Control method and equipment of binocular panel with expression interaction function

Abstract

The embodiment of the invention discloses a control method and device of a binocular panel with an expression interaction function, the method is applied to the binocular panel, the binocular panel comprises a binocular camera, a first display panel used for displaying an eyebrow image and a second display panel used for displaying a mouth image, the first display panel is arranged above the binocular camera, and the second display panel is arranged above the binocular camera. The method comprises the following steps: acquiring field image information shot by the binocular camera, calibrating a human face in the field image information to obtain human face calibration data, calculating a human face position of the human face in a physical space based on the human face calibration data and a binocular ranging algorithm, and displaying the human face position in the physical space. And generating eyebrow expressions and mouth expressions in corresponding orientations according to the face position, and displaying the eyebrow expressions and the mouth expressions through the first display panel and the second display panel respectively. According to the scheme, a brand new intelligent equipment interaction mode is realized, and the advantages of the binocular camera are exerted, so that the intelligent equipment with the panel has richer expression interaction functions.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart devices, and in particular to a control method and device for a binocular panel with an expression interaction function. Background Art

[0002] With the increasing use of smart devices, the appearance and interactive capabilities of smart devices are becoming increasingly important. Smart devices that are interesting, consistent, and technologically advanced are more popular with users.

[0003] Taking intelligent interactive robots as an example, the expressions of current intelligent interactive robots are mostly based on full-screen display, that is, one screen displays eyebrows, eyes, nose, mouth, blush and other expression images to achieve the purpose of machine expression interaction. Cameras are important sensors. When monocular cameras or binocular cameras are set up, in order to achieve consistency and coordination of appearance, they will try their best to make the cameras more concealed, which often makes the products lose their sense of harmony. In actual use, since intelligent devices are required to operate normally in the dark or low-light environment, cameras with large lenses are often used, which increases the difficulty of concealment. In addition, when using binocular cameras as face recognition devices, their two lenses are often close together, and no 3D detection information is obtained, and the unique advantages of binocular cameras are not brought into play. In addition, devices such as ranging modules often require holes to work properly. As the facial design of intelligent robots, any holes will hinder the consistency of the robot's face and affect the appearance of the device. Summary of the invention

[0004] The embodiments of the present invention provide a control method and device for a binocular panel with an expression interaction function, so as to solve the expression interaction of smart devices centered on a binocular camera, realize a new interaction mode of smart devices, and give full play to the advantages of the binocular camera, so that smart devices with panels such as smart terminals, panel machines, smart speakers, smart access control machines, payment devices, electronic ID card devices, smart home appliances, etc. can bring richer expression interaction functions.

[0005] In a first aspect, an embodiment of the present invention provides a method for controlling a binocular panel with an expression interaction function, comprising:

[0006] Acquire the scene image information captured by the binocular camera, and calibrate the face in the scene image information to obtain face calibration data;

[0007] Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm;

[0008] Eyebrow expressions and mouth expressions with corresponding orientations are generated according to the face position, and are displayed through the first display panel and the second display panel respectively.

[0009] Optionally, before generating the corresponding eyebrow expression and mouth expression according to the face position, it further includes:

[0010] Setting and storing the preset eyebrow expressions and preset mouth expressions corresponding to different orientations;

[0011] Correspondingly, generating the corresponding eyebrow expression and mouth expression according to the face position includes:

[0012] Determining the orientation direction according to the face position, where the orientation direction includes at least one of the leftward direction, rightward direction, upward direction, and downward direction;

[0013] Obtaining the preset eyebrow expression and preset mouth expression corresponding to the orientation direction stored and generating them.

[0014] Optionally, generating the corresponding eyebrow expression and mouth expression according to the face position includes:

[0015] Determining the eyebrow expression parameters and mouth expression parameters corresponding to the orientation according to the face position, where the eyebrow expression parameters include the eyebrow display position and the eyebrow display size, and the mouth expression parameters include the mouth display position and the mouth display size. Among them, different orientation directions correspond to different eyebrow display positions, eyebrow display sizes, mouth display positions, and mouth display sizes;

[0016] Generating the corresponding eyebrow expression based on the eyebrow display position and the eyebrow display size, and generating the corresponding mouth expression based on the mouth display position and the mouth display size.

[0017] Optionally, generating the corresponding eyebrow expression based on the eyebrow display position and the eyebrow display size, and generating the corresponding mouth expression based on the mouth display position and the mouth display size includes:

[0018] Displacing the preset eyebrow reference position according to the eyebrow display position, and scaling the preset eyebrow reference size according to the eyebrow display size to generate the corresponding eyebrow expression;

[0019] Displacing the preset mouth reference position according to the mouth display position, and scaling the preset mouth reference size according to the mouth display size to generate the corresponding mouth expression.

[0020] Optionally, generating the corresponding eyebrow expression and mouth expression according to the face position includes:

[0021] Determining the face displacement information according to the face positions at multiple different time points;

[0022] Generate eyebrow expressions and mouth expressions corresponding to the orientation based on the face displacement information.

[0023] Optionally, before obtaining the on-site image information captured by the binocular camera, it further includes:

[0024] Obtain the images captured in real time by the binocular camera;

[0025] When it is recognized that the image contains a human face, control the binocular camera to focus and capture the on-site image information after the focusing process.

[0026] Optionally, when obtaining the on-site image information captured by the binocular camera and calibrating the human face in the on-site image information to obtain the face calibration data, it includes:

[0027] Obtain the first on-site image captured by any one of the binocular cameras;

[0028] When the first on-site image contains a human face, turn on the other one of the binocular cameras to capture a second on-site image;

[0029] When the second on-site image synchronously contains a human face, calibrate the human faces in the first on-site image and the second on-site image to obtain the face calibration data.

[0030] Optionally, after obtaining the on-site image information captured by the binocular camera, it further includes:

[0031] Perform face recognition on the on-site image information to obtain the number of human faces;

[0032] Control the playback of advertisement information corresponding to the number of human faces according to the number of human faces.

[0033] Optionally, after obtaining the on-site image information captured by the binocular camera, it further includes:

[0034] When no human face is recognized in the on-site image information within a preset duration, generate the pre-set eyebrow expressions and mouth expressions corresponding to the situation of no detected human face, and display them through the first display panel and the second display panel respectively.

