Gesture control method, device, display terminal and storage medium

Abstract

The present invention discloses a gesture control method, device, display terminal and storage medium, wherein the method comprises: in response to an image acquisition instruction, acquiring a target frame of a target palm; performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal; determining the gesture intention corresponding to the target palm according to the target angle; and controlling the display terminal according to the gesture intention. The present invention can solve the technical problems in the prior art that a display terminal cannot be controlled by a remote control or a close-range touch method, which affects the user experience.

Description

Technical Field

[0001] The present invention relates to the field of image technology, and in particular to a gesture control method, device, display terminal and storage medium. Background Art

[0002] With the development of display technology, people's demand for large-screen displays is increasing. Especially in the fields of education and conferences, large-screen smart TVs and large-screen conference boards are widely favored by the industry.

[0003] At present, the operation and control methods for large-screen display terminals (also called display terminals) are remote control or close-range touch, but both methods have certain limitations. Specifically, the remote control is suitable for viewers and operators to operate at a distance. In the case where the remote control is lost or not beside the user, the user cannot operate the display terminal, affecting the user experience. In close-range touch, due to the user's height or insensitive touch, the user cannot touch the display terminal, which also affects the user experience.

[0004] Therefore, it is urgent to propose a better display terminal control solution. Summary of the invention

[0005] The embodiments of the present invention provide a gesture control method, device, display terminal and computer-readable storage medium, which solve the technical problems in the prior art that a display terminal cannot be controlled by a remote control or close-range touch control, affecting user experience.

[0006] On the one hand, the present invention provides a gesture control method through an embodiment of the present invention, which is applied to a display terminal, and the method includes:

[0007] In response to the image acquisition instruction, acquiring a target frame of the target palm;

[0008] Performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal;

[0009] Determining the gesture intention corresponding to the target palm according to the target angle;

[0010] The display terminal is controlled according to the gesture intention.

[0011] Optionally, performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal includes:

[0012] Performing depth calculation on the target frame to obtain a depth of field distance between the target palm and the display terminal;

[0013] A target angle between the target palm and the display terminal is calculated according to the depth of field distance.

[0014] Optionally, before performing depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal, the method further includes:

[0015] Performing gesture recognition on the target frame to obtain the palm position of the target palm in the current palm shape;

[0016] The performing depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal comprises:

[0017] A depth calculation is performed on the palm position in the current palm shape in the target frame to obtain a depth of field distance from the palm position of the target palm to the display terminal.

[0018] Optionally, the capturing of the target frame of the target palm includes: capturing at least two target frames of the target palm at different times;

[0019] The performing gesture recognition on the target frame to obtain the target angle between the target palm and the display terminal comprises: performing gesture recognition on at least two target frames at different times to obtain corresponding gesture information; wherein the gesture information comprises the target angle between the target palm and the display terminal at different times and the gesture movement direction corresponding to the target palm;

[0020] Determining the gesture intention corresponding to the target palm according to the target angle includes: determining the gesture intention corresponding to the target palm according to the target angle and the gesture movement direction at different moments.

[0021] Optionally, the method further comprises:

[0022] When it is detected that the target palm stays in the direction of the gesture movement, determining that the target palm completes one gesture control;

[0023] If at least two of the target frames at different times are frame images generated in the one gesture control, the target angle is the angle between the target palm and the display terminal at different times in the one gesture control, and determining the gesture intention corresponding to the target palm according to the target angle at different times and the gesture movement direction includes:

[0024] The gesture intention corresponding to the single gesture control is determined according to the target angle and the gesture movement direction at different moments in the single gesture control.

[0025] Optionally, the method further comprises:

[0026] Acquire a control parameter, where the control parameter is used to indicate the number of gesture controls of the target palm in a round of gesture control;

[0027] The display terminal is controlled according to the gesture intention determined corresponding to each gesture control in the number of gesture controls.

[0028] Optionally, before acquiring the target frame of the target palm, the method further includes:

[0029] Acquire a control parameter, where the control parameter is used to indicate a gesture step length when the target palm completes a gesture control;

[0030] The target frame for collecting the target palm includes:

[0031] At least two target frames of the target palm at different times in the gesture control are collected according to the gesture step length.

[0032] Optionally, the gesture information further includes gesture movement speed, and the acquiring control parameter includes:

[0033] Determining the control parameter according to the gesture movement speed and the target distance;

[0034] The target distance is the distance between the target user where the target palm is located and the display terminal.

[0035] Optionally, before determining the control parameter according to the gesture movement speed and the target distance, the method further includes:

[0036] Acquire the user height of the target user and the camera height of the camera device in the display terminal;

[0037] The determining the control parameter according to the gesture movement speed and the target distance includes:

[0038] The control parameter is determined according to the user height, the camera height, the gesture movement speed and the target distance.

[0039] Optionally, before acquiring the target frame of the target palm, the method further includes:

[0040] Collecting multiple initial frames of the target palm at different times;

[0041] Performing image recognition on a plurality of the initial frames to determine whether the target palm stays at the same position;

[0042] If yes, continue to execute the step of collecting the target frame of the target palm, wherein the target frame is a frame image generated when the target palm moves.

[0043] Optionally, the target frame includes palms of multiple users, and performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal includes:

[0044] Performing image recognition on the palms of the multiple users in the target frame to select a target palm of the target user that is closest to the camera device from the multiple users;

[0045] Performing gesture recognition on a target palm of the target user in the target frame to obtain a target angle between the target palm and the display terminal.

[0046] On the other hand, the present invention provides a gesture control device through an embodiment of the present invention, the device includes a collection module, a recognition module, a determination module and a control module, wherein:

[0047] The acquisition module is used to acquire a target frame of a target palm in response to an image acquisition instruction;

[0048] The recognition module is used to perform gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal;

[0049] The determination module is used to determine the gesture intention corresponding to the target palm according to the target angle;

[0050] The control module is used to control the display terminal according to the gesture intention.

[0051] For the contents not introduced or described in the embodiments of the present application, please refer to the relevant introduction in the aforementioned method embodiments, which will not be repeated here.

[0052] On the other hand, the present invention provides a display terminal through an embodiment of the present invention, and the display terminal includes: a processor, a memory, a communication interface and a bus; the processor, the memory and the communication interface are connected through the bus and communicate with each other; the memory stores executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the gesture control method as described above.

