DE102023116164B4 - METHOD FOR CREATING AN EVALUATION MODEL FOR DETECTING THE SEAT OCCUPANCY STATE OF A SEATING ARRANGEMENT - Google Patents

Abstract

Method for creating an evaluation model for automated detection of the occupancy status of a seating arrangement (105) with at least one seat (105a-e), wherein the method comprises:
- Providing a data set for a seat occupancy state, wherein the data set represents measurement data for at least two consecutive time points, wherein the measurement data each represent an associated radar point cloud (305), wherein the radar point cloud (305) was or is obtained on the basis of a radar scan of a spatial area surrounding the seating arrangement (105) at least sectionally, wherein providing the data set comprises the following:
- Generating feature vectors from the measurement data for each of the time points, where each feature vector represents a predetermined number of features of the radar point cloud for a given time point; and
- Combining the feature vectors into a total tensor to obtain the data set that represents the features of the radar point cloud at each of the time points;
- Providing hyperparameters for the evaluation model, where the hyperparameters are configured to be set based on a metric;
- Setting the hyperparameters, whereby a metric is provided and optimized for the dataset using an optimization procedure; and
- Creating the evaluation model with the set hyperparameters for training with training data for a method for automatically detecting a seat occupancy state of a seating arrangement (105) with at least one seat (105a-e), wherein the data set forms input data for the evaluation model and an output of the evaluation model is an evaluation result which is assigned to the seat occupancy state of the seating arrangement (105).

Description

The present invention relates to a method, a computer program, and a system configured for executing the method, each for automatically detecting the occupancy status of a seating arrangement with at least one seat using a trained evaluation model. In particular, the invention also relates to a method for creating and a method for training such an evaluation model, especially a machine learning model.

In various situations, 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 particularly in vehicles, for example, in 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.

For the automated detection of the current occupancy status of one or more seats, particularly an arrangement of vehicle seats in a vehicle, so-called seat occupancy mats are known. These mats are integrated into the seats (usually one per seat) and use pressure-sensitive sensors to detect whether the respective seat is occupied. The occupancy status of the seat is determined based on the sensor signals or data from these sensors, generally by means of a threshold test.

These existing solutions therefore require seats to be equipped with integrated sensors and are usually unable to distinguish between different seat occupancy states beyond "occupied" and "unoccupied". Furthermore, the sensors typically have to be integrated into the seats at the factory, making retrofitting difficult or impossible, and thus eliminating the possibility of detecting the occupancy status of seats not equipped in this way.

Therefore, methods are also known that use radar technology to automatically detect the current occupancy status of a vehicle's seats. Radar sensors scan the vehicle interior, generating measurement data in the form of radar point clouds. Based on these radar point clouds, the current occupancy can be determined. A suitable evaluation model, which can be a machine learning model, can be used for this purpose. This model can be trained with relevant data before its actual use.

Known methods, using machine learning models, can also detect the type of seat occupancy, for example, whether a seat is occupied by an adult or a child. Methods are also known that can perform a more differentiated evaluation of seat occupancy, particularly regarding the height and weight of an adult or the age of a child. However, errors can occur in detecting seat occupancy, especially if a person moves around a lot. In such cases, the presence of another person might not be correctly detected.

It is an object of the present invention to provide an improved solution for the automated detection of the occupancy status of a seating arrangement with at least one seat. In particular, an improved solution for creating and training an evaluation model for the automated detection of the occupancy status of a seating arrangement is to be provided.

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.

A first aspect of the solution presented here concerns a method, particularly a computer-implemented one, for creating an evaluation model for the automated detection of the occupancy status of a seating arrangement with at least one seat. The method provides a dataset for a seat occupancy status, where the dataset represents measurement data for at least two consecutive time points. Each measurement dataset represents an associated radar point cloud, which was or is obtained based on a radar scan of a spatial area that at least partially surrounds the seating arrangement. Providing the dataset includes generating feature vectors from the measurement data for each of the time points, where each feature vector represents a predefined number of features from the radar point cloud for that time point, and combining the feature vectors into a complete set. A vector, a total matrix, or a total tensor is used to obtain the dataset representing the features of the radar point cloud at each time point. The process also provides hyperparameters for the evaluation model, configured to be set based on a metric. These hyperparameters are set using a metric and optimized for the dataset. Finally, the evaluation model, with the configured hyperparameters, is created for training with training data for a method to automatically detect the occupancy status of a seating arrangement with at least one seat. The dataset serves as input data for the evaluation model, and the output of the evaluation model is an evaluation result corresponding to the occupancy status of the seating arrangement.

Using the method described in the first aspect, an evaluation model, in particular a machine learning model (ML model), can be created that achieves higher detection accuracy for various seat occupancy states. For example, by using a dataset containing measurement data at multiple time points, false classifications caused by strong movement of a person, such as the driver, can be avoided. Such strong movement can cause a person who moves little or not at all and therefore generates fewer points in the radar point cloud to "disappear." If multiple time points, instead of just one, are considered in the evaluation model, such effects can be avoided or at least reduced. This method is particularly advantageous for the machine learning of a radar-based system for seat occupancy detection. Specifically, the detection of seat occupancy states can be stabilized by considering the temporal evolution of the measurement data.

During the creation of the machine learning model, hyperparameters of the model are set using optimization methods. A metric for the recognition accuracy of an evaluation result for known parameters can be used, which is based on the difference between the correct result (e.g., the actual seat occupancy status) and a result of the evaluation model.

The process also utilizes features (parameters) from the radar point cloud for evaluation and provides them in the form of a feature vector. The evaluation model is thus defined such that, when determining the occupancy status of the seating arrangement, an evaluation result is determined based on the respective values of the features for the radar point clouds. In this way, the evaluation model can be defined and applied in a simplified manner, since only the values of the features need to be considered as input variables instead of entire radar point clouds. In particular, the temporal progression of the values can reflect a movement or a specific movement pattern of one or more objects on the seating arrangement, enabling the evaluation model to determine the occupancy status of the seating arrangement with exceptional reliability.