[0035] Optionally, after displaying through the first display panel and the second display panel respectively, it further includes:

[0036] Obtain the detected external control instruction;

[0037] When the currently executed instruction meets the end condition or the interruption condition, execute the external control instruction.

[0038] Optionally, after the display is respectively performed by the first display panel and the second display panel, the method further includes:

[0039] When it is determined that the current displayed eyebrow expression and mouth expression meet the end condition or the interruption condition, after re-acquiring the on-site image information and determining the updated face position, generate the eyebrow expression and mouth expression with corresponding orientations according to the updated face position, and respectively display them through the first display panel and the second display panel.

[0040] In a second aspect, an embodiment of the present invention further provides a control device for a binocular panel with an expression interaction function, including:

[0041] An acquisition module, configured to acquire on-site image information captured by the binocular camera;

[0042] A face detection module, configured to calibrate the face in the on-site image information to obtain face calibration data;

[0043] A binocular ranging module, configured to calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm;

[0044] An expression control module, configured to generate an eyebrow expression and a mouth expression with corresponding orientations according to the face position;

[0045] A display output module, configured to display the eyebrow expression through the first display panel and display the mouth expression through the second display panel.

[0046] In a third aspect, an embodiment of the present application further provides a control device for a binocular panel with an expression interaction function, and the device includes:

[0047] One or more processors;

[0048] A storage device, configured to store one or more programs,

[0049] When the one or more programs are executed by the one or more processors, the one or more processors implement the control method for a binocular panel with an expression interaction function according to the embodiments of the present application.

[0050] In a fourth aspect, the present invention provides a storage medium including computer-executable instructions, and the computer-executable instructions are used to execute the control method for a binocular panel with an expression interaction function as described in any one of the above when executed by a computer processor.

[0051] In this solution, the on-site image information captured by the binocular camera is obtained, the faces in the on-site image information are calibrated to obtain face calibration data, the face positions in the physical space are calculated based on the face calibration data and the binocular ranging algorithm, and the eyebrow expressions and mouth expressions in the corresponding orientations are generated according to the face positions and displayed through the first display panel and the second display panel respectively. By using the binocular camera as the eyes of the robot and cooperating with the eyebrow screen and the mouth screen to display the expressions of the robot, this solution solves the expression interaction of intelligent devices centered on the binocular camera, realizes a new intelligent device interaction mode, and gives full play to the advantages of the binocular camera, enabling intelligent devices with panels such as intelligent terminal machines, panel machines, smart speakers, intelligent access control machines, payment devices, electronic ID card devices, and smart home appliances to have richer expression interaction functions. Brief Description of the Drawings

[0052] Figure 1 It is a schematic diagram of the external structure of a binocular panel device with an expression interaction function provided by an embodiment of the present invention;

[0053] Figure 2 It is a flowchart of a control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0054] Figure 3 It is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0055] Figure 4 It is a schematic diagram of the expressions of a binocular panel device with an expression interaction function and a left-facing direction provided by an embodiment of the present invention;

[0056] Figure 5 It is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0057] Figure 6 It is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0058] Figure 7 It is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0059] Figure 8 It is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0060] Figure 9 It is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0061] Figure 10 The block diagram of the module structure of a control system for a binocular panel with an expression interaction function provided by an embodiment of the present application;

[0062] Figure 11 The structural schematic diagram of a control device for a binocular panel with an expression interaction function provided by an embodiment of the present application. Specific embodiments

[0063] The following further describes the embodiments of the present invention in detail with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, rather than limiting the embodiments of the present invention. Additionally, it should be noted that for the sake of description, only parts related to the embodiments of the present invention are shown in the drawings, rather than all the structures.

[0064] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character "or" generally represents an "or" relationship between the associated objects before and after.

[0065] A control method for a binocular panel with an expression interaction function provided by an embodiment of the present application is applied to a binocular panel. The binocular panel includes a binocular camera, a first display panel for displaying eyebrow images, and a second display panel for displaying mouth images. The first display panel is located above the binocular camera, and the second display panel is located below the binocular camera, as Figure 1 shown, Figure 1 The external structural schematic diagram of a binocular panel device with an expression interaction function provided by an embodiment of the present invention. An exemplary schematic diagram of a binocular panel device is given. Among them, components 201 and 202 are the first display panels for displaying eyebrow images, components 203 and 204 are fill lights, components 205 and 206 are binocular cameras, component 207 is the second display panel for displaying mouth images, and component 208 is an ambient light. The binocular panel can be a separately set panel device or integrated in any intelligent device, such as a smart robot.

[0066] Figure 2 The flowchart of a control method for a binocular panel with an expression interaction function provided by an embodiment of the present application, as Figure 2 shown, specifically includes:

[0067] Step S101: Obtain the on-site image information captured by the binocular camera, and calibrate the human faces in the on-site image information to obtain human face calibration data.

[0068] Among them, a binocular camera is a device with two cameras. By simulating the human binocular vision system, it can provide depth perception and three-dimensional information. Its working principle is similar to the human binocular vision system. The two cameras respectively capture different images of the same scene, and then obtain the depth information of the scene by processing the differences between these two images. The on-site image information can be the on-site image captured by the binocular camera. Calibrating the human faces in this on-site image information means precisely measuring and adjusting the parameters of the binocular camera (i.e., the two cameras) through a series of steps to achieve high-precision stereo imaging and human face recognition of the human face calibration data. The human face calibration data can include camera internal parameters, distortion parameters, and external parameters. In one embodiment, before obtaining the on-site image information captured by the binocular camera, an image of the current scene is captured by the binocular camera and determined as the on-site image information. Optionally, before obtaining the on-site image information captured by the binocular camera, an image captured in real time by the binocular camera is obtained. When it is recognized that the image contains a human face, the binocular camera is controlled to focus to capture the on-site image information after the focusing process. Determining whether the binocular camera focuses to capture the on-site image information through the human face recognition result can reduce the acquisition of invalid information, improve work efficiency, and ensure the clarity of the captured on-site image.

