Image smoothing method and device for close-up picture, equipment and storage medium

Abstract

The invention relates to the technical field of display equipment, in particular to an image smoothing method and device for a close-up picture, equipment and a storage medium, and the method comprises the steps: obtaining a display picture collected by a conference tablet computer and a first pixel position of an existing close-up picture, the existing close-up picture is used for tracking a target person, and the existing close-up picture corresponds to an interception frame; determining a target person area corresponding to the target person and a second pixel position of the target person area in the display picture according to the display picture, calculating a third pixel position meeting a pixel alignment limiting condition according to the first pixel position and the second pixel position, moving the interception frame according to the third pixel position to obtain a moved interception frame, and displaying the moved interception frame on the display picture. And intercepting a target close-up picture containing the target person area in the display picture according to the moved interception box, and controlling the conference panel to display the target close-up picture. By means of the scheme, it can be guaranteed that the situation that the picture shakes after the interception frame moves along with the target portrait is avoided, and picture movement is smoother.

Description

Technical Field

[0001] The present invention relates to the technical field of display devices, and in particular to a method, device, equipment and storage medium for smoothing a close-up image. Background Art

[0002] In a video conference, the conference tablet can close-up the speaker's image, display the speaker's close-up image separately, and track the speaker through the close-up image when the speaker moves to ensure that the speaker always appears in the close-up image.

[0003] When the close-up image of the speaker is displayed, due to the pixel alignment limitation in the conference tablet's hardware, the movement between the close-up image and the speaker will be uneven due to the uneven movement speed, resulting in an incoherent display and a jittery display. Summary of the invention

[0004] One purpose of an embodiment of the present invention is to provide a close-up image smoothing method, device, equipment and storage medium, which are used to solve the technical problem that when a close-up image is displayed in a video conference, the close-up image is used to track the conference participants, and the image is not coherent enough, resulting in jitter in the displayed image.

[0005] In a first aspect, an embodiment of the present invention provides an image smoothing method for a close-up picture, comprising:

[0006] Acquire the first pixel position of the display image and the existing close-up image captured by the conference tablet, wherein the existing close-up image is used to track the target person, and the existing close-up image corresponds to the capture frame;

[0007] Determine, according to the display picture, a target person area corresponding to the target person and a second pixel position of the target person area in the display picture;

[0008] Calculating a third pixel position satisfying a pixel alignment constraint condition according to the first pixel position and the second pixel position;

[0009] Moving the capture frame according to the third pixel position to obtain a moved capture frame;

[0010] intercepting a target close-up image including the target person area in the display image according to the moved interception frame;

[0011] Control the conference tablet to display the target close-up image.

[0012] In combination with the first aspect, in a possible implementation method, calculating the third pixel position that satisfies the pixel alignment restriction condition based on the first pixel position and the second pixel position includes: calculating the moving speed based on the first pixel position and the second pixel position; obtaining a preset pixel alignment restriction value; and calculating the third pixel position that satisfies the pixel alignment restriction condition based on the moving speed, the first pixel position, and the preset pixel alignment restriction value.

[0013] In combination with the first aspect, in a possible implementation, the display screen is configured with a coordinate system, the first pixel position includes a first horizontal coordinate and a first vertical coordinate, the third pixel position includes a second horizontal coordinate and a second vertical coordinate, and the calculation of the third pixel position that satisfies the pixel alignment restriction condition based on the moving speed, the first pixel position and the preset pixel alignment restriction value includes: determining the horizontal speed of the moving speed in the x-axis direction and the vertical speed in the y-axis direction of the coordinate system; calculating the second horizontal coordinate that satisfies the pixel alignment restriction condition based on the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value; calculating the second vertical coordinate that satisfies the pixel alignment restriction condition based on the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value.

[0014] In combination with the first aspect, in a possible implementation method, calculating the second horizontal coordinate that satisfies the pixel alignment restriction condition based on the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value includes: calculating the sum of the horizontal speed and the first horizontal coordinate to obtain a candidate horizontal coordinate; determining the horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment restriction value as the second horizontal coordinate.

[0015] In combination with the first aspect, in a possible implementation method, determining the horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate includes: if the decimal value of the candidate horizontal coordinate is less than 0.5, then selecting a horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate; if the decimal value of the candidate horizontal coordinate is greater than or equal to 0.5 and less than 1, then selecting a horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate.

[0016] In combination with the first aspect, in a possible implementation method, before calculating the candidate horizontal coordinate, it also includes: determining whether the horizontal speed is less than the preset pixel alignment limit value; if less than, setting the value of the second horizontal coordinate to the value of the first horizontal coordinate; if greater than or equal to, calculating the sum of the horizontal speed and the first horizontal coordinate to obtain the candidate horizontal coordinate.

[0017] In combination with the first aspect, in a possible implementation method, calculating the second vertical coordinate that satisfies the pixel alignment restriction condition based on the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value includes: rounding the vertical speed according to the preset pixel alignment restriction value to obtain an integer reference speed, and the reference speed is an integer multiple of the preset pixel alignment restriction value; calculating the sum of the reference speed and the first vertical coordinate to obtain the second vertical coordinate.

[0018] In combination with the first aspect, in a possible implementation, the longitudinal speed is rounded according to the preset pixel alignment limit value to obtain an integer reference speed, including: if the decimal value of the longitudinal speed is less than 0.5, a speed that is smaller than the longitudinal speed, closest to the longitudinal speed, and an integer multiple of the preset pixel alignment limit value is selected as the reference speed; if the decimal value of the longitudinal speed is greater than or equal to 0.5 and less than 1, a speed that is larger than the longitudinal speed, closest to the longitudinal speed, and an integer multiple of the preset pixel alignment limit value is selected as the reference speed.