The term "seat occupancy status" of a seating arrangement with at least one seat, as used herein, 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 spatial extent.

The term "radar point cloud," as used herein, refers in particular to a set of points in a vector space obtained by radar scanning of at least one object's surface, which exhibits a typically unorganized spatial structure ("cloud"). In the case of a radar point cloud, the points of the radar point cloud can be referred to as "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, for each radar point, indicate 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 a signal-to-noise ratio (SNR), can be recorded for the radar points.

The term "evaluation model", as used herein, refers to a model, particularly a mathematical one, that uses a radar point cloud or one or more characteristics or parameters characterizing it as input(s) in order to deliver an evaluation result depending on this, in this case one of several previously defined possible seat occupancy states of the seating arrangement. The evaluation model can, in particular, be a mathematical estimator, wherein the radar point cloud represents empirical data as a sample and the evaluation result represents an estimated value determined depending on this. The evaluation model can, in particular, be a "machine learning model" (or equivalently, a "machine learning model" (ML model)), which in this context refers specifically to a mathematical, in particular statistical, model for making predictions or decisions, created by means of at least one machine learning algorithm based on example data referred to as training data, without the algorithm(s) being explicitly programmed to make such predictions or decisions. In particular, decision tree-based machine learning models or artificial neural networks are machine learning models. When considering measurement data at multiple time points in the context of the present invention, recurrent neural networks (RNNs) can therefore be used, in particular.

The term "metric," as used herein, refers in particular to a mathematical mapping that assigns a numerical value to one or more detections based on data for which the desired values are known. This metric is intended to evaluate the quality of the predictions. The metric is used especially for hyperparameter optimization by feeding its value into an optimization procedure in order to adjust the hyperparameters accordingly. Specifically, weights in the evaluation model can be adjusted to achieve a particular behavior of the evaluation model.

The term "parameter," as used herein, refers in particular to a value relating to the seat occupancy status, as it may also occur in the actual operation of the evaluation model during a procedure for detecting seat occupancy. The parameters may, in particular, indicate whether a seat is occupied or not, how a seat is occupied (e.g., adult or child), and, where applicable, other circumstances such as the vehicle's status (e.g., whether it is moving or stationary).

The term "hyperparameter," as used herein, refers specifically—in contrast to the parameters explained previously—to a parameter of the evaluation model that is determined during the model's creation in order to control the model during training. The hyperparameters are thus determined and defined before the actual model training.

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.

Furthermore, unless explicitly 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).

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."

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

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 that it is at least 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.

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

In some embodiments, the seating arrangement has multiple seats, for which a seat occupancy status must be determined individually or cumulatively within the framework of the method. For each (individual) radar point cloud, the set of its radar points is subdivided into several clusters, each containing a subset of the radar points, by means of cluster formation, depending on the respective spatial location of the radar points relative to the seats. This allows each seat to be individually assigned to the cluster closest to it. The feature vectors are generated individually for each cluster and for each time point in time, and all feature vectors are combined to form the overall tensor, thereby obtaining the data set. The overall tensor thus consists of a series of composite feature vectors, each of which is assigned to a seat at a specific time point in time. The overall tensor can also be represented in matrix form, where the columns of the matrix can, for example, each contain data at a specific time point in time. Cluster formation facilitates and improves the determination of a seat occupancy status for each seat individually. Furthermore, the entire vehicle interior can be efficiently monitored in this way.

In some related embodiments, each radar point cloud is segmented into multiple clusters by assigning each seat a subset of the radar points from the respective radar point cloud as a cluster, depending on their respective positions, such that the radar points of the cluster lie within a defined, enclosed spatial area, in particular a cuboid, in the vicinity of the seat. This enables particularly simple and computationally efficient cluster formation and thus seat-specific occupancy detection, whereby the location (position and orientation) and shape of the spatial area is or can be defined such that it significantly overlaps the spatial area typically occupied by a detectable object, in particular a person, on a seat in the seating arrangement. In addition to the seats in the seating arrangement, it may optionally be possible to define a delimited spatial area as a cluster for other spatial areas, such as footwells, for example, also in the form of a cuboid.

Cluster formation thus enables seat-specific, i.e., individual, seat occupancy detection in the case of a multi-seat seating arrangement. This is particularly advantageous or even necessary when a seat-specific response to the detected occupancy is required, for example, by activating, deactivating, or otherwise controlling a specific functionality or system for a particular seat, such as a seat-specific airbag system, a seat-specific seatbelt reminder, or a seat-specific seat heater, depending on its detected occupancy. In some embodiments, cluster formation can be implemented in such a way that the clusters are disjoint, so that no radar point is assigned to two different clusters.

In some embodiments, at least one of the features is determined by the number of radar points in the radar point cloud (or cluster) or a quantity dependent on it. If, during radar scanning, the number of radar points in the generated radar point cloud depends on the extent of movement of the scanned object, the extent of movement can be represented in the feature, particularly with regard to the aforementioned detection of the object's breathing rate. In addition to the number of radar points, other features of the point cloud (or cluster) can also be used as features, such as the position of the center of gravity of the point cloud (or cluster), the density of the points (of a cluster), and/or an average Doppler value. These values are then summarized in the feature vector (for each time point and, if applicable, for each cluster).

In some embodiments, the evaluation model has the structure of a recurrent neural network (RNN). By using a recurrent (or feedback) neural network (RNN), a temporal evolution of the measurement data can be taken into account, particularly in comparison to a CNN, decision trees, or other networks without a time component. This temporal evolution is reflected, as described above, in the dataset provided to the evaluation model as input data.