[0069] In one embodiment, for the on-site image information captured by the binocular camera, a human face calibration method can be to obtain a pair of images of the same scene captured by the left and right cameras in the binocular camera, and calibrate the human faces in the pair of images to obtain human face calibration data. Optionally, for the on-site image information captured by the binocular camera, a human face calibration method can be to obtain the first on-site image captured by any one of the binocular cameras. When the first on-site image contains a human face, the other camera in the binocular camera is turned on to capture the second on-site image. When the second on-site image also contains a human face synchronously, the human faces in the first on-site image and the second on-site image are calibrated to obtain human face calibration data. By detecting human faces to turn on the cameras one by one and performing human face calibration when both images contain human faces, the time loss of operations can be reduced, and the detection and human face calibration efficiency can be improved.

[0070] In one embodiment, after acquiring the on-site image information captured by the binocular camera, face recognition is performed on the on-site image information to obtain the number of faces, and the advertisement information corresponding to the number of faces is controlled to be played according to the number of faces. Playing the advertisement information based on the number of faces in the on-site image information can play suitable advertisements according to the number of people to meet the requirements of product promotion. In another embodiment, after acquiring the on-site image information captured by the binocular camera, in the case where no face is recognized in the on-site image information within a preset time period, the pre-set eyebrow expression and mouth expression corresponding to the situation of no detected face are generated and displayed through the first display panel and the second display panel respectively. By pre-setting the eyebrow expression and mouth expression displayed in the case of no detected face, the situation of the display panel showing no expression can be avoided.

[0071] Step S102: Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm.

[0072] Among them, the binocular ranging algorithm is a method that uses a binocular camera system to measure the distance of an object. Its basic principle is to calculate the parallax of the target point on the imaging planes of the left and right cameras, and use the principle of similar triangles to estimate the distance of the target point in the three-dimensional space. The main implementation steps of this binocular ranging algorithm are to determine the internal parameters and external parameters of the camera (i.e., binocular calibration), eliminate distortion and make the imaging origin coordinates of the left and right views consistent, ensure that the left and right imaging planes are coplanar and the epipolar lines are row-aligned, obtain the disparity map by algorithmically matching the corresponding points of the same scene on the left and right views, and calculate the depth information of the target point using the principle of similar triangles according to the disparity map and the known camera parameters, so as to obtain the three-dimensional coordinates of the target point. Using this binocular ranging algorithm and the face calibration data obtained by face calibration, the face position of the face in the physical space can be calculated. The face position can be the specific position and direction of the face in the three-dimensional space. In one embodiment, the face calibration data is input into the binocular ranging algorithm to obtain the three-dimensional coordinates of the face in the on-site image information in the physical space, and the face position of the face in the on-site image information in the physical space is determined according to the three-dimensional coordinates.

[0073] Step S103: Generate the corresponding eyebrow expression and mouth expression according to the face position and display them through the first display panel and the second display panel respectively.

[0074] Among them, the orientation is used to characterize the direction of the recognized face relative to the binocular panel in space. For example, orientations such as upward, rightward, downward, and leftward. Taking the leftward orientation as an example, it means that the recognized face is located on the left side of the binocular panel. At this time, the generated eyebrow expression and mouth expression are expressions of looking left. The eyebrow expression is used to characterize the manifestation form of the eyebrows. The mouth expression is used to characterize the manifestation form of the mouth. The first display panel is the panel for displaying the eyebrow image. It can be two panels, respectively for displaying the left eyebrow and the right eyebrow, or it can be a long panel for displaying a pair of eyebrows. The second display panel is the face part for displaying the mouth image. The generation of the eyebrow expression and the mouth expression is a real-time dynamic execution process. Exemplarily, every preset time, the current face position is determined to change the expression, and the current face position is compared with the previous face position. If the orientation corresponding to the face position changes, then the eyebrow expression and mouth expression corresponding to the current face position are generated. If the orientation corresponding to the face position does not change, then the generation of the eyebrow expression and the mouth expression is not performed, and the original expression remains unchanged. In one embodiment, when there are multiple faces in the on-site image information, one way to select a face is to determine the face closest to the binocular camera according to the face positions of each face, and generate the eyebrow expression and mouth expression corresponding to the orientation according to the face position of the face closest to the binocular camera. In another embodiment, when there are multiple faces in the on-site image information, one way to select a face is to randomly select a face as the target face, and generate the eyebrow expression and mouth expression corresponding to the orientation according to the face position of the target face.

[0075] In one embodiment, before generating the eyebrow expression and mouth expression corresponding to the orientation according to the face position, the preset eyebrow expressions and preset mouth expressions corresponding to different orientations are set and stored. One way to generate the eyebrow expression and mouth expression is to determine the orientation direction according to the face position. The orientation direction includes at least one of the leftward direction, rightward direction, upward direction, and downward direction, obtain the preset eyebrow expression and preset mouth expression corresponding to the determined orientation direction, and perform the generation. Generating the corresponding eyebrow expression and mouth expression according to the determined orientation can realize the expression actions of the robot's face facing different directions. Through the expression of the face orientation in each direction, the expression of the robot's face is made more flexible and vivid, and more facial body languages can be expressed.

[0076] In another embodiment, a method for generating eyebrow expressions and mouth expressions may be as follows: according to the position of the human face, determine the eyebrow expression parameters and mouth expression parameters corresponding to the orientation. The eyebrow expression parameters include the display position and display size of the eyebrows, and the mouth expression parameters include the display position and display size of the mouth. Among them, different orientation directions correspond to different display positions of the eyebrows, display sizes of the eyebrows, display positions of the mouth, and display sizes of the mouth. Generate the corresponding eyebrow expression based on the display position and display size of the eyebrows, and generate the corresponding mouth expression based on the display position and the display size of the mouth. In another embodiment, a method for generating eyebrow expressions and mouth expressions may also be as follows: determine the face displacement information according to the positions of the human face at multiple different time points, and generate the corresponding eyebrow expressions and mouth expressions based on the face displacement information.