[0053] On the other hand, the present invention provides a computer-readable storage medium through an embodiment of the present invention, wherein the computer-readable storage medium stores a program, and when the program is run on a display terminal, the gesture control method as described above is executed.

[0054] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: the present invention collects a target frame of the target palm in response to an image acquisition instruction; performs gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal; determines the gesture intention corresponding to the target palm according to the target angle; and controls the display terminal according to the gesture intention. In the above scheme, the present invention identifies and determines the gesture intention corresponding to the target palm according to the angle between the target palm and the display terminal, and then performs corresponding intention control on the display terminal according to the gesture intention, thereby achieving convenient and efficient control of the display terminal, and also solves the technical problems in the prior art that the display terminal cannot be controlled by a remote control or close-range touch method, affecting the user experience, and so on. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 It is a structural schematic diagram of a display terminal provided by an embodiment of the present invention.

[0057] Figure 2 This is a possible gesture division schematic diagram provided by an embodiment of the present invention.

[0058] Figure 3 It is a flowchart of a gesture control method provided by an embodiment of the present invention.

[0059] Figure 4-Figure 6 This is a schematic diagram of target angle recognition based on different gesture motion directions provided by an embodiment of the present invention.

[0060] Figure 7-Figure 9 Schematic diagram of gesture control under three different control parameters provided by an embodiment of the present invention.

[0061] Fig.10 It is a structural schematic diagram of a gesture control device provided by an embodiment of the present invention.

[0062] Fig.11 It is a structural schematic diagram of a display terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0064] First of all, the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0065] The present invention is to solve the technical problems in the prior art that a display terminal cannot be controlled by a remote control or a close-range touch method, which affects the user experience. The present invention provides a gesture control method, which is applied to a display terminal. The display terminal may refer to a terminal device with a large or extra-large display screen (i.e., the size of the display screen exceeds a preset size), such as a display terminal with a display screen of 110 inches, 135 inches, or other extra-large sizes. The terminal device includes, but is not limited to, a smart phone, a PDA, a tablet computer, a personal digital assistant (PDA), a sales terminal, or other devices with a network communication function, etc., and the present invention does not limit this.

[0066] See also Figure 1 , is a schematic diagram of a possible display terminal provided by an embodiment of the present invention. Figure 1 The display terminal shown includes a display screen 101, a camera device 102, and a navigation bar 103 displayed on the display screen 101. The size of the display screen 101 exceeds the preset size, and it can also be called a large screen or a giant screen. The installation position of the camera device 102 is not limited by the present invention. For example, the camera device 102 shown in the figure is installed at the center of the top of the display screen 101. The camera device 102 can be used to capture images of objects in front of the display screen 101. For example, in the present invention, when the target palm of the user appears or moves in front of the display screen 101, the camera device 102 can be used to capture frame images of the target palm at different times.

[0067] In practical applications, the camera device 102 includes but is not limited to a camera, a camera module or other devices for taking photos or videos. The present invention also does not limit the type and model of the camera device 102. For example, the camera device 102 may be a depth camera that supports collecting depth of field data. Specifically, the camera device 102 may collect the depth of field data of the target palm.

[0068] The navigation bar 103 is only an example in this example and does not constitute a limitation. In actual applications, the navigation bar 103 may also be a specific application icon or application control, etc. Some applications are installed in the display terminal 10, and a corresponding floating window is configured in the display interface corresponding to each application. The display position of the floating window in the display interface is not limited by the present invention. Among them, the floating window is used to display the key value icons of the navigation bar 103. The user moves his own target palm (specifically, the gesture corresponding to the target palm) to the floating window to obtain the display focus corresponding to the floating window, and then open the navigation bar 103 corresponding to the key value icon in the floating window. The target palm can refer to the user's right palm or the user's left palm, which is not limited by the present invention.

[0069] Optionally, there is usually an exit control, such as an exit button, on the display interface of the navigation bar 103. Accordingly, the user can still close the display interface of the navigation bar 103 by gesture by moving the target palm, so that the display terminal 103 returns to the interface where the floating window was originally displayed.

[0070] It should be noted that the gestures involved in the present invention can be divided into up gestures, down gestures, front gestures, back gestures, left gestures and right gestures according to the movement direction of the target palm (also referred to as gesture movement direction). Figure 2 A possible gesture segmentation diagram based on the target palm is shown as an example. Figure 2 In the above, the upper gesture refers to the gesture generated when the target palm of the user moves upward, and the end point of the upward movement is not limited in the present invention. For example, the terminal of the upward movement can be the position that the user's arm can reach when it is stretched upward. The lower gesture refers to the gesture generated when the target palm moves downward, and the end point of the downward movement is also not limited in the present invention. Preferably, the end point of the downward movement can be the position where the user's arm is retracted downward to the chest of the human body.

[0071] The forward gesture refers to a gesture generated when the target palm moves forward, and the end point of the forward movement is not limited in the present invention. For example, the end point of the forward movement can be a position that the user's arm can reach when it is stretched forward. The rear gesture refers to a gesture generated when the target palm moves backward, and the end point of the backward movement is not limited in the present invention. Preferably, the end point of the backward movement can be a position where the user's arm is retracted backward to a position close to the user's face.

[0072] The left gesture refers to a gesture generated when the target palm moves to the left, and the end point of the leftward movement is not limited in the present invention. For example, the end point of the leftward movement can be a position that can be reached by the user's arm stretched to the left. The right gesture refers to a gesture generated when the target palm moves to the right, and the end point of the rightward movement is not limited in the present invention. For example, the end point of the rightward movement can be a position that can be reached by the user's arm stretched to the right, etc.

[0073] Based on the above examples, see Figure 3 FIG. 1 is a flow chart of a gesture control method provided in an embodiment of the present application. Figure 3 The gesture control method shown is applied to a display terminal, and the method includes the following implementation steps:

[0074] S301 . In response to an image acquisition instruction, acquire a target frame of a target palm.

[0075] The image acquisition instruction of the present invention may be generated by a user trigger, such as a user clicking an image acquisition button, or a user sending an image acquisition instruction through voice or a remote control, etc.; the image acquisition instruction may also be received from other devices (such as a server), which is not limited by the present invention. The image acquisition instruction is used to instruct the acquisition of frame images of the target palm, such as the acquisition of frame images of the target palm at different time periods or at different times.

