Locking system for motor vehicle
The user's body language and expression are recognized through image generation and processing units, and the keyless control of the motor vehicle is realized, solving the problems of insufficient complexity and safety of control and unlocking in the prior art, and improving the convenience and safety of the motor vehicle .
Patent Information
- Application Number
- CN202280094869.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-04-19
- Filing Date
- 2022-11-29
- Publication Date
- 2024-12-20
AI Technical Summary
The existing motor vehicle locking system has problems of complexity and insufficient safety during the control and unlocking process, especially in the identification of authorized users.
Using a locking system combining an image generation unit and an image processing unit, the user's body language, expressions and posture are recognized through wireless communication and image technology, and the function of keyless control of the motor vehicle is realized, including unlocking, starting the engine and other vehicle operations.
Improve the convenience, safety and simplify the unlocking process of motor vehicle control. By identifying authorized users and generating corresponding control commands based on their body language and expressions, the safety and user experience of the vehicle are enhanced.
Smart Images
Figure CN119173920A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a locking system for a motor vehicle and an associated method, the locking system being used for control, in particular based on gestures, or for detecting the approach of the motor vehicle. Background Art
[0002] In principle, locking systems are known in the prior art and, for example, from documents DE 10 2019 008 962 A1 or DE 43 40260 A1, which are based on a radio key that communicates with the vehicle, via which authorized users of the vehicle can be identified and the vehicle can be unlocked, for example, by pressing a button on the radio key or on the vehicle. Summary of the invention
[0003] The possibilities for controlling a motor vehicle and in particular unlocking a motor vehicle can be expanded and simplified by the present invention and also made safer.
[0004] The object of the present invention is therefore to make the control of a motor vehicle, in particular the approach detection, more convenient, simpler and safer for the user.
[0005] This object is achieved by the combination of features according to the following technical solutions.
[0006] Therefore, according to the invention, a locking system for a motor vehicle is proposed, which is used to control the motor vehicle. The control preferably also includes the function of releasing and / or triggering the motor vehicle, and in particular also includes locking and / or unlocking the motor vehicle. For this purpose, the locking system has a control unit and a key unit that can be carried by a user, and the control unit and the key unit are designed to communicate with each other wirelessly and preferably encrypted in order to control the motor vehicle. The key unit can be, for example, a radio key, a key tag (fob), a mobile phone or other items suitable for this purpose. According to the invention, it is proposed that the locking system also includes an image generation unit and an image processing unit, which are connected to the control unit by signals, that is, data can be exchanged. The control unit and the image processing unit are designed to identify a person captured by the image generation unit using image technology as an authorized user, capture the user's body language (Gestik) and / or expression (Mimik) and / or posture and / or body positioning, and assign them to predetermined control commands for controlling the motor vehicle.
[0007] The basic idea of the invention is therefore to expand an access system or locking system for a motor vehicle, for example with a so-called "keyless" function, so that the motor vehicle can be controlled by the user's body or a movement process of the user's body. Such a movement or movement process can be, for example, the user's body language and / or facial expressions and / or posture and / or body positioning or orientation.
[0008] In a simple case, the user can, for example, unlock the motor vehicle by means of a gesture, automatically open a door or a trunk lid, or trigger other functions of the motor vehicle.
[0009] It is also conceivable that the movement of the vehicle can be controlled in a gesture-controlled manner. Thus, for example, a motor vehicle can be parked in reverse in a gesture-controlled manner, wherein the vehicle starts moving when the hand is waved, and stops when the hand sends a stop signal.
[0010] Here, the control is not limited to, for example, a gesture. In the image processing unit, various gestures and / or facial expressions and / or postures and / or body positions or orientations of the user can be stored, which are each assigned a function or control signal in order to control a function of the motor vehicle.
[0011] The image generating unit for generating images can have at least one camera and / or a lidar sensor and / or a radar sensor.
[0012] If the vehicle is equipped with other assistance systems that have an image generating unit, the image generating units of these assistance systems can also be used, for example cameras for surround vision, traffic sign recognition or automated driving.
[0013] Regardless of which components the image generating unit comprises, it is preferably designed to capture the hands, body and face of a person or user and to be able to identify or capture their respective positions and orientations as well as their ongoing movements.
[0014] The image processing unit and the control unit may also be designed to be integrated with each other.