[0019] In a second aspect, an embodiment of the present invention provides an image smoothing device for a close-up image, comprising:

[0020] An acquisition unit, used to acquire a first pixel position of a display image and an existing close-up image captured by the conference tablet, wherein the existing close-up image is used to track a target person, and the existing close-up image corresponds to a capture frame;

[0021] A determination unit, configured to determine a target person region corresponding to the target person and a second pixel position of the target person region on the display screen according to the display screen;

[0022] a calculation unit, configured to calculate a third pixel position satisfying a pixel alignment constraint condition according to the first pixel position and the second pixel position;

[0023] A moving unit, configured to move the capture frame according to the third pixel position to obtain a moved capture frame;

[0024] A capture unit, configured to capture a target close-up image including the target person area in the display image according to the moved capture frame;

[0025] The display unit is used to control the conference tablet to display the target close-up picture.

[0026] In a third aspect, an embodiment of the present invention provides a conference tablet, including:

[0027] A camera, used to collect and display images;

[0028] Microphone array, used to collect voice information;

[0029] Memory;

[0030] A processor is respectively communicatively connected to the camera, the microphone array and the memory, wherein the processor is used to execute one or more computer programs stored in the memory, and when the processor executes the one or more computer programs, the conference tablet implements the method described in the first aspect.

[0031] In a fourth aspect, a computer device is provided, comprising a memory and one or more processors, wherein the memory is connected to the one or more processors, and the one or more processors are used to execute one or more computer programs stored in the memory, and when the one or more processors execute the one or more computer programs, the computer device implements the method described in the first aspect.

[0032] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method as described in the first aspect.

[0033] In the scheme implemented by the above-mentioned close-up image smoothing method, device, equipment and storage medium, the first pixel position of the display image and the existing close-up image collected by the conference tablet is first obtained, the existing close-up image is used to track the target person, and the existing close-up image corresponds to the capture frame. Secondly, the target person area corresponding to the target person and the second pixel position of the target person area in the display image are determined according to the display image. Then, according to the first pixel position and the second pixel position, the third pixel position that meets the pixel alignment restriction condition is calculated, and the capture frame is moved according to the third pixel position to obtain the moved capture frame. Finally, according to the moved capture frame, the target close-up image containing the target person area is captured in the display image, and the conference tablet is controlled to display the target close-up image. This scheme calculates the third pixel position that meets the pixel alignment restriction condition through the first pixel position of the close-up image and the second pixel position of the target person, so that the capture frame corresponding to the close-up image continuously approaches the target person in focus when tracking the target person. In this process, it is ensured that the close-up image is displayed coherently during tracking, so as to ensure the stability of the image, reduce image jitter, and provide a better visual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0035] Figure 1A This is a hardware architecture diagram of a conference tablet in one embodiment of the present invention;

[0036] Figure 1B This is a module diagram of a conference tablet in one embodiment of the present invention;

[0037] Figure 1C It is a scene diagram of a conference tablet in one embodiment of the present invention;

[0038] Figure 2 is a flow chart of an image smoothing method for a close-up picture in one embodiment of the present invention;

[0039] Figure 3A is a schematic diagram of a focus point of a capture frame in one embodiment of the present invention;

[0040] Figure 3B is a schematic diagram of a coordinate system for display screen configuration in one embodiment of the present invention;

[0041] Figure 3Cis a schematic diagram of reference points of a target person area in one embodiment of the present invention;

[0042] Figure 3D is a schematic diagram of a coordinate system for display screen configuration in one embodiment of the present invention;

[0043] Figure 3E is a schematic diagram of a pixel movement in one embodiment of the present invention;

[0044] Figure 4 is a schematic diagram of the structure of an image smoothing device for close-up images in one embodiment of the present invention;

[0045] Figure 5 It is a schematic diagram of the structure of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, all within the scope of protection of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device or the flow chart. Furthermore, the words "first", "second", "third", etc. used in the present invention do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0048] The technical solution of this application can be applied to various conference scenarios, such as remote conferences, etc.

[0049] The technical solution of the present application can be specifically applied to conference tablets, wherein the conference tablet can be a tablet device with multifunctional imaging such as display, broadcasting, and recording, and can specifically be a TV screen, a display, and an electronic whiteboard, etc. For ease of understanding, the conference tablet of the present application is first introduced.

[0050] See also Figure 1A , Figure 1A A schematic diagram of the hardware structure of a conference tablet provided in an embodiment of the present application is shown in FIG. Figure 1AAs shown, the conference tablet 10 includes a display panel 101, a microphone array 102, a camera module 103, a processor 104 and a memory 105. The display panel 101 is used to display the video stream image captured by the conference tablet and the close-up image captured by the capture frame; the microphone array 102 is used to locate the sound source information in the scene and calculate the sound source orientation angle. The layout of the microphone array 102 can be a linear array, a planar array, or a stereo array; the camera module 103 includes at least one camera, which is mainly used to obtain scene images or video streams. It can be a fixed-focus camera, a zoom camera, or a combination of the two; the processor 104 and the memory 105 are devices for storing and processing various sensor signals, such as processing audio information collected by the microphone array 102, or processing video information collected by the camera.

[0051] Among them, Figure 1B As shown, the conference tablet 10 includes four major functional modules: an image and video input module: obtaining image or video data input by the camera; a speed calculation module: calculating the current image movement speed according to the current display state; an original coordinate processing module: calculating the new original coordinates after superimposing the current original coordinates according to the image movement speed; a pixel alignment processing module: calculating the actual coordinates after processing according to the original coordinate information and the pixel alignment requirements; an image and video cropping module: cropping the corresponding image or video according to the calculated actual coordinates, and outputting the cropped close-up picture.

[0052] like Figure 1C As shown, Figure 1C The screen displayed on the display panel of the conference tablet is shown in the figure. For example, in a remote meeting, the screen displayed on the conference tablet is as follows: Figure 1C As shown in A in A, the content in the dotted box in A can be the PPT content being shown or other meeting materials, etc. In A, area a is an independent display area for participants A, B, and C at the meeting, area B shows an enlarged view of area a, area C is a specific picture of person C obtained by cutting the person in area a when person C is selected as the target person to speak, and area D is the final display effect of presenting the specific picture of area C on the display screen of the conference tablet.

[0053] In view of this, the present application proposes a close-up image smoothing method to solve the above problem, which is described in detail below.

[0054] See also Figure 2 , Figure 2 A flow chart of a method for smoothing a close-up image provided by an embodiment of the present invention is provided. The method comprises the following steps:

[0055] S10: Acquire the first pixel position of the display image and the existing close-up image captured by the conference tablet, where the existing close-up image is used to track the target person, and the existing close-up image corresponds to a capture frame.

