Methods for calibrating gesture recognition areas, gesture recognition methods, devices, and vehicles

Abstract

This application provides a method for calibrating a gesture recognition region, a gesture recognition method, an apparatus, and a vehicle, applied in the field of vehicle recognition technology. The calibration method includes: upon detecting a user entering the vehicle, performing user identification; if the user's identity information is not identified, collecting the user's body feature information and determining boundary data corresponding to the user based on the body feature information; if the user's identity information is identified, obtaining the boundary data corresponding to the user from multiple pre-stored boundary data; the pre-stored boundary data is boundary data pre-stored in the vehicle; wherein, the boundary data is used to define the gesture recognition region corresponding to the user when seated in the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information. This application determines a suitable gesture recognition region for the user based on the user's body feature information when seated, thereby improving the accuracy of gesture recognition.

Description

Technical Field

[0001] This application relates to the field of vehicle recognition technology, and in particular to a method for calibrating a gesture recognition area, a gesture recognition method, a device, and a vehicle. Background Technology

[0002] With the development of automotive intelligence, more and more vehicles are equipped with gesture recognition functions.

[0003] However, in related technologies, gesture recognition functions are based on gesture recognition devices, and the effective area that most gesture recognition devices can recognize, i.e. the gesture recognition area, is fixed and cannot adapt to different users, resulting in errors in gesture recognition.

[0004] Application content

[0005] In view of this, this application aims to provide a method for calibrating a gesture recognition area, a gesture recognition method, an apparatus, and a vehicle, providing different gesture recognition areas for different users to improve the accuracy of gesture recognition.

[0006] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0007] A method for calibrating a gesture recognition region, applied to a vehicle, the calibration method comprising:

[0008] Once a user is detected boarding the vehicle, their identity is verified.

[0009] If the user's identity information is not identified, then the user's physical characteristic information is collected, and based on the physical characteristic information, boundary data corresponding to the user is determined;

[0010] If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data; the pre-stored boundary data is the boundary data pre-stored in the vehicle.

[0011] The boundary data is used to define the gesture recognition area corresponding to the user being seated in the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information.

[0012] Furthermore, if the user's identity information is not identified, the identification method further includes:

[0013] Create an account corresponding to the user and store the boundary data in the account;

[0014] If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data, including:

[0015] Based on the identified identity information, a target pre-stored account corresponding to the user is determined from multiple pre-stored accounts, and boundary data corresponding to the user is obtained from the target pre-stored account.

[0016] Furthermore, the pre-stored account is associated with preset posture information of the user's seat; if the user's identity information is identified, the calibration method further includes:

[0017] Obtain the target preset posture information corresponding to the first seat where the user is currently located from the target pre-stored account corresponding to the user;

[0018] Based on the target preset posture information, the current posture of the first seat is adjusted so that the adjusted posture of the first seat matches the target preset posture information.

[0019] Furthermore, the pre-stored boundary data associated with the pre-stored account includes boundary data of the user being in different seats; if the user's identity information is identified, the calibration method further includes:

[0020] Obtain the identifier of the second seat where the user is currently located;

[0021] When the identifier is inconsistent with the identifier stored in the target pre-stored account, obtain the user's body feature information when the user is in the second seat, and obtain the boundary data corresponding to the second seat based on the body feature information;

[0022] The identifier and the acquired boundary data are stored in the target pre-stored account.

[0023] Furthermore, the step of collecting the user's body feature information and determining boundary data corresponding to the user based on the body feature information includes:

[0024] Collect the user's body characteristic information when the user is in the current seat;

[0025] Based on the body feature information, obtain the boundary data corresponding to the current seat.

[0026] Furthermore, the calibration method also includes:

[0027] When the user is detected to have adjusted the posture of the current seat, the posture information of the current seat after the adjustment is obtained;

[0028] Re-execute the process of obtaining the user's body characteristic information when the user is in the current seat;

[0029] The step of obtaining boundary data corresponding to the current seat based on the body feature information;

[0030] The reacquired boundary data will be used as the new boundary data for the user.