[0076] In step S301, the present invention can, for example, capture a target frame of the target palm through a camera device according to / in response to the image capture instruction. The number of the target frames is not limited by the present invention and can be customized according to user needs. The number of the target frames can be one or more.

[0077] In a specific implementation, the present invention can respond to the image acquisition instruction and acquire at least two target frames of the target palm at different times through a camera device.

[0078] S302: Perform gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal.

[0079] In a specific embodiment, when there are at least two target frames, for example, after at least two target frames at different times are collected in step S301, the present invention can perform gesture recognition on each target frame to obtain corresponding gesture information. The gesture information includes but is not limited to the target angle between the target palm and the display terminal in each target frame, that is, the target angle between the target palm and the display terminal at different times, the moving distance of the target palm, the gesture movement direction, the gesture movement speed, the current palm shape, the palm position or other gesture information corresponding to the target palm.

[0080] The specific implementation method of gesture recognition for each target frame is not limited by the present invention. For example, the present invention can perform gesture recognition and analysis on each target frame according to a preset gesture recognition algorithm to obtain gesture information such as the target angle at different times, the moving distance of the target palm, the palm position, the current palm shape, the gesture movement direction and the gesture movement speed. The gesture recognition algorithm is pre-defined by the system, such as a convolutional neural network algorithm, a local feature extraction algorithm, or other deep learning algorithms, and is not limited by the present invention.

[0081] In actual applications, when the target palm is performing gesture control, its palm shape is not fixed, and the palm shape varies at different times. For example, the target palm can be in shapes such as a clenched fist, bent, one finger extended, five fingers extended (or all fingers extended), etc. Correspondingly, the specific implementation method of the present invention for determining the palm position of the target palm can be, for example: the present invention can use a gesture recognition algorithm to extract the palm contour of each of the target frames to obtain the palm contour of the target palm in the target frame. Then, the palm position of the target palm is determined based on the palm contour of the target palm. Among them, the present invention does not limit the implementation method for determining the palm position. For example, the present invention can uniformly determine the center point position of the palm contour as the palm position of the target palm.

[0082] Another example is to improve the accuracy of determining the palm position, thereby improving the accuracy and precision of gesture control. The present invention can determine the palm position of the target palm based on the palm contour of the target palm and the current palm shape of the target palm. Specifically, for example, when the target palm is in a clenched fist state, the present invention can directly determine the point position located at the outermost side of the back of the hand or the innermost side of the palm in the palm contour as the palm position of the target palm; or, the present invention calculates the average value of the coordinates of the point position located at the outermost side of the back of the hand and the point position located at the innermost side of the palm, and uses the calculated coordinate point position as the palm position of the target palm, etc.

[0083] When the target palm is in a bent state, the present invention can determine the minimum circumscribed ellipse where the palm contour is located according to the palm contour, and then determine the center of the minimum circumscribed ellipse as the palm position of the target palm. Alternatively, the present invention can calculate the coordinates of the center point position according to the pixel coordinates of each pixel point in the palm contour, and determine the calculated coordinate center point position as the palm position of the target palm, etc.

[0084] When the target palm is in a state with one or two fingers extended, it can be treated as the target palm in a fist state. Alternatively, the present invention can still calculate the coordinates of the center point position according to the pixel coordinates of each pixel point in the palm contour, and determine the calculated coordinate center point position as the palm position of the target palm, etc.

[0085] When the target palm is in a state with at least three fingers extended, the present invention may treat it as the target palm in a state with all fingers extended for processing. Specifically, the present invention may calculate the minimum bounding rectangle of the palm outline based on the pixel coordinates of each pixel point in the palm outline, and the palm outline is located within the minimum bounding rectangle. Then, the center position of the minimum bounding rectangle is determined as the palm position of the target palm, etc. Alternatively, the depth of field information of different positions in the palm outline from the display terminal can be obtained by a depth camera, and the position with the smallest depth of field information is taken as the palm position of the target palm. Based on this gesture control, recognition can be performed based on the movement of a single finger.

[0086] It should be noted that the present invention does not limit the specific implementation method of performing gesture recognition on each of the target frames to obtain the target angle at different times. Specifically, for example, the present invention can perform depth calculation on each of the target frames to obtain the depth distance between the target palm in the target frame and the display terminal, wherein the depth distance refers to the depth distance between the palm position of the target palm and the display terminal. Since the palm position of the target palm is related to the current palm shape of the target palm, the depth distance can specifically refer to the distance from the palm position of the target palm in the current palm shape to the display terminal. Further, the present invention can calculate the target angle between the target palm in the target frame and the display terminal according to the depth distance. Specifically, the present invention can first calculate the position distance between the palm position of the target palm in the target frame and the installation position of the camera device used to collect the target frame, and then calculate the target angle at this time according to the position distance and the depth distance. In other words, the target angle is determined according to three parameters: the palm position, the installation position of the camera device, and the depth of field distance from the target position to the display terminal.

[0087] For example, see Figure 4-Figure 6 Several possible target angle recognition schematic diagrams based on different gesture motion directions are shown. Figure 4-Figure 6 Specifically, the target angle recognition and gesture tracking schematic diagram of the target palm in the up-down, left-right and front-back gesture motion directions are shown. The implementation methods for target angle recognition and gesture tracking in each gesture motion direction are the same. Figure 4 Take the following example to explain the relevant contents.

[0088] like Figure 4 When the target palm moves upward or downward, the present invention can collect at least two target frames at different times through a camera device, and then perform gesture recognition on at least two target frames at different times to obtain the following: Figure 4 The target angle between the target palm and the display terminal (specifically, the camera device in the display terminal) at different times is shown. Figure 4 Specifically, the target angles in different scenarios are shown when the gesture is turned on, when the target palm moves upward, and when the target palm moves downward. Figure 4 The medium depth of field distance specifically refers to the distance between the palm position of the target palm and the display terminal. The position distance specifically refers to the distance between the palm position of the target palm and the installation position of the camera device.

[0089] S303: Determine the gesture intention corresponding to the target palm according to the target angle.

[0090] After obtaining gesture information such as the gesture movement direction, target angles at different times, etc., the present invention can determine the user gesture corresponding to the target palm and its gesture intention according to the gesture information.