[0077] As can be seen from the above, obtain the on-site image information captured by the binocular camera, calibrate the human face in the on-site image information to obtain the human face calibration data, calculate the human face position in the physical space based on the human face calibration data and the binocular ranging algorithm, generate the corresponding eyebrow expressions and mouth expressions according to the human face position, and display them through the first display panel and the second display panel respectively. In this solution, the binocular camera is used as the eyes of the robot, and the eyebrow screen and the mouth screen are used to display the expressions of the robot, so as to solve the expression interaction of intelligent devices centered on the binocular camera, realize a new intelligent device interaction mode, and give full play to the advantages of the binocular camera, so that intelligent devices with panels such as intelligent terminal machines, panel machines, intelligent speakers, intelligent access control machines, payment devices, electronic ID devices, and intelligent home appliances have richer expression interaction functions.

[0078] Figure 3 This is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application, which gives an optional specific method for generating eyebrow expressions and mouth expressions, as Figure 3 shown, specifically including:

[0079] Step S201: Obtain the on-site image information captured by the binocular camera, and calibrate the human face in the on-site image information to obtain the human face calibration data.

[0080] Step S202: Calculate the human face position in the physical space based on the human face calibration data and the binocular ranging algorithm.

[0081] Step S203: Set and store the preset eyebrow expressions and preset mouth expressions corresponding to different orientations, determine the orientation direction according to the face position, where the orientation direction includes at least one of the leftward direction, rightward direction, upward direction, and downward direction, obtain the preset eyebrow expressions and preset mouth expressions corresponding to the stored orientation direction, generate them, and display them through the first display panel and the second display panel respectively.

[0082] Among them, the preset eyebrow expression is used to represent the corresponding eyebrow expression preset according to different orientations. The preset mouth expression is used to represent the corresponding mouth expression preset according to different orientations. The orientation direction is used to represent the direction that the current device, such as a smart robot integrated with a binocular panel, is facing, that is, the direction of the recognized face position relative to the smart robot. An exemplary example can be that the preset eyebrow expression in the leftward direction is eyebrow expression 1, the preset mouth expression is mouth expression 1, the preset eyebrow expression in the rightward direction is eyebrow expression 2, the preset mouth expression is mouth expression 2, the preset eyebrow expression in the upward direction is eyebrow expression 3, the preset mouth expression is mouth expression 3, the preset eyebrow expression in the downward direction is eyebrow expression 4, the preset mouth expression is mouth expression 4. If the orientation direction determined according to the face position is the leftward direction, then obtain eyebrow expression 1 and mouth expression 1, and generate them, as Figure 4 shown Figure 4 is the expression schematic diagram of a binocular panel device with an expression interaction function in the leftward orientation direction provided by an embodiment of the present invention. The displayed eyebrow expression is eyebrow expression 1, and the displayed mouth expression is mouth expression 1, which expresses the corresponding expression action of looking left.

[0083] As can be seen from the above, before generating the corresponding eyebrow expression and mouth expression according to the face position, set and store the preset eyebrow expressions and preset mouth expressions corresponding to different orientations, determine the orientation direction according to the face position, where the orientation direction includes at least one of the leftward direction, rightward direction, upward direction, and downward direction, obtain the preset eyebrow expressions and preset mouth expressions corresponding to the stored orientation direction, and generate them. This solution can generate eyebrow expressions and mouth expressions through the determined orientation, enabling the robot's face to make expression actions in the direction of the recognized face position, making the robot's expression more flexible and vivid, solving the problem of the robot's facial expression stiffness caused by the inability of the binocular cameras as eyes to rotate, and being able to express more facial body languages.

[0084] Figure 5 is the flowchart of another control method of a binocular panel with an expression interaction function provided by an embodiment of the present application, which gives another optional specific way to generate eyebrow expressions and mouth expressions, as Figure 5 shown, specifically including:

[0085] Step S301: Obtain the on-site image information captured by the binocular camera, and calibrate the human face in the on-site image information to obtain human face calibration data.

[0086] Step S302: Calculate the human face position of the human face in the physical space based on the human face calibration data and the binocular ranging algorithm.

[0087] Step S303: Determine the eyebrow expression parameters and mouth expression parameters corresponding to the corresponding orientation according to the human face position. The eyebrow expression parameters include the eyebrow display position and the eyebrow display size, and the mouth expression parameters include the mouth display position and the mouth display size. Among them, different orientation directions correspond to different eyebrow display positions, eyebrow display sizes, mouth display positions and mouth display sizes.

[0088] Among them, the eyebrow display position is used to represent the parameter for displaying the eyebrow expression position, which can be the parameter for moving the original eyebrow expression position or the coordinate parameter of the eyebrow expression position. The eyebrow display size is used to represent the parameter for displaying the eyebrow expression size, which can be the parameter for adjusting the original eyebrow expression size or the actual parameter of the eyebrow expression size. The mouth display position is used to represent the parameter for displaying the mouth expression position, which can be the parameter for moving the original mouth expression position or the coordinate parameter of the mouth expression position. The mouth display size is used to represent the parameter for displaying the mouth expression size, which can be the parameter for adjusting the original mouth expression size or the actual parameter of the mouth expression size. An exemplary example is that the determined orientation is the right direction. The eyebrow display position corresponding to the right direction is shifted 1 cm to the right, the eyebrow display size is -10% (reduced by 10%), the mouth display position is shifted 1.5 cm to the right, and the mouth display size is -15% (reduced by 15%), so as to achieve the expression action of looking to the right.

[0089] Step S304: Generate the corresponding eyebrow expression based on the eyebrow display position and the eyebrow display size, and generate the corresponding mouth expression based on the mouth display position and the mouth display size, and display them through the first display panel and the second display panel respectively.

[0090] Optionally, a method for generating an eyebrow expression and a mouth expression may be as follows: displace a preset eyebrow reference position according to the displayed eyebrow position, and scale a preset eyebrow reference size according to the displayed eyebrow size, to generate a corresponding eyebrow expression; displace a preset mouth reference position according to the displayed mouth position, and scale a preset mouth reference size according to the displayed mouth size, to generate a corresponding mouth expression. The eyebrow reference position may be the position where the currently displayed eyebrow expression is located, the eyebrow reference size may be the size of the currently displayed eyebrow expression, the mouth reference position may be the position where the currently displayed mouth expression is located, and the mouth reference size may be the size of the currently displayed mouth expression. An exemplary example may be that the displayed eyebrow position is shifted 1 cm to the right, the displayed eyebrow size is -10% (reduced by 10%), the displayed mouth position is shifted 1.5 cm to the right, and the displayed mouth size is -15% (reduced by 15%). Then, shift the preset eyebrow reference position 1 cm to the right, reduce the preset eyebrow reference size by 10% to generate a corresponding eyebrow expression, shift the preset mouth reference position 1.5 cm to the right, and reduce the preset mouth reference size by 15% to generate a corresponding mouth expression.