[0031] Compared with existing technologies, the gesture recognition region calibration method described in this application has the following advantages:

[0032] This application provides a method for calibrating a gesture recognition region, applied to a vehicle. The calibration method includes: upon detecting a user entering the vehicle, identifying the user; if the user's identity information is not identified, collecting the user's body feature information and determining boundary data corresponding to the user based on the body feature information; if the user's identity information is identified, obtaining the boundary data corresponding to the user from multiple pre-stored boundary data; the pre-stored boundary data is boundary data pre-stored in the vehicle; wherein, the boundary data is used to define the gesture recognition region corresponding to the user when the user is in the seat of the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information.

[0033] Therefore, this application first identifies the user's identity information after the user boards the vehicle. If the user's identity information is not identified, it collects at least one of the user's body information, arm length information, age information, and gender information, i.e., body feature information. Based on the collected body feature information, it can determine the boundary data corresponding to the user, thereby determining the gesture recognition area corresponding to the user when seated. This provides suitable gesture recognition areas for users with different body shapes, arm lengths, ages, and even genders, thereby improving the accuracy of gesture recognition and reducing the false recognition rate. If the user's identity information is identified, it can directly obtain the boundary data corresponding to the user from the pre-stored boundary data, thereby quickly determining the appropriate gesture recognition area for that user and improving the accuracy of gesture recognition while reducing the false recognition rate.

[0034] Another objective of this application is to propose a gesture recognition method that provides different gesture recognition areas for different users in order to improve the accuracy of gesture recognition.

[0035] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0036] A gesture recognition method, applied to a vehicle, the gesture recognition method comprising:

[0037] Obtain boundary data for at least one user currently located inside the vehicle, wherein the boundary data is determined using the aforementioned method for calibrating the gesture recognition area;

[0038] Capture images inside the vehicle;

[0039] Based on the boundary data, the region to be identified in the image is determined;

[0040] The hand gestures in the area to be identified are recognized.

[0041] The gesture recognition method described above has the same advantages over the prior art as the calibration method described above, and will not be elaborated here.

[0042] Another objective of this application is to provide a calibration device for a gesture recognition area, which provides different gesture recognition areas for different users in order to improve the accuracy of gesture recognition.

[0043] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0044] A calibration device for a gesture recognition area, applied to a vehicle, the calibration device comprising:

[0045] An identity recognition unit is used to recognize the user's identity when the user is detected boarding the vehicle.

[0046] The boundary data determination unit is used to collect the user's body feature information if the user's identity information is not identified, and to determine the boundary data corresponding to the user based on the body feature information.

[0047] A boundary data acquisition unit is used to acquire boundary data corresponding to the user from multiple pre-stored boundary data if the user's identity information is identified; the pre-stored boundary data is boundary data pre-stored in the vehicle.

[0048] The boundary data is used to define the gesture recognition area corresponding to the user being seated in the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information.

[0049] The calibration device and the calibration method described above have the same advantages over the prior art, which will not be elaborated here.

[0050] Another objective of this application is to provide a gesture recognition device that provides different gesture recognition areas for different users in order to improve the accuracy of gesture recognition.

[0051] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0052] A gesture recognition device, applied to a vehicle, the gesture recognition device comprising:

[0053] The boundary data acquisition module is used to acquire the boundary data corresponding to at least one user currently located in the vehicle. The boundary data is determined by the above-mentioned gesture recognition area calibration method.

[0054] The image acquisition module is used to acquire images inside the vehicle.

[0055] The region to be identified module is used to determine the region to be identified in the image based on the boundary data;

[0056] The gesture recognition module is used to recognize gestures in the area to be recognized.

[0057] The gesture recognition device and the above-mentioned calibration method have the same advantages over the prior art, which will not be elaborated here.

[0058] Another objective of this application is to propose a vehicle that provides different gesture recognition areas for different users in order to improve the accuracy of gesture recognition.

[0059] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0060] A vehicle includes a control module, the control module being used to implement the above-described method for calibrating the gesture recognition area, or to implement the above-described gesture recognition method.

[0061] The advantages of the vehicle and the calibration method described above compared to the prior art are the same, and will not be repeated here. Attached Figure Description

[0062] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0063] Figure 1 This is a schematic diagram of a gesture recognition system according to an embodiment of this application;

[0064] Figure 2 This is a flowchart illustrating the steps of a gesture recognition region calibration method according to an embodiment of this application.