[0056] Among them, the displayed picture is the real-time picture of the scene captured by the conference tablet.

[0057] Among them, the conference tablet can have its own camera module, and the display image is captured by controlling the camera module. The size of the capture area corresponding to the display image is set according to the capture range of the camera module itself.

[0058] Alternatively, the above-mentioned conference tablet can be connected to an external camera device, and the external camera receives the control command of the conference tablet to collect the current space. The camera device can communicate with the conference tablet to transmit audio and video. The above-mentioned external camera device needs to cover the area range of the area where the conference tablet is located. The external camera device can be placed above the spatial area where the conference tablet is located or on both sides parallel to the conference tablet, etc. There is no sole limitation on the above-mentioned external camera here.

[0059] Among them, the above-mentioned close-up picture is a picture containing the target person area displayed on the conference tablet, which has been displayed through the display panel.

[0060] The first pixel position is the focus point position of the capture frame corresponding to the close-up image. The specific steps of obtaining the focus point are: obtaining the midpoint of the horizontal line of the capture frame and the three-point line perpendicular to the horizontal line, and determining the intersection of the midpoint of the horizontal point and the three-point line as the focus point. The position of the focus point is the position of the first pixel, which can be as follows: Figure 3A shown.

[0061] Among them, the first pixel position includes a first horizontal coordinate and a first vertical coordinate, and the first horizontal coordinate and the first vertical coordinate can be obtained through the coordinate system configured by the display screen. The configuration of the display coordinate system usually follows the standard screen or image coordinate system. The following are some common display coordinate configuration methods. The first is the upper left corner origin coordinate system, and the coordinate origin is located in the upper left corner of the display screen. The horizontal coordinate (X-axis) usually increases from left to right, and the vertical coordinate (Y-axis) increases from top to bottom. Under this coordinate, the first horizontal coordinate of the first pixel position represents the horizontal position of the pixel from the left boundary, and the first vertical coordinate represents the vertical position of the pixel from the upper boundary; the second is the lower left corner origin coordinate system, and the coordinate origin is located in the lower left corner of the display screen. The horizontal coordinate (X-axis) increases from left to right, and the vertical coordinate (Y-axis) increases from bottom to top. Under this coordinate system, the first horizontal coordinate of the first pixel position represents the horizontal position of the pixel from the left boundary, and the first vertical coordinate represents the vertical position of the pixel from the bottom boundary. The third type is the center origin coordinate system. Some applications use a coordinate system with the center of the display screen as the origin. Under this coordinate system, the positive direction of the horizontal and vertical coordinates is usually relative to the center of the screen, with negative values ​​on the left and top and positive values ​​on the right and bottom.

[0062] For example, refer to Figure 3B , Figure 3B A schematic diagram of a coordinate system configured for a display screen, with the upper left corner of the display screen as the coordinate origin, establishing a Y axis with vertical downward as the positive direction and an X axis with right as the positive direction, wherein area A is the display screen, and area B is a specific screen, and the current first pixel position can be obtained as (X1, Y1).

[0063] Among them, the capture frame corresponding to the above close-up picture can automatically track the target person, and finally make the target person appear in focus. The capture frame is the area set for selecting the target person area in the conference tablet, and the step of selecting the target person is not limited here.

[0064] It can be seen that by acquiring the existing close-up images and the corresponding capture frames, the target person can be tracked, and the acquisition of the first pixel position can be used to stabilize the display image, reduce image jitter and unnecessary movement, and make the conference image more stable and easy to watch.

[0065] S20: Determine, according to the display picture, a target person region corresponding to the target person and a second pixel position of the target person region in the display picture.

[0066] The target person area is any person area in the display screen. The target person area must include a complete person area of ​​each person. Other persons except the target person may also exist in the area.

[0067] The target person area may include the target person or other objects or persons other than the target person. Such irrelevant persons may be processed by Gaussian blurring or virtualization.

[0068] For example, if Figure 1C In the example, person C is identified as speaking in area a, person C is selected as the target person, and the area corresponding to C is framed.

[0069] The second pixel position is the reference point position corresponding to the moving position of the target person before the close-up image is displayed. The reference point can be obtained by the following steps: generating a face recognition frame of the target person area, obtaining the midpoint of the horizontal line of the face recognition frame and a three-point line perpendicular to the horizontal line, and determining the intersection of the midpoint of the horizontal point and the three-point line as the reference point. The position of the reference point is the second pixel position. Figure 3C .

[0070] Among them, in the coordinate system described in step 10, Figure 3D As shown, the second pixel position (X2, Y2) may be as shown in the figure.

[0071] It can be seen that this solution can automatically adjust the camera focal length and viewing angle according to the position of the target person to ensure that the target person appears in focus, reducing the need to manually adjust the camera. Further acquisition of the second pixel position can achieve real-time dynamic tracking of the target person. No matter how the target person moves or changes position, the target person's position information can be updated in time to ensure that he is visible in the picture.

[0072] S30: Calculate a third pixel position that satisfies a pixel alignment restriction condition according to the first pixel position and the second pixel position.

[0073] The third pixel position is the pixel movement position of the close-up picture at the time of the i+1 movement corresponding to the i+1th pixel movement of the capture frame satisfying the pixel alignment restriction condition.

[0074] For example, the existing close-up picture is the i-1th close-up picture. Assuming that the coordinates of the focus point of the i-1th close-up picture are (Xi-1, Yi-1), the person moves at this time, and the coordinates (Xi, Yi) of the i-th close-up picture are calculated in combination with the moving speed v1 of the first frame, and then the i-th close-up picture is output. At this time, the target person area of ​​the i-th close-up picture has not appeared at the focus point; then, the conference tablet calculates the coordinates (Xi+1, Yi+1) of the i+1th close-up picture in combination with the moving speed v2 of the second frame, and then outputs the i+1th close-up picture. At this time, the target person area of ​​the i+1th close-up picture still has not appeared at the focus point. The conference tablet calculates the coordinates (Xi+2, Yi+2) of the i+2th close-up picture in combination with the moving speed v3 of the third frame, and then outputs the i+2th close-up picture. At this time, the target person area of ​​the i+2th close-up picture appears at the focus point. At the same time, since d=0, the moving speed v4=0, this embodiment will not move the capture frame to capture the close-up picture.

