duration determined based on the detection transmission wave, and the detection reference data is configured to include a reference transmission wave reverberation duration determined based on the reference transmission wave, wherein the object detection unit is further configured to: when the detection transmission wave reverberation duration included in the in-cabin characteristic data is greater than the reference transmission wave reverberation duration included in the detection reference data, determine that there is a target object in the cabin.

According to a more detailed implementation of the in-cabin detection device disclosed in the present invention, the object detection unit is further configured to: in the case of judging that there is a target object in the cabin, at a first moment, sequentially send a first plurality of transmission waves with the help of the ultrasonic sensing unit, respectively determine a first plurality of reverberation durations corresponding to the first plurality of transmission waves, and determine a first discrete degree of the first plurality of reverberation durations; at a second moment after the first moment, sequentially send a second plurality of transmission waves with the help of the ultrasonic sensing unit, respectively determine a second plurality of reverberation durations corresponding to the second plurality of transmission waves, and determine a second discrete degree of the second plurality of reverberation durations; and judge the distance from the target object according to the relationship between the first discrete degree and the second discrete degree: when the discrete degree becomes larger, it is judged that the target object is close to the ultrasonic sensing unit; when the discrete degree becomes smaller, it is judged that the target object is far away from the ultrasonic sensing unit.

According to a more detailed embodiment of the in-cabin detection device disclosed in the present invention, the storage unit is further configured to store the detection reference data during factory commissioning of the in-cabin detection device, and/or update the stored detection reference data according to the in-cabin feature data determined when there is no target object in the cabin. The input detection reference data.

According to a more detailed embodiment of the in-cabin detection device disclosed in the present invention, the ultrasonic sensing unit is further configured to send a reference transmission wave and/or receive a reference return wave when the motor vehicle on which the in-cabin detection device is installed is started; the object detection unit is further configured to determine the detection reference data based on the reference return wave received by the ultrasonic sensing unit when the motor vehicle on which the in-cabin detection device is installed is started.

In addition, according to the third aspect of the present disclosure, an in-cabin detection device is also proposed, comprising an ultrasonic sensor, a memory, a processor, and computer instructions stored on the memory, wherein when the instructions are executed by the processor, the in-cabin detection device performs the in-cabin detection method according to the present disclosure.

According to a more detailed embodiment of the in-cabin detection device of the present disclosure, the in-cabin detection device is installed in a motor vehicle, and the ultrasonic sensors are arranged in pairs at doors of the motor vehicle.

In addition, according to a fourth aspect of the present disclosure, a computer program product is proposed, comprising a computer program, wherein when the computer program is executed by a processor, an in-cabin detection device executes the in-cabin detection method according to the present disclosure.

Furthermore, according to a fifth aspect of the present disclosure, a motor vehicle is provided, comprising the in-cabin detection device according to the present disclosure.

Here, according to the in-cabin detection method, in-cabin detection device, computer program product and motor vehicle disclosed in the present invention, it is possible to collect different types of in-cabin feature data in, for example, the cabin of a motor vehicle by using an ultrasonic sensor, and compare it with the detection reference data to determine whether there is a target object in the cabin, which has the advantages of good privacy protection and low cost.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. The following drawings are not deliberately scaled according to the actual size, and the focus is on illustrating the main purpose of the present disclosure.

FIG1A shows a flow chart of an in-cabin detection method according to an embodiment of the present disclosure;

FIG1B shows a flow chart of an in-cabin detection method according to another embodiment of the present disclosure;

FIG2 shows an arrangement of an ultrasonic sensor unit according to an embodiment of the present disclosure;

FIG3 is a schematic diagram showing a detection return wave received by an ultrasonic sensor unit;

4A and 4B show the first flight time measured multiple times by the third ultrasonic sensor unit and the fourth ultrasonic sensor unit;

FIG5 shows a flow chart of an in-cabin detection method according to another embodiment of the present disclosure;

FIG6 shows a flow chart of an in-cabin detection method according to another embodiment of the present disclosure;

FIG7 shows a schematic block diagram of an in-cabin detection device according to an embodiment of the present disclosure;

FIG8 shows a schematic block diagram of an in-cabin detection device according to an embodiment of the present disclosure;

FIG. 9 illustrates a motor vehicle according to an embodiment of the disclosure.

Detailed ways

The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present disclosure.

As shown in the present disclosure and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and/or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

In addition, in this specification and the drawings, the terms "first\second" are only used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein.

In addition, in this specification and the accompanying drawings, if a flow chart is used to illustrate the steps of the method according to the embodiments of the present disclosure, it should be understood that the previous or subsequent steps are not necessarily performed precisely in order. Instead, various steps can be processed in reverse order or simultaneously, unless explicitly limited by the embodiments of the present disclosure. At the same time, other operations can also be added to these processes, or one or more steps can be removed from these processes.