[0015] For example, in order to identify the user, it is proposed that the control unit is designed to determine the position and / or distance of the key unit relative to the control unit or a predetermined point. For the predetermined point, it can be, for example, the coordinate origin of a vehicle coordinate system fixed relative to the vehicle.
[0016] For this purpose, for example, the signal propagation time between the key unit and the control unit can be used, wherein the control unit can have, for example, a plurality of antennas, so that the position of the key unit can be determined from the difference in signal propagation time between the key unit and the antennas.
[0017] It is further proposed that the control unit is designed to identify a person as a user by evaluating the position and / or distance of the key unit and in particular by comparing it with a predetermined proximity zone relative to the control unit or a predetermined point and / or to start image generation by the image generation unit.
[0018] In a simple case, if the key unit or a person carrying the key unit moves into an area defined as an access zone, which may be, for example, an area adjacent to a door or a trunk of a vehicle, then the person can be identified as an authorized user and his movements evaluated.
[0019] Furthermore, the image processing unit can be designed to determine the position and / or distance of a person relative to the control unit or a predetermined point.
[0020] Alternatively or additionally, the control unit and the image processing unit are designed to capture the body language and / or expression and / or posture and / or body position of the person captured by the image generation unit by image technology, compare it with the body language and / or expression and / or posture and / or body position of the user defined as the key or identifier and stored in the control unit or the image processing unit, and identify the person as a user if the captured body language and / or expression and / or posture and / or body position match the stored body language and / or expression and / or posture and / or body position. For example, it is also conceivable that the person can be identified as a user when waving to the vehicle or performing other hand movements when approaching the vehicle.
[0021] This identification by means of the identifier can be combined with a position comparison of the person and the key unit. In particular, the control unit can be designed to determine the position of the key unit and the image capture unit to determine the position of the person, wherein if the combined position corresponds to the identifier emitted by the person, the person is identified as a user.
[0022] Furthermore, the control unit and the image processing unit can also be designed to capture visible features of the person captured by the image generation unit using imaging technology, in particular visible features of the face and / or the front of the head, compare them with features of previously known users stored in the control unit, and identify the person as a user if the features match. This can accordingly achieve a facial recognition, in which the corresponding features of the control unit must be known. In order to increase security, facial recognition can be combined with other variants of user recognition, such as a comparison of the position of the person and the key and / or recognition by means of gestures.
[0023] Preferably, the control unit can also be further designed to control the motor vehicle by means of the control commands, and in particular unlock the doors or lid of the motor vehicle, and / or start the engine of the motor vehicle. In principle, a large number of other functions of the motor vehicle can also be controlled.
[0024] Another aspect of the invention relates to a method for controlling a motor vehicle with a locking system according to the invention. The method proposes that a person, in particular one captured by an image generation unit using image technology, be identified as a user, wherein the user's body language and / or facial expressions and / or posture and / or body positioning are captured by the image generation unit as a feature combination and transmitted to an image processing unit. Subsequently, the image processing unit determines whether the feature combination is a static feature combination or a dynamic feature combination, wherein a movement process is understood as a dynamic feature combination and a static posture is understood as a static feature combination. In particular, for gestures, a distinction can be made between static gestures, such as individual hand gestures, and dynamic gestures, such as a series of hand gestures. In addition, the image processing unit extracts predetermined features from the feature combination and compares the features in the static feature combination with a feature matrix of static features stored in the image processing unit, and compares the features in the dynamic feature combination with a feature matrix of dynamic features stored in the image processing unit. Subsequently, based on this comparison, the image processing unit can determine the control command assigned to the feature combination from the corresponding feature matrix.
[0025] The image processing unit can then transmit the control command to a control unit which is designed to control the motor vehicle according to the control command.
[0026] When comparing the features in the static feature combination with the feature matrix of static features stored in the image processing unit, and comparing the features in the dynamic feature combination with the feature matrix of dynamic features stored in the image processing unit to assign control commands, the image processing unit can also supplement the features with stored statistical data, or determine the control command after comparison based on the statistical data. These statistical data can also be stored as a model, in particular as a neural network, in the control unit or the image processing unit, so that the most likely gesture and the most likely control command can be determined or predicted based on the features extracted from the feature combination by such a model.
[0027] If features are extracted from feature combinations, ie, for example, gestures, which cannot be completely assigned to a single or specific control command, it is possible to determine which gesture or which control command is most likely involved based on statistical data or models and then select the gesture or control command.