[0065] Figure 3 This is a flowchart illustrating the steps of a gesture recognition method according to an embodiment of this application.

[0066] Figure 4 This is a schematic diagram of a module of a gesture recognition area calibration device according to an embodiment of this application.

[0067] Figure 5 This is a schematic diagram of a gesture recognition device according to an embodiment of this application.

[0068] Reference numerals: 1. Recognition system; 101. Recognition controller; 102. Camera; 2. Body control system; 201. Body controller; 202. Door touch switch; 3. Vehicle infotainment system; 301. Vehicle infotainment display screen; 302. Voice system; 4. Seat system; 401. Seat; 402. Seat sensor; 5. Calibration device; 501. Identity recognition unit; 502. Boundary data determination unit; 503. Boundary data acquisition unit; 6. Gesture recognition device; 601. Boundary data acquisition module; 602. Image acquisition module; 603. Area to be recognized determination module; 604. Gesture action recognition module. Detailed Implementation

[0069] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0070] The present application will now be described in detail with reference to the accompanying drawings and embodiments.

[0071] In related technologies, most vehicles provide a fixed gesture recognition area to recognize user gestures. However, the applicant found that users with different body shapes, arm lengths, ages, and even genders have different preferred gesture recognition areas. Furthermore, the gesture recognition area changes when these users are seated in different postures. In other words, the user's body characteristics (body shape, arm length, age, gender), seat posture, etc., all affect gesture recognition, leading to errors in gesture recognition.

[0072] In view of this, embodiments of this application propose a gesture recognition system, referring to... Figure 1 , Figure 1 A schematic diagram of a gesture recognition system according to an embodiment of this application is shown, such as... Figure 1 As shown, the gesture recognition system includes:

[0073] Recognition system 1 is used to identify the user's identity information and to recognize the user's hand gestures in the gesture recognition area;

[0074] The vehicle body control system 2 is used to detect the status of the doors to determine whether a user is getting on or off the vehicle.

[0075] The vehicle infotainment system 3 includes a vehicle infotainment display screen 301 and a voice system 302. The vehicle infotainment display screen 301 is used by the user to trigger the gesture recognition function and to display the interactive content after gesture recognition. The voice system 302 is used by the user to activate the gesture recognition function by voice and to display the voice interactive content after gesture recognition.

[0076] Based on the aforementioned gesture recognition system, this application proposes a method for calibrating a gesture recognition region, applied to vehicles. This method provides different gesture recognition regions for different users to improve the accuracy of gesture recognition. The evaluation method can be referenced... Figure 2 , Figure 2 A flowchart illustrating the steps of a gesture recognition region calibration method according to an embodiment of this application is shown, as follows: Figure 2 As shown, the calibration method includes:

[0077] Step S101: After detecting that a user has boarded the vehicle, the user's identity is verified.

[0078] In the embodiments of this application, such as Figure 1 As shown, the vehicle body control system 2 includes a body controller 201 and door contact switches 202 for the vehicle doors connected to the body controller 201. The door contact switches 202 are used to indicate door opening and closing information. Thus, when a user enters the vehicle and closes the door, the corresponding door contact switch 202 sends a message indicating door closure to the body controller 201, notifying the body controller 201 that a user has entered the vehicle. Upon receiving this information, the body controller 201 sends an identification signal to the identification system 1. The identification system 1 receives this identification signal and identifies the user who entered the vehicle.

[0079] Among them, such as Figure 1 As shown, the identification system 1 includes an identification controller 101 and a camera 102. The identification controller 101 stores the identity information of multiple users, which in this embodiment may be facial information. The camera 102 is used to collect the facial information of users. Thus, when the identification system 1 receives the identity recognition signal sent by the vehicle body controller 201, the camera 102 begins to collect the facial information of the user currently boarding the vehicle and sends the collected facial information to the identification controller 101. After receiving the facial information, the identification controller 101 compares the facial information with the stored facial information to identify the user and determine whether the facial information of the user currently boarding the vehicle matches the stored facial information.

