Method for monitoring the interior of a vehicle

Abstract

The invention relates to a method (400) for monitoring an interior of a vehicle (100). A first measurement method is carried out, wherein the first measurement method comprises: capturing first measurement data by means of a radar system, wherein the first measurement data represent a radar point cloud (305) which is obtained on the basis of a radar scan of a spatial region which at least partially covers the interior of the vehicle; and determining the presence of a person in the interior of the vehicle (100) on the basis of the first measurement data. If it is determined by the first measurement method that no person is present in the interior of the vehicle (100), a second measurement method is carried out, wherein the second measurement method comprises: capturing second measurement data by means of the radar system, wherein vital parameters of persons in the interior of the vehicle (100) can be determined by the second measurement method in order to determine the presence of a person; and determining the presence of a person in the interior of the vehicle (100) on the basis of the second measurement data.

Description

[0001] 2024PF00144

[0002] METHOD FOR MONITORING THE INTERIOR OF A VEHICLE

[0003] The present invention relates to a method for monitoring the interior of a vehicle, in particular by means of a radar system such as an FMCW radar system. In particular, it is intended to detect whether a child is in a vehicle.

[0004] Modern vehicles can be equipped with radar systems, particularly for interior monitoring. For example, it may be necessary to automatically determine the current occupancy status of a seating arrangement with at least one seat. Such a situation can occur especially in vehicles, such as motor vehicles, where vehicle configuration or the activation, deactivation, and / or control of one or more vehicle functionalities is to be carried out depending on the current occupancy status. For example, it is known in motor vehicles to issue an acoustic or visual warning to vehicle occupants to fasten their seat belts or to control the activation or deactivation of airbags, depending on a detected occupancy status. It may also be necessary, for safety reasons, to detect the presence of a child in a seat ("live presence detection" (LPD)).„child presence detection“ (CPD)).

[0005] Methods are known for the automated detection of the current occupancy status of one or more seats, particularly the arrangement of seats in a vehicle, which utilize radar technology for this purpose. Radar sensors scan the vehicle interior, generating measurement data in the form of radar point clouds. The current seat occupancy can then be determined from the measured radar point cloud. These known methods, employing a machine learning model, can even identify the type of occupancy, for example, whether a seat is occupied by an adult or a child.Methods are also known which are able to carry out a more differentiated evaluation of the seat occupancy status through appropriate classification, in particular with regard to the height and weight of an adult or the age of a child.

[0006] Radar systems that can be used include, in particular, FMCW radar systems (“Frequency Modulated Continuous Wave”), which are based on the principle of continuous 2024PF00144

[0007] Frequency modulation is used. This also makes continuous detection of even very small movements possible, such as those encountered in interior monitoring of a vehicle, where seated occupants typically move very little.

[0008] FMCW radar systems are therefore not only suitable for the aforementioned detection of a vehicle's seat occupancy, but also for more demanding tasks. In particular, they can detect whether a person, especially a child or baby, has been accidentally left in the vehicle, which can be crucial for saving lives, for example, if the vehicle heats up in the sun. Generally, radar sensor technology can be used to detect the presence of life in a vehicle, which can also include pets. The sensitive radar technology is capable of detecting the slightest movements, such as breathing or heartbeats, even if, for example, a baby is asleep in a car seat and otherwise moving little or not at all.

[0009] The system can issue a signal or alarm if it detects the presence of life after the vehicle has been exited and locked, in order to inform a user, particularly the driver, of a child or pet left inside. This alarm typically sounds within seconds of the doors closing and locking. For example, the signal or alarm could be a loud honk from the vehicle's horn, or a notification could be sent to the driver's smartphone to draw their attention. Due to the urgency of the situation, the driver must be alerted within seconds, or at most a few minutes, of leaving the parked vehicle.

[0010] It is an object of the present invention to provide an improved method for monitoring the interior of a vehicle, in particular by means of a radar system. In particular, it is intended to detect whether a person, especially a child or baby, is in a vehicle.

[0011] The solution to this problem is achieved according to the teaching of the independent claims. Various embodiments and further developments of the invention are the subject of the dependent claims. 2024PF00144

[0012] A first aspect of the solution presented here concerns a method, particularly a computer-implemented one, for monitoring the interior of a vehicle. This method begins with an initial measurement procedure ("first algorithm"). Initial measurement data is acquired using a radar system. This initial data represents a radar point cloud, which is generated by a radar scan of a spatial area that at least partially or sectionarily covers the vehicle's interior. Based on this initial measurement data, the presence of a person in the vehicle's interior is determined; that is, it is checked whether at least one person is present.