[0091] In a specific embodiment, the gesture information includes the target angle and the gesture movement direction at different times. The present invention can determine the user gesture and gesture intention corresponding to the target palm according to the target angle and the gesture movement direction at different times. Specifically, for example, the present invention can determine the user gesture and gesture intention corresponding to the target palm according to the change trend of the target angle and the gesture movement direction at different times. Among them, the user gesture and the gesture intention are in a one-to-one correspondence, and different user gestures correspond to different gesture intentions. And the gesture intention corresponding to each user gesture can be customized by the system, such as customized according to the user's operating habits or hobbies, which is not limited by the present invention.

[0092] For example, see Figure 4-Figure 6 Example shown. If the present invention determines that the gesture movement direction of the target palm is upward, and the target angle at different times gradually decreases with time, then the present invention can determine that the user gesture corresponding to the target palm is an upward gesture, and its gesture intention can be used to indicate upward movement, which can be similar to the upward direction key on the remote control. Similarly, if the present invention determines that the gesture movement direction is downward, and the target angle at different times gradually increases with time, then the present invention can determine that the user gesture corresponding to the target palm is a downward gesture, and its gesture intention is used to indicate downward movement. The gesture intention here can be similar to the downward direction key on the remote control.

[0093] If the present invention determines that the gesture movement direction of the target palm is to the left or to the right, and the target angle at different times does not change over time, then the present invention can directly determine the corresponding user gesture and gesture intention based on the gesture movement. Specifically, for example, when the gesture movement direction is to the left, the user gesture corresponding to the target palm may be a left move gesture, and its gesture intention can be used to indicate movement to the left, which can be similar to the left move direction key on the remote control. Conversely, when the gesture movement direction is to the right, the user gesture corresponding to the target palm may be a right move gesture, and its gesture intention can be used to indicate movement to the right, which can be similar to the right move direction key on the remote control.

[0094] If the present invention determines that the direction of the gesture movement of the target palm is forward, and the target angle at different times gradually increases with time, then the present invention can determine that the user gesture corresponding to the target palm is a forward gesture, and the gesture is intended to indicate the confirmation or entry of an option (such as any application icon, control or display interface option on the display screen), which can be similar to the confirmation key on the remote control. Similarly, if the present invention determines that the direction of the gesture movement of the target palm is backward, and the target angle at different times gradually decreases with time, then the present invention can determine that the user gesture corresponding to the target palm is a backward gesture, and the gesture is intended to indicate the exit of an option, which can be similar to the exit key or return key on the remote control.

[0095] S304: Control the display terminal according to the gesture intention.

[0096] After determining the gesture intention, the present invention can perform corresponding control processing on the display terminal according to the gesture intention. For example, if the gesture intention is used to indicate exiting the application interface currently displayed by the display terminal, the present invention exits the application interface currently displayed by the display terminal according to the indication of the gesture intention.

[0097] Some optional embodiments of the present invention are described below.

[0098] In some optional embodiments, before the target frame of the target palm is collected in step S301, the present invention may also detect whether the gesture control process of the target palm is turned on, so as to continue the step of collecting the target palm in step S301 of the present invention. The present invention does not limit the specific implementation method of the gesture control process of detecting whether the target palm is turned on. For example, the palm image of the target palm may be collected to analyze whether the target palm has stayed or moved a preset distance for detection. The present invention exemplarily gives two specific implementation methods below, but does not constitute a limitation.

[0099] In a specific embodiment, the present invention can use a camera device to collect multiple initial frames of the target palm at different times, and perform image recognition on the multiple initial frames to determine whether the target palm has moved a preset distance. If so, the entire gesture control process of the target palm is determined to be started; otherwise, the process can be terminated. The preset distance is a system custom setting, for example, it is set according to the actual needs of the target user where the target palm is located. For example, if the target user is an adult, the preset distance can be set to 5cm, otherwise the target user is a minor, and the preset distance can be set to 2cm, etc., which is not limited by the present invention. When the camera collects the target frame of the target palm, the person in front of the display terminal is identified at the same time. Through the collected person information, the age of the person in front of the current display terminal is obtained by face recognition or body analysis. If it is identified as an adult, the parameters are adjusted to the parameters corresponding to the adult, such as the preset distance is adjusted to 5cm; similarly, if it is identified as a minor, the parameters are adjusted to the parameters corresponding to the minor, such as the preset distance is adjusted to 3cm, so as to meet the needs of different operators.

[0100] In another specific embodiment, the present invention can also use a camera device to collect multiple initial frames of the target palm at different times. Then, image recognition is performed on the multiple initial frames to determine whether the target palm has stayed at the same position, and optionally, it can also be synchronously determined whether the target palm has performed a preset gesture start operation to start the entire gesture control process.

[0101] Among them, the gesture start operation is pre-customized by the system, such as a palm opening operation, a palm closing operation or other operations used to indicate the start of a gesture control process, etc., which are not limited in the present invention. For the convenience of describing the present invention, the gesture start operation is taken as an example of a palm opening operation to illustrate the relevant content, but it does not constitute a limitation. The present invention does not limit the specific implementation method of the image recognition. For example, the present invention can use a pre-configured image recognition algorithm such as local feature extraction to perform image recognition on multiple initial frames to determine whether the target palm has stayed in the same position. The second dwell time corresponding to the stay here is also not limited in the present invention. For example, the second dwell time can be 2s.

[0102] When the present invention determines that the target palm has been opened and stayed at the same position, it can optionally be combined with whether the second stay time of the stay has reached a preset time. If so, the present invention can determine that the display terminal has turned on the gesture recognition function, or determine that the target palm has turned on gesture recognition, and then continue the step of collecting the target frame of the target palm in step S301. In this case, the target frame is specifically a frame image generated when the target palm moves. On the contrary, when the present invention determines that the target palm has not been opened or stayed at the same position, or the target palm has been opened and stayed at the same position, but the stay time does not exceed the preset time (such as 2s), the present invention can determine that the display terminal has not turned on the gesture recognition function, or determine that the target palm has not turned on gesture recognition, and the process can be ended.

[0103] In some optional embodiments, if there are multiple users' palms performing gesture operations / controls during image acquisition, then each of the target frames acquired in step S301 includes user gestures corresponding to the palms of multiple users. Accordingly, when the present invention performs gesture recognition on each of the target frames, the present invention may first perform image recognition on the palms of multiple users in each of the target frames, so as to first select the target palm of the target user that is closest to the camera device from the palms of the multiple users, and then analyze the gesture information, user gesture and gesture intention of the target palm of the target user. For a specific introduction to the image recognition, the gesture information, the user gesture and the gesture intention, please refer to the relevant introduction in the aforementioned embodiments, which will not be repeated here.

