Calibration of a gesture recognition algorithm for the gesture-controlled opening of an area of a vehicle closed by a movable component

Abstract

According to a method for calibrating a gesture recognition algorithm for the gesture-controlled opening of an area of a vehicle (1) closed by a movable component (3), a gesture recognition algorithm is provided in a computer-readable format, which is adapted to recognise a predetermined gesture as a function of a time-dependent sensor signal from an ultrasonic sensor (5) of the vehicle (1). The ultrasonic sensor (5) is used to generate a time-dependent first sensor signal, while a first person (8) performs a gesture movement in a field of view of the ultrasonic sensor (5) and, depending on the first sensor signal, a first value of a predetermined parameter of the gesture recognition algorithm is determined and stored.

Description

[0001] Calibration of a gesture recognition algorithm for gesture-controlled opening of a vehicle area closed by a movable component

[0002] The present invention relates to a method for calibrating a gesture recognition algorithm for gesture-controlled opening of a vehicle area closed by a movable component. The invention further relates to a method for gesture-controlled opening of a vehicle area closed by a movable component, as well as a corresponding device for a vehicle and a computer program product.

[0003] Devices are known for automatically opening vehicle trunk lids or tailgates when a user, for example, places a leg in a designated target area in the vehicle's vicinity. Capacitive sensors are used, for example, to detect the presence of the leg in the target area.

[0004] A disadvantage is that these devices react relatively non-specifically, thus potentially leading to the risk of false positive detections if, for example, another object is brought into the target area without the user having the corresponding intention to automatically open the trunk lid or tailgate. To counteract this, the device can, for example, be designed so that the target area is correspondingly small, thus reducing the likelihood of an object being brought into the target area unintentionally. However, this is also disadvantageous because, should automatic opening of the trunk lid or tailgate actually be desired, the user must hit a relatively small target area, which in turn reduces the reliability of detecting the user's intention.

[0005] Furthermore, the use of ultrasonic sensors for gesture recognition is known. Since an ultrasonic sensor can be used to evaluate the distance of an object from the ultrasonic sensor over time, the temporal progression of, for example, a user's leg and, accordingly, a gesture performed by the user with that leg can also be detected and characterized using ultrasonic sensors. However, even when using ultrasonic sensors for gesture recognition, it can generally happen that a corresponding user movement is not recognized as a gesture, since the movement details can differ depending on the person or user, for example.

[0006] Document DE 10 2016 013 935 A1 describes a method for automatically executing vehicle functions. A user is recognized via a vehicle key, and gestures or behavior patterns are subsequently recorded via one or more vehicle cameras. Depending on this, a vehicle setting can be personalized, for example, a seat position can be adjusted accordingly.

[0007] It is an object of the present invention to provide a possibility for contactless opening of an area of ​​the vehicle closed by a movable component of a vehicle, by means of which the user's intention to open can be recognized more reliably.

[0008] This object is achieved by the respective subject matter of the independent claims. Advantageous further developments and preferred embodiments are the subject matter of the dependent claims.

[0009] The invention is based on the idea of ​​calibrating a predetermined gesture recognition algorithm for ultrasound-based gesture recognition by determining and storing a value of a predetermined parameter of the gesture recognition algorithm depending on a sensor signal generated by an ultrasonic sensor of the vehicle while a person performs a gesture movement.

[0010] According to one aspect of the invention, a method is provided for calibrating a gesture recognition algorithm for gesture-controlled opening of an area of ​​a vehicle, in particular a motor vehicle, closed by a movable component. A gesture recognition algorithm is provided in computer-readable form. The gesture recognition algorithm is adapted to recognize a predefined gesture depending on a time-dependent sensor signal from an ultrasonic sensor of the vehicle. A time-dependent first sensor signal is generated by the ultrasonic sensor while a first person performs a gesture movement in a field of view of the ultrasonic sensor. Depending on this, a first value of a predefined parameter of the gesture recognition algorithm is determined and stored, in particular adapted, in particular by means of at least one computing unit.

[0011] The ultrasonic sensor, and possibly other ultrasonic sensors of the vehicle, can, for example, be part of an ultrasonic sensor system of the vehicle. The ultrasonic sensor system can also have at least one computing unit that can control the ultrasonic sensor and determine and store the first value of the specified parameter depending on the first sensor signal.