[0013] If the first measurement procedure determines that no person is present inside the vehicle, a second measurement procedure ("second algorithm") is performed. Specifically, it is possible to switch from the first measurement procedure to the second measurement procedure; that is, the first measurement procedure is terminated when the second measurement procedure begins.

[0014] Second set of measurement data is acquired using the radar system. This second measurement method allows for the determination of vital parameters of individuals inside the vehicle to ascertain their presence. Based on this second set of measurement data, the presence of a person inside the vehicle is then determined; that is, it is checked whether at least one person is present. These vital parameters include, in particular, a person's respiration and / or heart rate.

[0015] The invention is therefore based on combining different measurement methods (algorithms). This allows for an efficient determination of whether a person is present in the vehicle or whether the vehicle is empty. In particular, it can be determined whether (especially after a vehicle has been parked) no one is left in the vehicle, especially not a child or baby without the presence of an adult.

[0016] First, an initial measurement procedure is performed to detect (and, if necessary, classify) vehicle occupants. This procedure utilizes a radar point cloud, from which, for example, seat occupancy can be inferred. In particular, the presence of a person can be determined. If very little or no movement is detected with the first measurement procedure, a second measurement procedure is applied to ensure that no one is actually in the vehicle. This second procedure is suitable for detecting vital parameters such as respiration and heart rate. However, such a procedure is typically not suitable for distinguishing between adults and children. By combining both procedures, an efficient and reliable method for monitoring the interior of a vehicle can be provided.

[0017] The first method could be a known algorithm used to detect seat occupancy in a vehicle and classify passengers accordingly. This could, for example, be called "Child Presence Detection" (CPD). A radar sensor inside the vehicle is usually sufficient for this, even to monitor two rows of seats.

[0018] However, problems arise when this method cannot detect the presence of a passenger due to little or no movement, even if, for example, a sleeping baby or child is still in the vehicle. Due to the lack of movement, there are not enough, or even any, moving points for the radar to capture as a point cloud to detect and classify the presence. While this could potentially be solved with a second radar sensor or one radar sensor per row of seats, this would increase costs, power consumption, and installation effort within the vehicle.

[0019] Therefore, according to the procedures following the first aspect, a method for detecting breathing and / or heartbeat is then used. While this method, as mentioned, is not usually suitable for classifying passengers, it is highly sensitive to even the slightest movements. This combination of two measurement methods allows for a reliable determination of whether a child or baby is still alone in the vehicle. Thus, the detection of children, adults, and empty vehicles for two rows within the vehicle is possible using only a single radar sensor, specifically an FMCW radar sensor.

[0020] It goes without saying that, in principle, both methods could be executed in parallel at any time. However, this requires resources, especially computing power. Furthermore, detecting, for example, breathing or heartbeat is unnecessary if significant movements of a passenger have already been detected. According to the method described in the first aspect, the combination of both methods results in 2024PF00144

[0021] Methods in which the appropriate method is selected or switched between the two methods, increasing efficiency while simultaneously ensuring high reliability and safety.

[0022] Terms such as "radar," "radar sensor," "radar sensor device," "radar sensor system," or the like, as used herein, refer specifically to the general understanding of a radar or radar system. More precisely, the "radar" may be a single radar solution or a multiple radar solution located in the passenger compartment of the vehicle. Hereinafter, the nomenclature "radar" or "radar system" may include single or multiple radar solutions. A solution with a radar may be a 3D or a 4D radar. 3D refers to three parameters: range, velocity, azimuth, or elevation angle, while 4D refers to four parameters: distance, velocity, azimuth, and elevation angle. A 3D radar is typically used to illuminate only one row of seats, whereas a 4D radar, depending on its field of view, can illuminate multiple rows. A single unit of this type of radar may be sufficient to provide a decision for the LPD function.The radar sensor system can in particular be a frequency-modulated continuous wave radar system (“FMCW radar system”).

[0023] The term "radar point cloud" as used here refers specifically to a set of points in a vector space obtained by radar scanning of at least one object's surface, exhibiting a typically unorganized spatial structure ("cloud"). In the case of a radar point cloud, the points within the radar point cloud can be called "radar points." A (radar) point cloud can be described, in particular, by the (radar) points it contains. The radar points, in turn, can each be described, in particular, by their spatial coordinates, which specify, for each radar point, the location of the reflection of an emitted radar signal from an object's surface, as measured during the radar scan. Additional attributes, such as the measured Doppler velocity or the signal-to-noise ratio (SNR), can be recorded for each radar point.

