Close-up image smoothing method, device, equipment and storage medium

Abstract

The present application relates to display device technical field, specifically to a kind of close-up picture image smoothing method, device, equipment and storage medium, the present application includes: obtaining the display picture of conference panel acquisition and the first pixel position of existing close-up picture, existing close-up picture is used to track target person, existing close-up picture corresponds to intercept frame, according to display picture, determine the target person area corresponding to target person and the second pixel position of target person area in display picture, according to the first pixel position and the second pixel position, calculate the third pixel position that satisfies pixel alignment restriction condition, according to third pixel position, move intercept frame, obtain the intercept frame after moving, according to the target close-up picture of target person area in display picture being intercepted according to the intercept frame after moving, control conference panel display target close-up picture.Through the present application, it can be guaranteed that the situation that intercept frame does not appear picture jitter after moving following target person image, so that picture moves more smoothly.

Description

Technical Field

[0001] This invention relates to the field of display device technology, and specifically to an image smoothing method, apparatus, device, and storage medium for close-up images. Background Technology

[0002] During video conferences, the conference tablet can provide close-up shots of the speaker, displaying a separate close-up view of the speaker and tracking the speaker's movements through the close-up view to ensure that the speaker remains in the close-up frame.

[0003] When displaying a speaker in close-up, due to pixel alignment limitations in the conference tablet's hardware, the movement between the close-up and the speaker can be uneven, resulting in a discontinuous display and screen jitter. Summary of the Invention

[0004] One objective of this invention is to provide an image smoothing method, apparatus, device, and storage medium for close-up shots, to address the technical problem of inconsistent close-up shots used to track participants during video conferencing, resulting in image jitter.

[0005] In a first aspect, embodiments of the present invention provide an image smoothing method for close-up shots, comprising:

[0006] The first pixel position of the display screen and the existing close-up screen captured by the conference tablet is obtained. The existing close-up screen is used to track the target person. The existing close-up screen corresponds to the capture box.

[0007] Determine the target person area corresponding to the target person and the second pixel position of the target person area on the display screen based on the display screen;

[0008] Based on the first pixel position and the second pixel position, calculate the third pixel position that satisfies the pixel alignment constraint.

[0009] The cropping box is moved according to the third pixel position to obtain the moved cropping box;

[0010] Based on the moved capture frame, a close-up image of the target person area is captured in the display screen;

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

[0012] In conjunction with the first aspect, in one possible implementation, calculating the third pixel position that satisfies the pixel alignment constraint 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 constraint value; and calculating the third pixel position that satisfies the pixel alignment constraint value based on the moving speed, the first pixel position, and the preset pixel alignment constraint value.

[0013] In conjunction with the first aspect, in one 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 step of calculating the third pixel position that satisfies the pixel alignment constraint based on the moving speed, the first pixel position, and the preset pixel alignment constraint value includes: determining the horizontal velocity of the moving speed in the x-axis direction and the vertical velocity in the y-axis direction of the coordinate system; calculating the second horizontal coordinate that satisfies the pixel alignment constraint based on the horizontal velocity, the first horizontal coordinate, and the preset pixel alignment constraint value; and calculating the second vertical coordinate that satisfies the pixel alignment constraint based on the vertical velocity, the first vertical coordinate, and the preset pixel alignment constraint value.

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

[0015] In conjunction with the first aspect, in one possible implementation, 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 the horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and 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 the horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate.

[0016] In conjunction with the first aspect, in one possible implementation, before calculating the candidate horizontal coordinate, the method further includes: determining whether the horizontal velocity is less than the preset pixel alignment limit value; if it is less, then 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 calculating the sum of the horizontal velocity and the first horizontal coordinate to obtain the candidate horizontal coordinate.

[0017] In conjunction with the first aspect, in one possible implementation, calculating the second ordinate that satisfies the pixel alignment constraint based on the vertical speed, the first ordinate, and the preset pixel alignment constraint value includes: rounding the vertical speed according to the preset pixel alignment constraint value to obtain an integer reference speed, wherein the reference speed is an integer multiple of the preset pixel alignment constraint value; and calculating the sum of the reference speed and the first ordinate to obtain the second ordinate.