[0075] Among them, the above-mentioned pixel alignment constraint is a constraint in image processing or moving operations, which requires that image elements or objects must be aligned or adjusted in pixels when moving, scaling or resizing to maintain the overall stability and consistency of the image. This alignment is based on the discrete nature of pixels, where each pixel represents a point or color value in the image. The pixel alignment constraint conditions usually include the following aspects: position alignment, size alignment, rotation alignment, pixel grid alignment, etc. In this scheme, the preset pixel alignment constraint value corresponding to the pixel alignment constraint condition can be set to 2, and the pixels are rounded down to the maximum integer multiple of 2. The pixel alignment constraint value is not uniquely limited here. The specific pixel alignment constraint value may depend on many factors, including image processing requirements, application design, and specific image processing tasks.

[0076] For example, given the coordinates of the first pixel position (X1, Y1) and the coordinates of the second pixel position (X2, Y2), the moving vector (ΔX, ΔY) from the first pixel position to the second pixel position is calculated, where ΔX = X2-X1, ΔY = Y2-Y1, and the preset pixel alignment limit value that satisfies the pixel alignment limit condition is obtained, which can be calculated by the formula: X3 = X1+

[0077] round(ΔX / pixel alignment limit value)*pixel alignment limit value, Y3=Y1+round(ΔY / pixel alignment limit value)*pixel alignment limit value, where the round() function is used to round the calculation result to the nearest integer multiple of the pixel alignment limit value, thereby obtaining the third pixel position (X3, Y3) that meets the pixel alignment limit condition.

[0078] It can be seen that this step ensures that the third pixel position meets the pixel alignment restriction condition, thereby achieving smooth movement and adjustment of the image, reducing jitter and irregular movement, and improving the quality and stability of the image.

[0079] S40: Move the capture frame according to the third pixel position to obtain a moved capture frame.

[0080] Among them, the above-mentioned moved screenshot frame is a relative concept. For the screenshot frame presented on the conference tablet, it will not move in position, nor will it jump from a fixed display area to another area; but for the target person that the screenshot frame needs to capture, it is not a fixed position. The screenshot frame will track the target person according to the moving speed, that is, the area size of the screenshot frame remains unchanged, but the content of the screenshot frame will chase the target person and move dynamically to ensure that the screenshot frame can completely capture the target person area.

[0081] Optionally, moving the capture frame according to the third pixel position to obtain the moved capture frame includes: determining four vertex coordinates according to the third pixel position, and moving the capture frame according to the four vertex coordinates to obtain the moved capture frame.

[0082] In determining the coordinates of the four vertices according to the third pixel position, the specific steps are as follows: according to the information of the first pixel position and the second pixel position, the coordinates of the center point of the interception frame are determined, and the coordinates of the center point will be used as the center point of the interception frame. Then, the width and height of the interception frame are calculated. Generally, the width and height can be determined by the distance from the first pixel position to the third pixel position, and calculated using the following formula: width (w) = x coordinate of the third pixel position - x coordinate of the first pixel position; height (h) = y coordinate of the third pixel position - y coordinate of the first pixel position Coordinates; further vertex coordinates can be calculated by the following formula: upper left vertex coordinates: (center point x-width / 2, center point y-height / 2); upper right vertex coordinates: (center point x+width / 2, center point y-height / 2); lower left vertex coordinates: (center point x-width / 2, center point y+height / 2); lower right vertex coordinates: (center point x+width / 2, center point y+height / 2), the four vertex coordinates of the interception frame are calculated according to the coordinates of the third pixel position, so as to move the interception frame and obtain the moved interception frame.

[0083] It can be seen that by moving the capture frame to the third pixel position that satisfies the pixel alignment restriction condition, the smoothness of the picture can be ensured.

[0084] S50: capturing a target close-up image including the target person area in the display image according to the moved capture frame.

[0085] For example, in a remote meeting, the conference tablet only displays Figure 3A The image on the left shows the frame of the right image, and the target close-up image is Figure 3A The right picture in .

[0086] S60: Control the conference tablet to display the target close-up image.

[0087] The close-up picture may be a picture including the target person area, or a picture only including the target person area.

[0088] Among them, the above-mentioned conference tablet can partially display the close-up picture in a specific area or display the close-up picture in the entire display panel of the conference tablet, which is not limited here.

[0089] For example, if the conference tablet displays a close-up image in a specific area, you can Figure 1C The D area in the figure shows a specific area.

[0090] In the prior art, at a certain speed, the image movement is not consistent over time and there are some jerks. Figure 3E As shown in the figure, when the image wants to move to the right at a speed of 3 pixels per frame, there will be coordinates in the intermediate process that are not integer multiples of 2. At this time, it is necessary to force alignment to an integer multiple of 2. In the first movement, the coordinates that should be (123, 40) are forced to be aligned to (122, 40). In the second movement, the expected coordinates (126, 40) meet the alignment and the coordinates are retained. In the first movement process, the actual speed is 2pixel / frame, and in the second movement process, the actual speed is 4pixel / frame. The speed is back and forth between 2 and 4, and the movement will cause the picture to shake due to uneven speed.

[0091] This solution calculates the third pixel position that meets the pixel alignment constraint condition through the first pixel position of the close-up image and the second pixel position of the target person, so that the corresponding capture frame of the close-up image continuously approaches the target person when tracking the target person, and in this process ensures that the close-up image is displayed coherently during tracking, thereby ensuring image stability, reducing image jitter, and providing a better visual experience.

[0092] In one embodiment, calculating the third pixel position that satisfies the pixel alignment restriction condition based on the first pixel position and the second pixel position includes: calculating a moving speed based on the first pixel position and the second pixel position; obtaining a preset pixel alignment restriction value; and calculating the third pixel position that satisfies the pixel alignment restriction condition based on the moving speed, the first pixel position, and the preset pixel alignment restriction value.