[0012] The ultrasonic sensor system can, for example, be operated in a calibration mode, and the first sensor signal can be generated in the calibration mode. Furthermore, the ultrasonic sensor system can, for example, be operated in a gesture recognition mode, in particular after the first value of the parameter has been determined and stored. The gesture recognition algorithm is particularly adapted to recognize the gesture in the gesture recognition mode depending on the sensor signal of the ultrasonic sensor.

[0013] The at least one computing unit can control the ultrasonic sensor to emit ultrasonic waves and, for example, activate or deactivate the calibration mode and / or the gesture recognition mode.

[0014] The ultrasonic waves can be emitted by the ultrasonic sensor, for example, in the form of one or more ultrasonic pulses. Portions of the emitted ultrasonic waves reflected in the environment and detected by the ultrasonic sensors cause the ultrasonic sensor to generate the sensor signal, or the first sensor signal, in particular as an electrical signal, voltage signal, or current signal. The ultrasonic sensor can also be referred to as an ultrasonic transducer.

[0015] The first sensor signal can, for example, correspond to an amplitude or intensity of the ultrasonic waves reflected and detected at a specific time or to a corresponding envelope.

[0016] Since the first person is located in the field of view of the ultrasonic sensor and performs the gesture movement, the first sensor signal reflects the gesture movement or is generated depending on the gesture movement. The gesture movement can be understood as the movement of a body part, in particular a leg or knee, of the first person, which represents or is intended to represent or replicate the specified gesture. When performing the gesture movement, the first person can, for example, be located in a predefined gesture recognition area outside the vehicle, in particular in the immediate vicinity of the ultrasonic sensor, whereby the field of view of the ultrasonic sensor covers the gesture recognition area.

[0017] After determining and saving the first value for the parameter, the calibration mode can be deactivated, for example. For example, the gesture recognition mode can then be activated. Determining and saving, in particular adjusting, the first value of the parameter of the gesture recognition algorithm can be understood as calibrating the gesture recognition algorithm. After the inventive method for calibrating the gesture recognition algorithm has been carried out, the gesture recognition can be used to recognize the specified gesture depending on the first value of the parameter. In an analogous manner, further parameters of the gesture recognition algorithm can also be determined and saved depending on the first sensor signal and used for further use of the gesture recognition algorithm in gesture recognition mode.

[0018] Since the first value of the parameter is determined on a person-specific basis depending on the gesture movement of the first person, characteristic movement patterns or properties of the gesture movement of the first person can be taken into account for later gesture recognition in gesture recognition mode. For example, the gesture recognition algorithm can, in principle, already be capable of detecting the gesture based on a sensor signal from the ultrasonic sensor even before performing the calibration method according to the invention. However, the method according to the invention takes person-specific characteristics of the gesture movement into account, and the gesture recognition mode is adapted accordingly. This can increase the reliability of gesture recognition in gesture recognition mode.In other words, the probability that the first person wants to perform the gesture, but this is not recognized by the gesture recognition algorithm due to characteristic properties of the first person's movement, can be reduced.

[0019] According to at least one embodiment of the method for calibrating the gesture recognition algorithm, a characteristic property of the gesture movement with respect to the first person is determined as a function of the first sensor signal, in particular by means of the at least one computing unit, and the first value of the parameter is determined as a function of the characteristic property determined with respect to the first person, in particular by means of the at least one computing unit.

[0020] The characteristic property can, for example, be an initial distance of a body part of the first person moved during the gesture movement, or the characteristic property can be derived from it. This advantageously takes into account the fact that different people typically maintain different distances from the vehicle when performing the gesture movement.

[0021] Likewise, the characteristic property can correspond to or be derived from a final distance of the body part after or at the completion of the gesture movement.

[0022] The gesture movement can, for example, correspond to a movement of the body part, in particular the leg, from a starting position toward the vehicle or the ultrasonic sensor and back to the starting position or approximately to the starting position. The distance of the body part from the ultrasonic sensor is thus equal to the initial distance, especially at the beginning of the gesture movement, is then reduced, and then increased again until the final distance is reached.

[0023] By considering the final distance, it can be taken into account that different people typically make a movement or step toward the ultrasonic sensor when performing the gesture. In other words, people may not fully return their leg to the starting position and the initial distance, so the final distance does not match the initial distance. This can be used for person-specific characterization and corresponding person-specific determination of the first value for the parameter.