[0104] In some optional embodiments, if there are multiple users' palms performing gesture operations / controls during image acquisition, and the present invention detects that the palms of multiple users are open and stay, it can be determined that the palms of multiple users have turned on gesture recognition. Correspondingly, each of the target frames acquired in step S301 of the present invention also includes the palms of multiple users. When performing gesture recognition on each of the target frames, the present invention can first select the target palm of the target user that is closest to the camera device from the palms of multiple users according to the relevant introduction in the above embodiments, and then analyze the gesture information, user gesture and gesture intention of the target palm of the target user.

[0105] In some optional embodiments, in step S303, after the present invention performs gesture recognition on at least two of the target frames, if it is detected / determined that the target palm has stayed in the direction of the gesture movement, the present invention can determine that the target palm has currently completed a gesture control. The present invention does not limit the first dwell time corresponding to the stay, for example, the first dwell time can be 1 second (s), 2s, etc., which can be set according to the actual needs of the user. For example, assuming that the first dwell time is 1s, the target palm stays in the direction of the gesture movement for 1s, which means that the target palm has completed a gesture control.

[0106] Correspondingly, optionally, if at least two of the target frames collected at different moments in step S301 are frame images generated at different moments in a gesture control, then the target angle obtained in step S302 is also the angle between the target palm and the display terminal at different moments in the gesture control. Correspondingly, in step S303, the present invention also determines the gesture intention corresponding to the target palm in the gesture control based on the target angle and the gesture movement direction at different moments in the gesture control. In other words, assuming that the target frame collected in step S301 is a frame image collected at different moments in a gesture control, steps S301-S304 are the terminal control implementation process in the gesture control.

[0107] In some optional embodiments, the present invention can obtain a control parameter, which is a step parameter set by the system, and can be used to indicate the number of gesture controls included in a round of gesture control by the target palm. The number of gesture controls can be set according to the actual needs of the system, and the present invention does not limit it. For example, the number of gesture controls indicated by the control parameter can be 4, indicating that when the target palm performs a round of gesture control, it needs to stay 4 times and complete 4 gesture controls.

[0108] Further, the present invention can determine the gesture intention corresponding to each gesture control in the number of gesture controls according to the implementation process of one gesture control shown in steps S301-S304, and control the display terminal to complete a round of gesture control for the display terminal.

[0109] For example, see Figure 7 and Figure 8 Figure 2 shows a schematic diagram of gesture control under two different control parameters. Figure 7 Schematic diagram of gesture control when the control parameter is 1. Figure 7In the example, the display interface of the display terminal has function controls for functions 1 to 6 arranged along the horizontal axis, and function controls for functions 1, 7 to 10 arranged along the vertical axis. Assume that in this example, the target user starts the gesture from function 1 and wants to move to function 6 through gesture control, and the target user's target palm is recorded as one round of gesture control from being raised to being dropped. Then, according to the implementation process of the above steps S301-S304, this embodiment requires 6 rounds of gesture control to move the display focus of function 1 to function 6, thereby completing the movement from function 1 to function 6. The focus movement of each round of gesture control is as follows. Figure 7 As shown, the display focus of one time / one round of gesture control is shown in the figure.

[0110] like Figure 8 FIG. 4 shows a schematic diagram of gesture control when the control parameter is 4. Figure 8 The display interface shown is also equipped with function controls from function 1 to function 10. Assume that in this example, the target user starts the gesture from function 1 and wants to move to function 6 through gesture control. Since the control parameter in this example is 4, it means that 4 gesture controls are required in one round of gesture control, so 2 rounds of gesture control are required in this example. Similarly, the target user's target palm is recorded as one round of gesture control from being raised to being dropped. In this example, the 4 gesture controls in the first round of gesture control are first performed according to the implementation process of the above steps S301-S304 to move the display focus of function 1 to function 5. Then start the second round of gesture control, and perform a gesture control according to the implementation process of steps S301-S304 to move the display focus of function 5 to function 6, thereby completing the movement from function 1 to function 6.

[0111] In some optional embodiments, the present invention may obtain a control parameter, which is a step length parameter customized by the system, and may be used to indicate the step length of a gesture when the target palm completes a gesture control. The gesture step length may specifically be, for example, a moving distance, the number of application icons, the number of function controls, the number of user options, or other system customized step length parameters. The gesture step length may be specifically set according to the actual needs of the system, and the present invention does not limit it. For example, the gesture step length indicated by the control parameter may be 4, indicating that the target palm may jump and move 4 steps when performing a gesture control.

[0112] Accordingly, in step S301, the present invention can collect at least two target frames of the target palm at different times in a gesture control according to the gesture step length. Similarly, the present invention can complete a gesture control of the display terminal according to the implementation process shown in steps S301-S304.

[0113] For example, see Fig. 9 Another gesture control schematic diagram is shown when the control parameter is 4. Fig. 9 The display interface shown is also deployed with function controls from function 1 to function 10. Assume that in this example, the target user starts the gesture from function 1 and wants to move to function 6 through gesture control. Since the control parameter in this example is 4, it means that the distance of 4 function controls can be moved in one gesture control, so two gesture controls are required in this example. In this example, the target palm of the target user can be recorded as one gesture control from being raised to falling, or there is one stop during the movement. Correspondingly, in this example, the first gesture control can be performed first according to the implementation process of the above steps S301-S304, and the display focus of function 1 can be moved to function 5. Then start the second round of gesture control, and perform the second gesture control according to the implementation process of steps S301-S304. Since there are 6 function controls deployed on the horizontal axis of the display interface, the display focus of function 5 can be moved to function 6 in the second gesture control, thereby completing the movement from function 1 to function 6.

[0114] In some optional embodiments, the control parameter may be a step parameter set by the system, and the parameter range may not be limited in the present invention, and it may be customized according to the actual needs of the system. The present invention also does not limit the implementation method of obtaining the control parameter. For example, in a specific implementation, the present invention may obtain the moving distance of the target palm during each gesture control, and then determine the control parameter according to the moving distance, that is, determine the step parameter indicated by the control parameter. Specifically, the present invention may calculate the control parameter according to the moving distance and the preset step distance. Among them, the acquisition method of the moving distance may refer to the relevant introduction in the aforementioned step S302, which will not be repeated here. The preset step distance is a system-defined setting, which is related to the target user where the target palm is located. It is understandable that due to individual differences in target users, for example, the distance that adults and minors move the target palm each time is limited, and the distance size also has a large difference. Therefore, the present invention may set the corresponding preset step distance according to the actual needs of different target users. For example, for adults, the preset step distance may be 5cm; for minors, the preset step distance may be 2cm, and so on.