[0093] The moving speed is the moving speed of the capture frame relative to the target person. The capture frame is moved according to the moving speed to achieve the purpose of tracking the target person.

[0094] The above-mentioned moving speed can be divided into speed components in the horizontal and vertical directions. The horizontal speed component (Vx) = (x coordinate of the second pixel position - x coordinate of the first pixel position) / time interval; the vertical speed component (Vy) = (y coordinate of the second pixel position - y coordinate of the first pixel position) / time interval, and the time interval is the time it takes to move between two pixel positions.

[0095] For example, the moving speed can be calculated according to the first pixel position (X1, Y1) and the second pixel position (X2, Y2), where the horizontal speed = X2-X1 and the vertical speed = Y2-Y1.

[0096] The preset pixel alignment limit value is a parameter set according to user needs or conference tablet settings, which determines the alignment rule of pixel positions. For example, if the preset pixel alignment limit value is 2, it means that the system hopes that the pixel will move at most 2 pixels each time when moving. The selection of the preset pixel alignment limit value depends on the specific application scenario and needs. It can control the granularity of pixel alignment, thereby affecting the smoothness and stability of the image.

[0097] Among them, the x coordinate of the third pixel position = the x coordinate of the first pixel position + (horizontal speed component * preset pixel alignment limit value); the y coordinate of the third pixel position = the y coordinate of the first pixel position + (vertical speed component * preset pixel alignment limit value).

[0098] It can be seen that by calculating the difference between the first pixel position and the second pixel position, the movement direction and speed of the target object can be accurately determined. By obtaining the preset pixel alignment limit value, the pixel alignment behavior of the image can be adjusted as needed, ensuring that the image can be adjusted according to the specified pixel alignment rules when moving, avoiding image jitter or irregular movement.

[0099] In one embodiment, the display screen is configured with a coordinate system, the first pixel position includes a first horizontal coordinate and a first vertical coordinate, the third pixel position includes a second horizontal coordinate and a second vertical coordinate, and the calculation of the third pixel position that satisfies the pixel alignment restriction condition based on the moving speed, the first pixel position and the preset pixel alignment restriction value includes: determining the horizontal speed of the moving speed in the x-axis direction and the vertical speed in the y-axis direction of the coordinate system; calculating the second horizontal coordinate that satisfies the pixel alignment restriction condition based on the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value; calculating the second vertical coordinate that satisfies the pixel alignment restriction condition based on the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value.

[0100] The display screen is configured with a coordinate system, and reference may be made to the description of the coordinate system in step 10, which will not be repeated here.

[0101] The second horizontal coordinate=the first horizontal coordinate+(horizontal speed*preset pixel alignment limit value); the second vertical coordinate=the first vertical coordinate+(vertical speed*preset pixel alignment limit value).

[0102] It can be seen that the moving speed, the first pixel position and the preset pixel alignment limit value are used to ensure that the pixel alignment conditions are met. During the tracking process, the position of the capture frame is adjusted based on the relative movement between the close-up picture and the face recognition frame to achieve the pixel alignment effect.

[0103] In one embodiment, calculating the second horizontal coordinate that satisfies the pixel alignment restriction condition based on the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value includes: calculating the sum of the horizontal speed and the first horizontal coordinate to obtain a candidate horizontal coordinate; determining the horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment restriction value as the second horizontal coordinate.

[0104] The candidate horizontal coordinates represent the next horizontal coordinate position estimated according to the speed.

[0105] For example, the horizontal speed = 4.5 pixels / frame; the first horizontal coordinate = 23.8 pixels; the preset pixel alignment limit value = 10 pixels; the candidate horizontal coordinate = the horizontal speed + the first horizontal coordinate, that is, 4.5 + 23.8 = 28.3 pixels, in determining the second horizontal coordinate that is closest to the pixel alignment limit condition, in this case, the horizontal coordinate that is closest to and meets the pixel alignment limit condition is 30 pixels, because it is the integer multiple value of the candidate horizontal coordinate 28.3 pixels, and is an integer multiple relationship with the preset pixel alignment limit value 10 pixels. Therefore, according to the horizontal speed, the first horizontal coordinate and the preset pixel alignment limit value, the second horizontal coordinate that meets the pixel alignment limit condition is calculated to be 30 pixels.

[0106] It can be seen that by calculating the candidate horizontal coordinate of the sum of the horizontal speed and the first horizontal coordinate, the next horizontal coordinate position estimated according to the speed is reflected, ensuring the alignment of the new position with the current pixel. Among all possible horizontal coordinates, the one closest to the candidate horizontal coordinate is selected, and the horizontal coordinate must meet the pixel alignment restriction condition, that is, it is an integer multiple of the preset pixel alignment restriction value, ensuring that the selected second horizontal coordinate meets the pixel alignment requirements.

[0107] In one embodiment, determining the horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate includes: if the decimal value of the candidate horizontal coordinate is less than 0.5, then selecting a horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate; if the decimal value of the candidate horizontal coordinate is greater than or equal to 0.5 and less than 1, then selecting a horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate.

[0108] Among them, if the decimal value of the candidate horizontal coordinate is less than 0.5, then the horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value is selected as the second horizontal coordinate. Assume the following values: horizontal speed = 6 pixels / second, first horizontal coordinate = 28 pixels, preset pixel alignment limit value = 10 pixels. Candidate horizontal coordinate = first horizontal coordinate + horizontal speed = 28 pixels + 6 pixels / second = 34 pixels; the decimal part of the candidate horizontal coordinate is 0.4 (less than 0.5); since the decimal value is less than 0.5, we should select a horizontal coordinate that is smaller than the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value; the preset pixel alignment limit value is 10 pixels, so we need to select an integer that is closest to 34 pixels and is an integer multiple of 10, so that the second horizontal coordinate that meets the pixel alignment limit condition is 30 pixels.