[0024] The characteristic property can also correspond to or be derived from a distance between the final distance and the initial distance.

[0025] The characteristic property can also correspond to or be derived from the movement speed of the body part during the gesture movement. This advantageously takes into account the fact that different people typically move the body part at different speeds to perform the gesture movement.

[0026] The characteristic property can correspond to the temporal duration of the gesture movement or be derived from it. Person-specific characteristics of the gesture movement can also be mapped and taken into account via the temporal duration, for example, the varying speed of the gesture movement, or person-specific body proportions such as leg length, etc.

[0027] The characteristic property can also correspond to or be derived from an amplitude, in particular a maximum amplitude, of a signal pulse of the first sensor signal during the gesture movement. The maximum amplitude can be influenced, for example, by the height, stature, or clothing of the first person, which are further typical influencing factors on the characteristics of the gesture movement or the first value of the parameter.

[0028] The characteristic property is not limited to the examples mentioned. Several of the above-mentioned or additional characteristic properties can also be determined based on the first sensor signal, and the first value of the parameter can be determined based on these. Two or more characteristic properties can also be combined or calculated to determine the first value for the parameter.

[0029] In general, the parameter can correspond directly to one of the characteristic properties or be derived from one or more of the characteristic properties.

[0030] By using the characteristic property as the basis for determining the first value for the parameter, the gesture recognition algorithm can be specifically influenced to increase the reliability of gesture recognition. This allows the first value of the parameter to be determined in such a way that the gesture recognition algorithm can consider particularly relevant characteristic properties during gesture recognition and, if necessary, assigns no or lesser weight to less relevant characteristic properties during gesture recognition. This can, in particular, prevent the gesture recognition algorithm from being over-specified and, if necessary, prevent deviations in gesture movement for one and the same person from influencing the reliability of gesture recognition.

[0031] According to at least one embodiment, the generation of the first sensor signal is repeated while the first person repeatedly performs the gesture movement in the field of view of the ultrasonic sensor. The determination of the characteristic property of the gesture movement with respect to the first person is also repeated based on the repeatedly generated first sensor signal. The first value of the parameter is determined depending on the repeatedly determined characteristic property, for example, by averaging or other statistical processing.

[0032] In this way, fluctuations in the characteristic properties when performing the gesture movement by the same person can be addressed. This can further increase the reliability of gesture recognition.

[0033] According to at least one embodiment, the gesture recognition algorithm implements a state machine.

[0034] The state machine represents an algorithm that can determine one of two or more predefined states, for example of the first sensor signal or the gesture movement or the first person, depending on the first sensor signal and, in particular, can detect the presence of the gesture based on a temporal sequence of the states thus determined.

[0035] For example, different states of the state machine can correspond to situations in which the body part is stationary at certain distances from the ultrasonic sensor and / or situations in which the body part is moved in a certain direction. In one non-limiting example, the gesture could therefore be detected, for example, if a state in which the body part is stationary in the gesture recognition area is followed by a state in which the body part is moved towards the ultrasonic sensor, this state in turn is followed by a state in which the body part is moved away from the ultrasonic sensor, and this state in turn is followed by a state in which the body part is again stationary in the gesture recognition area. The specified parameter and further parameters can be used, for example, to identify the individual states.For example, one or more characteristic properties can be used directly or processed as parameters for the state machine to recognize individual states. In this way, by specifying the first value for the parameter for a specific person, the state machine's state recognition can be directly influenced, and consequently, gesture recognition.

[0036] According to at least one embodiment, a time-dependent second sensor signal is generated by the ultrasonic sensor while a second person, who is in particular different from the first person, performs the gesture movement in the field of view of the ultrasonic sensor. Depending on the second sensor signal, the characteristic property of the gesture movement with respect to the second person is determined, in particular by means of the at least one computing unit. Depending on the characteristic property determined with respect to the second person, a second value of the parameter is determined and stored, in particular by means of the at least one computing unit.

[0037] This allows different parameter values ​​or different variants of the gesture recognition algorithm to be stored and maintained, assigned to different people. For example, corresponding user profiles can be created for different people, saving the respective parameter value or the correspondingly adapted gesture recognition algorithm. This can further increase the reliability of gesture recognition.