As mentioned above, the use of visual or millimeter wave radar to achieve in-cabin detection has many problems in terms of privacy protection or electromagnetic safety certification, and the cost is high. Therefore, there is a way to use low-cost ultrasonic sensors to achieve privacy protection and without cumbersome electromagnetic safety certification. Similar to the demand for in-cabin detection in motor vehicles, to achieve safety reminder functions such as detecting whether there are target objects such as babies and pets forgotten in the cabin of the motor vehicle, whether there are target objects such as unauthorized persons entering the cabin of the motor vehicle, etc.

Based on this, according to the first aspect of the present disclosure, an in-cabin detection method 100 is proposed. The in-cabin detection method 100 uses an ultrasonic sensor unit arranged in the cabin to achieve in-cabin detection of the target object. Figures 1A and 1B show a flow chart of the in-cabin detection method 100 according to an embodiment of the present disclosure. Figure 2 schematically shows the arrangement of the ultrasonic sensor unit according to an embodiment of the present disclosure. For the sake of clarity, the in-cabin detection method 100 according to an embodiment of the present disclosure will be described in conjunction with Figures 1A, 1B and 2.

As shown in FIG. 1A , the in-cabin detection method 100 according to the embodiment of the present disclosure includes: in step S110, using ultrasonic sensor units 210, ..., 240 to send detection transmission waves into the cabin, and receive detection return waves. Schematically, the arrangement of the ultrasonic sensor units 210, ..., 240 in the motor vehicle 200 is shown in FIG. 2 . Exemplarily, the ultrasonic sensor units used by the in-cabin detection method 100 according to the present disclosure can be arranged at the doors of the motor vehicle 200 in pairs, for example. Here, the first ultrasonic sensor unit 210 is arranged at the left front door, the second ultrasonic sensor unit 220 is arranged at the right front door opposite to the first ultrasonic sensor unit 210, the third ultrasonic sensor unit 230 is arranged at the left rear door, and the fourth ultrasonic sensor unit 240 is arranged at the right rear door opposite to the third ultrasonic sensor unit 230. And here, the ultrasonic sensor units 210, ..., 240 can all have transceiver functions. Or the ultrasonic sensor units 210, ..., 240 may also only have the receiving/transmitting functions, i.e., for example, the first ultrasonic sensor unit 210 and the third ultrasonic sensor unit 230 only have the transmitting function, and the second ultrasonic sensor unit 220 and the fourth ultrasonic sensor 240 only have the receiving function, for receiving the receiving waves sent by the remaining ultrasonic sensor units or reflected back from the cabin. However, those skilled in the art should be able to imagine that the installation positions and numbers of the ultrasonic sensor units are not limited thereto. Here, any number of ultrasonic sensor units may be arranged at any of the following positions in the cabin of the motor vehicle 200: at this position, the ultrasonic sensor unit can send a transmitting wave to each possible position of the target object to be detected in the cabin and/or receive a receiving wave reflected back from the position.

After the ultrasonic sensor units 210, ..., 240 receive the detection return waves reflected from the cabin, the cabin detection method 100 according to the embodiment of the present disclosure may further include: in step S120, the current cabin feature data of the motor vehicle may be determined according to the received detection return waves; and in step S130, whether there is a target object in the cabin may be determined based on the detection reference data and the cabin feature data. Here, according to specific functional requirements, the cabin detection method 100 according to the embodiment of the present disclosure may further include: in step S120, the current cabin feature data of the motor vehicle may be determined according to the received detection return waves; and in step S130, whether there is a target object in the cabin may be determined based on the detection reference data and the cabin feature data. The detected target object may be a typical object that the driver needs to be reminded of having forgotten or intruded into the cabin of the motor vehicle, such as a baby, a pet, an unauthorized person, etc.

Here, the detection reference data is configured to correspond to the reference return wave received by the ultrasonic sensor unit when there is no target object in the cabin, that is, to represent the reference return wave that the ultrasonic sensor units 210, ..., 240 should receive when there is no target object in the cabin. The detection reference data can be determined in various situations where there is no target object in the cabin.

For example, according to an embodiment of the in-cabin detection method 100 disclosed herein, the detection reference data can be determined during factory commissioning and written into a storage unit of the in-cabin detection device for subsequent comparison with the in-cabin characteristic data. In addition, in the subsequent use of the in-cabin detection device that executes the in-cabin detection method 100, the detection reference data can also be updated based on the in-cabin characteristic data determined when there is no target object in the cabin. In addition, it is necessary to consider that the placement of items in the cabin may change with the use of the motor vehicle, resulting in changes in the reference return wave that should be received when there is no target object in the cabin. Therefore, as shown in FIG. 1B , according to another embodiment of the in-cabin detection method 100 of the present disclosure, the in-cabin detection method 100 of the present disclosure may also include, when the motor vehicle on which the in-cabin detection device is installed is started, a preprocessing step of updating/re-determining the detection reference data to correctly characterize the state when there is no target object in the cabin, that is: in step S1101, with the aid of the ultrasonic sensor unit 210, ..., 240, a reference transmission wave is sent and a reference return wave is received; and in step S1102, the detection reference data is determined according to the reference return wave received by the ultrasonic sensor unit. In subsequent in-cabin detection, the updated/re-determined detection reference data is used to compare the detection reference data with the in-cabin characteristic data characterizing the current in-cabin state to determine whether there is a target object in the current cabin.