[0109] Among them, if the decimal value of the candidate horizontal coordinate is greater than or equal to 0.5 and less than 1, a horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value is selected as the second horizontal coordinate. Assume the following values: horizontal speed = 8 pixels / second, first horizontal coordinate = 45 pixels, preset pixel alignment limit value = 12 pixels. Candidate horizontal coordinate = first horizontal coordinate + horizontal speed = 45 pixels + 8 pixels / second = 53 pixels; since the decimal part of the candidate horizontal coordinate is 0.125 (greater than or equal to 0.5 but less than 1), a horizontal coordinate that is larger than the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value is selected. The preset pixel alignment limit value is 12 pixels, so we need to select an integer that is closest to 53 pixels and is an integer multiple of 12. The second horizontal coordinate that meets the pixel alignment restriction condition is 60 pixels.

[0110] It can be seen that, on the one hand, when the decimal value of the candidate horizontal coordinate is less than 0.5, it means that it is closer to the previous integer pixel. By selecting a horizontal coordinate that is smaller than the candidate horizontal coordinate, the closest distance and is an integer multiple of the preset pixel alignment limit value, it is ensured that the second horizontal coordinate is closer to the previous integer pixel than the candidate horizontal coordinate, which helps to maintain the alignment of the image; on the other hand, when the decimal value of the candidate horizontal coordinate is greater than or equal to 0.5 and less than 1, it means that it is closer to the next integer pixel. By selecting a horizontal coordinate that is larger than the candidate horizontal coordinate, the closest distance and is an integer multiple of the preset pixel alignment limit value, it is ensured that the second horizontal coordinate is closer to the next integer pixel than the candidate horizontal coordinate, which helps to maintain the alignment of the image.

[0111] In one embodiment, before calculating the candidate horizontal coordinates, it also includes: determining whether the horizontal speed is less than the preset pixel alignment limit value; if less than, setting the value of the second horizontal coordinate to the value of the first horizontal coordinate; if greater than or equal to, calculating the sum of the horizontal speed and the first horizontal coordinate to obtain the candidate horizontal coordinate.

[0112] When the horizontal speed is less than the preset pixel alignment limit value, it means that the horizontal speed is too slow to cross an integer pixel unit. In this case, the value of the second horizontal coordinate is set to the same value as the first horizontal coordinate. Under the requirement of pixel alignment, it is impossible to move to the next integer pixel position, so it needs to stay at the current pixel position.

[0113] When the lateral speed is greater than or equal to the preset pixel alignment limit value, it means that the lateral speed is fast enough to cross one or more integer pixel units. In this case, the sum of the lateral speed and the first horizontal coordinate is calculated to obtain the candidate horizontal coordinate, ensuring that the pixel alignment requirement can be met without misalignment when the speed is fast.

[0114] It can be seen that this step ensures that no matter what the speed is, the second horizontal coordinate finally obtained can meet the pixel alignment restriction condition.

[0115] In one embodiment, calculating the second vertical coordinate that satisfies the pixel alignment restriction condition based on the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value includes: rounding the vertical speed according to the preset pixel alignment restriction value to obtain an integer reference speed, and the reference speed is an integer multiple of the preset pixel alignment restriction value; calculating the sum of the reference speed and the first vertical coordinate to obtain the second vertical coordinate.

[0116] The longitudinal velocity is used to describe the value of the moving speed in the vertical direction.

[0117] The longitudinal speed is rounded to the preset pixel alignment limit value, that is, the longitudinal speed is constrained to an integer multiple of the pixel alignment limit value. For example, if the preset pixel alignment limit value is 2 pixels, and the calculated speed is 3.5 pixels per frame, then the rounding operation constrains it to 4 pixels per frame.

[0118] It can be seen that this step ensures pixel alignment in the longitudinal direction, thereby improving the stability and accuracy of movement.

[0119] In one embodiment, the longitudinal speed is rounded according to the preset pixel alignment limit value to obtain an integer reference speed, including: if the decimal value of the longitudinal speed is less than 0.5, a speed that is smaller than the longitudinal speed, closest to the longitudinal speed, and is an integer multiple of the preset pixel alignment limit value is selected as the reference speed; if the decimal value of the longitudinal speed is greater than or equal to 0.5 and less than 1, a speed that is larger than the longitudinal speed, closest to the longitudinal speed, and is an integer multiple of the preset pixel alignment limit value is selected as the reference speed.

[0120] Among them, if the decimal value of the longitudinal speed is less than 0.5, the speed that is smaller than the longitudinal speed, closest to the longitudinal speed and in an integer multiple relationship with the preset pixel alignment limit value is selected as the reference speed, for example: the first vertical coordinate is 85 pixels; the longitudinal speed is 2.3 pixels / frame; the preset pixel alignment limit value is 4 pixels; the decimal part of the longitudinal speed is 0.3, which is less than 0.5. Therefore, we will select a speed that is smaller than 2.3 pixels / frame and in an integer multiple relationship with 4 pixels. The closest and qualified speed is 0 pixels / frame, because the integer multiple relationship between 0 and 4 is 0. Therefore, the reference speed is 0 pixels / frame, the second vertical coordinate = 85 pixels + 0 pixels / frame = 85 pixels; it meets the pixel alignment restriction condition.

[0121] Among them, if the decimal value of the longitudinal speed is greater than or equal to 0.5 and less than 1, a speed that is greater than the longitudinal speed, closest to the longitudinal speed, and is an integer multiple of the preset pixel alignment limit value is selected as the reference speed, for example: the first vertical coordinate is 125 pixels; the longitudinal speed is 3.7 pixels / frame; the preset pixel alignment limit value is 5 pixels. The decimal part of the longitudinal speed is 0.7, which is greater than or equal to 0.5 and less than 1. Therefore, we will select a speed that is greater than 3.7 pixels / frame and is an integer multiple of 5 pixels. The closest and qualified speed is 5 pixels / frame, because 5 is an integer multiple of 5. Therefore, the reference speed is 5 pixels / frame, and the second vertical coordinate = 125 pixels + 5 pixels / frame = 130 pixels.

[0122] It can be seen that by rounding the longitudinal speed, it is ensured that the reference speed is an integer, which makes it easier to perform pixel alignment when calculating the second longitudinal coordinate, and by selecting the closest integer speed, the error introduced by speed calculation and rounding operations is reduced, thereby improving the accuracy of pixel alignment.