[0091] As can be seen from the above, according to the face position, the corresponding eyebrow expression parameters and mouth expression parameters in the facing direction are determined. The eyebrow expression parameters include the displayed eyebrow position and the displayed eyebrow size, and the mouth expression parameters include the displayed mouth position and the displayed mouth size. Among them, different facing directions correspond to different displayed eyebrow positions, displayed eyebrow sizes, displayed mouth positions, and displayed mouth sizes. Based on the displayed eyebrow position and the displayed eyebrow size, a corresponding eyebrow expression is generated, and based on the displayed mouth position and the displayed mouth size, a corresponding mouth expression is generated. This solution generates eyebrow expressions and mouth expressions according to the determined facing direction, making the expression of the robot's expressions more flexible and vivid, and capable of expressing more facial body languages.

[0092] Figure 6 The following is a flowchart of another control method for a binocular panel with an expression interaction function provided in an embodiment of the present application, which gives another optional specific method for generating an eyebrow expression and a mouth expression, as Figure 6 shown, specifically including:

[0093] Step S401: Obtain the on-site image information captured by the binocular camera, and calibrate the face in the on-site image information to obtain face calibration data.

[0094] Step S402: Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm.

[0095] Step S403: Determine the facial displacement information based on the facial positions at multiple different time points, generate the corresponding eyebrow expressions and mouth expressions according to the facial displacement information, and display them through the first display panel and the second display panel respectively.

[0096] Among them, the facial displacement information can be the movement change information of the facial position at multiple different time points, such as the facial movement speed, the number of facial movements, etc. In one embodiment, determine the facial movement speed according to the facial positions at multiple different time points, match the facial movement speed with each preset speed interval, determine the expression classification associated with the successfully matched preset speed interval, obtain the preset eyebrow expression and the preset mouth expression of this expression classification corresponding to the facial orientation, and generate them. An exemplary example can be that the expression classification associated with preset speed interval 1 is a smiling expression, the expression classification associated with preset speed interval 2 is a happy expression, the expression classification associated with preset speed interval 3 is a surprised expression. It is determined that the current facial movement speed falls into preset speed interval 3 and the orientation is to the right direction, then obtain the preset eyebrow expression and the preset mouth expression of the surprised expression in the right orientation, and generate them.

[0097] In another embodiment, determine the number of facial movements according to the facial positions at multiple different time points, match the number of facial movements with each preset number interval, determine the expression classification associated with the successfully matched preset speed interval, obtain the preset eyebrow expression and the preset mouth expression of this expression classification corresponding to the facial orientation, and generate them.

[0098] As can be seen from the above, determine the facial displacement information according to the facial positions at multiple different time points, generate the corresponding eyebrow expressions and mouth expressions based on the facial displacement information, thereby realizing richer robot facial expressions and making the interaction effect better.

[0099] Figure 7 This is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application, which gives an optional specific way to play advertisement information, such as Figure 7 shown, specifically including:

[0100] Step S501: Obtain the on-site image information captured by the binocular camera, perform face recognition on the on-site image information to obtain the number of faces, control the playback of advertisement information corresponding to the number of faces according to the number of faces, and calibrate the faces in the on-site image information to obtain face calibration data.

[0101] Among them, the number of human faces is the total number of human faces appearing in the on-site image information. The number of human faces can be used to control the playback of corresponding advertisement information. In one embodiment, a way to play advertisement information can be to obtain the preset quantity interval associated with each pre-stored advertisement information, determine the preset quantity interval into which the number of human faces falls, and control the playback of the advertisement information associated with this preset quantity interval. An exemplary example can be that the preset quantity interval associated with advertisement information 1 is (0, 10], the preset quantity interval associated with advertisement information 2 is (10, 20], the preset quantity interval associated with advertisement information 3 is (20, 30]. After performing face recognition on the on-site image information and obtaining the number of human faces as 25, then control the playback of advertisement information 2.

[0102] In another embodiment, a way to play advertisement information can be to determine the preset quantity interval into which the number of human faces falls and the advertisement importance level associated with this preset quantity interval. One advertisement importance level corresponds to an advertisement information combination. Randomly select one advertisement information from the advertisement information combination corresponding to this advertisement importance level to control the playback. Among them, the advertisement importance level can be the importance degree level of the advertisement information, and the advertisement information combination includes multiple advertisement information with the same advertisement importance level.

[0103] Step S502: Calculate the face position of the human face in the physical space based on the face calibration data and the binocular ranging algorithm.

[0104] Step S503: Generate the eyebrow expression and mouth expression corresponding to the orientation according to the face position, and display them through the first display panel and the second display panel respectively.

[0105] As can be seen from the above, after obtaining the on-site image information captured by the binocular camera, perform face recognition on the on-site image information to obtain the number of human faces, and control the playback of the advertisement information corresponding to the number of human faces according to the number of human faces. This solution plays advertisement information through the number of human faces in the on-site image information, and can play suitable advertisements according to the number of people to meet the requirements of product promotion.

[0106] Figure 8 This is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application, which gives an optional specific way to execute an external control instruction, such as Figure 8 shown, specifically including:

[0107] Step S601: Obtain the on-site image information captured by the binocular camera, and calibrate the human faces in the on-site image information to obtain face calibration data.

[0108] Step S602: Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm.

[0109] Step S603: Generate the corresponding eyebrow expression and mouth expression according to the face position, and display them through the first display panel and the second display panel respectively.

[0110] Step S604: Obtain the detected external control instruction, and execute the external control instruction when the current execution instruction meets the end condition or the interruption condition.