[0024] The individual radar points of the radar point cloud can each be described by the position of the respective radar point in three-dimensional space, as well as by a Doppler shift value of the radar signal relative to the respective radar point and / or a signal-to-noise ratio value of the radar signal relative to the respective radar point. Radar points whose Doppler shift value is at or above a value of 2024PF00144

[0025] Radar points that do not exceed a predetermined displacement threshold can be described as "dynamic radar points," meaning radar points that indicate movement of the scanned object, where the Doppler displacement value is at or above the displacement threshold. Such points, exhibiting dynamic movement, are therefore highly likely to be associated with a living being, especially a person or animal.

[0026] The term "vehicle", as used herein, refers in particular to a car, including any type of motor vehicle, hybrid electric vehicle and battery electric vehicle, as well as other vehicles such as trucks, vans or buses.

[0027] The term "seat occupancy status" of a seating arrangement with at least one seat, as used here, refers in particular to information indicating whether or to what extent the seating arrangement, or at least one of its seats, is occupied by an object, especially a thing or a person. In a simple example, the seat occupancy status can simply indicate the presence or absence of an object. In a more advanced example, if at least one object is present on the seating arrangement, or on one or more of its seats, it can provide information about the type or other property of the object, such as its size. Classification can also occur, for example, to distinguish between adults and children.

[0028] The term "detection of the presence of life," as used herein, refers specifically to the detection of a living human being or animal and can be seen as distinct from the detection of moving or stationary objects. Highly sensitive methods are known that can detect even minute changes within a vehicle, such as chest movements of a passenger caused by breathing, which may include the detection of breathing patterns ("Breathing / Heart Beating Detection" - BHBD). This can apply to adults as well as, in particular, children or infants and pets, especially when no other significant movements are detected, for example, when a child or infant is asleep. Thus, the term "detection of the presence of life" (LPD) used here may specifically include "detection of the presence of a child" (Child Presence Detection - CPD).The LPD function can typically be found after the 2024PF00144.

[0029] The LPD function is activated when the vehicle's ignition is switched off and the doors are closed. The term "LPD function" thus refers to an activated live-detection mode. This function or mode is typically inactive, for example, while driving. The LPD function may be activated for a specific period after the vehicle is parked (e.g., a few minutes). It may be possible to deactivate the LPD function once live-detection has been confirmed.

[0030] It should be noted that even less sensitive methods, namely those for determining seat occupancy, can be suitable for "Child Presence Detection" (CPD), provided the child moves sufficiently. As described herein, methods for detecting breathing and heart rate (BHBD) can be used if no movement is detected, so that a child can be detected in any case, especially if left alone in a vehicle.

[0031] Where applicable, the terms "first", "second", "third", and the like are used in the description and in the claims to distinguish between similar elements and not necessarily to describe a sequential or temporal order. It is understood that the terms used in this way are interchangeable under suitable circumstances and that the embodiments of the invention described herein may be operated in a different order than described or illustrated here.

[0032] Any terms used herein, such as "comprises," "includes," "features," "has," "with," or any other variant thereof, are intended to cover non-exclusive inclusion. For example, a method or apparatus that includes or features a list of elements is not necessarily limited to those elements but may include other elements not expressly listed or inherent in such method or apparatus.

[0033] Furthermore, unless expressly stated otherwise, "or" refers to an inclusive or and not an exclusive "or". For example, a condition A or B is satisfied by one of the following: A is true (or present) and B is false (or not present), A is false (or not present) and B is true (or present), and both A and B are true (or present). 2024PF00144

[0034] The terms "ein" or "eine," as used here, are defined as "one or more." The terms "ein anderer" and "ein Weitere," as well as any other variant thereof, are to be understood as "at least one more."

[0035] The term “plural” or “several”, as used here, is to be understood in the sense of “two or more”.

[0036] The terms "configured" or "set up" (and any variations thereof) used herein to fulfill a specific function are understood, within the meaning of the invention, to mean that the corresponding device already exists in a configuration or setting in which it can perform the function, or at least that it is adjustable—i.e., configurable—so that it can perform the function after appropriate adjustment. Configuration can be achieved, for example, by adjusting parameters of a process sequence or by using switches or similar devices to activate or deactivate functionalities or settings. In particular, the device can have several predetermined configurations or operating modes, so that configuration can be carried out by selecting one of these configurations or operating modes.