[0123] Based on the above steps, an example can be given: Assume that the preset pixel alignment limit value is 2, that is, the coordinates must be integer multiples of 2. The initial coordinates (x, y) are (100, 100), and the speed is calculated to obtain the current speed V on the x-axis. fx is 7.3, and the moving speed V on the y-axis fy is 4.2. On the x-axis, according to X i-1 , that is, X i-1 =100, plus the current speed V fx Record the latest X f The coordinate is 107.3, and after aligning downward, we get X i = 106. On the y-axis, the actual instantaneous speed 4.2 is taken down to the maximum integer multiple of 2, which is 4. Then V y The speed of downward movement is 4, and the Y-axis coordinate Y of the next step is obtained. i is 104. Then the coordinates of the first step are (106,104).

[0124] Repeat the above steps. If the speed is calculated to get the current speed V on the x-axis fx is 5.8, and the moving speed V on the y-axis fy is 2.4. On the x-axis, according to the recorded coordinates X i-1 is 107.3, plus the instantaneous velocity V fx , get the latest X f The coordinate is 113.1, and after aligning downwards, we get X i is 112. On the y-axis, i-1 The actual instantaneous speed 2.4 is rounded down to the maximum integer multiple of 2, which is 2. Then Vy The speed of downward movement is 2, and the Y-axis coordinate Y of the next step is obtained. i is 106. Then the coordinates of the second step are (112,106). If you need to continue processing the image, repeat the above steps. For example, when the speed is calculated to get a new V fx 5.8 and V fy When it is 2.4, the coordinate positions on the X-axis and Y-axis are calculated repeatedly, and the coordinates are updated in sequence.

[0125] In summary, this section describes an algorithm or method that processes image coordinates according to the pixel alignment requirement (align=2) to ensure that they are always integer multiples of 2, and updates the coordinate positions based on the calculated speed information to achieve image smoothing. This processing method can be used on devices such as conference tablets to improve the display quality of images or videos.

[0126] The method of the present application is introduced above, and the device of the present application is introduced below.

[0127] See also Figure 4 , Figure 4 Schematic diagram of a close-up image smoothing device provided in an embodiment of the present application. Figure 4 As shown, the image smoothing device of the close-up picture includes:

[0128] An acquisition unit 401 is used to acquire a first pixel position of a display image and an existing close-up image captured by the conference tablet, wherein the existing close-up image is used to track a target person, and the existing close-up image corresponds to a capture frame;

[0129] A determination unit 402 is used to determine a target person region corresponding to the target person and a second pixel position of the target person region in the display picture according to the display picture;

[0130] A calculation unit 403, configured to calculate a third pixel position satisfying a pixel alignment restriction condition according to the first pixel position and the second pixel position;

[0131] A moving unit 404 is used to move the capture frame according to the third pixel position to obtain a moved capture frame;

[0132] A capture unit 405, configured to capture a target close-up image including the target person area in the display image according to the moved capture frame;

[0133] The display unit 406 is used to control the conference tablet to display the target close-up picture.

[0134] In one embodiment, in the calculation of the third pixel position that satisfies the pixel alignment restriction condition based on the first pixel position and the second pixel position, the calculation unit 403 is further used to: calculate the moving speed based on the first pixel position and the second pixel position; obtain a preset pixel alignment restriction value; and calculate the third pixel position that satisfies the pixel alignment restriction condition based on the moving speed, the first pixel position, and the preset pixel alignment restriction value.

[0135] In one embodiment, the display screen is configured with a coordinate system, the first pixel position includes a first horizontal coordinate and a first vertical coordinate, the third pixel position includes a second horizontal coordinate and a second vertical coordinate, and in the calculation of the third pixel position that satisfies the pixel alignment restriction condition based on the moving speed, the first pixel position and the preset pixel alignment restriction value, the calculation unit 403 is also used to: determine the horizontal speed of the moving speed in the x-axis direction and the vertical speed in the y-axis direction of the coordinate system; calculate the second horizontal coordinate that satisfies the pixel alignment restriction condition based on the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value; calculate the second vertical coordinate that satisfies the pixel alignment restriction condition based on the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value.

[0136] In one embodiment, in the calculation of the second horizontal coordinate that satisfies the pixel alignment restriction condition based on the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value, the calculation unit 403 is further used to: calculate the sum of the horizontal speed and the first horizontal coordinate to obtain a candidate horizontal coordinate; and determine the horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment restriction value as the second horizontal coordinate.

[0137] In one embodiment, in the determination of the horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate, the calculation unit 403 is further used to: include: if the decimal value of the candidate horizontal coordinate is less than 0.5, then select a horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate; if the decimal value of the candidate horizontal coordinate is greater than or equal to 0.5 and less than 1, then select a horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate.

[0138] In one embodiment, before calculating the candidate horizontal coordinates, the calculation unit 403 is also used to: determine whether the horizontal speed is less than the preset pixel alignment limit value; if less than, set the value of the second horizontal coordinate to the value of the first horizontal coordinate; if greater than or equal to, calculate the sum of the horizontal speed and the first horizontal coordinate to obtain the candidate horizontal coordinate.

[0139] In one embodiment, in the calculation of the second vertical coordinate that satisfies the pixel alignment restriction condition based on the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value, the calculation unit 403 is also used to: round the vertical speed according to the preset pixel alignment restriction value to obtain an integer reference speed, and the reference speed is an integer multiple of the preset pixel alignment restriction value; calculate the sum of the reference speed and the first vertical coordinate to obtain the second vertical coordinate.

[0140] In one embodiment, in the process of rounding the longitudinal speed according to the preset pixel alignment limit value to obtain an integer reference speed, the calculation unit 403 is further used to: if the decimal value of the longitudinal speed is less than 0.5, select as the reference speed a speed that is smaller than the longitudinal speed, is closest to the longitudinal speed, and is an integer multiple of the preset pixel alignment limit value; if the decimal value of the longitudinal speed is greater than or equal to 0.5 and less than 1, select as the reference speed a speed that is larger than the longitudinal speed, is closest to the longitudinal speed, and is an integer multiple of the preset pixel alignment limit value.