[0038] According to at least one embodiment, the gesture recognition algorithm includes a trained recurrent neural network RNN, for example a long short-term memory (LSTM), and the parameter is a weighting factor or a bias parameter of the RNN.

[0039] In such embodiments, for example, the gesture recognition algorithm can directly recognize the gesture based on input data generated as a function of the sensor signal from the ultrasonic sensor, without having to perform the intermediate step of determining the characteristic property. This has the advantage that the person-specific differences in gesture movement and their influence on gesture detection do not necessarily have to be known. In such embodiments, the method for calibrating the gesture recognition algorithm can be understood as improving or refining the training of the RNN based on the first sensor signal.

[0040] For example, if the ultrasonic sensor system is in calibration mode, it can be assumed that the gesture movement performed actually corresponds to the gesture. Accordingly, if necessary, the RNN's parameterization can be adjusted depending on the first sensor signal, for example, to increase the confidence with which the gesture is detected based on it.

[0041] According to at least one embodiment, a calibration mode of the ultrasonic sensor system is activated, for example, by means of the at least one computing unit, and the first sensor signal is generated in the calibration mode. The calibration mode can be initiated, for example, by the first person.

[0042] For example, at least one radio signal can be transmitted to the at least one computing unit by means of an electronic device external to the vehicle, and the calibration mode can be activated depending on the at least one radio signal transmitted.

[0043] The vehicle-external electronic device, which is therefore not part of the vehicle, can, for example, be a mobile electronic device, a smartphone, a smartwatch, or another so-called wearable device, or a vehicle key for the vehicle, a key fob, or the like. Calibration mode can be initiated, in particular, if the first person determines that there is a need to improve the reliability of gesture detection.

[0044] According to at least one embodiment, identification information of the first person is transmitted to the at least one computing unit based on the at least one radio signal. The first value of the parameter is stored in a user profile of the first person depending on the identification information. The same applies in corresponding embodiments, for example, to the second person.

[0045] In various embodiments, the calibration mode can also be activated depending on a user input detected by a user input device of the vehicle. According to a further aspect of the invention, a method for gesture-controlled opening of an area of ​​a vehicle closed by a movable component is also specified. A method according to the invention for calibrating the gesture recognition algorithm is carried out. After carrying out the method for calibrating the gesture recognition algorithm, a time-dependent further first sensor signal is generated by means of the ultrasonic sensor while the first person in the field of view of the ultrasonic sensor performs the gesture movement again, for example, during the gesture recognition mode.By applying the gesture recognition algorithm to input data dependent on the further sensor signal, depending on the stored first value, a predetermined gesture is detected, in particular by means of the at least one computing unit. In response to the detection of the gesture, the movable component is automatically moved to open the locked area.

[0046] "Reaction to gesture detection" can be understood as meaning that the automatic movement of the movable component only occurs when the gesture has been detected. In other words, the input data is generated depending on the further first sensor signal, and the gesture recognition algorithm is applied to the input data depending on the stored first value of the parameter to detect the gesture.

[0047] For example, gesture recognition mode can be activated when the first person is within the gesture recognition area. However, other conditions can also be specified for activating gesture recognition mode.

[0048] Since the further first sensor signal reflects the distance of the first person or the body part of the first person from the ultrasonic sensor, the execution of the gesture movement can be recognized as the gesture and detected accordingly.

[0049] Depending on the embodiment of the method and the vehicle, the movable component can be, for example, a door, in particular a side door, a driver's door, a passenger door, a rear door, a rear door, a sliding door, a tailgate or a trunk lid. Preferably, it is a tailgate or a trunk lid. In this case, the closed area of ​​the vehicle is, for example, a trunk or an open or closed loading area of ​​the vehicle. An open loading area can, in particular, be open at the top, which does not preclude the open loading area from being closed, for example, in the rear direction by the tailgate, as is the case with a small van or a pickup truck with an open loading area.

[0050] For use cases or application situations that may arise during the method and which are not explicitly described here, it may be provided that, in accordance with the method, an error message and / or a request to enter user feedback is issued and / or a default setting and / or a predetermined initial state is set.