Here, the determined cabin feature data for analyzing whether there is a target object in the cabin and the detection reference data for comparison therewith may have different forms.

For example, the cabin characteristic data and the detection reference data may be configured in the form of envelope curves for characterizing corresponding return waves.

According to an embodiment of the in-cabin detection method 100 disclosed in the present invention, the in-cabin characteristic data used in step S120 and step S130 can be configured as an envelope curve for characterizing the detection return wave, and correspondingly, the detection reference data can also be configured as an envelope curve for characterizing the reference return wave. FIG3 schematically shows the detection return wave 310 received by the ultrasonic sensor unit and its envelope curve 320. Here, the ultrasonic sensor units 210, ..., 240 can filter the received detection return wave 310 to remove noise and extract the envelope curve of the detection return wave. The envelope curve 320 is used as the in-cabin characteristic data according to the present disclosure. In addition, for example, during factory commissioning and/or subsequent use of the in-cabin detection device and/or when the motor vehicle 200 is started, the ultrasonic sensor units 210, ..., 240 can filter the received reference return waves in the same manner to remove noise and extract the envelope curve of the detection return wave as the detection reference data according to the present disclosure. The form of the reference return wave and its envelope curve is similar to that of the detection return wave 310 and its envelope curve 320 shown in FIG. 3, and is not shown separately for the sake of brevity.

Accordingly, according to an embodiment of the in-cabin detection method 100 disclosed in the present invention, step S130 may also include: when the in-cabin characteristic data (i.e., the envelope curve 320 used to characterize the detection return wave) characterizing the current in-cabin state is inconsistent with the detection reference data (i.e., the envelope curve used to characterize the reference return wave) characterizing the reference return wave that should be received when there is no target object in the cabin, it can be determined that there is a target object in the current cabin. Here, a known method can be used to compare the trends of the two envelope curves and determine whether they are consistent, and the present disclosure does not limit this.

For another example, the cabin characteristic data and the detection reference data may be configured in the form of flight time.

According to another embodiment of the in-cabin detection method 100 disclosed in the present invention, the in-cabin characteristic data used in step S120 and step S130 can be configured to include the flight time determined according to the detection return wave, and correspondingly, the detection reference data can be configured to include the flight time determined according to the reference return wave. Here, for example, the first flight time determined according to the time difference between the moment of sending the transmission wave and the moment of first receiving the return wave can be used. FIG. 3 also schematically shows the first flight time TOF1 determined by the ultrasonic sensor unit according to the detection return wave 310. However, those skilled in the art should be able to think that the flight time that can be used here is not limited to this. In addition, preferably, the ultrasonic sensor unit 210, ..., 240 can also be used to send the transmission wave multiple times and determine the above-mentioned first flight time multiple times to calculate the statistical value (such as the average first flight time, the median value of the first flight time, etc.) based on this, and the statistical value is determined as the first flight time in the sense of the present disclosure. Here, the above-mentioned statistical value and the first flight time can be regarded as equivalent, and the present disclosure does not limit the specific determination method and specific representation method of the first flight time.

The following further describes the in-cabin detection method 100 according to the present disclosure with the aid of experimental data. Table 1 lists the first ultrasonic sensor unit 230 and the fourth ultrasonic sensor unit 240 used for detecting the rear seats in five test scenarios: no person on the rear seat in the cabin (scenario 1), one person in the middle of the rear seat (scenario 2), two people on the rear seat (scenario 3), one person on one side of the rear seat (scenario 4), and a person lying on the rear seat (scenario 5). The distance value corresponding to the flight time TOF1 and the return wave peak value MAG1.

Table 1

As can be seen from Table 1, in scenario 1, since there is no target object in the cabin to reflect the detection transmission wave, the maximum distance value corresponding to the first flight time TOF1 determined is 670mm and 662mm. In other scenarios 2 to 5, due to the presence of the target object, the detection transmission wave will contact the target object in advance to reflect the detection return wave. Therefore, the first flight time TOF1 determined is less than the first flight time determined in scenario 1.

Accordingly, the size of the flight time can be used to determine whether there is a target object in the cabin. According to an embodiment of the in-cabin detection method 100 disclosed in the present invention, in step S1101, for example, during factory commissioning and/or subsequent use of the in-cabin detection device and/or when the motor vehicle 200 is started, the first flight time can be determined as detection reference data characterizing that there is no target object in the cabin. Subsequently, in step S130, when the flight time TOF1 included in the in-cabin characteristic data is less than the flight time included in the detection reference data, it can be determined that there is a target object in the cabin.

For another example, the cabin characteristic data and the detection reference data may be configured in the form of return wave peak values.