The RNN could, for example, be a Long Short-Term Memory (LSTM) model, which is a subtype of RNN. An LSTM can be used to recognize patterns in data sequences, such as those found in the sensor data representing the radar point cloud. Alternatively, a Gated Recurrent Unit (GRU) can be used. This is a gating mechanism in recurrent neural networks.

In some embodiments, the optimization method is a Bayesian optimization. In particular, a value of the metric can be optimized using Bayesian optimization.

In some implementations, the optimization procedure is performed with a predetermined number of iterations. While Bayesian optimization, for example, theoretically allows any number of iterations, it can be advantageous to limit the number of iterations and, after this number, adjust the hyperparameters to represent the most promising hyperparameters for the evaluation model. Further iterations can then follow.

In some embodiments, the individual radar points of the radar point cloud are each represented by a position of the respective radar point in three-dimensional space and by at least one of the following parameters: (i) a Doppler shift value of the radar signal relative to the respective radar point; (iii) a signal-to-noise ratio value of the radar signal relative to the respective radar point. These parameters can be used, in particular, for pre-filtering the radar point cloud as part of a pre-processing step preceding feature determination.

As will be explained below, the developed evaluation model, which is primarily a machine learning model, is trained before its actual use for seat occupancy detection (see below, procedure according to the third aspect). Data sets representing at least a radar point cloud or values of one or more specific features at various times are provided as input data to the machine learning model. The output of this input is an evaluation result indicating the seat occupancy status. This allows for a particularly flexible and adaptable implementation of the evaluation model, whereby machine learning can be used to continuously improve the evaluation model and thus the quality and reliability of the seat occupancy detection. The evaluation result can, in particular, specify a class of seat occupancy status classification. The machine learning model can, in particular, be based on an artificial neural network.

A second aspect of the solution presented here concerns a method, particularly a computer-implemented one, for training an evaluation model created according to a method based on a first aspect, for the automated detection of the occupancy status of a seating arrangement with at least one seat. In this method, a data set for a seat occupancy status is acquired, where the data set represents measurement data for at least two consecutive time points. This measurement data represents an associated radar point cloud, which was or is obtained based on a radar scan of a spatial area that at least partially surrounds the seating arrangement and is assigned to one of several predefined possible occupancy states of the seating arrangement. Training data is then generated from the data set, and this training data is provided as input data to the evaluation model. The model's output is an evaluation result that corresponds to the occupancy status of the seating arrangement.

As already explained in connection with the method according to the first aspect, clustering also occurs in some embodiments of the method according to the second aspect, particularly when the seating arrangement has a plurality of seats, wherein the seat occupancy state is an individual or cumulative occupancy state of the seats. For the radar point cloud or each individual radar point cloud (i.e., at any given time), the set of its radar points is subdivided into several clusters, each containing a subset of the points, by means of clustering, depending on the respective spatial position of the points with respect to the seats, in order to individually assign each seat to the cluster closest to it. In particular, the radar point cloud, or each individual radar point cloud (i.e., at any given time), is segmented into multiple clusters by assigning each seat a subset of radar points as a cluster, depending on their respective positions. This assignment is unique for each radar point, ensuring that the radar points of the cluster lie within a defined, closed, and especially cuboid, spatial region in the vicinity of the seat. The assignment can be made, in particular, by assigning each radar point to the cluster of its nearest seat. In this way, the radar point cloud can be divided into clusters, i.e., subsets of the radar point cloud located in the vicinity of the respective seats. This allows for the targeted and therefore highly reliable determination of seat-specific occupancy states based on the cluster assigned to the respective seat.

A third aspect of the solution presented here concerns a method, particularly computer-implemented, for the automated detection of the occupancy status of a seating arrangement with at least one seat (or equivalently: seat), especially a seat in or for a vehicle, such as an automobile (e.g., truck, car, or bus). Driving comprises: (i) acquiring, in particular receiving or generating, a data set for a seat occupancy state, wherein the data set represents measurement data for at least two consecutive time points, the measurement data representing an associated radar point cloud. Each radar point cloud is or was obtained based on a radar scan of a spatial area that at least partially surrounds the seating arrangement; (ii) determining, in particular estimating, a seat occupancy state of the seating arrangement using an evaluation model that, depending on the radar point cloud, provides one of several predefined possible seat occupancy states of the seating arrangement as an evaluation result; and (iii) outputting information defined as a function of the evaluation result. The method according to the second aspect uses an evaluation model, in particular a machine learning model, which was trained using the method according to the first aspect.

Using the method described in the third aspect, a radar point cloud obtained by radar scanning of the area surrounding the seating arrangement allows for an evaluation result (particularly in the sense of a prediction or classification) that characterizes the occupancy status of the seating arrangement. This enables the implementation of radar-based solutions, especially in a vehicle context (particularly for automobiles), that can reliably detect a seat occupancy status (particularly exclusively) using radar and, based on this, activate, deactivate, or control/regulate certain functionalities or systems, such as a seatbelt warning system or an airbag system, either entirely or selectively. By considering measurement data from at least two consecutive time points, the quality of the evaluation result in the actual detection of a seat occupancy status can be improved.

The information to be output can, in particular, represent the evaluation result itself. It can also be a detectable signal, especially one perceptible to a human sense, such as a warning, a control signal for activating a signal source, or a data signal carrying the information.

The following describes various exemplary embodiments of the method according to the third aspect, which, unless expressly excluded or technically impossible, can be combined with each other and with the other described aspects of the present solution. Embodiments of the method according to the first and/or second aspect may also be applicable to the method according to the third aspect, and vice versa. In other words, features of the method used in creating the evaluation model can equally be used in training the evaluation model and/or in detecting a seat occupancy state, and vice versa.

In some embodiments, outputting the information includes controlling a signal source based on the information, causing the signal source to output a defined signal depending on the control. The signal source can be, in particular, an audio source, an optical signal source, especially a display device for images or text, and/or a haptic actuator, or a combination of at least two of the aforementioned signal sources. Thus, the detected seat occupancy status can be communicated to a user based on the signaling or used to control another technical system, such as an airbag system.