[0080] Step S1021: If the user's identity information is not identified, the user's body feature information is collected, and boundary data corresponding to the user is determined based on the body feature information.

[0081] After identifying the user, if it is determined that the user's facial information does not match the facial information stored in the recognition controller 101, meaning the user's identity information has not been recognized, indicating that the user is boarding the vehicle for the first time, the recognition controller 101 sends a collection signal to the camera 102. In response to this collection signal, the camera 102 collects the user's body feature information. Based on the collected body feature information, the boundary data corresponding to the user can be determined. The boundary data is used to define the gesture recognition area corresponding to the user.

[0082] In practical implementation, since the posture of the user in the seat will affect gesture recognition, the boundary data in this application embodiment is specifically used to define the gesture recognition area corresponding to the user being in the seat of the vehicle.

[0083] Furthermore, in practical implementation, since user body characteristics, such as torso, arm length, age, and gender, can all affect gesture recognition, the body characteristic information in this application embodiment includes at least one of the user's torso information, arm length information, age information, and gender information. Based on this body characteristic information, boundary data corresponding to the user is determined, thereby determining the gesture recognition area corresponding to the user. This gesture recognition area conforms to the user's usage habits, that is, most of the gestures made by the user will fall within the determined gesture recognition area. Therefore, this application embodiment can provide suitable gesture recognition areas for users with different torsos, different arm lengths, different ages, and even different genders, thereby improving the accuracy of gesture recognition and reducing the false recognition rate.

[0084] Step S1022: If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data; the pre-stored boundary data is the boundary data pre-stored in the vehicle.

[0085] After identifying the user, if it is determined that the user's facial information matches the facial information stored in the recognition controller 101, that is, the user's identity information is recognized, indicating that the user is boarding the vehicle for the second or more times, then the boundary data corresponding to the user is directly obtained from multiple pre-stored boundary data, thereby quickly determining the gesture recognition area suitable for the user.

[0086] The pre-stored boundary data is the boundary data that is pre-stored in the vehicle, specifically in the recognition controller 101.

[0087] In this embodiment, after a user boards the vehicle, the system first identifies the user's identity information. If the user's identity information is not identified, at least one of the user's body information, arm length information, age information, and gender information—that is, body feature information—is collected. Based on the collected body feature information, boundary data corresponding to the user can be determined, thereby determining the gesture recognition area corresponding to the user when seated. This provides suitable gesture recognition areas for users with different body shapes, arm lengths, ages, and even genders, thereby improving the accuracy of gesture recognition and reducing the false recognition rate. If the user's identity information is identified, the boundary data corresponding to the user can be directly obtained from the pre-stored boundary data, thereby quickly determining the appropriate gesture recognition area for that user and improving the accuracy of gesture recognition while reducing the false recognition rate.

[0088] In one optional implementation, the step of collecting the user's body feature information and determining boundary data corresponding to the user based on the body feature information includes:

[0089] Collect the user's body characteristic information when the user is in the current seat;

[0090] Based on the body feature information, obtain the boundary data corresponding to the current seat.

[0091] In reality, after a user sits down, their posture requirements for the seat vary depending on their riding or driving habits. For example, the angle of the seat back or the position of the seat relative to the front of the car will affect the posture of the seat. The different postures of the seat will affect the boundary parameters, namely the gesture recognition area.

[0092] Based on this, in this embodiment of the application, after the user adjusts the seat, it is necessary to determine the user's current posture information in the seat and, under this posture information, acquire the user's body feature information. Then, by combining the determined posture information, the acquired body feature information, and the pre-trained algorithm model, the boundary data corresponding to the current seat can be calculated, that is, the boundary data corresponding to the user in the current seat, thereby determining the user's corresponding gesture recognition area.

[0093] In an optional implementation, the calibration method further includes:

[0094] When the user is detected to have adjusted the posture of the current seat, the posture information of the current seat after the adjustment is obtained;

[0095] Re-execute the process of obtaining the user's body characteristic information when the user is in the current seat;

[0096] The step of obtaining boundary data corresponding to the current seat based on the body feature information;

[0097] The reacquired boundary data will be used as the new boundary data for the user.