[0051] According to a further aspect of the invention, a device for a vehicle for gesture-controlled opening of a region of the vehicle closed by a movable component is provided. The device comprises an ultrasonic sensor system with an ultrasonic sensor, wherein the ultrasonic sensor system is configured to generate a time-dependent first sensor signal using the ultrasonic sensor while a first person performs a gesture movement in a field of view of the ultrasonic sensor. The ultrasonic sensor system has at least one computing unit configured to determine and store a first value of a predetermined parameter of a gesture recognition algorithm depending on the first sensor signal.

[0052] A computing unit can be understood, in particular, as a data processing device that contains a processing circuit. The computing unit can therefore, in particular, process data to perform computing operations. This may also include operations for performing indexed access to a data structure, for example, a look-up table (LUT).

[0053] The computing unit can in particular contain one or more computers, one or more microcontrollers and / or one or more integrated circuits, for example one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more single-chip systems (SoCs). The computing unit can also contain one or more processors, for example one or more microprocessors, one or more central processing units (CPUs), one or more graphics processing units (GPUs), and / or one or more signal processors, in particular one or more digital signal processors (DSPs). The computing unit can also contain a physical or virtual network of computers or other of the aforementioned units.

[0054] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.

[0055] A memory unit can be a volatile data memory, for example a dynamic random access memory (DRAM) or a static random access memory (SRAM), or a non-volatile data memory, for example a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or flash EEPROM, a ferroelectric random access memory (FRAM), a magnetoresistive random access memory,MRAM (magnetoresistive random access memory) or phase-change random access memory (PCRAM).

[0056] According to at least one embodiment, the device comprises a storage medium that stores the gesture recognition algorithm in computer-readable form. The ultrasonic sensor system is configured to generate a time-dependent further first sensor signal after determining and storing the first value of the parameter by means of the ultrasonic sensor while the first person in the field of view of the ultrasonic sensor performs the gesture movement again. The at least one computing unit is configured to apply the gesture recognition algorithm, depending on the stored first value of the parameter, to input data dependent on the further first sensor signal in order to detect a predetermined gesture. The at least one computing unit is configured to generate at least one control signal for automatically moving the movable component in response to the detection of the gesture.According to at least one embodiment, the device comprises at least one actuator which is configured to automatically move the movable component depending on the control signal in order to open the closed area.

[0057] In this case, the at least one computing unit can transmit the control signal directly to the at least one actuator or to a control unit for the at least one actuator, and the control unit for the at least one actuator generates a further control signal, which it transmits to the at least one actuator in order to cause the latter to move the movable component depending on the further control signal.

[0058] If, within the scope of the present disclosure, it is stated that a component of the device according to the invention, in particular the at least one computing unit of the device, is set up, designed, configured or the like to carry out or implement a specific function, to achieve a specific effect or to serve a specific purpose, this can be understood to mean that the component, beyond the fundamental or theoretical usability or suitability of the component for this function, effect or purpose, is concretely and actually capable of carrying out or implementing the function, achieving the effect or serving the purpose through appropriate adaptation, programming, physical design and so on.

[0059] Further embodiments of the device according to the invention follow directly from the various embodiments of the method according to the invention, and vice versa. In particular, individual features and corresponding explanations as well as advantages relating to the various embodiments of the method according to the invention can be transferred analogously to corresponding embodiments of the device according to the invention. In particular, the device according to the invention is designed or programmed to carry out a method according to the invention. In particular, the device according to the invention carries out a method according to the invention.

[0060] According to a further aspect of the invention, a computer program with commands is provided. When the commands are executed by a device according to the invention, in particular by the at least one computing unit, the commands cause the device to perform a method according to the invention for calibrating the gesture recognition algorithm and / or a method according to the invention for gesture-controlled opening of a locked area of ​​a vehicle.

[0061] According to a further aspect of the invention, a computer-readable storage medium is provided which stores a computer program according to the invention.

[0062] The computer program and the computer-readable storage medium can be regarded as respective computer program products with the instructions.

[0063] Further features of the invention emerge from the claims, the figures and the description of the figures. The features and combinations of features mentioned above in the description as well as the features and combinations of features mentioned below in the description of the figures and / or shown in the figures can be encompassed by the invention not only in the respectively specified combination, but also in other combinations. In particular, the invention can also encompass embodiments and combinations of features that do not have all the features of an originally formulated claim. Furthermore, the invention can encompass embodiments and combinations of features that go beyond the combinations of features set out in the backreferences to the claims or deviate from them.