[0141] This solution calculates the third pixel position that meets the pixel alignment constraint condition through the first pixel position of the close-up image and the second pixel position of the target person, so that the corresponding capture frame of the close-up image continuously approaches the target person when tracking the target person, and in this process ensures that the close-up image is displayed coherently during tracking, thereby ensuring image stability, reducing image jitter, and providing a better visual experience.

[0142] See also Figure 5 , Figure 5 Schematic diagram of the structure of a computer device provided in an embodiment of the present application. Figure 5 As shown, the computer device 50 includes a processor 501 and a memory 502. The memory 502 is connected to the processor 501, for example, via a bus.

[0143] The processor 501 is configured to support the computer device 50 to perform the corresponding functions in the method in the above method embodiment. The processor 501 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0144] Specifically, the processor 501 may include a sending card, a receiving card and a driving chip.

[0145] The memory 502 is used to store program codes, etc. The memory 502 may include a volatile memory (VM), such as a random access memory (RAM); the memory 502 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 502 may also include a combination of the above-mentioned types of memories.

[0146] The processor 501 may call the program code to perform the following operations:

[0147] Acquire the first pixel position of the display image and the existing close-up image captured by the conference tablet, wherein the existing close-up image is used to track the target person, and the existing close-up image corresponds to the capture frame;

[0148] Determine, according to the display picture, a target person area corresponding to the target person and a second pixel position of the target person area in the display picture;

[0149] Calculating a third pixel position satisfying a pixel alignment constraint condition according to the first pixel position and the second pixel position;

[0150] Moving the capture frame according to the third pixel position to obtain a moved capture frame;

[0151] intercepting a target close-up image including the target person area in the display image according to the moved interception frame;

[0152] Control the conference tablet to display the target close-up image.

[0153] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method described in the above embodiment.

[0154] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0155] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A close-up image smoothing method, applied to a conference tablet, characterized in that: include: Acquire the first pixel position of the display image and the existing close-up image captured by the conference tablet, wherein the existing close-up image is used to track the target person, and the existing close-up image corresponds to the capture frame; Determine, according to the display picture, a target person area corresponding to the target person and a second pixel position of the target person area in the display picture; Calculating a third pixel position satisfying a pixel alignment constraint condition according to the first pixel position and the second pixel position; Moving the capture frame according to the third pixel position to obtain a moved capture frame; intercepting a target close-up image including the target person area in the display image according to the moved interception frame; Control the conference tablet to display the target close-up image.

2. The method according to claim 1, characterized in that The calculating, according to the first pixel position and the second pixel position, a third pixel position satisfying the pixel alignment restriction condition comprises: Calculating a moving speed according to the first pixel position and the second pixel position; Get the preset pixel alignment limit value; A third pixel position satisfying a pixel alignment restriction condition is calculated according to the moving speed, the first pixel position and the preset pixel alignment restriction value.

3. The method according to claim 2, characterized in that The display screen is configured with a coordinate system, the first pixel position includes a first horizontal coordinate and a first vertical coordinate, the third pixel position includes a second horizontal coordinate and a second vertical coordinate, and the calculating the third pixel position satisfying the pixel alignment restriction condition according to the moving speed, the first pixel position and the preset pixel alignment restriction value includes: Determine the lateral speed of the moving speed in the x-axis direction and the longitudinal speed in the y-axis direction of the coordinate system; Calculating a second horizontal coordinate satisfying a pixel alignment restriction condition according to the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value; A second vertical coordinate satisfying a pixel alignment restriction condition is calculated according to the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value.

4. The method according to claim 3, characterized in that The calculating, according to the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value, a second horizontal coordinate satisfying a pixel alignment restriction condition comprises: Calculating the sum of the lateral velocity and the first horizontal coordinate to obtain a candidate horizontal coordinate; The horizontal coordinate that is closest to the candidate horizontal coordinate and is an integer multiple of the preset pixel alignment limit value is determined as the second horizontal coordinate.

5. The method according to claim 4, characterized in that The step of determining the abscissa that is closest to the candidate abscissa and is an integer multiple of the preset pixel alignment limit value as the second abscissa comprises: If the decimal value of the candidate horizontal coordinate is less than 0.5, a horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value is selected as the second horizontal coordinate; If the decimal value of the candidate horizontal coordinate is greater than or equal to 0.5 and less than 1, a horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit value is selected as the second horizontal coordinate.

6. The method according to claim 4, characterized in that Before calculating the candidate horizontal coordinates, the method further includes: Determining whether the lateral speed is less than the preset pixel alignment limit value; If it is less than, setting the value of the second horizontal coordinate to the value of the first horizontal coordinate; If it is greater than or equal to, then the sum of the lateral velocity and the first horizontal coordinate is calculated to obtain a candidate horizontal coordinate.

7. The method according to claim 3, characterized in that The calculating, according to the longitudinal speed, the first longitudinal coordinate and the preset pixel alignment restriction value, a second longitudinal coordinate satisfying a pixel alignment restriction condition comprises: According to the preset pixel alignment limit value, the longitudinal speed is rounded to obtain an integer reference speed, where the reference speed is an integer multiple of the preset pixel alignment limit value; The sum of the reference speed and the first ordinate is calculated to obtain a second ordinate.

8. The method according to claim 7, characterized in that The rounding operation of the longitudinal speed according to the preset pixel alignment limit value to obtain an integer reference speed includes: If the decimal value of the longitudinal speed is less than 0.5, a speed that is smaller than the longitudinal speed, closest to the longitudinal speed and an integer multiple of the preset pixel alignment limit value is selected as the reference speed; If the decimal value of the longitudinal speed is greater than or equal to 0.5 and less than 1, a speed that is greater than the longitudinal speed, closest to the longitudinal speed, and is an integer multiple of the preset pixel alignment limit value is selected as the reference speed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the image smoothing method for close-up pictures according to any one of claims 1 to 8.

10. A conference tablet, characterized in that: include: A camera, used to collect and display images; Microphone array, used to collect voice information; Memory; A processor is communicatively connected to the camera, the microphone array and the memory, respectively, wherein the processor is used to execute one or more computer programs stored in the memory, and when the processor executes the one or more computer programs, the conference tablet implements the image smoothing method for close-up images as described in any one of claims 1-8.

Images