[0098] In practice, during subsequent driving or riding in a vehicle, the user may adjust the current seat posture again. At this point, it is necessary to obtain the posture information of the current seat after the adjustment, and also to obtain the user's body feature information under the adjusted posture. Then, by combining the adjusted posture information, the newly obtained body feature information, and the pre-trained algorithm model, the boundary data corresponding to the current seat after the adjustment can be calculated. This calculated boundary data is used as the user's new boundary data.

[0099] In an optional implementation, if the user's identity information is not identified, the identification method further includes:

[0100] An account corresponding to the user is created, and the boundary data is stored in the account.

[0101] When a user's identity information is not recognized, an account is created for that user, and the defined boundary data is stored in the account. Thus, when the user boards the vehicle for the second time or subsequent times, the boundary data corresponding to that user, i.e., the user's gesture recognition area, can be directly retrieved from the account corresponding to that user.

[0102] The accounts are stored in the recognition controller 101, and each account is associated with the corresponding user's facial information. Thus, when a user boards the vehicle for the second time or subsequent times, the recognition controller 101 recognizes the user's identity information, finds the account associated with the identity information, logs into the account, and obtains the boundary data stored in the account, thereby determining the user's corresponding gesture recognition area.

[0103] If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data, including:

[0104] Based on the identified identity information, a target pre-stored account corresponding to the user is determined from multiple pre-stored accounts, and boundary data corresponding to the user is obtained from the target pre-stored account.

[0105] In this embodiment, the recognition controller 101 stores multiple pre-stored accounts, each associated with a corresponding user's facial information. Therefore, when a user's identity information, i.e., their facial information, is recognized, a target pre-stored account corresponding to that user can be determined from the multiple pre-stored accounts based on that facial information. Thus, boundary data corresponding to the user is obtained from the target pre-stored account, thereby determining the user's corresponding gesture recognition area. The entire process is fast and convenient.

[0106] Next, when the user finishes using the vehicle and opens the door, the corresponding door touch switch 202 will send a message indicating that the door is open to the body controller 201, notifying the body controller 201 that the user has gotten out of the vehicle. After receiving the message, the body controller 201 sends a logout signal to the identification system 1, specifically the identification controller 101. Upon receiving the logout signal, the identification controller 101 logs out the user's logged-in account.

[0107] In one optional implementation, the pre-stored account is associated with preset posture information of the user's seat; if the user's identity information is identified, the calibration method further includes:

[0108] Obtain the target preset posture information corresponding to the first seat where the user is currently located from the target pre-stored account corresponding to the user;

[0109] Based on the target preset posture information, the current posture of the first seat is adjusted so that the adjusted posture of the first seat matches the target preset posture information.

[0110] In this embodiment of the application, after the user adjusts the seat, it is necessary to determine the preset posture information of the seat in which the user is currently located. This preset posture information is obtained by, for example, Figure 1 The seat system 4 shown is obtained, as follows: Figure 1 As shown, the seat system 4 includes a seat 401 and a seat sensor 402 mounted on the seat 401. The seat sensor 402 is used to detect the posture of the seat 401 in real time. When the user adjusts the posture of the seat 401, the seat sensor 402 acquires the posture information of the seat 401 after adjustment, which is the preset posture information. Then, the seat sensor 402 sends the acquired preset posture information to the body controller 201. The body controller 201 saves the preset posture information and associates it with the user's account.

[0111] Therefore, when a user's identity information is identified and the user's corresponding target pre-stored account is logged in, the target preset posture information associated with that target pre-stored account can be obtained. The target preset posture information is the preset posture information of the first seat where the user is currently located. During this process, the seat sensor 402 continuously detects the posture information of the first seat and sends the current posture information of the first seat to the body controller 201. After comparing the current posture information with the target preset posture information, if the body controller 201 determines that the current posture information does not match the target preset posture information, it adjusts the current posture of the first seat according to the target preset posture information so that the adjusted posture of the seat matches the target preset posture information.