[0028] The above features can be combined as desired as long as it is technically feasible and not contradictory to each other. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Further advantageous embodiments of the invention are described in the dependent claims or are described in more detail below together with the description of the preferred embodiments of the invention with reference to the accompanying drawings. Shown in the drawings are:
[0030] Figure 1 is a schematic diagram of the locking system;
[0031] Figure 2 The process of capturing gestures and assigning them to control commands;
[0032] Figure 3 A process for storing statistics about static gestures;
[0033] Figure 4 The process of storing statistics about dynamic gestures. DETAILED DESCRIPTION
[0034] exist Figure 1 , a variant of a locking system 1 for a motor vehicle 2 is shown by way of example and illustration, by means of which the motor vehicle 2 can be controlled. For this purpose, the locking system 1 has a control unit 3 and a key unit that can be carried by a user 4, which is not shown here, but can be carried by the user 4. The control unit 3 and the key unit communicate with each other wirelessly, which is indicated by signals 7, in order to control the motor vehicle 2, i.e., to control a keyless start system or a keyless entry system.
[0035] In order to expand the functionality of such a keyless start system or keyless entry system, the locking system 1 further comprises an image generation unit 5 and an image processing unit 6, which are signal-connected to the control unit 3 and the image generation unit 5, so that the image generation unit 5 generates an image and transmits it to the image processing unit 5, which evaluates the image and transmits the evaluation result to the control unit 3. Here, an image can be understood as a single image, a sequence of single images or a video stream. Accordingly, the control unit 3 and the image processing unit 6 are designed to, in particular, identify a person as a user or an authorized user 4 from a plurality of persons, specifically capture their body language here, and assign the captured body language to a predetermined control command for controlling the motor vehicle 2.
[0036] When approaching the vehicle 2 from the driver's side of the vehicle 2, the user 4 unlocks the driver's door, for example, by a hand gesture. Here, the gesture 10 can also be raising a hand to the door handle 8 of the vehicle door 9. When the user 4 approaches the passenger side of the vehicle 2, the user 4 can correspondingly unlock the passenger door 9 by means of the gesture 10. In addition, the user 4 can unlock all doors of the vehicle 2 or activate other functions of the vehicle 2 by means of other optional gestures.
[0037] Figures 2 to 4 Flowchart illustrations of the proposed methods are shown respectively.
[0038] For clarity, in Figure 3 and Figure 4 It is shown in Figure 2 Part Y and part Z of the method, wherein according to Figure 2 The method can also be used without any basis Figure 3 and Figure 4 is used in some cases.
[0039] according to Figure 2 The method specifically includes part X (process of image-based gesture recognition), part Y (process of static gesture training) and part Z (process of dynamic gesture training). Specifically, the following steps are performed:
[0040] A identifies an authorized user 4 in the proximity zone of the vehicle 2 .
[0041] B starts the image generation unit 5.
[0042] C transmits the image to the image processing unit 6.
[0043] D performs preprocessing to distinguish static or dynamic gestures, especially capturing gestures as feature combinations.
[0044] E The gesture or feature combination captured by the image is about a static gesture (if yes, it is s) or about a dynamic gesture (if yes, it is d).
[0045] sF extracts features from static gestures or feature combinations.
[0046] dF extracts features from dynamic gestures or feature combinations.
[0047] sG is compared with a feature matrix of a static gesture, in which a large number of features related to the static gesture are stored.
[0048] dG is compared with a feature matrix of a dynamic gesture, in which a large number of features related to the dynamic gesture are stored.
[0049] sH Statistical prediction of static hand gestures.
[0050] Statistical prediction of dH dynamic hand gestures.
[0051] Is sJ the first predetermined static gesture? If yes (1), the relevant control command sL is transmitted to the control unit 3. If no (0), the process continues to the next static gesture.
[0052] Is dJ the first predetermined dynamic gesture? If yes (1), the relevant control command dL is transmitted to the control unit 3. If no (0), the next dynamic gesture is continued.
[0053] Is sK the last or nth predetermined static gesture? If yes (1), the relevant control command sM is transmitted to the control unit 3. If no (0), the relevant control command sN is transmitted to the control unit 3, which may also be an error message.
[0054] Is dK the last or nth predetermined dynamic gesture? If yes (1), the relevant control command dM is transmitted to the control unit 3. If no (0), the relevant control command dN is transmitted to the control unit 3, which may also be an error message.