[0037] The following describes various exemplary embodiments of the method, which, unless expressly excluded or technically impossible, can be combined with each other and with the other described aspects of the present solution.

[0038] In some embodiments, a number of dynamic radar points are determined for the radar point cloud. Based on the initial measurement data, the presence of a person is detected if the radar point cloud contains at least a predetermined minimum number of dynamic radar points. As explained above, dynamic radar points represent moving points. In other words, if a minimum level of movement is detected inside the vehicle, it is determined that at least one person is present. It should be noted that the second measurement procedure is then no longer necessary.

[0039] In some embodiments, the second measurement method is therefore only carried out if the radar point cloud contains fewer dynamic radar points than the specified minimum number. The absence or minimal movement inside the vehicle (2024PF00144) may initially indicate that no one is present. However, the second measurement method is then executed, which is more sensitive to even the smallest movements and can thus detect vital parameters, potentially identifying a person present, particularly a sleeping child or baby.

[0040] In some embodiments, each radar point cloud is segmented into several clusters by assigning to each of the seats a subset of the radar points of the respective radar point cloud depending on their respective position, such that the radar points of the cluster lie in a defined, in particular enclosed, spatial area, especially a cuboid, in the vicinity of the seat, whereby the presence of a person is determined individually for each of the clusters based on the first measurement data.

[0041] This enables particularly simple and computationally efficient clustering, and thus seat-specific occupancy detection, i.e., presence detection. The location (position and orientation) and shape of the spatial area are defined, or can be defined, in such a way that they significantly overlap the area typically occupied by a person in a seat within the seating arrangement. In addition to the seats themselves, it may be possible to define a separate spatial area as a cluster for other areas, such as footwells, for example, also in the form of a cuboid. This clustering thus enables seat-specific, i.e., individual, seat occupancy detection or presence detection in the case of a multi-seat seating arrangement.In some embodiments, the cluster formation can be carried out in such a way that the clusters are disjoint, so that no radar point is assigned to two different clusters.

[0042] In some related embodiments, the second measurement procedure is only performed if the cluster with the most dynamic radar points has fewer dynamic radar points than a predetermined minimum number. Instead of considering the entire radar point cloud, it can be advantageous to consider dynamic radar points for each cluster. A maximum value of dynamic radar points can be calculated across all clusters. If even this maximum value indicates fewer dynamic radar points than the predetermined minimum number, i.e., that no or very little movement was detected in that cluster, it can be assumed that no or even less movement was detected in the other clusters as well. The second measurement procedure is then used to ensure that no one is actually present in the vehicle.

[0043] In some embodiments, when the first measurement procedure is executed, the initial measurement data is stored for a predetermined duration. This stored data is then used to initiate the execution of the second measurement procedure. The predetermined duration can be specified, in particular, as the number of radar scan frames. Thus, a data history is recorded, which can be transferred to the second measurement procedure when switching from the first. This allows for faster decision-making using the second measurement procedure after the transfer. This can be described as a "dynamic soft handover" between the first measurement procedure (especially "point cloud classification") and the second measurement procedure (especially algorithms for detecting respiration and heartbeat).

[0044] In some embodiments, the first measurement method is (re)executed if the second measurement method detects movements inside the vehicle that exceed those required for determining vital parameters. In other words, if the second measurement data, which is actually designed for detecting vital parameters, registers larger movements than are typical, for example, during breathing, the method can switch back to the first measurement method, meaning the second measurement method can be terminated. The process can then essentially start again from the beginning, and the presence of a person can be determined using the first measurement method.

[0045] In some embodiments, when the presence of a person is detected during the first measurement procedure, the person is classified, with the classification allowing at least a distinction between an adult and a child. In particular, the procedure according to the first aspect is intended to provide a solution to reliably prevent children or babies (or even pets) from being accidentally left in the vehicle, which can pose a significant safety risk in warm and sunny weather. Therefore, it is determined whether an adult 2024PF00144 is present in the vehicle. If so, the procedure can be terminated without further action. However, if only a child is detected without the presence of an adult (already through the first measurement procedure), an alarm signal can be issued (see also the following explanations regarding an alarm signal).

[0046] In some embodiments, an alarm signal is triggered if the second set of measurements detects the presence of a person inside the vehicle. This person will likely be a child or infant, as no person was detected by the first measurement. It is assumed that an adult would be detected by the first measurement due to their mass and movement. If the second set of measurements also detects no person, meaning the result of the first measurement is confirmed by the second, the vehicle is considered "empty." The interior monitoring procedure can then be terminated.