[0115] For example, in another specific embodiment, the present invention may display an interactive interface, and the interactive interface is used to display parameter options. The user can customize the control parameters according to actual needs or personal habits in the parameter options displayed on the interactive interface. For example, the parameter options in the interface can provide dynamic values ​​from 1 to 5, and then the user can select the parameter values ​​required by the user according to actual needs as the control parameters. Accordingly, after detecting the input operation in the interactive interface, the present invention can obtain the control parameters input by the user.

[0116] For example, in another specific embodiment, the present invention can obtain the target distance between the target user where the target palm is located and the display terminal, and then determine the control parameter according to the gesture movement speed and the target distance. The present invention does not limit the method for determining the control parameter. Specifically, for example, the present invention can further obtain the user height of the target user and the camera height of the camera device. Among them, the user height of the target user can be obtained by the present invention through image recognition of the frame image including the target user. The specific implementation method of the image recognition can be referred to the relevant introduction in the aforementioned embodiment and will not be repeated here. The camera height of the camera device refers to the installation height of the camera device relative to the ground, which can be a pre-customized setting of the system, and the present invention does not limit it.

[0117] Furthermore, the present invention can calculate the control parameter according to the user height, the camera height, the gesture movement speed and the target distance. Specifically, for example, formula (1) shows a possible calculation formula for the control parameter.

[0118]

[0119] Wherein, represents a rounding operation, Y is the control parameter, a is a user-defined coefficient, V is the gesture movement speed, X1 is the user height of the target user, X2 is the camera height, and H is the target distance.

[0120] In practical applications, a is an adjustment coefficient set by the system for adjusting the control parameter, and its coefficient value can be, for example, or The gesture movement speed V may also be within a speed range pre-defined by the system, which can be set according to the actual needs of the system, and the present invention does not limit or elaborate on this.

[0121] It should be noted that the several control parameter acquisition implementation methods shown above in the present invention can be implemented separately or in combination with any one or more of the implementation methods, and the present invention is not limited thereto.

[0122] By implementing the embodiments of the present invention, the present invention responds to the image acquisition instruction, acquires the target frame of the target palm; performs gesture recognition on the target frame to obtain the target angle between the target palm and the display terminal; determines the gesture intention corresponding to the target palm according to the target angle; and controls the display terminal according to the gesture intention. In the above scheme, the present invention identifies and determines the gesture intention corresponding to the target palm according to the angle between the target palm and the display terminal, and then performs corresponding intention control on the display terminal according to the gesture intention, thereby achieving convenient and efficient control of the display terminal, and also solves the technical problems in the prior art that the display terminal cannot be controlled by a remote control or close-range touch method, affecting the user experience, etc.

[0123] Based on the same inventive concept, another embodiment of the present invention provides a device and a display terminal corresponding to the gesture control method described in the embodiment of the present invention.

[0124] See also Fig.10 , is a schematic diagram of the structure of a gesture control device provided by an embodiment of the present invention. Fig.10 The gesture control device 100 shown includes: a collection module 1001, a recognition module 1002, a determination module 1003 and a control module 1004, wherein:

[0125] The acquisition module 1001 is used to acquire a target frame of a target palm in response to an image acquisition instruction;

[0126] The recognition module 1002 is used to perform gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal;

[0127] The determination module 1003 is used to determine the gesture intention corresponding to the target palm according to the target angle;

[0128] The control module 1004 is used to control the display terminal according to the gesture intention.

[0129] Optionally, the identification module 1002 is specifically configured to:

[0130] Performing depth calculation on the target frame to obtain a depth of field distance between the target palm and the display terminal;

[0131] A target angle between the target palm and the display terminal is calculated according to the depth of field distance.

[0132] Optionally, before performing depth calculation on the target frame to obtain the depth distance between the target palm and the display terminal, the recognition module 1002 is further configured to perform gesture recognition on the target frame to obtain the palm position of the target palm in the current palm shape;

[0133] The recognition module 1002 is specifically configured to perform depth calculation on the palm position in the current palm shape in the target frame to obtain a depth of field distance from the palm position of the target palm to the display terminal.

[0134] Optionally, the acquisition module 1001 is specifically used to acquire at least two target frames of the target palm at different times;

[0135] The recognition module 1002 is specifically used to perform gesture recognition on at least two target frames at different times to obtain corresponding gesture information; wherein the gesture information includes a target angle between the target palm and the display terminal at different times and a gesture movement direction corresponding to the target palm;

[0136] The determination module 1003 is specifically configured to determine the gesture intention corresponding to the target palm according to the target angle and the gesture movement direction at different moments.

[0137] Optionally, the determination module 1003 is further configured to determine that the target palm completes a gesture control when it is detected that the target palm stays in the direction of the gesture movement;

[0138] If at least two of the target frames at different times are frame images generated in the gesture control, then the target angle is the angle between the target palm and the display terminal at different times in the gesture control, and the determination module 1003 is specifically used to determine the gesture intention corresponding to the gesture control according to the target angle and the gesture movement direction at different times in the gesture control.

[0139] Optionally, the device further includes an acquisition module 1005, wherein:

[0140] The acquisition module 1005 is used to acquire a control parameter, where the control parameter is used to indicate the number of gesture controls of the target palm in one round of gesture control;

[0141] The control module 1004 is further configured to control the display terminal according to the gesture intention corresponding to each gesture control in the number of gesture controls.

[0142] Optionally, the acquisition module 1005 is further used to acquire a control parameter, where the control parameter is used to indicate a gesture step length when the target palm completes a gesture control;

[0143] The acquisition module 1001 is specifically configured to acquire at least two target frames of the target palm at different times in the gesture control according to the gesture step length.

[0144] Optionally, the gesture information further includes gesture movement speed, and the acquisition module 1005 is specifically used to:

[0145] Determining the control parameter according to the gesture movement speed and the target distance;

[0146] The target distance is the distance between the target user where the target palm is located and the display terminal.