In some of these embodiments, the signal source is controlled depending on the information in such a way that it outputs a signal, defined in particular by the control, when the information results from an evaluation result according to which at least one seat of the seating arrangement is occupied and/or a selected predetermined seat occupancy state exists.

In some embodiments, the method further comprises: (i) detecting a seatbelt fastening state of at least one seat in the seating arrangement or receiving seatbelt information indicating this fastening state; (ii) wherein the signal source is controlled depending on the seatbelt information and the information from the evaluation result such that it outputs a seatbelt fastening warning signal when, according to the information, at least one seat in the seating arrangement is occupied and/or a selected predetermined seat occupancy state exists and seatbelt information indicates that the corresponding seatbelt of the seat is not fastened. In this way, a seatbelt fastening check and warning system based exclusively on radar, particularly with regard to detection, can be achieved.

In some embodiments, the seating arrangement has multiple seats, for which a seat occupancy state must be determined individually or cumulatively within the framework of the method. For each (individual) radar point cloud, the set of its radar points is divided into several subsets of radar points by means of clustering, depending on the respective spatial position of the radar points in relation to the seats. The seating arrangement is divided into clusters to individually assign each seat to the cluster closest to it. The occupancy status of each seat is determined based on the radar point cloud assigned to its respective cluster, in order to obtain an evaluation result, specifically a classification result, that characterizes the occupancy status of that seat. The information to be output is then defined based on the individual evaluation results for each seat. For further explanations regarding cluster formation, please refer to the above descriptions of the procedure according to the first or second aspect.

In some embodiments, the series of values for at least one of the features is analyzed to determine whether a periodic pattern, particularly one corresponding to a periodic breathing pattern, is detected. The evaluation result is then determined based on the outcome of the analysis. This allows not only the detection of any object on a seat in the seating arrangement, but also a highly reliable differentiation between living objects present on the seating arrangement, especially people and mammals such as pets (e.g., dogs). In particular, it is possible to define the information to be output according to the method as a function of whether or not such a periodic pattern is detected. In this context, one or more detected frequencies of the periodic pattern can also be taken into account, specifically such that the information is defined based on whether the frequency(ies) lies within a specific frequency range, such as a typical breathing rate range. In particular, a seatbelt warning function or an airbag system can be controlled depending on whether a breathing rate has been detected, and thus with a high probability a person has been detected on the seating arrangement or a specific seat.

In some embodiments, the individual radar points of the radar point cloud are each represented by a position of the respective radar point in three-dimensional space and by at least one of the following parameters: (i) a Doppler shift value of the radar signal relative to the respective radar point; (iii) a signal-to-noise ratio value of the radar signal relative to the respective radar point. These parameters can be used, in particular, for pre-filtering the radar point cloud as part of a pre-processing step preceding feature determination.

In some of these embodiments, the determination of the occupancy status of the seating arrangement can be based exclusively, or at least predominantly, on radar points whose Doppler shift value is at or above a predetermined, non-zero shift threshold. Thus, only, or at least predominantly, so-called dynamic radar points are used as the basis for the evaluation; these are radar points that indicate movement of the scanned object and whose Doppler shift value is at or above the shift threshold. The Doppler shift value can be positive or negative, but only the magnitude is relevant in this step. This can be used, in particular, to further improve the quality, especially the reliability, of the method because static points on the object surfaces, such as points on the seat surface, are not included in the evaluation, or are included only in smaller numbers, than points that exhibit dynamic movement and are therefore highly likely to be associated with a living being, especially a person or an animal. This allows the use of the information obtained and output through the evaluation (e.g., for airbag control or a seatbelt warning system) to depend in particular on whether a living being or a static object surface was detected.

In some embodiments, the seat occupancy state includes at least one type of seat occupancy for at least one seat in the seating arrangement. In particular, determining the seat occupancy state can include determining a type of seat occupancy. The type of seat occupancy can include at least one unoccupied (i.e., free) seat, a seat occupied by an adult, a seat occupied by a child, a seat occupied by a child seat with a toddler, and a seat occupied by an infant carrier with a baby. Additionally, it can be provided to detect whether a seat is occupied, for example, by an object or a doll. A person can be simulated, for example, using the established THUMS human model. Here, the values AM95, AM50, and AF05, for example, represent different adult persons (tall/heavy man, medium/medium-weight man, and small/light woman, respectively). Children can be identified by their age, e.g., 4YO or 6YO for a four-year-old or six-year-old child, respectively.

By determining not only whether a seat is occupied, but also how, and outputting the corresponding information, more differentiated control of, for example, a seatbelt warning system is possible. This applies to the safety systems or airbag systems. For example, certain airbags can only be activated when an adult occupies a seat, while an airbag can (or must) be deactivated if a seat is occupied, but not by an adult, but rather by, for example, a rear-facing infant car seat. Furthermore, when using a child car seat or infant carrier, which are typically not secured with a seat belt but rather with a special attachment system (e.g., "Isofix"), it is advantageous if a seat belt warning is not issued, thus avoiding unnecessary warning messages that are unhelpful and may be perceived as annoying by the user.

A fourth aspect of the present solution concerns a system, in particular a data processing device, for the automated detection of the occupancy status of a seating arrangement with at least one seat, in particular with at least one vehicle seat in or for a vehicle. The system includes a data processing device that is configured, in particular by means of a corresponding computer program, to execute the procedure according to the third aspect for detecting the occupancy status.

A fifth aspect of the present solution relates to a computer program or computer program product comprising instructions which, when executed on the data processing device of the system according to the fourth aspect, cause the system to execute the procedure according to the third aspect.

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 be configured, in particular, or at least be usable, to be executed on different devices (computers or processor units) that are geographically separated and interconnected via a data network, in accordance with the principles of distributed computing.