[0047] In some embodiments, the method is executed as soon as the vehicle is or has been parked. "Parked" can mean, in particular, that the vehicle comes to a stop and the engine is switched off, especially that it is parked. This can also include locking the vehicle, which may encompass all doors and windows, and especially locking it. As already mentioned, the method is intended, in particular, to determine whether a child or baby has been accidentally left in a vehicle when the vehicle is parked. Preferably, this determination is made within a few seconds of the vehicle being parked, in order to be able to issue an alarm signal as quickly as possible, if necessary.

[0048] A second aspect of the present solution relates to a system for monitoring the interior of a vehicle, comprising one, in particular exactly one, radar sensor and a data processing device, wherein the system is configured to perform the method according to the first aspect. The system can, in particular, be configured to be installed in the interior of a vehicle in order to monitor the interior of the vehicle. Due to the specific design of the method according to the first aspect, a single radar sensor is sufficient, in particular also to monitor more than one row of seats, e.g., two rows of seats as described above. 2024PF00144

[0049] A third aspect of the present solution concerns a computer program or computer program product comprising instructions which, when executed on the data processing device of the system according to the second aspect, cause the system to execute the procedure according to the first aspect.

[0050] The computer program can be stored, in particular, on a non-volatile data carrier. Preferably, this is a data carrier in the form of an optical data carrier or a flash memory module. This can be advantageous if the computer program itself is to be handled independently of a processor platform on which the one or more programs are to be executed. In another implementation, the computer program can exist as a file on a data processing unit, in particular on a server, and be downloadable via a data connection, for example, the Internet or a dedicated data connection, such as a proprietary or local network. Furthermore, the computer program can comprise a plurality of interacting individual program modules. The modules can, in particular, be configured, or at least be usable, in such a way that they function in the sense of distributed computing (i.e., distributed computing)."Distributed computing" is performed on different devices (computers or processor units) that are geographically separated and connected via a data network.

[0051] The system described in the second aspect may accordingly have a program memory in which the computer program is stored. Alternatively, the system may also be configured to access an external computer program, for example on one or more servers or other data processing units, via a communication link, in particular to exchange data with it that is used during the execution of the procedure or computer program or represents outputs of the computer program.

[0052] A fourth aspect of the present solution concerns a vehicle comprising a system according to the second aspect for monitoring the interior of the vehicle.

[0053] The features and advantages described in relation to the first aspect of the present solution also apply accordingly to the other aspects of the solution. 2024PF00144

[0054] Further advantages, features and application possibilities of the present solution will become apparent from the following detailed description in conjunction with the drawings.

[0055] This shows:

[0056] Fig. 1 schematically shows an exemplary embodiment of a vehicle equipped with a system for automatically detecting the occupancy status of a seating arrangement in the vehicle;

[0057] Fig. 2 schematically shows the vehicle from Fig. 1, where seats are occupied;

[0058] Fig. 3A is an exemplary two-dimensional representation of a radar point cloud recorded by a radar sensor of the vehicle from Fig. 2;

[0059] Fig. 3B shows an exemplary representation of a clustering of the radar point cloud from Fig. 3A according to the positions of the individual seats in the seating arrangement; and

[0060] Fig. 4 is a flowchart illustrating an exemplary embodiment of a method for monitoring the interior of a vehicle.

[0061] In the figures, identical reference symbols denote identical, similar, or corresponding elements. Elements depicted in the figures are not necessarily shown to scale. Rather, the various elements depicted in the figures are represented in such a way that their function and general purpose are understandable to a person skilled in the art. Connections and couplings between functional units and elements shown in the figures can, unless expressly stated otherwise, also be implemented as indirect connections or couplings. Functional units can, in particular, be implemented as hardware, software, or a combination of hardware and software.

[0062] First, with reference to Figures 1 to 3B, the detection of seat occupancy in a vehicle using a radar system is described, i.e., presence detection. Based on radar point clouds, not only can the presence of persons be determined, but also a classification of detected passengers can be made, i.e., in particular a distinction between adults 2024PF00144 and children. Thus, the detection of a child's presence (CPD) is possible. Further details of the invention, in particular the combination of this CPD method with a BHBD method to detect the presence of a child even without movement based on breathing or heartbeat, are then explained, especially with reference to Figure 4.