[0147] Optionally, the acquisition module 1005 is further specifically configured to:

[0148] Acquire the user height of the target user and the camera height of the camera device in the display terminal;

[0149] The control parameter is determined according to the user height, the camera height, the gesture movement speed and the target distance.

[0150] Optionally, the acquisition module 1001 is further used to acquire multiple initial frames of the target palm at different times;

[0151] The recognition module 1002 is further used to perform image recognition on the multiple initial frames to determine whether the target palm stays at the same position;

[0152] If yes, continue to execute the step of collecting the target frame of the target palm, wherein the target frame is a frame image generated when the target palm moves.

[0153] Optionally, the target frame includes palms of multiple users, and the recognition module 1002 is further used for:

[0154] Performing image recognition on the palms of the multiple users in the target frame to select a target palm of the target user that is closest to the camera device from the palms of the multiple users;

[0155] Performing gesture recognition on a target palm of the target user in the target frame to obtain a target angle between the target palm and the display terminal.

[0156] Please refer to 11, which is a schematic diagram of the structure of a display terminal provided by an embodiment of the present invention. Fig.11The display terminal 110 shown includes: at least one processor 1101, a communication interface 1102, a user interface 1103 and a memory 1104. The processor 1101, the communication interface 1102, the user interface 1103 and the memory 1104 can be connected via a bus or other means. The embodiment of the present invention takes the connection via a bus 1105 as an example.

[0157] The processor 1101 may be a general-purpose processor, such as a central processing unit (CPU).

[0158] The communication interface 1102 may be a wired interface (eg, an Ethernet interface) or a wireless interface (eg, a cellular network interface or a wireless local area network interface) for communicating with other terminals or websites. In the embodiment of the present invention, the communication interface 1102 is specifically used to obtain frame images.

[0159] The user interface 1103 may be, for example, a touch panel, including a touch screen and a touch screen, for detecting operation instructions on the touch panel. The user interface 1103 may also be a physical button or a mouse. The user interface 1103 may also be a display screen for outputting and displaying images or data. The size of the display screen is larger than the preset size, and in this case, the display terminal may also be referred to as a large-screen display terminal.

[0160] The memory 1104 may include a volatile memory, such as a random access memory (RAM); the memory may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 1104 may also include a combination of the above-mentioned types of memory. The memory 1108 is used to store a set of program codes, and the processor 1101 is used to call the program codes stored in the memory 1104 to perform the following operations:

[0161] In response to the image acquisition instruction, acquiring a target frame of the target palm;

[0162] Performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal;

[0163] Determining the gesture intention corresponding to the target palm according to the target angle;

[0164] The display terminal is controlled according to the gesture intention.

[0165] Optionally, performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal includes:

[0166] Performing depth calculation on the target frame to obtain a depth of field distance between the target palm and the display terminal;

[0167] A target angle between the target palm and the display terminal is calculated according to the depth of field distance.

[0168] Optionally, before performing depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal, the processor 1101 is further configured to:

[0169] Performing gesture recognition on the target frame to obtain the palm position of the target palm in the current palm shape;

[0170] The performing depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal comprises:

[0171] A depth calculation is performed on the palm position in the current palm shape in the target frame to obtain a depth of field distance from the palm position of the target palm to the display terminal.

[0172] Optionally, the capturing of the target frame of the target palm includes: capturing at least two target frames of the target palm at different times;

[0173] The performing gesture recognition on the target frame to obtain the target angle between the target palm and the display terminal comprises: performing gesture recognition on at least two target frames at different times to obtain corresponding gesture information; wherein the gesture information comprises the target angle between the target palm and the display terminal at different times and the gesture movement direction corresponding to the target palm;

[0174] Determining the gesture intention corresponding to the target palm according to the target angle includes: determining the gesture intention corresponding to the target palm according to the target angle and the gesture movement direction at different moments.

[0175] Optionally, the processor 1101 is further configured to:

[0176] When it is detected that the target palm stays in the direction of the gesture movement, determining that the target palm completes one gesture control;

[0177] If at least two of the target frames at different times are frame images generated in the one gesture control, the target angle is the angle between the target palm and the display terminal at different times in the one gesture control, and determining the gesture intention corresponding to the target palm according to the target angle at different times and the gesture movement direction includes:

[0178] The gesture intention corresponding to the single gesture control is determined according to the target angle and the gesture movement direction at different moments in the single gesture control.

[0179] Optionally, the processor 1101 is further configured to:

[0180] Acquire a control parameter, where the control parameter is used to indicate the number of gesture controls of the target palm in a round of gesture control;

[0181] The display terminal is controlled according to the gesture intention determined corresponding to each gesture control in the number of gesture controls.

[0182] Optionally, before acquiring the target frame of the target palm, the processor 1101 is further configured to:

[0183] Acquire a control parameter, where the control parameter is used to indicate a gesture step length when the target palm completes a gesture control;

[0184] The target frame for collecting the target palm includes:

[0185] At least two target frames of the target palm at different times in the gesture control are collected according to the gesture step length.

[0186] Optionally, the gesture information further includes gesture movement speed, and the acquiring control parameter includes:

[0187] Determining the control parameter according to the gesture movement speed and the target distance;

[0188] The target distance is the distance between the target user where the target palm is located and the display terminal.

[0189] Optionally, before determining the control parameter according to the gesture movement speed and the target distance, the processor 1101 is further configured to:

[0190] Acquire the user height of the target user and the camera height of the camera device in the display terminal;

[0191] The determining the control parameter according to the gesture movement speed and the target distance includes:

[0192] The control parameter is determined according to the user height, the camera height, the gesture movement speed and the target distance.

[0193] Optionally, before acquiring the target frame of the target palm, the method further includes:

[0194] Collecting multiple initial frames of the target palm at different times;

[0195] Performing image recognition on a plurality of the initial frames to determine whether the target palm stays at the same position;

[0196] If yes, continue to execute the step of collecting the target frame of the target palm, wherein the target frame is a frame image generated when the target palm moves.

[0197] Optionally, the target frame includes palms of multiple users, and performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal includes:

[0198] Performing image recognition on the palms of the multiple users in the target frame to select a target palm of the target user that is closest to the camera device from the multiple users;

[0199] Performing gesture recognition on a target palm of the target user in the target frame to obtain a target angle between the target palm and the display terminal.