[0111] Among them, the external control instruction can be the control instruction for the first display panel and the second display panel sent externally. The current execution instruction can be the control instruction for the first display panel and the second display panel currently being executed. The end condition is used to represent the condition for ending the current execution instruction. The interruption condition is used to represent the condition for interrupting the current execution instruction. An exemplary example can be that the end condition is that the execution time of the current execution instruction is greater than or equal to the preset time, the interruption condition can be that the current execution instruction belongs to an interruptible instruction, the preset time is 1 s, the currently detected external control instruction is obtained, and the execution time of the current execution instruction is 1.5 s, which is greater than the preset time and meets the end condition, so the external control instruction is executed.

[0112] As can be seen from the above, after displaying through the first display panel and the second display panel respectively, obtain the detected external control instruction, and execute the external control instruction when the current execution instruction meets the end condition or the interruption condition. By judging the conditions of the current execution instruction, the device can quickly respond to external instructions to expand the artificial intelligence capabilities and device functions of the device.

[0113] Figure 9 The following is a flowchart of another control method for a binocular panel with an expression interaction function provided by an embodiment of the present application, which gives an optional specific way to regenerate expressions, as Figure 9 shown, specifically including:

[0114] Step S701: Obtain the on-site image information captured by the binocular camera, and calibrate the face in the on-site image information to obtain face calibration data.

[0115] Step S702: Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm.

[0116] Step S703: Generate the corresponding eyebrow expression and mouth expression according to the face position, and display them through the first display panel and the second display panel respectively.

[0117] Step S704: When it is determined that the current displayed eyebrow expression and mouth expression meet the end condition or the interruption condition, after re-acquiring the on-site image information and determining the face update position, generate the eyebrow expression and mouth expression with the corresponding orientation according to the face update position, and display them through the first display panel and the second display panel respectively.

[0118] Among them, the end condition is used to represent the condition for ending the currently displayed eyebrow expression and mouth expression. For example, the end condition is that the display time of the eyebrow expression and mouth expression reaches the preset time. The interruption condition is used to represent the condition for interrupting the currently displayed eyebrow expression and mouth expression. For example, an external control instruction for re-generating the expression is received. An exemplary example can be that the end condition is that the display time of the eyebrow expression and mouth expression reaches 1 s. It is determined that the display time of the currently displayed eyebrow expression and mouth expression is 1 s, which meets the end condition. Then, after re-acquiring the on-site image information and determining the face update position, generate the eyebrow expression and mouth expression with the corresponding orientation according to the face update position, and display them through the first display panel and the second display panel respectively.

[0119] As can be seen from the above, after displaying through the first display panel and the second display panel respectively, when it is determined that the currently displayed eyebrow expression and mouth expression meet the end condition or the interruption condition, re-acquire the on-site image information and determine the face update position, then generate the eyebrow expression and mouth expression with the corresponding orientation according to the face update position, and display them through the first display panel and the second display panel respectively. In this solution, by re-acquiring the on-site image information and generating the eyebrow expression and mouth expression when the expression meets the end or interruption condition, corresponding execution instructions can be generated according to the actual situation of the on-site environment, meeting the personalized needs of interacting with on-site users.

[0120] Figure 10 This is a module structure block diagram of a control system for a binocular panel with an expression interaction function provided by an embodiment of the present application. This system is used to execute a control method for a binocular panel with an expression interaction function provided by the above embodiment, and has functional modules and beneficial effects corresponding to the execution method. As Figure 10 shown, this system specifically includes:

[0121] An acquisition module 101, configured to acquire on-site image information captured by the binocular camera;

[0122] A face detection module 102, configured to calibrate the face in the on-site image information to obtain face calibration data;

[0123] The binocular ranging module 103 is used to calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm;

[0124] The expression control module 104 is used to generate eyebrow expressions and mouth expressions in corresponding orientations according to the face position;

[0125] The display output module 105 is used to display the eyebrow expressions through the first display panel and display the mouth expressions through the second display panel.

[0126] As can be seen from the above solution, the on-site image information captured by the binocular camera is obtained, the face in the on-site image information is calibrated to obtain the face calibration data, the face position of the face in the physical space is calculated based on the face calibration data and the binocular ranging algorithm, the eyebrow expressions and mouth expressions in corresponding orientations are generated according to the face position, and are respectively displayed through the first display panel and the second display panel. In this solution, the binocular camera is used as the eyes of the robot, and the eyebrows screen and the mouth screen are used to display the expressions of the robot, so as to solve the expression interaction of intelligent devices centered on the binocular camera, realize a new intelligent device interaction mode, and give play to the advantages of the binocular camera, so that intelligent devices with panels such as intelligent terminal machines, panel machines, intelligent speakers, intelligent access control machines, payment devices, electronic ID card devices, and intelligent home appliances bring richer expression interaction functions.

[0127] In a possible embodiment, the first display panel includes a first display sub-panel and a second display sub-panel. The first display sub-panel is located in the upper left of the binocular camera, and the second display sub-panel is located in the upper right of the binocular camera, and two separate panels are used to display the eyebrow expressions respectively. For example, the first display sub-panel displays the first eyebrow expression, and the second display sub-panel displays the second eyebrow expression, so as to achieve the simulation effect of facial expressions and save costs at the same time; or, the first display panel is a single panel, including a first display sub-region and a second display sub-region, which are respectively used to display two eyebrow expressions. This method displays the corresponding eyebrow expressions through different sub-regions of an integrated panel, which is another setting method for the binocular panel.

[0128] In a possible embodiment, the internal functional units of the system further include:

[0129] The audio module is used for inputting and outputting audio;

[0130] The fill light control module is used to control the fill light for supplementary lighting;

[0131] The communication module is used to realize data communication with external devices;

[0132] The AI intelligent module is used to identify any one or more of barcodes, QR codes, gender, age, expressions, voices, semantics, gestures, behaviors, gaits, palm prints, palm veins, irises, and vacant states.

[0133] In a possible embodiment, the external interaction unit of the system further includes any one or more of an ambient light module, a microphone module, a speaker module, a visible light fill light module, and a near-infrared fill light module.

[0134] In a possible embodiment, a storage module is further included, specifically used for:

[0135] Set and store the preset expressions of the eyebrows and the preset expressions of the mouth corresponding to different orientations.