[0063] The exemplary embodiment of a vehicle 100, schematically depicted in Fig. 1, has a seating arrangement 105 with five individual seats or seating positions 105a to 105e. Each of the seats 105a to 105e is suitable for accommodating one person as a passenger of the vehicle 100. The vehicle 100 further has a radar sensor 110, which is mounted on the ceiling of the vehicle cabin and configured to scan the seating arrangement 105, at least substantially, using radar beams. Accordingly, the seats 105a to 105e, in particular their seating surfaces, are located, at least predominantly, within a field of view 110a that can be scanned by the radar sensor 110. In particular, a frequency-modulated continuous wave radar system ("FMCW radar system") can be used.

[0064] Furthermore, the vehicle 100 has a system 115 for interior monitoring. The system 115 includes, in particular, a data processing unit 115a with at least one microprocessor and a signal-connected memory 115b, in which a computer program configured to carry out the method for monitoring the interior of the vehicle 100, as described below with reference to Fig. 4, is stored. Furthermore, the sensor data generated by the radar sensor 110 during radar scanning, or information already obtained from it through further processing, can be stored or will be stored in the memory 115b.

[0065] The vehicle 100 shown in Fig. 2 corresponds to the vehicle in Fig. 1, except that here the front passenger seat 105b is occupied by a person P. Furthermore, the rear right seat 105e is occupied by a baby B in a baby carrier. The subsequent discussion of Figs. 3A and 3B refers to the configuration in Fig. 2.

[0066] Reference is now made to Figures 3A and 3B, which each represent a radar point cloud, whereby for the purpose of representation the respective, in itself three-dimensional radar point cloud was reduced to two dimensions by projecting the positions of the radar points 2024PF00144 of the radar point cloud onto a plane spanned by two of its dimensions.

[0067] Figure 3A illustrates an exemplary radar point cloud 305, as it was acquired as a result of a radar scan of the seating arrangement 105 by the radar sensor 110 during a defined time interval (measurement period). The position of the individual radar points within the radar point cloud 305 can be represented by spatial coordinates; for example, Cartesian coordinates X and Y can be assigned to the plane of the drawing and to each individual point. In reality, if the dimensional reduction due to the drawing is disregarded, a third coordinate Z for the third spatial dimension is also required.

[0068] If, during radar scanning, not only the spatial positions of the points where the radar beam is reflected by the scanned objects are recorded as coordinates, but also a corresponding Doppler shift is measured, then the individual radar points can be classified according to the magnitude of this Doppler shift, in particular divided into two different classes. The latter can be done, for example, by comparing the Doppler shift with a predefined shift threshold that corresponds to a specific displacement velocity. Depending on the result of the comparison, those radar points 310 that, according to the value of their associated Doppler shift, exhibit no velocity or a surface velocity at the reflection point that is below the displacement wave, can be classified as "static" radar points (in the Fig.3A and 3B are each represented by a filled black circle). Conversely, those radar points 315 that exhibit a Doppler shift above the shift threshold can be classified as “dynamic” radar points 315 (represented by a black ring in Figs. 3A and 3B).

[0069] Figure 3B shows the same radar point cloud 305 as Figure 3A. However, in addition, selected spatial regions 325a to 325e, which are cuboid (in the 3D case) or rectangular (in the present 2D representation), are shown. These regions correspond spatially to the respective locations of the individual seats 105a to 105e. The definition of these spatial regions 325a to 325e can now be used to cluster the radar point cloud 305, whereby each radar point 310 or 315 is assigned, where possible, to the spatial region 325a to 325e in which it lies. All radar points not located in one of the spatial regions 325a to 325e can be disregarded.

[0070] It is particularly evident that the areas 320 with a particularly high radar point density are located in the area of ​​the passenger seat 105b, where person P is located according to Fig. 2. In contrast, no increased radar point density is observed in the area of ​​seat 105e, where the infant carrier with baby B is placed according to Fig. 2. Therefore, the algorithm described above is combined, as will be explained below, with an algorithm that can detect even the smallest movements, such as breathing and heartbeat, in the absence of movement, in order to reliably detect the presence of baby B, especially when the (adult) person P is no longer present in the vehicle 100.

[0071] Fig. 4 shows a flowchart illustrating an exemplary embodiment of a method 400 for monitoring the interior of the vehicle 100. The method can, in particular, be designed as a computer-implemented method. For this purpose, it can, in particular, be stored as a computer program in memory 1 15b of the system 115 and be executable on the data processing unit 1 15a.

[0072] The Procedure 400 for monitoring the interior of a vehicle combines two measurement methods (algorithms) and dynamically switches between them. Specifically, the first measurement method checks whether a child is present in the vehicle ("Child Presence Detection" - CDP). If the CDP algorithm is unable to detect and classify life in the vehicle, a second measurement method ("Breathing / Heart Beating Detection" - BHBD) is used. By detecting breathing or heartbeat, the second method may still identify life or a child, thus reliably issuing a warning or alarm.