The system according to the fourth aspect can accordingly have a program memory in which the computer program is stored. Alternatively, the system can 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.

A sixth aspect of the present solution relates to a vehicle comprising: (i) a seating arrangement with at least one seat; (ii) a radar sensor for at least section-by-section radar scanning of the seating arrangement; and (iii) a system according to the fourth aspect for automatically detecting a, in particular, respective, seat occupancy state of the seating arrangement as a function of at least section-by-section radar scanning of the seating arrangement performed by the radar sensor, in particular according to a method according to the third aspect.

The features and advantages explained in relation to the first, second and third aspects of the present solution also apply accordingly to the other aspects of the solution.

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

• 1 schematisch eine beispielhafte Ausführungsform eines Fahrzeugs, das mit einem System zum automatisierten Erkennen eines Sitzbelegungszustands einer Sitzanordnung im Fahrzeug ausgerüstet ist;
• 2 schematisch das Fahrzeug aus 1, wobei hier der Beifahrersitz belegt ist;
• 3A eine beispielhafte zweidimensionale Darstellung einer durch einen Radarsensor des Fahrzeugs aus 2 aufgenommenen Radarpunktwolke;
• 3B eine beispielhafte Darstellung einer Clusterung der Radarpunktwolke aus 3A gemäß den Positionen der einzelnen Sitzplätze der Sitzanordnung;
• 4 ein Flussdiagramm zur Veranschaulichung einer beispielhaften Ausführungsform eines Verfahrens zum automatisierten Erkennen eines Sitzbelegungszustands einer Sitzanordnung;
• 5A ein Flussdiagramm zur Veranschaulichung einer beispielhaften Ausführungsform eines Prozesses zum Erstellen eines Datensatzes; und
• 5B ein Flussdiagramm zur Veranschaulichung einer beispielhaften Ausführungsform eines Verfahrens zum Erstellen eines Auswertungsmodells für das automatisierte Erkennen eines Sitzbelegungszustands einer Sitzanordnung.

This shows:

• 1 schematically an exemplary embodiment of a vehicle equipped with a system for the automated detection of the occupancy status of a seating arrangement in the vehicle;
• 2 schematically the vehicle 1 , where the passenger seat is occupied;
• 3A an exemplary two-dimensional representation of a radar sensor of the vehicle 2 recorded radar point cloud;
• 3B an exemplary representation of a clustering of the radar point cloud from 3A according to the positions of the individual seats in the seating arrangement;
• 4 a flowchart to illustrate an exemplary embodiment a method for the automated detection of the seat occupancy status of a seating arrangement;
• 5A a flowchart to illustrate an exemplary embodiment of a process for creating a data set; and
• 5B a flowchart to illustrate an exemplary embodiment of a method for creating an evaluation model for the automated detection of a seat occupancy status of a seating arrangement.

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.

First, with reference to 1 to 4 The detection of seat occupancy in a vehicle using a radar system is described, as the method according to the present invention is advantageously applicable in this context. The present invention is then described in particular with reference to 5A and 5B explained.

The in 1 A schematically depicted exemplary embodiment of a vehicle 100 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 inside 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. Furthermore, the vehicle 100 has a system 115 for the automated detection of a seat occupancy state of the seat arrangement 105 depending on a radar scan of the seat arrangement 105 carried out by the radar sensor 110, at least sectionally with respect to the observation field 110a.

System 115 includes, in particular, a data processing unit 115a with at least one microprocessor and a signal-connected memory 115b, in which a memory for carrying out the process described below with reference to 4 The computer program configured for the described procedure for the automated detection of the seat occupancy status of the seat arrangement 105 is stored. Furthermore, the sensor data generated by the radar sensor 110 during radar scanning, or information already obtained from it through further processing, may be stored or will be stored in memory 115b.

The 2 The vehicle shown, number 100, corresponds to the vehicle from 1 , however, in this case the passenger seat 105b is occupied by person P. In the further discussion of the 3A and 3B will be based on the constellation of 2 Reference made to.

The following section will discuss the 3A and 3B Reference is made to each of which represents a radar point cloud, whereby, for the purpose of representation, the respective, inherently three-dimensional radar point cloud was reduced to two dimensions by projecting the positions of the radar points of the radar point cloud onto a plane spanned by two of its dimensions.

In 3A Figure 305 illustrates an exemplary radar point cloud as it was acquired by radar sensor 110 during a radar scan of seating arrangement 105 over a defined time interval (measurement period). The position of the individual radar points within 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.

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 achieved, for example, by applying a predefined shift threshold to the Doppler shift, which corresponds to a specific shift value. The speed corresponds to the speed and can be compared. Depending on the result of the comparison, those radar points 310 that, according to the value of their associated Doppler shift, have no speed or a speed of the object surface at the reflection point that is below the shift wave, can be classified as "static" radar points (in the 3A and 3B 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 (in the 3A and 3B (each represented by a black ring).

Classifying radar points 310 and 315 according to their Doppler shift is not strictly necessary; however, it can be used to process radar point cloud 305, particularly as part of preprocessing prior to evaluation, and especially to filter based on the classification. For example, such filtering could be performed to consider only dynamic radar points 315 for evaluation, in order to detect only moving objects.

In 3B is the same radar point cloud 305 as in 3A The diagram shows that, in addition, selected cuboid (3D case) or rectangular (in the present 2D representation) spatial areas 325a to 325e are shown, spatially assigned to the respective location of the individual seats 105a to 105e. The definition of these spatial areas 325a to 325e can now be used to cluster the radar point cloud 305, whereby each radar point 310 or 315 is assigned, as far as possible, to the spatial area 325a to 325e in which it lies. All radar points not located in one of the spatial areas 325a to 325e can be disregarded in the further analysis. It can be seen in particular that the areas 320 with a particularly high radar point density are located in the area of the front passenger seat 105b, on which, according to the diagram, the radar point cloud 305 is located. 2 where person P is located.