According to another embodiment of the in-cabin detection method 100 of the present disclosure, the in-cabin characteristic data used in step S120 and step S130 may also be configured to include The determined detection return wave peak value, and correspondingly, the detection reference data can be configured to include a reference return wave peak value determined according to the reference return wave. For example, the first return wave peak value of the return wave received first can be used here. Figure 3 also schematically shows the first return wave peak value MAG1 determined by the ultrasonic sensor unit according to the detection return wave 310. However, those skilled in the art should be able to imagine that the return wave peak value that can be used here is not limited to this. In addition, preferably, the ultrasonic sensor unit 210, ..., 240 can be used to send the transmission wave multiple times and determine the above-mentioned first return wave peak value multiple times to calculate the statistical value (such as the average first return wave peak value, the first return wave peak value median value, etc.) based on this, and determine the statistical value as the first return wave peak value in the sense of the present disclosure. Here, the above-mentioned statistical value can be regarded as equivalent to the first return wave peak value, and the present disclosure does not limit the specific determination method and specific representation method of the first return wave peak value MAG1.

The following further describes the in-cabin detection method 100 according to the present disclosure with the aid of experimental data. As shown in Table 1, in scenario 1, the maximum value of the first return wave peak value MAG1 is -1.19 dB. In other scenarios 2 to 5, the first return wave peak value is less than or equal to -1.19 dB.

Accordingly, the size of the return wave peak value can be used to determine whether there is a target object in the cabin. According to an embodiment of the in-cabin detection method 100 disclosed in the present invention, the first return wave peak value can be determined in step S1101 as detection reference data characterizing that there is no target object in the cabin, for example, during factory commissioning and/or subsequent use of the in-cabin detection device and/or when the motor vehicle 200 is started, in a scenario corresponding to scenario 1. Subsequently, in step S130, when the first return wave peak value MAG1 included in the in-cabin characteristic data is smaller than the first return wave peak value included in the detection reference data, it can be determined that there is a target object in the cabin.

For another example, the cabin characteristic data and the detection reference data may be configured to include both the above-mentioned flight time format and the return wave peak value format.

Here, as shown in Table 1, for scenes 2 to 5 where people/target objects exist, the first flight time TOF1 determined in these cases all satisfy that the flight time is less than or equal to 0.9 times the first flight time TOF1_INIT determined in scene 1, and the first return wave peak value MAG1 all satisfies that it is less than or equal to the first return wave peak value MAG1_INIT determined in scene 1.

According to this, the flight time and the return wave peak value can be used to determine whether there is a target object in the cabin. According to another embodiment of the cabin detection method 100 disclosed in the present invention, in step S130, if the flight time included in the cabin characteristic data is less than or equal to 0.9 times the flight time included in the detection reference data and the return wave peak value MAG1 included in the cabin characteristic data is less than or equal to the return wave peak value included in the detection reference data, it can be determined that there is a target object in the cabin. In addition, for the sake of accurate reminder, it is also possible to determine that there is a target object in the cabin when the flight time and return wave peak value detected by multiple ultrasonic sensor units 230 and 240 meet the above conditions. In addition, for the sake of insurance/redundancy, it is also possible to determine that there is a target object in the cabin when the flight time and return wave peak value detected by one of the multiple ultrasonic sensor units 230 and 240 meet the above conditions. The specific judgment logic under multiple ultrasonic sensor units is not limited in this disclosure.

For another example, the cabin characteristic data and the detection reference data may be configured in the form of discrete degrees of flight time.

According to another embodiment of the in-cabin detection method 100 of the present disclosure, in step S110, detection transmission waves are sent into the cabin multiple times, and detection return waves are received multiple times. In addition, the in-cabin characteristic data used in steps S120 and S130 are configured to include the discrete degree of the flight time determined according to the detection return wave, and the detection reference data are configured to include the discrete degree of the flight time determined according to the reference return wave.

The following further illustrates the in-cabin detection method 100 according to the present disclosure with the aid of experimental data. Compared to Table 1, FIG. 4A and FIG. 4B show the distances corresponding to the first flight time TOF1 measured multiple times by the third ultrasonic sensor unit 230 and the fourth ultrasonic sensor unit 240, and Table 2 further shows the variance of the first flight time TOF1 determined by multiple measurements by the third ultrasonic sensor unit 230 and the fourth ultrasonic sensor unit 240, and adds a scene 6 reflecting the movement of personnel/target objects in the cabin.

Table 2

As can be seen from Table 2 and Figures 4A and 4B, in scenario 1, since there is no target object in the cabin or there is a moving target object to reflect and detect the transmitted wave, the determined first flight time remains relatively constant, and its variance is small, only 0.41 or 6.2. In contrast, in other scenarios 2 to 6, the variance will increase significantly. In particular, for scenario 6 where there is movement of personnel, the variance of the first flight time TOF1 is as high as more than 28,000.