[0064] The invention is explained in more detail below using specific embodiments and associated schematic drawings. In the figures, identical or functionally equivalent elements may be provided with the same reference numerals. The description of identical or functionally equivalent elements may not necessarily be repeated for different figures.

[0065] The figures show:

[0066] Fig. 1 is a schematic representation of a vehicle with an exemplary embodiment of a device for a vehicle for automatically opening a region of the vehicle closed by a movable component according to the invention; and

[0067] Fig. 2 shows a schematic flow diagram of an exemplary embodiment of a method for automatically opening a region of a vehicle closed by a movable component according to the invention. Fig. 1 schematically shows a vehicle 1 with an exemplary embodiment of a device 2 according to the invention for gesture-controlled opening of a region of the vehicle 1 closed by a movable component 3.

[0068] The movable component 3 is illustrated here as an example as the trunk lid of the vehicle 1, so that the area closed by it is a trunk of the vehicle 1. In other embodiments, the movable component can instead be a tailgate or a door of the vehicle 1.

[0069] The vehicle, for example the device 2, has in particular one or more actuators 4a, 4b, two in the non-limiting example of Fig. 1, as well as a computing unit 6. The computing unit 6 can be regarded as representative of one or more control, computing and / or evaluation units, which are described functionally together to simplify the description. The computing unit 6 can in particular control the actuators 4a, 4b so that they can, for example, automatically initiate a movement of the movable component 3 and, if necessary, release a locking of the movable component 3. As a result, the area of ​​the vehicle closed by the movable component 3 can be opened automatically, i.e., without a user having to manually open the movable component 3. Systems are known in which this can be triggered using a vehicle key for the vehicle 1.This may also be possible with the present device 2, but is not absolutely necessary. Rather, the device 2 can implement a method according to the invention for gesture-controlled opening of the locked area.

[0070] For this purpose, the device 2 comprises an ultrasonic sensor 5 which has a field of view in which it can detect objects such as a person 8. In particular, the ultrasonic sensor 5 can emit ultrasonic pulses and detect portions of the ultrasonic pulses reflected by an object in the field of view of the ultrasonic sensor 5 and, depending thereon, generate a correspondingly time-dependent sensor signal which represents the intensity of the detected portions of the ultrasonic pulses. The sensor signal then typically contains signal pulses, also referred to as peaks or echoes, with each signal pulse being traced back to an emitted ultrasonic pulse. The temporal position of the signal pulses allows the distance of the reflecting object from the ultrasonic sensor 5 to be determined by means of the computing unit 6.The ultrasonic sensor 5 and the computing unit 6 or parts of the computing unit 6, as well as possibly other ultrasonic sensors (not shown), can be understood as parts of an ultrasonic sensor system of the device 2. The ultrasonic sensor system, in particular the ultrasonic sensor 5, can not necessarily be used only in the sense of the invention, but can also be used for other functions, for example, to assist a driver of the vehicle 1 in parking.

[0071] The method according to the invention for gesture-controlled opening of the area of ​​the vehicle 1 closed by the movable component 3 provides for the implementation of a method according to the invention for calibrating a gesture recognition algorithm. The gesture recognition algorithm is stored, in particular, in computer-readable form on a storage medium of the computing unit 6.

[0072] In a calibration mode, which can be initiated by the person 8, for example, via a user input interface of the vehicle 1 or an electronic device external to the vehicle, such as a smartphone, the person 8 can perform a gesture movement in the field of view of the ultrasonic sensor 5, for example in a predetermined gesture recognition area 7 in the vicinity of the ultrasonic sensor 5, for example moving a leg from a standing position towards the ultrasonic sensor 5 and back again. While the person 8 performs the gesture movement, the ultrasonic sensor 5 generates a corresponding time-dependent sensor signal. Depending on this, the computing unit 6 determines a value of a predetermined parameter of the gesture recognition algorithm, in particular specific to the person 8, and stores it.

[0073] For this purpose, the computing unit 6 can, for example, determine a characteristic property of the gesture movement with respect to the person 8 based on the sensor signal and determine the value of the parameter based on the characteristic property. If necessary, the person 8 can also perform the gesture movement repeatedly to compensate for fluctuations in the characteristic property.