[0112] In this embodiment, the seat 401 has a front axle motor, a front axle motor Hall signal, a rear axle motor, a rear axle motor Hall signal, a backrest motor, and a backrest motor Hall signal. Therefore, after determining that the current posture information does not match the target preset posture information, the body controller 201 will send drive signals to the front axle motor, the rear axle motor, and the backrest motor. After receiving the drive signals sent by the body controller 201, the front axle motor, the rear axle motor, and the backrest motor enter the working state and feed back the distance of movement through the corresponding Hall signals, thereby making the posture of the adjusted seat match the target preset posture information.

[0113] In practice, it is also possible to adjust the current posture of the first seat directly according to the target preset posture information without obtaining the current posture information of the first seat, so that the posture of the adjusted seat matches the target preset posture information.

[0114] In one optional implementation, the pre-stored boundary data associated with the pre-stored account includes boundary data of the user being in different seats; if the user's identity information is identified, the calibration method further includes:

[0115] Obtain the identifier of the second seat where the user is currently located;

[0116] When the identifier is inconsistent with the identifier stored in the target pre-stored account, obtain the user's body feature information when the user is in the second seat, and obtain the boundary data corresponding to the second seat based on the body feature information;

[0117] The identifier and the acquired boundary data are stored in the target pre-stored account.

[0118] In practice, the seat where the user sits may be the driver's seat, the front passenger seat, or one of the rear seats. Therefore, the pre-stored boundary data associated with the pre-stored account stored in the identification controller 101 includes boundary data of the user being in different seats, as well as the identifiers of different seats, and each identifier corresponds to at least one boundary data.

[0119] Therefore, after a user boards the vehicle, if the user's identity information is recognized, it is necessary to first determine the identifier of the second seat the user is currently in. If this identifier matches the identifier stored in the target pre-stored account, then the target preset posture information corresponding to the second seat the user is in is retrieved from the target pre-stored account. Next, based on the retrieved target preset posture information, the current posture of the second seat is adjusted so that the adjusted posture of the second seat matches the target preset posture information.

[0120] If the identified identifier of the second seat does not match the identifier stored in the target pre-stored account (i.e., the target pre-stored account does not store boundary data corresponding to the second seat), then it is necessary to obtain the user's body feature information when in the second seat, and based on this body feature information, obtain the boundary data corresponding to the second seat. Specifically, the user's posture information in the second seat is obtained; this posture information is the target preset posture information, and it is associated with the user's corresponding target pre-stored account. Simultaneously, based on the target preset posture information, the user's body feature information when in the second seat, and a pre-trained algorithm model, the boundary data corresponding to the second seat is obtained. Finally, the identifier of the second seat and the obtained boundary data are stored in the target pre-stored account. This allows the boundary data to be directly retrieved from the user's corresponding target pre-stored account the next time the user gets in and sits in the second seat, thus quickly determining the user's corresponding gesture recognition area.

[0121] Based on the same inventive concept, this application also proposes a gesture recognition method, referring to... Figure 3 , Figure 3 A flowchart illustrating the steps of a gesture recognition method according to an embodiment of this application is shown, as follows: Figure 3 As shown, the gesture recognition method includes:

[0122] Step S201: Obtain boundary data corresponding to at least one user currently located in the vehicle. The boundary data is determined by the above-described gesture recognition area calibration method.

[0123] Once a user boards the vehicle, the system identifies the user. If the user's identity information is not identified, the system collects the user's physical characteristics and determines the boundary data corresponding to the user based on the collected physical characteristics. If the user's identity information is identified, the system directly retrieves the boundary data corresponding to the user from multiple pre-stored boundary data sets.

[0124] Step S202: Acquire images inside the vehicle.

[0125] After determining the user's boundary data, images inside the vehicle can be captured by the camera 102 in the recognition system 1.

[0126] Step S203: Based on the boundary data, determine the region to be identified in the image.

[0127] After the camera 102 completes the acquisition, it sends the image to the recognition controller 101. The recognition controller 101 receives the image and, based on the determined boundary data, determines the area to be recognized in the image, that is, the gesture recognition area corresponding to the user.

[0128] Step S204: Recognize the gestures in the area to be recognized.