Accordingly, the variance of the flight time can be used to determine whether there is a target object in the cabin. According to another embodiment of the in-cabin detection method 100 of the present disclosure, the discrete degree of the flight time, such as the variance value, determined in a scene corresponding to scene 1 in step S1101, for example, during factory commissioning and/or subsequent use of the in-cabin detection device and/or when the motor vehicle 200 is started, can be used as detection reference data characterizing that there is no target object in the cabin. Subsequently, in step S130, when the discrete degree included in the in-cabin characteristic data is greater than the discrete degree included in the detection reference data, it is determined that there is a target object in the cabin. For the case of using multiple ultrasonic sensor units 230, 240, according to actual needs, different logical relationships can also be used here to associate the detection results of multiple ultrasonic sensor units 230, 240 to output the final judgment result of whether there is a target object in the cabin, and the present disclosure does not limit this.

In addition, as shown in Table 2 and Figures 4A and 4B, for scene 6 where there is movement of personnel, the variance of the first flight time TOF1 is as high as more than 28,000, which is significantly higher than scenes 2 to 5 where there is no movement of personnel. In other words, with the help of the size of the variance of the flight time, it is possible to further determine whether the target object in the cabin moves. This is very beneficial for further providing the type of target object in the cabin: if the target object moves, it can be inferred that the target object may be a pet, baby or child with vital signs, etc., based on which a first reminder message can be sent to the motor vehicle driver; if the target object does not move, the target object may be a package without vital signs, etc., based on which a second reminder message can be sent to the motor vehicle driver. Therefore, according to the in-cabin detection method 100 disclosed in the present invention, it is also possible to further detect vital signs by determining whether the target object in the cabin moves, and accordingly, necessary reminders can be issued to the motor vehicle driver when the target object may have vital signs, that is, when it moves, to further improve the safety reminder function in the cabin.

Therefore, as shown in FIG. 5 , according to another embodiment of the in-cabin detection method 500 of the present disclosure, the in-cabin detection method 500 may further include: in step S540, When the discrete degree included in the data is greater than the target object motion threshold, it is determined that the target object in the cabin is moving.

For another example, the cabin characteristic data and the detection reference data may be configured in the form of reverberation duration.

According to another embodiment of the in-cabin detection method 100 of the present disclosure, the in-cabin characteristic data used in step S120 and step S130 can be configured to include a detection transmission wave reverberation duration determined based on the detection transmission wave, and the detection reference data can be configured to include a reference transmission wave reverberation duration determined based on the reference transmission wave.

The following further describes the in-cabin detection method 100 according to the present disclosure with the aid of experimental data. Table 3 lists the reverberation duration RevTime measured by the third ultrasonic sensor unit 230 and the fourth ultrasonic sensor unit 240 for detecting the rear seats in three test scenarios: no person on the rear seat in the cabin (scenario 1), one person on one side of the rear seat (scenario 2), and two people on the rear seat (scenario 3).

table 3

Since the space inside the cabin of a motor vehicle is relatively small, and the ultrasonic sensor unit is arranged near the target object, such as at the door, when there is a target object in the cabin, it is possible that the vibrator of the ultrasonic sensor unit is still in damped vibration while the receiving wave has returned to the ultrasonic sensor unit. As a result, the ongoing damped vibration will be mixed and superimposed with the returned receiving wave, causing the ultrasonic sensor unit to detect enhanced signal strength and a longer reverberation duration. Therefore, as shown in Table 3, compared with the case where there is no one in the cabin (scenario 1), the reverberation duration of the transmitted wave collected by the third ultrasonic sensor unit 230 and the fourth ultrasonic sensor unit 240 (0.7168ms and 0.6656 ms), when there is a target object in the cabin of the motor vehicle (Scenario 2, Scenario 3), the reverberation duration of the transmitted wave will become longer.

Accordingly, it is possible to determine whether there is a target object in the cabin by means of the size of the reverberation duration. According to another embodiment of the in-cabin detection method 100 of the present disclosure, the reverberation duration determined in a scene corresponding to scene 1 in step S1101, for example, during factory commissioning and/or subsequent use of the in-cabin detection device and/or when the motor vehicle 200 is started, can be used as detection reference data characterizing that there is no target object in the cabin. Subsequently, in step S130, when the detection transmission wave reverberation duration included in the in-cabin characteristic data is greater than the reference transmission wave reverberation duration included in the detection reference data, it is determined that there is a target object in the cabin. For the case of using multiple ultrasonic sensor units 230, 240, according to actual needs, different logical relationships can also be used here to associate the detection results of multiple ultrasonic sensor units 230, 240 to output the final judgment result of whether there is a target object in the cabin, and the present disclosure does not limit this.