[0074] After completing the procedure for calibrating the gesture recognition algorithm, the same person 8 can return to the gesture recognition area 7 at a later time in a gesture recognition mode and perform the gesture movement again. The calibrated gesture recognition algorithm can now generate input data for the gesture recognition algorithm depending on the additional sensor signal generated by the ultrasonic sensor and apply the gesture recognition algorithm to the input data, in particular with the stored value of the parameter or depending on the stored value of the parameter. As a result, the gesture recognition algorithm can detect a specified gesture.

[0075] If the gesture has been detected, the computing unit 6 can generate at least one control signal for automatically moving the movable component 3 and transmit it to the actuators 4a, 4b, so that the opening of the closed area is initiated.

[0076] For gesture recognition itself, the computing unit 6 can use known methods. For example, the gesture recognition algorithm can implement a state machine. By applying the gesture recognition algorithm to the input data, the computing unit 6 can recognize when the gesture movement performed by the person 8 corresponds to a predetermined and predefined sequence of two or more states and detect the gesture based on this.

[0077] However, other gesture recognition algorithms are also conceivable and applicable. For example, the gesture recognition algorithm can include a trained recurrent neural network (RNN).

[0078] Fig. 2 shows a schematic flow diagram of an exemplary embodiment of a method according to the invention for gesture-controlled opening of an area of ​​the vehicle 1 closed by a movable component 3. In this case, an embodiment of a method according to the invention for calibrating the gesture recognition algorithm is carried out according to steps S1, S2 and S3, if necessary repeatedly for several people.

[0079] In particular, in step S1, the gesture recognition algorithm is provided in computer-readable form, and in step S2, while the person 8 is in the field of view of the ultrasonic sensor 5 and performing the gesture movement, the time-dependent sensor signal is generated. In step S3, the value of the parameter is determined and stored depending on the sensor signal, for example, by determining the characteristic property of the gesture movement with respect to the person 8. After performing steps S1 to S3, the calibration mode is terminated, and at a later time, for example, the gesture recognition mode is activated.In step S4, while the person 8 performs the gesture movement again in the field of view of the ultrasonic sensor 5, another sensor signal is generated by the ultrasonic sensor 5. In step S5, the gesture recognition algorithm is applied to the input data dependent on the additional sensor signal depending on the stored value of the parameter, and the specified gesture is detected. In step S6, in response to the detection of the gesture, the movable component 3 is automatically moved to open the closed area.

[0080] This enables particularly robust gesture recognition that can detect different types or characteristics of gesture movements. The sensor signal can, for example, be fed directly to the RNN, which can make a binary decision as to whether the gesture movement corresponds to the gesture or not.

[0081] One advantage of the RNN is that it has an internal state that acts like a memory for previous measurements, allowing changes between measurements to be detected. This also eliminates the need for external storage for measurement results, thus saving storage space. The RNN used can be an LSTM, for example.

[0082] The RNN can be trained using recorded data to learn its internal parameters and detect when the gesture is present. It may be beneficial to tailor a pre-trained RNN to the specific model of vehicle 1, as sensor positions and other properties may vary depending on the vehicle model. This can be achieved by recording a dataset specifically for that vehicle model and further training the RNN accordingly.

Claims

Patent claims 1. A method for calibrating a gesture recognition algorithm for gesture-controlled opening of an area of ​​a vehicle (1) closed by a movable component (3), characterized in that the gesture recognition algorithm is provided in computer-readable form, which is adapted to recognize a predetermined gesture depending on a time-dependent sensor signal of an ultrasonic sensor (5) of the vehicle (1); a time-dependent first sensor signal is generated by means of the ultrasonic sensor (5) while a first person (8) performs a gesture movement in a field of view of the ultrasonic sensor (5); and a first value of a predetermined parameter of the gesture recognition algorithm is determined and stored depending on the first sensor signal.

2. Method according to claim 1, characterized in that a characteristic property of the gesture movement with respect to the first person (8) is determined as a function of the first sensor signal; and the first value of the parameter is determined as a function of the characteristic property determined with respect to the first person (8).

3. Method according to claim 2, characterized in that the characteristic property relates to an initial distance of a body part moved during the gesture movement from the ultrasonic sensor (5); and / or relates to a final distance of the body part after or upon completion of the gesture movement; and / or relates to a movement speed of the body part during the gesture movement; and / or a temporal duration of the gesture movement; and / or a maximum amplitude of a signal pulse of the first sensor signal during the gesture movement.