4 Figure 400 shows a flowchart illustrating an exemplary embodiment of a method for automatically detecting the occupancy status of a seating arrangement. 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 115b of system 115 and be executable on the data processing unit 115a.

In method 400, a radar point cloud 305 is acquired by receiving radar measurement data in a step 410, in the present example from the radar sensor 110 of the vehicle 100, and processing it to form one or more radar point clouds.

The radar point cloud 305 now available can then be clustered in a further process 420 by checking for each of its radar points whether it lies within one of the defined spatial areas 325a to 325e (see 3B) The location and, if applicable, the specific location are determined. Thus, each point can be assigned to either one of the spatial areas 325a to 325e or to the other observation field. All radar points located within the same spatial area 325a to 325e are grouped into a respective cluster. As a result, each of the seats 105a to 105e is assigned a corresponding cluster of radar point cloud 305. This forms the basis for subsequently conducting an individual evaluation for each seat 105a to 105e to determine whether the respective seat 105a to 105e was occupied or unoccupied while radar point cloud 305 was being generated.

For the subsequent analysis of the clustered radar point cloud 305, 430 features are determined for each cluster in a single process. These features can include, in particular, the number of radar points in the cluster. If no filtering according to Doppler shift value has taken place, this can be a combined count of both the static and dynamic radar points 310 and 315, respectively. However, if the static radar points 310 were filtered out beforehand, it is only a count of the dynamic radar points 315. Further features can include the position of a cluster's centroid, the point density in a cluster, or the mean Doppler values of a cluster. These features are each summarized in a feature vector for each cluster, as will be explained in more detail below.

The features for the cluster corresponding to seat 105b can now be evaluated (the same can be done analogously for the respective clusters for the other seats). For this purpose, in process 440, the feature vector (or a temporal progression of the features in a total vector or total tensor, su) is provided as input to an evaluation model. This can be, in particular, a machine learning-based model, such as an artificial neural network. Since the temporal progression is also taken into account in the present example, a recurrent neural network (RNN) is particularly suitable (see description below). 5A and 5B) .

The training and, if applicable, validation data used for the preceding training can be structured in such a way that each dataset contains a corresponding, correct class within a classification of possible seat occupancy states. This allows the model to be trained and validated using supervised learning. In the simplest case, seat occupancy states indicate whether the seat is occupied or not. However, more sophisticated classifications are also conceivable, where, in the case of an object's presence, the respective class additionally specifies the type of object, for example, whether it is moving or stationary, and, in the case of a moving object, specifically whether it is a person (generally recognizable based on a breathing pattern over the course of the features).

If, in process 440, a seat occupancy status for the seating arrangement 105 has been determined using the evaluation model, in particular for one or more of its seats 105a to 105e individually, this result can be output as corresponding information in process 445, for example at a user interface of the vehicle or in the form of data for further processing by one or more other systems, in particular systems of the vehicle.

In the present example, this information is to be used in particular to check whether, depending on the occupancy status of a respective seat 105a to 105e and the result of a check as to whether a corresponding seat belt has been fitted for this seat or not, a seat belt warning signal should be issued or not.

In process 450, it can be checked whether the seat belt is fastened for the relevant seat (here, for example, seat 105b). In step 455, a function of the vehicle 100 can be controlled depending on the seat occupancy information output in process 445 and the seat belt status determined in process 450. Specifically, this can be done by activating a signal source in process 455 to output a seat belt status signal, particularly visual and/or audible, to indicate to one or more other vehicle occupants that a seat is occupied but the seat belt is not fastened. The process then branches back to step 410 to start another loop iteration.

The evaluation model is created before the actual application in Procedure 400 and before training. In particular, the hyperparameters are optimized accordingly, as explained below. 5A First, a flowchart illustrating an exemplary embodiment of a process 510 for providing a data set is shown. A flowchart illustrating an exemplary embodiment of a method 500 for creating the evaluation model is then shown in 5B shown.

In step 501, a radar point cloud is first acquired and, as mentioned above, subjected to preprocessing. Each of the radar points in the radar point cloud can be characterized, in particular, by the position of the respective radar point in three-dimensional space (3D coordinates), as well as by the Doppler shift value of the radar signal to the respective radar point and the signal-to-noise ratio value of the radar signal to the respective radar point.

Datasets can be provided for various seat occupancy states, such as those with people, objects, and empty seats. For each seat, a decision must be made as to whether a seatbelt reminder (i.e., a seatbelt warning signal) should be issued, as explained above. This decision is based on the presence of a person and their size (for children, age is used, as it correlates strongly with size). Different types of passengers (or seat occupancy states) can be considered, such as medium-sized adult males (e.g., AM50), large adult males (e.g., AM95), small adult females (e.g., AF05), or children of different ages. The hyperparameter optimization described below can account for this by selecting a suitable metric, which is then optimized using an optimization method (here, Bayesian optimization).

In step 502, the radar points are then grouped according to their location in the vehicle; that is, clusters are formed as explained above. For example, a cuboid box is defined for each seat, and all radar points that lie within the box of a seat are grouped into a cluster corresponding to that seat.