[0129] After determining the area to be recognized in the image, that is, the gesture recognition area corresponding to the user, the recognition controller 101 will recognize the gesture action made by the user in the gesture recognition area. After successful recognition, the vehicle system 3 will respond to the user's gesture action.

[0130] It should be noted that the recognition controller 101 will only recognize the user's gestures within the gesture recognition area when the user has enabled the gesture recognition function in the vehicle infotainment system 3. For example, when a user triggers the gesture recognition function on the vehicle infotainment display screen 301 in the vehicle infotainment system 3, the recognition controller 101 recognizes the user's gestures within the gesture recognition area, the vehicle infotainment display screen 301 responds to the user's gestures, and displays the interactive content after gesture recognition. Similarly, when a user enables the gesture recognition function in the voice system 302 in the vehicle infotainment system 3, the recognition controller 101 recognizes the user's gestures within the gesture recognition area, the voice system 302 responds to the user's gestures, and displays the interactive content after gesture recognition.

[0131] Based on the same inventive concept, this application also proposes a calibration device for a gesture recognition area, applied to a vehicle, as shown in the following example. Figure 4 , Figure 4 This application shows a schematic diagram of a calibration device for a gesture recognition area according to an embodiment of the present application. Figure 4 As shown, the calibration device 5 includes:

[0132] The identity recognition unit 501 is used to recognize the user's identity after detecting that the user has boarded the vehicle.

[0133] Boundary data determination unit 502 is used to collect the user's body feature information if the user's identity information is not identified, and determine the boundary data corresponding to the user based on the body feature information;

[0134] The boundary data acquisition unit 503 is used to acquire boundary data corresponding to the user from multiple pre-stored boundary data if the user's identity information is identified; the pre-stored boundary data is boundary data pre-stored in the vehicle.

[0135] The boundary data is used to define the gesture recognition area corresponding to the user being seated in the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information.

[0136] Based on the same inventive concept, this application also proposes a gesture recognition device for use in vehicles, see reference. Figure 5 , Figure 5 A schematic diagram of a gesture recognition device according to an embodiment of this application is shown, such as... Figure 5 As shown, the gesture recognition device 6 includes:

[0137] Boundary data acquisition module 601 is used to acquire boundary data corresponding to at least one user currently located in the vehicle, wherein the boundary data is determined by the above-mentioned gesture recognition area calibration method;

[0138] Image acquisition module 602 is used to acquire images inside the vehicle;

[0139] The region to be identified module 603 is used to determine the region to be identified in the image based on the boundary data;

[0140] The gesture recognition module 604 is used to recognize gestures in the area to be recognized.

[0141] Based on the same inventive concept, this application also proposes a vehicle, which includes a control module. The control module is used to implement the above-mentioned gesture recognition area calibration method, or to implement the above-mentioned gesture recognition method.

[0142] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0143] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0144] It should also be noted that, in this document, the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or posture relationships based on the orientation or posture relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations, nor should they be construed as indicating or implying relative importance. Moreover, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. In the absence of further restrictions, an element defined by the phrase "includes a..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the element.

[0145] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand this application, and the content of this specification should not be construed as a limitation of this application. Furthermore, for those skilled in the art, there will be different forms of changes in the specific implementation methods and application scope based on this application. It is neither necessary nor possible to exhaustively list all implementation methods here, and obvious changes or modifications derived therefrom are still within the protection scope of this application.

Claims

1. A method for calibrating a gesture recognition region, characterized in that, Applied to vehicles, the calibration method includes: Once a user is detected boarding the vehicle, their identity is verified. If the user's identity information is not identified, then the user's physical characteristic information is collected, and based on the physical characteristic information, boundary data corresponding to the user is determined; If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data; the pre-stored boundary data is the boundary data pre-stored in the vehicle. The boundary data is used to define the gesture recognition area corresponding to the user being seated in the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information. If the user's identity information is not identified, the identification method further includes: establishing an account corresponding to the user and storing the boundary data in the account; If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data, including: based on the identified identity information, determining the target pre-stored account corresponding to the user from multiple established pre-stored accounts, and obtaining the boundary data corresponding to the user from the target pre-stored account; The step of collecting the user's body feature information and determining boundary data corresponding to the user based on the body feature information includes: Collect the user's body characteristic information when the user is in the current seat; Based on the body feature information, obtain the boundary data corresponding to the current seat; The calibration method further includes: When the user is detected to have adjusted the posture of the current seat, the posture information of the current seat after the adjustment is obtained; Re-execute the process of obtaining the user's body characteristic information when the user is in the current seat; The step of obtaining boundary data corresponding to the current seat based on the body feature information; The reacquired boundary data will be used as the new boundary data for the user.