4. Method according to one of claims 2 or 3, characterized in that the generation of the first sensor signal is repeated while the first person (8) in the field of view of the ultrasonic sensor (5) the gesture movement is repeatedly performed; the determination of the characteristic property of the gesture movement with respect to the first person (8) is repeated based on the repeatedly generated first sensor signal; the first value of the parameter is determined depending on the repeatedly determined characteristic property.

5. Method according to one of claims 2 to 4, characterized in that the gesture recognition algorithm implements a state machine.

6. Method according to one of claims 2 to 5, characterized in that a time-dependent second sensor signal is generated by means of the ultrasonic sensor (5) while a second person performs the gesture movement in the field of view of the ultrasonic sensor; depending on the second sensor signal, the characteristic property of the gesture movement with respect to the second person is determined; depending on the characteristic property determined with respect to the second person, a second value of the parameter is determined and stored.

7. The method according to claim 1, characterized in that the gesture recognition algorithm contains a recurrent neural network and the parameter is a weighting factor or a bias parameter of the recurrent neural network.

8. Method according to one of the preceding claims, characterized in that a calibration mode of an ultrasonic sensor system (5, 6) containing the ultrasonic sensor (5) is activated and the first sensor signal is generated in the calibration mode.

9. The method according to claim 8, characterized in that at least one radio signal is transmitted to at least one computing unit (6) of the ultrasonic sensor system (5, 6) by means of an electronic device external to the vehicle; and the calibration mode is activated depending on the transmitted at least one radio signal.

10. The method according to claim 8 or 9, characterized in that, based on the at least one radio signal, identification information of the first person (8) is transmitted to the at least one computing unit (6); and the first value of the parameter is stored in a user profile of the first person (8) depending on the identification information.

11. Method according to claim 8, characterized in that the calibration mode is activated depending on a user input detected by means of a user input device of the vehicle (1).

12. Method for gesture-controlled opening of a movable component (3) closed area of ​​a vehicle (1), characterized in that a method for calibrating the gesture recognition algorithm according to one of the preceding claims is carried out; after carrying out the method for calibrating the gesture recognition algorithm by means of the ultrasonic sensor (5), a time-dependent further first sensor signal is generated while the first person (8) in the field of view of the ultrasonic sensor (5) performs the gesture movement again; By applying the gesture recognition algorithm to input data dependent on the further first sensor signal, a predetermined gesture is detected depending on the stored first value of the parameter; in response to the detection of the gesture, the movable component (3) is automatically moved to open the closed area. A device (2) for a vehicle (1) for gesture-controlled opening of an area of ​​the vehicle (1) closed by a movable component (3), characterized in that the device (2) has a storage medium that stores a gesture recognition algorithm in computer-readable form, which is adapted to recognize a predetermined gesture depending on a time-dependent sensor signal of an ultrasonic sensor (5) of the vehicle (1);the device (2) comprises an ultrasonic sensor system (5, 6) with an ultrasonic sensor (5), wherein the ultrasonic sensor system (5, 6) is configured to generate a time-dependent first sensor signal by means of the ultrasonic sensor (5) while a first person (8) performs a gesture movement in a field of view of the ultrasonic sensor (5);the ultrasonic sensor system (5, 6) has at least one computing unit (6) configured to determine and store a first value of a predefined parameter of a gesture recognition algorithm depending on the first sensor signal. Device (2) according to claim 13, characterized in that the ultrasonic sensor system (5, 6) is configured to generate a time-dependent further first sensor signal after determining and storing the first value of the parameter by means of the ultrasonic sensor (5) while the first person (8) in the field of view of the ultrasonic sensor (5) performs the gesture movement again; the at least one computing unit (6) is configured to apply the gesture recognition algorithm depending on the stored first value of the parameter to input data dependent on the further first sensor signal in order to detect a predefined gesture; and; the at least one computing unit (6) is configured to generate at least one control signal for automatically moving the movable component (3) in response to the detection of the gesture.

15. Computer program product with instructions which, when executed by a Device (2) according to claim 13, causing the device (2) to carry out a method according to one of claims 1 to 11 and / or when executed by a device (2) according to claim 14, causing the device (2) to carry out a method according to claim 12.

Images