In addition, although it is difficult to judge the exact distance to the target object by the size of the reverberation duration, the discrete degree of the reverberation duration measured multiple times can show a certain regularity to provide information about the distance of the target object. As mentioned above, the reason for the extension of the reverberation duration is: the mixed superposition of the damped vibration of the ultrasonic sensor vibrator and the returned reflected wave. The returned reflected wave can affect the damped vibration of the ultrasonic sensor vibrator, so that the size of the reverberation duration shows randomness. If the distance between the measured object and the ultrasonic sensor is closer, the above-mentioned influence of the reflected wave on the ultrasonic sensor vibrator will be stronger, so that the size of the reverberation duration shows stronger randomness. Here, the discrete degree of the reverberation duration measured multiple times can be used to characterize the above-mentioned randomness. In other words, by determining the discrete degree of the reverberation duration measured multiple times, even if the measured object is located in the close range area/blind area of the ultrasonic sensing system, information about the distance of the measured object can still be provided.

Therefore, as shown in FIG6 , according to another embodiment of the in-cabin detection method 600 of the present disclosure, the in-cabin detection method 600 may further include: in the case of judging that there is a target object in the cabin, in step S640, at a first moment, sequentially sending a first plurality of transmission waves by means of the ultrasonic sensing units 210, ..., 240, respectively determining a first plurality of reverberation durations corresponding to the first plurality of transmission waves, and determining a first discrete degree of the first plurality of reverberation durations; in step S650, at a second moment after the first moment, sequentially sending a second plurality of transmission waves by means of the ultrasonic sensing units 210, ..., 240, respectively determining a second plurality of reverberation durations corresponding to the second plurality of transmission waves, and determining a second discrete degree of the second plurality of reverberation durations; and in step S660 In the example, the distance to the target object is determined based on the magnitude relationship between the first discrete degree and the second discrete degree: when the discrete degree increases, the target object is determined to be close to the ultrasonic sensor unit 210, ..., 240; when the discrete degree decreases, the target object is determined to be far away from the ultrasonic sensor unit 210, ..., 240. Here, the discrete degrees of the multiple reverberation durations can be characterized by a statistical parameter commonly used in statistics to characterize the discrete degree of data samples, such as the variance value or standard deviation value of the multiple reverberation durations. In other words, by considering the changes in the discrete degrees of the multiple reverberation durations, the in-cabin detection method 600 according to the present disclosure can further provide information about the distance of the detected object.

It should be understood that the various forms of the cabin characteristic data and the detection reference data disclosed above can also be used in combination according to a predetermined logical relationship based on actual needs, and the present disclosure does not limit this.

In summary, in the present disclosure, the in-cabin detection method realizes the in-cabin detection function by means of ultrasonic sensor units 210, ..., 240. Here, based on various types of in-cabin feature data determined according to the received detection return waves and the detection reference data reflecting the in-cabin state when the target object is not present, it is possible to determine whether the target object exists in the cabin without the need for cumbersome electromagnetic safety certification and without privacy concerns, so that a safety reminder can be issued when necessary according to the use scenario of the in-cabin detection, which has advantages in terms of cost and privacy protection.

In addition, according to the second aspect of the present disclosure, an in-cabin detection device 700 is proposed. FIG. 7 shows a schematic block diagram of an in-cabin detection device 700 according to an embodiment of the present disclosure. Here, the in-cabin detection device 700 includes: an ultrasonic sensor unit 710, which is configured to send a detection transmission wave into the cabin and/or receive a detection return wave; a storage unit 720, which is configured to store detection reference data; an object detection unit 730, which is configured to determine the in-cabin characteristic data according to the detection return wave received by the ultrasonic sensor unit; wherein the object detection unit is also configured to determine whether there is a target object in the cabin based on the detection reference data and the in-cabin characteristic data; wherein the detection reference data is configured to correspond to the reference return wave received by the ultrasonic sensor unit when there is no target object in the cabin.

In addition, the in-cabin detection device 700 and its preferred embodiment according to the present disclosure correspond to the in-cabin detection method described in detail according to Figures 1 to 6. Therefore, for the specific description of the in-cabin detection device 700 and its preferred embodiment, please refer to the specific description of Figures 1 to 6 above, which will not be repeated here for the sake of brevity.

In addition, according to the third aspect of the present disclosure, an in-cabin detection device 800 is proposed. A schematic block diagram of an in-cabin detection device 800 according to an embodiment of the present disclosure is shown. The in-cabin detection device 800 includes an ultrasonic sensor 810, a memory 820, a processor 830, and computer instructions stored on the memory 820. Here, the memory 820 may include RAM, ROM, or a combination thereof. And here, the processor 830 may include an intelligent hardware device (for example, a general-purpose processor, DSP, CPU, microcontroller, ASIC, FPGA, programmable logic control device, MCU, domain controller, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). Wherein, when the instructions are executed by the processor 830, the in-cabin detection device executes the in-cabin detection method described above for Figures 1 to 6. For the sake of brevity, it will not be repeated here.

In addition, according to a fourth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the in-cabin detection device executes the in-cabin detection method described above with respect to Figures 1 to 6. For the sake of brevity, it will not be described in detail here.

In addition, according to the fifth aspect of the present disclosure, a motor vehicle 800 is provided. Fig. 9 schematically shows a motor vehicle 900 according to an embodiment of the present disclosure, including an in-cabin detection device 700, 800 according to the present disclosure. For the sake of brevity, no further description is given here.