2. The method for calibrating the gesture recognition region according to claim 1, characterized in that, The pre-stored account is associated with the preset posture information of the user's seat; If the user's identity information is identified, the identification method further includes: Obtain the target preset posture information corresponding to the first seat where the user is currently located from the target pre-stored account corresponding to the user; Based on the target preset posture information, the current posture of the first seat is adjusted so that the adjusted posture of the first seat matches the target preset posture information.

3. The method for calibrating the gesture recognition region according to claim 1, characterized in that, The pre-stored boundary data associated with the pre-stored account includes boundary data of the user being in different seats; If the user's identity information is identified, the identification method further includes: Obtain the identifier of the second seat where the user is currently located; When the identifier is inconsistent with the identifier stored in the target pre-stored account, obtain the user's body feature information when the user is in the second seat, and obtain the boundary data corresponding to the second seat based on the body feature information; The identifier and the acquired boundary data are stored in the target pre-stored account.

4. A gesture recognition method, characterized in that, Applied to vehicles, the gesture recognition method includes: Obtain boundary data corresponding to at least one user currently located in the vehicle, wherein the boundary data is determined by the gesture recognition region calibration method as described in any one of claims 1-3; Capture images inside the vehicle; Based on the boundary data, the region to be identified in the image is determined; The hand gestures in the area to be identified are recognized.

5. A calibration device for a gesture recognition area, characterized in that, Applied to vehicles, the calibration device includes: An identity recognition unit is used to recognize the user's identity when the user is detected boarding the vehicle. The boundary data determination unit is used to collect the user's body feature information if the user's identity information is not identified, and to determine the boundary data corresponding to the user based on the body feature information. A boundary data acquisition unit is used to acquire boundary data corresponding to the user from multiple pre-stored boundary data if the user's identity information is identified; the pre-stored boundary data is boundary data pre-stored in the vehicle. The boundary data is used to define the gesture recognition area corresponding to the user being seated in the vehicle; the body feature information includes at least one of the user's body information, arm length information, age information, and gender information. If the user's identity information is not identified, the calibration device further includes: establishing an account corresponding to the user and storing the boundary data in the account; If the user's identity information is identified, then the boundary data corresponding to the user is obtained from multiple pre-stored boundary data, including: based on the identified identity information, determining the target pre-stored account corresponding to the user from multiple established pre-stored accounts, and obtaining the boundary data corresponding to the user from the target pre-stored account; The step of collecting the user's body feature information and determining boundary data corresponding to the user based on the body feature information includes: Collect the user's body characteristic information when the user is in the current seat; Based on the body feature information, obtain the boundary data corresponding to the current seat; The calibration device further includes: When the user is detected to have adjusted the posture of the current seat, the posture information of the current seat after the adjustment is obtained; Re-execute the process of obtaining the user's body characteristic information when the user is in the current seat; The step of obtaining boundary data corresponding to the current seat based on the body feature information; The reacquired boundary data will be used as the new boundary data for the user.

6. A gesture recognition device, characterized in that, Applied to vehicles, the gesture recognition device includes: A boundary data acquisition module is used to acquire boundary data corresponding to at least one user currently located in the vehicle, wherein the boundary data is determined by the gesture recognition area calibration method as described in any one of claims 1-3. The image acquisition module is used to acquire images inside the vehicle. The region to be identified module is used to determine the region to be identified in the image based on the boundary data; The gesture recognition module is used to recognize gestures in the area to be recognized.

7. A vehicle, characterized in that, The vehicle includes a control module, which is used to implement the gesture recognition area calibration method as described in any one of claims 1-3, or to implement the gesture recognition method as described in claim 4.

Images