[0200] Since the display terminal introduced in this embodiment is a display terminal used to implement the method for gesture control in the embodiment of the present invention, based on the method for gesture control introduced in the embodiment of the present invention, a person skilled in the art can understand the specific implementation of the display terminal of the embodiment and its various variations, so how the display terminal implements the method in the embodiment of the present invention is not described in detail here. As long as a display terminal used by a person skilled in the art to implement the method for gesture control in the embodiment of the present invention is used, it belongs to the scope of protection of the present invention.

[0201] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: the present invention collects a target frame of the target palm in response to an image acquisition instruction; performs gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal; determines the gesture intention corresponding to the target palm according to the target angle; and controls the display terminal according to the gesture intention. In the above scheme, the present invention identifies and determines the gesture intention corresponding to the target palm according to the angle between the target palm and the display terminal, and then performs corresponding intention control on the display terminal according to the gesture intention, thereby achieving convenient and efficient control of the display terminal, and also solves the technical problems in the prior art that the display terminal cannot be controlled by a remote control or close-range touch method, affecting the user experience, and so on.

[0202] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0203] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0204] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0205] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0206] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0207] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A gesture control method, characterized in that: Applied in a display terminal, the method comprises: In response to the image acquisition instruction, acquiring a target frame of the target palm; Performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal; Determining the gesture intention corresponding to the target palm according to the target angle; Controlling the display terminal according to the gesture intention; The performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal comprises: Performing depth calculation on the target frame to obtain a depth of field distance between the target palm and the display terminal; Calculating a target angle between the target palm and the display terminal according to the depth of field distance; Before performing depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal, the method further includes: Performing gesture recognition on the target frame to obtain the palm position of the target palm in the current palm shape; The performing depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal comprises: A depth calculation is performed on the palm position in the current palm shape in the target frame to obtain a depth of field distance from the palm position of the target palm to the display terminal.

2. The method according to claim 1, characterized in that The capturing of the target frame of the target palm comprises: capturing at least two target frames of the target palm at different times; The performing gesture recognition on the target frame to obtain the target angle between the target palm and the display terminal comprises: performing gesture recognition on at least two target frames at different times to obtain corresponding gesture information; wherein the gesture information comprises the target angle between the target palm and the display terminal at different times and the gesture movement direction corresponding to the target palm; Determining the gesture intention corresponding to the target palm according to the target angle includes: determining the gesture intention corresponding to the target palm according to the target angle and the gesture movement direction at different moments.

3. The method according to claim 2, characterized in that The method further comprises: When it is detected that the target palm stays in the direction of the gesture movement, determining that the target palm completes one gesture control; If at least two of the target frames at different times are frame images generated in the one gesture control, the target angle is the angle between the target palm and the display terminal at different times in the one gesture control, and determining the gesture intention corresponding to the target palm according to the target angle at different times and the gesture movement direction includes: The gesture intention corresponding to the single gesture control is determined according to the target angle and the gesture movement direction at different moments in the single gesture control.

4. The method according to claim 3, characterized in that The method further comprises: Acquire a control parameter, where the control parameter is used to indicate the number of gesture controls performed by the target palm in one round of gesture control; The display terminal is controlled according to the gesture intention determined corresponding to each gesture control in the number of gesture controls.

5. The method according to claim 3, characterized in that: Before acquiring the target frame of the target palm, the method further includes: Acquire a control parameter, where the control parameter is used to indicate a gesture step length when the target palm completes a gesture control; The target frame for collecting the target palm includes: At least two target frames of the target palm at different times in the gesture control are collected according to the gesture step length.

6. The method according to claim 4 or 5, characterized in that: The gesture information also includes gesture movement speed, and the acquisition control parameters include: Determining the control parameter according to the gesture movement speed and the target distance; The target distance is the distance between the target user where the target palm is located and the display terminal.

7. The method according to claim 6, characterized in that Before determining the control parameter according to the gesture movement speed and the target distance, the method further includes: Acquire the user height of the target user and the camera height of the camera device in the display terminal; The determining the control parameter according to the gesture movement speed and the target distance includes: The control parameter is determined according to the user height, the camera height, the gesture movement speed and the target distance.

8. The method according to any one of claims 1 to 5, characterized in that Before acquiring the target frame of the target palm, the method further includes: Collecting multiple initial frames of the target palm at different times; Performing image recognition on a plurality of the initial frames to determine whether the target palm stays at the same position; If yes, continue to execute the step of collecting the target frame of the target palm, wherein the target frame is a frame image generated when the target palm moves.

9. The method according to any one of claims 1 to 5, characterized in that The target frame includes palms of multiple users, and performing gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal includes: Performing image recognition on the palms of the multiple users in the target frame to select a target palm of the target user that is closest to the camera device from the palms of the multiple users; Performing gesture recognition on a target palm of the target user in the target frame to obtain a target angle between the target palm and the display terminal.

10. A gesture control device, characterized in that: Applied in a display terminal, the device comprises: a collection module, an identification module, a determination module and a control module, wherein: The acquisition module is used to acquire a target frame of a target palm in response to an image acquisition instruction; The recognition module is used to perform gesture recognition on the target frame to obtain a target angle between the target palm and the display terminal; The recognition module is specifically used to perform depth calculation on the target frame to obtain the depth of field distance between the target palm and the display terminal; Calculating a target angle between the target palm and the display terminal according to the depth of field distance; Before performing depth calculation on the target frame to obtain the depth distance between the target palm and the display terminal, the recognition module is further used to perform gesture recognition on the target frame to obtain the palm position of the target palm in the current palm shape; The recognition module is further used to perform depth calculation on the palm position in the current palm shape in the target frame to obtain a depth of field distance from the palm position of the target palm to the display terminal; The determination module is used to determine the gesture intention corresponding to the target palm according to the target angle; The control module is used to control the display terminal according to the gesture intention.

11. A display terminal, characterized in that: include: Processors, memories, communication interfaces and buses; The processor, the memory and the communication interface are connected via the bus and communicate with each other; The memory stores executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the gesture control method as described in any one of claims 1 to 9.

12. The display terminal according to claim 11, characterized in that: The display terminal also includes a display screen, and the size of the display screen is larger than a preset size.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, and when the program is run on the display terminal, the gesture control method as described in any one of claims 1 to 9 is executed.

Images