The present disclosure uses specific words to describe the embodiments of the present disclosure. For example, "a more detailed embodiment" or "a more detailed implementation method" means a certain feature, structure or characteristic related to at least one embodiment of the present disclosure. Therefore, it should be emphasized and noted that "a more detailed embodiment" or "a more detailed implementation method" mentioned twice or more in different places in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present disclosure may be appropriately combined.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure are described, it will be readily appreciated by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

Claims

A method for in-cabin detection, comprising:

Using an ultrasonic sensor unit, a detection transmission wave is sent into the cabin, and a detection return wave is received;

Determine the cabin characteristic data according to the received detection return wave;

Based on the detection reference data and the in-cabin characteristic data, determining whether there is a target object in the cabin;

The detection reference data is configured to correspond to a reference return wave received by the ultrasonic sensor unit when there is no target object in the cabin.
The in-cabin detection method according to claim 1, wherein:

The cabin characteristic data is configured as an envelope curve for characterizing the detection return wave, and

The detection reference data is configured as an envelope curve for characterizing the reference return wave;

Wherein, judging whether there is a target object in the cabin based on the detection reference data and the cabin feature data includes:

When the envelope curve represented by the in-cabin characteristic data is inconsistent with the envelope curve represented by the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection method according to claim 1, wherein:

The cabin characteristic data is configured to include a flight time determined based on the detected return wave, and

The detection reference data is configured to include a flight time determined based on the reference return wave;

Wherein, judging whether there is a target object in the cabin based on the detection reference data and the cabin feature data includes:

When the flight time included in the cabin characteristic data is less than the flight time included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection method according to claim 3, wherein:

The cabin characteristic data is further configured to include a detection return wave peak value determined according to the detection return wave, and

The detection reference data is configured to include a reference return wave peak value determined according to the reference return wave;

Wherein, judging whether there is a target object in the cabin based on the detection reference data and the cabin feature data includes:

When the detection return wave peak value included in the in-cabin characteristic data is smaller than the reference return wave peak value included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection method according to claim 3 or 4, wherein:

When the flight time included in the cabin characteristic data is less than or equal to 0.9 times the flight time included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection method according to claim 1, further comprising:

Send detection waves to the cabin multiple times, and receive detection return waves multiple times, among which,

The cabin characteristic data is configured to include a discrete degree of flight time determined according to the detection return wave, and

The detection reference data is configured to include a discrete degree of the flight time determined according to the reference return wave;

Wherein, judging whether there is a target object in the cabin based on the detection reference data and the cabin feature data includes:

When the discrete degree included in the in-cabin characteristic data is greater than the discrete degree included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection method according to claim 6, further comprising:

When the discrete degree included in the in-cabin characteristic data is greater than the target object motion threshold, it is determined that the target object in the cabin is moving.
The in-cabin detection method according to claim 1, wherein:

The cabin characteristic data is configured to include a detection transmission wave reverberation duration determined according to the detection transmission wave, and

The detection reference data is configured to include a reference transmission wave reverberation duration determined according to the reference transmission wave,

Wherein, judging whether there is a target object in the cabin based on the detection reference data and the cabin feature data includes:

When the detection transmission wave reverberation duration included in the cabin characteristic data is greater than the reference transmission wave reverberation duration included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection method according to claim 8, further comprising:

In the case where it is determined that there is a target object in the cabin, at a first moment, sequentially sending a first plurality of transmission waves by means of the ultrasonic sensor unit, respectively determining a first plurality of reverberation durations corresponding to the first plurality of transmission waves, and determining a first discrete degree of the first plurality of reverberation durations;

At a second moment after the first moment, sequentially transmitting a second plurality of transmission waves by means of the ultrasonic sensor unit, respectively determining a second plurality of reverberation durations corresponding to the second plurality of transmission waves, and determining a second discrete degree of the second plurality of reverberation durations; and

The distance from the target object is judged based on the size relationship between the first discrete degree and the second discrete degree: when the discrete degree becomes larger, it is judged that the target object is close to the ultrasonic sensor unit; when the discrete degree becomes smaller, it is judged that the target object is far away from the ultrasonic sensor unit.
The in-cabin detection method according to any one of claims 1 to 9, wherein:

The detection reference data is determined during factory commissioning, and/or

The detection reference data is updated according to the in-cabin feature data determined when no target object exists in the cabin.
The in-cabin detection method according to any one of claims 1 to 9, further comprising:

When the motor vehicle on which the in-cabin detection device is installed is started,

By means of the ultrasonic sensor unit, a reference transmission wave is transmitted and a reference return wave is received; and

The detection reference data is determined according to the reference return wave received by the ultrasonic sensor unit.
An in-cabin detection device, comprising:

An ultrasonic sensor unit configured to send a detection transmission wave into the cabin and/or receive a detection return wave;

a storage unit configured to store detection reference data;

an object detection unit configured to detect return waves received by the ultrasonic sensor unit, Determine cabin characteristic data;

Wherein, the object detection unit is further configured to determine whether there is a target object in the cabin based on the detection reference data and the cabin feature data;

The detection reference data is configured to correspond to a reference return wave received by the ultrasonic sensor unit when there is no target object in the cabin.
The in-cabin detection device according to claim 12, wherein:

The cabin characteristic data is configured as an envelope curve for characterizing the detection return wave, and

The detection reference data is configured as an envelope curve for characterizing the reference return wave;

Wherein, the object detection unit is further configured as follows:

When the envelope curve represented by the in-cabin characteristic data is inconsistent with the envelope curve represented by the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection device according to claim 12, wherein:

The cabin characteristic data is configured to include a flight time determined based on the detected return wave, and

The detection reference data is configured to include a flight time determined based on the reference return wave;

Wherein, the object detection unit is further configured as follows:

When the flight time included in the cabin characteristic data is less than the flight time included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection device according to claim 14, wherein:

The cabin characteristic data is further configured to include a detection return wave peak value determined according to the detection return wave, and

The detection reference data is configured to include a reference return wave peak value determined according to the reference return wave;

Wherein, the object detection unit is further configured as follows:

When the detection return wave peak value included in the in-cabin characteristic data is smaller than the reference return wave peak value included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection device according to claim 14 or 15, wherein:

The object detection unit is further configured to:

When the flight time included in the cabin characteristic data is less than or equal to 0.9 times the flight time included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection device according to claim 12, wherein:

The ultrasonic sensor unit is also configured to send detection transmission waves multiple times into the cabin and/or receive detection return waves multiple times.

The cabin characteristic data is configured to include a discrete degree of flight time determined according to the detection return wave, and

The detection reference data is configured to include a discrete degree of the flight time determined according to the reference return wave;

Wherein, the object detection unit is further configured as follows:

When the discrete degree included in the in-cabin characteristic data is greater than the discrete degree included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection device according to claim 17, wherein:

The object detection unit is further configured to:

When the discrete degree included in the in-cabin characteristic data is greater than the target object motion threshold, it is determined that the target object in the cabin is moving.
The in-cabin detection device according to claim 12, wherein:

The cabin characteristic data is configured to include a detection transmission wave reverberation duration determined according to the detection transmission wave, and

The detection reference data is configured to include a reference transmission wave reverberation duration determined according to the reference transmission wave,

Wherein, the object detection unit is further configured as follows:

When the detection transmission wave reverberation duration included in the cabin characteristic data is greater than the reference transmission wave reverberation duration included in the detection reference data, it is determined that a target object exists in the cabin.
The in-cabin detection device according to claim 19, wherein:

The object detection unit is further configured to:

In the case where it is determined that there is a target object in the cabin, at a first moment, sequentially sending a first plurality of transmission waves by means of the ultrasonic sensor unit, respectively determining a first plurality of reverberation durations corresponding to the first plurality of transmission waves, and determining a first discrete degree of the first plurality of reverberation durations;

At a second moment after the first moment, sequentially transmitting a second plurality of transmission waves by means of the ultrasonic sensor unit, respectively determining a second plurality of reverberation durations corresponding to the second plurality of transmission waves, and determining a second discrete degree of the second plurality of reverberation durations; and

The distance from the target object is judged based on the size relationship between the first discrete degree and the second discrete degree: when the discrete degree becomes larger, it is judged that the target object is close to the ultrasonic sensor unit; when the discrete degree becomes smaller, it is judged that the target object is far away from the ultrasonic sensor unit.
The in-cabin detection device according to any one of claims 12 to 20, wherein:

The storage unit is further configured to:

The detection reference data is stored in the detection device during factory commissioning, and/or

The stored detection reference data is updated according to the in-cabin feature data determined when no target object exists in the cabin.
The in-cabin detection device according to any one of claims 12 to 20, wherein:

The ultrasonic sensor unit is further configured to transmit a reference transmission wave and/or receive a reference return wave when the motor vehicle on which the in-cabin detection device is installed is started;

The object detection unit is further configured to determine the detection reference data based on the reference return wave received by the ultrasonic sensor unit when the motor vehicle on which the in-cabin detection device is installed is started.
An in-cabin detection device comprises an ultrasonic sensor, a memory, a processor and computer instructions stored in the memory, wherein when the instructions are executed by the processor, the in-cabin detection device executes the in-cabin detection method according to any one of claims 1 to 11.
The in-cabin detection device according to claim 23, wherein:

The in-cabin detection device is installed in a motor vehicle, and the ultrasonic sensors are arranged in pairs at doors of the motor vehicle.
A computer program product comprises a computer program, wherein when the computer program is executed by a processor, an in-cabin detection device is caused to execute the in-cabin detection method according to any one of claims 1 to 11.
A motor vehicle comprising an in-cabin detection device according to claims 12 to 24.