[0073] Procedure 400 starts in step 401 after the vehicle has been switched off (100), specifically after the engine has been switched off, all doors and windows have been closed, and the vehicle has been locked. It is understood that various variables of procedure 400, which will be mentioned below, can be initialized in this step.

[0074] The first measurement procedure is now carried out. In step 410, a radar point cloud is generated by radar scanning of the vehicle's interior. For this purpose, a radar system (2024PF00144) is used, in particular an FMCW radar system with one (in particular exactly one) radar sensor. In step 411, the radar point cloud is then divided into clusters, as explained above with reference to Fig. 3B. For example, as in the example above, five clusters can be provided, one cluster for each seat in the seating arrangement 105. Furthermore, other areas of the interior can be used for cluster formation, for example, the footwell of the first row of seats and the footwell of the second row of seats, which would result in a total of seven clusters.

[0075] In the next stage of the first measurement procedure, the dynamic radar points of the radar point cloud or the individual clusters are specifically considered. The number of detected moving (dynamic) radar points per cluster is accumulated for the following frames. In step 412, the maximum number of dynamic radar points across all clusters is determined; that is, for the decision criterion described below, the cluster with the most dynamic radar points is used.

[0076] It should be noted that the steps of the first measurement procedure can be carried out for at least a specified minimum duration, which can be specified in frames. For example, it may be stipulated that the first measurement procedure is carried out for at least 16 frames of the radar scan.

[0077] After this minimum duration, the maximum number of dynamic radar points is compared to a threshold value (step 413). In other words, the number of dynamic radar points in the cluster with the most dynamic radar points is now compared to the threshold value. The threshold value can be set and may depend on various factors, such as vehicle type, radar system, etc.

[0078] If the number of dynamic radar points exceeds the threshold, this indicates a minimum level of detected movement, meaning the presence of a person inside the vehicle has been detected. The system then checks (particularly based on the classification above) whether the person is a child (step 414). If so, result 430 is displayed, indicating that a child is present in the vehicle. If not, step 415 checks whether an adult has been detected. If not, result 431 is displayed, indicating that the vehicle is empty. No alarm or warning is issued. Otherwise, result 432 2024PF00144 is displayed, indicating that an adult is present in the vehicle. In this case, an alarm is usually unnecessary and therefore not issued. If a child or an adult is detected, the system may choose to continue the measurement using the initial measurement procedure.

[0079] However, if step 413 reveals that the number of dynamic radar points (in the cluster with the most dynamic radar points) is less than the threshold, this indicates that little or no movement was detected. Therefore, the first measurement method could not detect any occupancy, i.e., the presence of a person inside the vehicle. To confirm this, the second measurement method is now performed. It begins in step 420 and utilizes a history of data from the first measurement method, specifically the minimum number of frames. This allows for a faster transition from the first to the second measurement method. This is particularly advantageous because method 400 aims to determine within a few seconds whether the vehicle is empty or if a child has been left inside.This allows for a “soft” and “dynamic” handover, since the second measurement method does not have to collect radar data over several frames, but can use this radar data from the first measurement method.

[0080] The second measurement method can use the measurement data to detect vital parameters such as respiration and heart rate. If step 421 detects life inside the vehicle, this specifically means that a child (or baby) is still inside, as an adult would most likely have already been detected in the first measurement method. Therefore, result 430 will be displayed, indicating that a child is present in the vehicle. As mentioned above, a corresponding alarm signal can be issued. Otherwise, result 431 will be displayed, indicating that the vehicle is (in fact) empty.

[0081] If a strong movement is detected during the execution of the second measurement procedure (step 422), particularly movements exceeding typical movements for breathing or heartbeat, procedure 400 can restart with the first measurement procedure. Otherwise, procedure 400 remains in the second measurement procedure. Larger movements are advantageously evaluated using the first measurement procedure, as described above, via a radar point cloud, clustering, and classification. Smallest movements, such as those occurring during breathing or heartbeat (2024PF00144), are advantageously evaluated using the second measurement procedure. Therefore, a dynamic switching between the two measurement procedures occurs.