[0136] The expression control module 104 is specifically used for:

[0137] Determine the orientation direction according to the face position, and the orientation direction includes at least one of the left direction, the right direction, the upward direction, and the downward direction.

[0138] Obtain the preset expressions of the eyebrows and the preset expressions of the mouth corresponding to the stored orientation direction, and generate them.

[0139] In a possible embodiment, the expression control module 104 is further used for:

[0140] Determine the eyebrow expression parameters and mouth expression parameters corresponding to the orientation according to the face position. The eyebrow expression parameters include the eyebrow display position and the eyebrow display size, and the mouth expression parameters include the mouth display position and the mouth display size. Among them, different orientation directions correspond to different eyebrow display positions, eyebrow display sizes, mouth display positions, and mouth display sizes.

[0141] Generate the corresponding eyebrow expression based on the eyebrow display position and the eyebrow display size, and generate the corresponding mouth expression based on the mouth display position and the mouth display size.

[0142] In a possible embodiment, the expression control module 104 is further used for:

[0143] Displace the preset eyebrow reference position according to the eyebrow display position, and scale the preset eyebrow reference size according to the eyebrow display size to generate the corresponding eyebrow expression.

[0144] Displace the preset mouth reference position according to the mouth display position, and scale the preset mouth reference size according to the mouth display size to generate the corresponding mouth expression.

[0145] In a possible embodiment, the expression control module 104 is further configured to:

[0146] Determine face displacement information based on the face positions at multiple different time points;

[0147] Generate corresponding eyebrow expressions and mouth expressions in the facing direction based on the face displacement information.

[0148] In a possible embodiment, it further includes a focus control module, which is specifically configured to:

[0149] Obtain an image captured in real time by the binocular camera;

[0150] When it is recognized that the image contains a face, control the binocular camera to focus and capture the on-site image information after focus processing.

[0151] In a possible embodiment, the face detection module 102 is specifically configured to:

[0152] Obtain a first on-site image captured by any one of the binocular cameras;

[0153] When the first on-site image contains a face, turn on the other one of the binocular cameras to capture a second on-site image;

[0154] When the second on-site image synchronously contains a face, calibrate the faces in the first on-site image and the second on-site image to obtain face calibration data.

[0155] In a possible embodiment, it further includes an advertisement playing module, which is specifically configured to:

[0156] Perform face recognition on the on-site image information to obtain the number of faces;

[0157] Control the playing of advertisement information corresponding to the number of faces according to the number of faces.

[0158] In a possible embodiment, the display output module 105 is specifically configured to:

[0159] When it is not recognized that the on-site image information includes a face within a preset duration, generate pre-set eyebrow expressions and mouth expressions corresponding to the situation of not detecting a face, and display them through the first display panel and the second display panel respectively.

[0160] In a possible embodiment, it further includes an external instruction execution module, which is specifically configured to:

[0161] Obtain the detected external control instruction;

[0162] Execute the external control instruction when the currently executed instruction meets the end condition or the interruption condition.

[0163] In a possible embodiment, the display output module 105 is further configured to:

[0164] When it is determined that the current eyebrow expression and mouth expression meet the end condition or the interruption condition, after re-acquiring the on-site image information and determining the face update position, generate an eyebrow expression and a mouth expression with corresponding orientations according to the face update position, and display them through the first display panel and the second display panel respectively.

[0165] Figure 11 The structural schematic diagram of a control device for a binocular panel with an expression interaction function provided by an embodiment of the present application is shown in Figure 11 As shown, the device includes a processor 710 and a memory 720, and may further include an input device 730, an output device 740, and a communication device 750; the number of processors 710 in the electronic device may be one or more, Figure 11 Taking one processor 710 as an example; the processor 710, memory 720, input device 730, output device 740, and communication device 750 in the electronic device may be connected through a bus or other means, Figure 11 Taking the connection through the bus as an example. The memory 720, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to a control method for a binocular panel with an expression interaction function in an embodiment of the present invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 720, that is, implements the above-mentioned control method for a binocular panel with an expression interaction function. The memory 720 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the electronic device. In addition, the memory 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 720 may further include a memory remotely set relative to the processor 710, and these remote memories may be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof. The input device 730 can be used to receive input digital or character information, and generate key signal inputs related to the user settings and function control of the electronic device. The output device 740 may include a display device such as a display screen.

[0166] The embodiment of the present application further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute a control method for a binocular panel with an expression interaction function when executed by a computer processor. The method includes:

[0167] Obtain the on-site image information captured by the binocular camera, and calibrate the face in the on-site image information to obtain face calibration data;

[0168] Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm;

[0169] Generate corresponding eyebrow expressions and mouth expressions in the corresponding orientations according to the face position, and display them through the first display panel and the second display panel respectively.

[0170] It should be noted that in the embodiments of the control method system of the above binocular panel with an expression interaction function, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the embodiments of the present application.

[0171] Note that the above is only the preferred embodiment of the embodiments of the present application and the applied technical principle. Those skilled in the art will understand that the embodiments of the present application are not limited to the specific embodiments described here, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the embodiments of the present application. Therefore, although the embodiments of the present application have been described in more detail through the above embodiments, the embodiments of the present application are not limited to the above embodiments. Without departing from the concept of the embodiments of the present application, more other equivalent embodiments can be included, and the scope of the embodiments of the present application is determined by the scope of the appended claims.

Claims

1. A control method for a binocular panel with an expression interaction function, applied to a binocular panel, wherein the binocular panel comprises a binocular camera, a first display panel for displaying an eyebrow image, and a second display panel for displaying a mouth image, wherein the first display panel is located above the binocular camera, and the second display panel is located below the binocular camera, characterized in that: The method comprises: Acquire the scene image information captured by the binocular camera, and calibrate the face in the scene image information to obtain face calibration data; Calculate the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm; Eyebrow expressions and mouth expressions with corresponding orientations are generated according to the face position, and are displayed through the first display panel and the second display panel respectively.