For each cluster, a fixed set of features is calculated in step 503, and a feature vector is created containing a corresponding numerical value for each feature. The calculated features describe various properties of the cluster, such as the number of points, the position of the centroid, the point density, or the mean of the Doppler values of the points belonging to the cluster (see also the corresponding description above). The feature vector b of a A cluster (i.e., a "box") with n features can look like this, where f _i represents the numerical values of the features: $$b=\left[\begin{array}{c}{f}_1\\ f_2\\ ⋮\\ f_n\end{array}\right]$$

The feature vectors b _i for m clusters are stacked in a single vector y in step 504. For a vehicle with five seats and correspondingly five clusters, m = 5 would apply, for example. $$y=\left[\begin{array}{c}{b}_1\\ b_2\\ ⋮\\ b_m\end{array}\right]$$

The vector y represents measurement data at a specific point in time (if a cluster or box contains no points, the values in the corresponding feature vector are set to 0). To account for the temporal evolution of the features, a sequence with l time points is now considered. The corresponding vectors y _{_i} are summarized in a matrix s in step 505: $$S=\left[\begin{array}{cccc}{b}_1^1& b_1^2& \cdots & b_1^l\\ b_2^1& b_2^2& \cdots & b_2^l\\ ⋮& ⋮& \ddots & ⋮\\ b_m^1& b_m^2& \cdots & b_m^l\end{array}\right]$$

In this way, data sets for different seat occupancy states can be provided (step 506). The features of the matrix s are stacked, i.e., combined into a long overall vector or tensor. The stacked vector serves as input for a recurrent neural network (RNN), which consists, for example, of one or more LSTM cells or GRU cells. The output of this RNN is then processed by a linear layer, which outputs the classification based on the vector calculated by the RNN (for the given time interval).

The overall network has as many outputs as there are boxes or clusters; so for a vehicle with five seats and five clusters, there are five outputs. Each of these outputs can then indicate the probability of the seat being occupied by an adult or unoccupied (e.g., a child, a water bottle, empty). Accordingly, a (binary) classification can be performed for each seat, and a seatbelt warning can be issued if the person is not buckled up (however, the information about whether the seatbelt is buckled up is not part of the network). The output might look like this, for example, if two seats are occupied and three are unoccupied: $$\left[\begin{array}{l}0\hfill \\ 0\hfill \\ 0\hfill \\ 1\hfill \\ 1\hfill \end{array}\right]$$

The following refers to 5B The hyperparameter optimization for a number of different parameters will now be explained. The hyperparameters can relate in particular to the structure of the RNN (e.g., LSTM or GRU) and may include, for example, the following: batch size, number of hidden units, positive/negative class weights, bidirectionality, and number of stacked RNN layers.

First, a set of parameters is selected, i.e., different seat occupancy states for which the optimization aims to establish a balance. Examples include whether the engine is running or not, or the occupancy of a specific seat (105a to 105e). One combination would be, for example, AF05 (small woman) in the driver's seat while the vehicle is stationary. This is a combination of the person's size, the seat, and the vehicle's condition. Other parameter examples include values AM95, AM50, and AF05 for different adult occupants (tall/heavy man, medium/medium-weight man, and small/light woman, respectively). Children can be identified by their age, e.g., 4YO or 6YO for a four-year-old or six-year-old child, respectively. Similarly, objects or an empty seat can be classified.

Using Bayesian optimization, appropriate weights can be determined. For all possible combinations of the selected parameters, an accuracy can be calculated. From each of these calculated accuracies, the difference between a target value and the calculated accuracy can be determined for every combination of parameters.

For Bayesian optimization 511, a fixed number of iterations (m) is defined before the start. Bayesian optimization optimizes the chosen metric to adjust the hyperparameters, treating the function that defines the metric as a random function that it attempts to estimate. The number of iterations is fixed because it is crucial in Bayesian optimization. Theoretically, it has no limit due to the implementation.

The hyperparameters are provided, with a range of input values specified for each hyperparameter, and the Bayesian optimization 511 selects random values for the first few iterations (here: 10) (step 520). After 10 iterations, during which the evaluation model is trained with the parameters from the dataset and the metric is evaluated (step 530), the Bayesian optimization 511 selects the most promising hyperparameters (step 540).

In the next (m-10) iterations, where the evaluation model is further trained with the parameters from the dataset and the metric is evaluated accordingly (step 550), the most promising hyperparameters are always selected. Specifically, the next selected hyperparameters are those from the range of input values with the highest values. After the chosen number of iterations has been completed (here, a total of m), the result of the process (i.e., the Bayesian optimization 511) is the set of hyperparameters that was evaluated and leads to the lowest measured value.

This initial "short" training (e.g., 10% of the total training) is advantageous because model evaluation can be lengthy. The longer, final training then takes place with the most promising hyperparameters already selected (step 560). The evaluation model is then saved with the hyperparameters obtained from the optimization, allowing it to be used, for example, in procedure 400 to detect seat occupancy.

The evaluation model created using Method 500 delivers more stable results because, unlike predictions for each individual time point ("frame"), it considers a longer time span with multiple time points. Furthermore, the model (based on clusters) considers the entire vehicle, enabling it to learn interactions between different seats. For example, a person who moves a lot (e.g., the driver in the driver's seat) might reduce the number of points in the radar point cloud of a person in another seat who moves little (e.g., a sleeping passenger). The evaluation model also has the advantage of being able to learn patterns of disappearing points, such as when someone holds their breath.

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.

REFERENCE MARK LIST

P

Person in the passenger seat

100

vehicle

105

Seating arrangement

105a-e

Seats or seating places

110

radar sensor

110a

Observation field of the radar sensor 110

115

System for automated seat occupancy detection

115a

Data processing unit

115b

memory

305

radar spot cloud

310

static radar points

315

Dynamic radar points

320

Areas of radar point cloud 305 with high radar point density

325a-e

Spatial areas for cluster definition

400

Method for the automated detection of seat occupancy status

410-455

individual processes or procedural steps within the framework of procedure 400

500

Procedure for creating an evaluation model

501-560

individual processes or procedural steps within the framework of procedure 500

Claims (15)