[0055] In both steps sH and dH, statistical data are taken into account, which are collected by training the model or are included in the selection of gestures. Since the processes shown by way of example - the training process for dynamic gestures Z and the training process for static gestures Y - are identical in sequence, Figure 3 and 4 Describe them together.
[0056] according to Figure 3 and Figure 4 It is proposed that the following steps are mainly performed:
[0057] A collects static gestures of authorized users 4 ( Figure 3 ) or dynamic gestures ( Figure 4 ), in particular as a combination of features.
[0058] B Summary of training data.
[0059] C extracts features or feature combinations about a single gesture from the training data.
[0060] D generates a feature matrix from the extracted features.
[0061] E assigns gestures and / or control commands to gestures or feature combinations stored via their features in a feature matrix.
[0062] F. Training models, especially training neural networks.
[0063] G obtains the trained model so that in step sH( Figure 3 ) or in step dH( Figure 4 ) to predict dynamic gestures.
[0064] H Evaluation model.
[0065] J obtains and considers the indicators extracted during the evaluation process.
[0066] The implementation of the invention is not limited to the preferred embodiments given above. On the contrary, a number of variants are conceivable which make use of the proposed solution even in different types of implementation.
Claims
1. A locking system (1) for a motor vehicle (2), in, The locking system (1) comprises a control unit (3) and a key unit which can be carried by a user (4), wherein the control unit and the key unit are designed to communicate wirelessly with each other in order to control the motor vehicle (2). The locking system (1) further comprises an image generating unit (5) and an image processing unit (6), wherein the image processing unit (6) is connected to the control unit (3) by signals. The control unit (3) and the image processing unit (6) are designed to identify a person as a user (4), capture the body language and / or facial expression and / or posture and / or body position of the user (4), and assign the captured body language and / or facial expression and / or posture and / or body position to a predetermined control command for controlling the motor vehicle (2).
2. The locking system according to claim 1, in, The image generation unit (5) for generating an image has at least one camera and / or a lidar sensor and / or a radar sensor.
3. The locking system according to claim 1 or 2, in, The control unit (3) is designed to determine the position and / or distance of the key unit relative to the control unit (3) or a predetermined point.
4. Locking system according to the preceding claim, in, The control unit (3) is designed to identify a person as a user (4) by evaluating the position and / or distance of the key unit and, in particular, by comparing it with a predetermined proximity zone relative to the control unit (3) or the predetermined point, and / or to initiate image generation by an image generation unit.
5. Locking system according to any one of the preceding claims, in, The image processing unit (6) is designed to determine the position and / or distance of a person relative to the control unit (3) or a predetermined point.
6. Locking system according to any one of the preceding claims, in, The control unit (3) and the image processing unit (6) are designed to capture the body language and / or expression and / or posture and / or body positioning of a person captured by the image generation unit (5) through image technology, compare it with a predetermined identifier stored in the control unit (3) or the image processing unit (6), and identify the person as a user (4) when the comparison results are consistent.
7. Locking system according to any one of the preceding claims, in, The control unit (3) and the image processing unit (6) are designed to capture visible features of a person captured by the image generation unit (5) using image technology, in particular visible features of the face and / or the front of the head, compare them with features of previously known users stored in the control unit, and identify the person as a user (4) when the features match.
8. A method for controlling a motor vehicle (2) having a locking system (1) according to any one of the preceding claims, in, identifying a person, in particular captured by an image generating unit (5) using imaging technology, as a user (4), The body language and / or facial expression and / or posture and / or body positioning of the user (4) are captured as a feature combination by the image generation unit (5) and transmitted to the image processing unit (6). The image processing unit (6) determines whether the feature combination is a static feature combination or a dynamic feature combination; extracts predetermined features from the feature combination; compares features in the static feature combination with a feature matrix of static features stored in the image processing unit (6), and compares features in the dynamic feature combination with a feature matrix of dynamic features stored in the image processing unit (6); and determines a control command assigned to the feature combination from the corresponding feature matrix.
9. The method according to the preceding claim, in, The image processing unit (6) transmits the control command to the control unit (3), and the control unit (3) is designed to drive the motor vehicle (2) according to the control command.
10. The method according to any one of the two preceding claims, in, When comparing features in a static feature combination with a feature matrix of static features stored in the image processing unit (6), and when comparing features in a dynamic feature combination with a feature matrix of dynamic features stored in the image processing unit (6) to assign control commands, the image processing unit (6) supplements the features with stored statistical data, or determines the control commands after comparison based on the statistical data.