2. The control method of the binocular panel with expression interaction function according to claim 1, characterized in that: Before generating the eyebrow expression and mouth expression of the corresponding orientation according to the face position, the method further includes: Set preset eyebrow expressions and mouth expressions corresponding to different directions for storage; Correspondingly, generating eyebrow expressions and mouth expressions of corresponding orientations according to the face position includes: Determine a direction according to the face position, wherein the direction includes at least one of a left direction, a right direction, an upward direction, and a downward direction; The stored preset eyebrow expressions and preset mouth expressions corresponding to the orientation direction are obtained and generated.

3. The control method of the binocular panel with expression interaction function according to claim 1, characterized in that: The step of generating eyebrow expressions and mouth expressions with corresponding orientations according to the face position includes: Determining eyebrow expression parameters and mouth expression parameters of corresponding orientations according to the face position, wherein the eyebrow expression parameters include eyebrow display positions and eyebrow display sizes, and the mouth expression parameters include mouth display positions and mouth display sizes, wherein different orientations correspond to different eyebrow display positions, eyebrow display sizes, mouth display positions, and mouth display sizes; A corresponding eyebrow expression is generated based on the eyebrow display position and the eyebrow display size, and a corresponding mouth expression is generated based on the mouth display position and the mouth display size.

4. The control method of the binocular panel with expression interaction function according to claim 3, characterized in that: The generating a corresponding eyebrow expression based on the eyebrow display position and the eyebrow display size, and the generating a corresponding mouth expression based on the mouth display position and the mouth display size, comprises: Displacing a preset eyebrow reference position according to the eyebrow display position, and scaling a preset eyebrow reference size according to the eyebrow display size, so as to generate a corresponding eyebrow expression; The preset mouth reference position is displaced according to the mouth display position, and the preset mouth reference size is scaled according to the mouth display size to generate a corresponding mouth expression.

5. The control method of the binocular panel with expression interaction function according to claim 1, characterized in that: The step of generating eyebrow expressions and mouth expressions with corresponding orientations according to the face position includes: Determine face displacement information according to face positions at multiple different time points; Generate eyebrow expressions and mouth expressions with corresponding orientations based on the face displacement information.

6. The control method of a binocular panel with expression interaction function according to any one of claims 1 to 5, characterized in that: Before acquiring the on-site image information captured by the binocular camera, the method further includes: Acquire an image captured in real time by the binocular camera; When it is recognized that the image contains a human face, the binocular camera is controlled to focus to capture the scene image information after focusing processing.

7. The control method of a binocular panel with expression interaction function according to any one of claims 1 to 5, characterized in that: The acquiring of the scene image information captured by the binocular camera and calibrating the face in the scene image information to obtain face calibration data includes: Acquire a first scene image captured by any one of the binocular cameras; When the first scene image contains a human face, another of the binocular cameras is turned on to capture a second scene image; In the case that the second scene image synchronously contains a face, the faces in the first scene image and the second scene image are calibrated to obtain face calibration data.

8. The control method of a binocular panel with expression interaction function according to any one of claims 1 to 5, characterized in that: After acquiring the on-site image information captured by the binocular camera, the method further includes: Performing face recognition on the on-site image information to obtain the number of faces; According to the number of faces, the advertising information corresponding to the number of faces is played.

9. The control method of a binocular panel with expression interaction function according to any one of claims 1 to 5, characterized in that: After acquiring the on-site image information captured by the binocular camera, the method further includes: When the on-site image information is not recognized to include a face within a preset time period, preset eyebrow expressions and mouth expressions corresponding to the situation where no face is detected are generated and displayed through the first display panel and the second display panel respectively.

10. The control method of a binocular panel with expression interaction function according to any one of claims 1 to 5, characterized in that: After displaying by the first display panel and the second display panel respectively, the method further includes: Obtaining detected external control instructions; When the currently executed instruction meets the end condition or the interrupt condition, the external control instruction is executed.

11. The control method of a binocular panel with expression interaction function according to any one of claims 1 to 5, characterized in that: After displaying by the first display panel and the second display panel respectively, the method further includes: When it is determined that the eyebrow expression and the mouth expression currently displayed meet the end condition or the interruption condition, after reacquiring the on-site image information and determining the face update position, the eyebrow expression and the mouth expression with corresponding directions are generated according to the face update position, and are displayed respectively through the first display panel and the second display panel.

12. A control system for a binocular panel with expression interaction function, characterized in that: The device comprises an internal functional unit and an external interactive unit, wherein the external interactive unit comprises a binocular camera, a first display panel for displaying an eyebrow image, and a second display panel for displaying a mouth image, wherein the first display panel is located above the binocular camera, and the second display panel is located below the binocular camera. The internal functional unit comprises: An acquisition module, used to acquire on-site image information captured by the binocular camera; A face detection module, used for calibrating faces in the scene image information to obtain face calibration data; A binocular ranging module, used for calculating the face position of the face in the physical space based on the face calibration data and the binocular ranging algorithm; An expression control module, used for generating eyebrow expressions and mouth expressions of corresponding directions according to the face position; The display output module is used to display the eyebrow expression through the first display panel and to display the mouth expression through the second display panel.

13. The control system of the binocular panel with expression interaction function according to claim 12, characterized in that: The first display panel includes a first display sub-panel and a second display sub-panel, the first display sub-panel is located at the upper left of the binocular camera, and the second display sub-panel is located at the upper right of the binocular camera; or, the first display panel is a panel, including a first display sub-area and a second display sub-area, respectively used to display corresponding eyebrow expressions.

14. The control system of the binocular panel with expression interaction function according to claim 12, characterized in that: The internal functional unit further includes: Audio module, used for audio input and output; A fill light control module is used to control the fill light for fill lighting; Communication module, used to realize data communication with external devices; AI intelligent module, used to recognize any one or more of barcode, QR code, gender, age, expression, voice, semantics, gesture, behavior, gait, palm print, palm vein, iris and vacant status.

15. The control system of the binocular panel with expression interaction function according to claim 12, characterized in that: The external interaction unit also includes: any one or more of an ambient light module, a microphone module, a speaker module, a visible light fill light module and a near infrared fill light module.

16. A control device for a binocular panel with an expression interaction function, the device comprising: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the control method of the binocular panel with expression interaction function as described in any one of claims 1-11.

17. A storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the control method of a binocular panel with expression interaction function as claimed in any one of claims 1 to 11 when executed by a computer processor.

Images