[0082] While at least one exemplary embodiment has been described above, it should be noted that a large number of variations exist. It should also be noted that the described exemplary embodiments are merely non-limiting examples, and it is not intended to restrict the scope, applicability, or configuration of the devices and methods described herein. Rather, the preceding description will provide the person skilled in the art with guidance for implementing at least one exemplary embodiment. It is understood that various modifications to the function and arrangement of the elements described in an exemplary embodiment can be made without derogating from the subject matter defined in the appended claims and their legal equivalents.

[0083] 2024PF00144

[0084] REFERENCE MARK LIST

[0085] P Person in the front passenger seat

[0086] B Baby in baby carrier

[0087] 100 vehicles

[0088] 105 Seating arrangement

[0089] 105a-e seats or seating places

[0090] 110 radar sensor

[0091] 110a Observation field of the radar sensor 110

[0092] 115 System for monitoring the vehicle's interior 100

[0093] 115a Data processing unit

[0094] 115b memory

[0095] 305 radar point cloud

[0096] 310 static radar points

[0097] 315 dynamic radar points

[0098] 320 areas of radar point cloud 305 with high radar point density

[0099] 325a-e Spatial areas for cluster definition

[0100] 400 methods for monitoring the interior of a vehicle

[0101] 401-432 Processes / Procedural steps / Results within the framework of procedure 400

Claims

2024PF00144 REQUIREMENTS 1. Method (400) for monitoring the interior of a vehicle (100), the method comprising: Performing a first measurement procedure, wherein the first measurement procedure comprises: Acquisition of initial measurement data using a radar system, wherein the initial measurement data represent a radar point cloud (305) obtained on the basis of a radar scan of a spatial area that at least partially covers the interior of the vehicle (100); Determining the presence of a person inside the vehicle (100) based on the first measurement data; if the first measurement procedure determines that no person is present inside the vehicle (100), performing a second measurement procedure, the second measurement procedure comprising: Acquisition of secondary measurement data using the radar system, wherein vital parameters of persons inside the vehicle can be determined using the secondary measurement method in order to establish the presence of a person; and Determining the presence of a person inside the vehicle (100) based on the second measurement data.

2. Method according to claim 1, wherein a number of dynamic radar points (315) are determined for the radar point cloud (305), wherein the presence of a person is determined on the basis of the first measurement data if the radar point cloud (305) has at least a predetermined minimum number of dynamic radar points (315).

3. Method according to claim 2, wherein the second measurement method is only carried out if the radar point cloud (305) has fewer dynamic radar points (315) than the specified minimum number.

4. A method according to any of the preceding claims, wherein the interior of the vehicle (100) has a seating arrangement with a plurality of seats (105a-e), wherein the radar point cloud (305) is segmented into several clusters by assigning to each of the seats (105a-e) as a cluster a subset of the radar points (310, 315) of the respective radar point cloud (305) depending on 2024PF00144 is assigned from their respective positions such that the radar points (310, 315) of the cluster are located in a defined spatial area in the vicinity of the seat (105a-e), whereby the presence of a person is determined individually for each of the clusters based on the first measurement data.

5. Method according to claim 4, wherein the second measurement method is only carried out if the cluster with the most dynamic radar points has fewer dynamic radar points than a predetermined minimum number.

6. Method according to one of the preceding claims, wherein, during the execution of the first measurement method, the first measurement data are stored for a predetermined duration, wherein the first measurement data stored for the predetermined duration are used to initiate the execution of the second measurement method.

7. A method according to any of the preceding claims, wherein the method further comprises: Performing the first measurement procedure if movements inside the vehicle (100) are detected by means of the second measurement procedure that go beyond movements for determining vital parameters.

8. Method according to one of the preceding claims, wherein, in the first measurement method, when the presence of a person is detected, a classification of the person is carried out, wherein, based on the classification, at least a distinction is made between an adult and a child.

9. A method according to any of the preceding claims, further comprising: Issuing an alarm signal if the presence of a person inside the vehicle (100) is detected based on the second measurement data.

10. Method according to any of the preceding claims, wherein the method is carried out as soon as the vehicle (100) has been parked. 2024PF00144 11. System for monitoring the interior of a vehicle (100), comprising a radar sensor (110) and a data processing device (115a), wherein the system is configured to perform the method (400) according to any one of the preceding claims.

12. System according to claim 11, wherein the system comprises a frequency-modulated It includes a continuous wave radar system.

13. Computer program or computer program product comprising instructions which, when executed on the data processing device of the system according to claim 11 or 12, cause the system to execute the method according to any one of claims 1 to 10.

14. Vehicle (100) comprising a system according to claim 11 or 12 for monitoring the interior of the vehicle.

Images