Method for creating an evaluation model for the automated detection of the occupancy status of a seating arrangement (105) with at least one seat (105a-e), the method comprising: - providing a data set for a seat occupancy status, wherein the data set represents measurement data for at least two consecutive time points, the measurement data each representing an associated radar point cloud (305), the radar point cloud (305) being obtained from a radar scan of a spatial area at least partially surrounding the seating arrangement (105), the provision of the data set comprising: - generating feature vectors from the measurement data for each of the time points, each feature vector representing a predetermined number of features of the radar point cloud for a time point; and - combining the feature vectors into a composite tensor to obtain the data set representing the features of the radar point cloud at each of the time points; - Providing hyperparameters for the evaluation model, wherein the hyperparameters are configured to be set based on a metric; - Setting the hyperparameters, wherein a metric is provided and optimized for the dataset using an optimization procedure; and - Creating the evaluation model with the set hyperparameters for training with training data for a procedure for automatically detecting the occupancy state of a seating arrangement (105) with at least one seat (105a-e), wherein the dataset forms input data for the evaluation model and an output of the evaluation model is an evaluation result that is associated with the occupancy state of the seating arrangement (105). Procedure according to Claim 1 , wherein: the seating arrangement (105) has a plurality of seats (105a-e), wherein the seat occupancy state is an individual or cumulative seat occupancy state of the seats (105a-e); and for the radar point cloud (305), the set of its radar points (310, 315) is subdivided by means of clustering depending on the respective spatial location of the radar points (310, 315) with respect to the seats (105a-e) into several clusters, each containing a subset of the radar points (310, 315), in order to individually assign to each of the seats (105a-e) a spatially nearest cluster, wherein the feature vectors are individually generated for each cluster and for each time point, wherein all feature vectors are combined to form the overall tensor in order to obtain the data set. Procedure according to Claim 2 , 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 their respective position such that the radar points (310, 315) of the cluster lie in a defined closed spatial area in the vicinity of the seat (105a-e). Method according to one of the preceding claims, wherein the evaluation model comprises a structure of a recurrent neural network (RNN). A method according to any of the preceding claims, wherein the optimization method is a Bayesian optimization. Method according to one of the preceding claims, wherein the optimization method is carried out with a predetermined number of iterations. A method according to any of the preceding claims, wherein the individual radar points (310, 315) of each radar point cloud (305) are each represented by a position of the respective radar point in three-dimensional space and by at least one of the following parameters: - A Doppler shift value of the radar signal to the respective radar point; - A signal-to-noise ratio value of the radar signal to the respective radar point. Method for training an evaluation model created according to a method according to one of the preceding claims for the automated detection of a seat occupancy state of a seating arrangement (105) with at least one seat (105a-e), wherein the method comprises: - acquiring a data set for a seat occupancy state, wherein the data set represents measurement data for at least two consecutive time points, wherein the measurement data each represent an associated radar point cloud (305), wherein the radar point cloud (305) was or is obtained on the basis of a radar scan of a spatial area surrounding the seating arrangement (105) at least partially and is assigned to one of several predefined possible seat occupancy states of the seating arrangement (105); and - generating training data from the data set, wherein the training data are provided as input data to the evaluation model in order to obtain as its output an evaluation result which is assigned to the seat occupancy state of the seat arrangement (105). Procedure according to Claim 8 , wherein: the seating arrangement (105) has a plurality of seats (105a-e), wherein the seat occupancy state is an individual or cumulative seat occupancy state of the seats (105a-e); and for the radar point cloud (305), the set of its radar points (310, 315) is subdivided into several clusters, each containing a subset of the points (310, 315), by means of cluster formation depending on the respective spatial location of the points (310, 315) in relation to the seats (105a-e), in order to individually assign to each of the seats (105a-e) one of the clusters closest to it in space. Method for automatically detecting the occupancy status of a seating arrangement (105) with at least one seat (105a-e), the method comprising: - acquiring a data set for a seat occupancy status, wherein the data set represents measurement data for at least two consecutive time points, the measurement data each representing an associated radar point cloud (305), wherein each radar point cloud (305) was or is obtained on the basis of a radar scan of a spatial area at least partially surrounding the seating arrangement (105); - determining a seat occupancy status of the seating arrangement (105) using an evaluation model developed according to a method according to one of the Claims 1 until 7 created and prepared according to a procedure following one of the Claims 8 or 9 was trained and, depending on the radar point cloud, provides one of several predefined possible seat occupancy states of the seating arrangement (105) as an evaluation result based on the recorded data set; and - outputting information defined depending on the evaluation result. Procedure according to Claim 10 , wherein the output of the information comprises controlling a signal source depending on the information in order to cause the signal source to output a defined signal depending on the control, wherein the signal source is controlled in such a way as to output a signal when the information results from an evaluation result according to which at least one seat of the seating arrangement (105) is occupied and/or a selected predetermined seat occupancy state exists. Procedure according to Claim 11 , further comprising: detecting a seat belt fastening state of at least one seat of the seating arrangement (105) or receiving seat belt information characterizing this seat belt fastening state; wherein the signal source is controlled in such a way as to depend on the seat belt information and the information from the evaluation result, such that it outputs a seat belt fastening indicator signal when, according to the information, at least one seat of the seating arrangement (105) is occupied and/or a selected predetermined seat occupancy state is present and seat belt information indicates that the corresponding seat belt of the seat is not fastened. System (115) for automatically detecting the occupancy status of a seating arrangement (105) with at least one seat (105a-e), wherein the system (115) comprises a data processing device configured to detect the occupancy status using the method according to one of the Claims 10 until 12 to execute. computer program or computer program product comprising instructions which, when executed on the data processing device of the system (115) Claim 13 , cause the system (115) to proceed according to one of the Claims 10 until 12 to execute. Vehicle (100) comprising: a seating arrangement (105) with at least one seat (105a-e); a radar sensor (110) for at least section-by-section radar scanning of the seating arrangement (105); and a system (115) according to Claim 13 for the automated detection of a seat occupancy state of the seat arrangement (105) depending on a radar scan of the seat arrangement (105) carried out by the radar sensor (110), at least in sections.