[0018] In conjunction with the first aspect, in one possible implementation, the step of rounding the vertical speed according to the preset pixel alignment limit value to obtain an integer reference speed includes: if the decimal value of the vertical speed is less than 0.5, then selecting a speed that is smaller than the vertical speed, closest to the vertical speed, and an integer multiple of the preset pixel alignment limit value as the reference speed; if the decimal value of the vertical speed is greater than or equal to 0.5 and less than 1, then selecting a speed that is larger than the vertical speed, closest to the vertical speed, and an integer multiple of the preset pixel alignment limit value as the reference speed.

[0019] Secondly, embodiments of the present invention provide an image smoothing device for close-up shots, comprising:

[0020] The acquisition unit is used to acquire the first pixel position of the display screen and the existing close-up screen captured by the conference tablet. The existing close-up screen is used to track the target person, and the existing close-up screen corresponds to a capture box.

[0021] The determining unit is configured to determine, based on the display screen, a target person region corresponding to the target person and the second pixel position of the target person region on the display screen;

[0022] The calculation unit is used to calculate the position of the third pixel that satisfies the pixel alignment constraint based on the first pixel position and the second pixel position;

[0023] A moving unit is used to move the cropping box according to the position of the third pixel to obtain the moved cropping box;

[0024] The cropping unit is used to crop a close-up image of the target person area in the display screen according to the moved cropping frame;

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

[0026] In a third aspect, embodiments of the present invention provide a conference tablet, comprising:

[0027] A camera is used to capture and display images.

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

[0029] Memory;

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

[0031] Fourthly, a computer device is provided, including a memory and one or more processors, the memory being connected to the one or more processors, the one or more processors being configured to execute one or more computer programs stored in the memory, the one or more processors causing the computer device to perform the method described in the first aspect above when executing the one or more computer programs.

[0032] In a fifth aspect, embodiments of the present invention provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in the first aspect.

[0033] In the aforementioned image smoothing method, apparatus, device, and storage medium for close-up shots, the first pixel position of the display screen captured by the conference tablet and the existing close-up screen are first acquired. The existing close-up screen is used to track the target person, and the existing close-up screen corresponds to a cropping frame. Next, the target person region corresponding to the target person and the second pixel position of the target person region on the display screen are determined based on the display screen. Then, based on the first pixel position and the second pixel position, a third pixel position satisfying pixel alignment constraints is calculated. The cropping frame is moved according to the third pixel position to obtain the moved cropping frame. Finally, a target close-up shot containing the target person region is cropped from the display screen according to the moved cropping frame, and the conference tablet is controlled to display the target close-up shot. This solution calculates the third pixel position satisfying pixel alignment constraints by using the first pixel position of the close-up screen and the second pixel position of the target person. This ensures that the cropping frame corresponding to the close-up screen continuously approaches the target person when tracking them, ensuring smooth image display during tracking, thus guaranteeing image stability, reducing image jitter, and providing a better visual experience. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

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

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

[0037] Figure 1C This is a scene diagram of a conference tablet according to an embodiment of the present invention;

[0038] Figure 2 This is a flowchart illustrating an image smoothing method for a close-up shot according to an embodiment of the present invention;

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

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

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

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

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

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

[0045] Figure 5 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0047] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0048] The technical solution of this application is applicable to various meeting scenarios, such as remote meetings.

[0049] The technical solution of this application can be specifically applied to a conference flat panel, which can be a multi-functional imaging device with display, broadcasting, recording, etc., specifically such as a television screen, monitor, and electronic whiteboard. For ease of understanding, the conference flat panel of this application will first be introduced.

[0050] See Figure 1A , Figure 1A This is a schematic diagram of the hardware structure of a conference tablet provided in an embodiment of this application, as shown below. 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 displays video streams captured by the conference tablet and close-up shots captured by a frame. The microphone array 102 is used to locate 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, mainly used to acquire scene images or video streams; it can be a fixed-focus camera, a zoom camera, or a combination of both. The processor 104 and the memory 105 are devices for storing and processing signals from various sensors, such as processing audio information captured by the microphone array 102 or video information captured by the camera.

[0051] Among them, such as Figure 1B As shown, the conference tablet 10 includes four main functional modules: an image and video input module (acquiring image or video data from a camera), a speed calculation module (calculating the current image movement speed based on the current display state), an original coordinate processing module (calculating new original coordinates by superimposing the current original coordinates on the image movement speed), a pixel alignment processing module (calculating the processed actual coordinates based on the original coordinate information and pixel alignment requirements), and an image and video cropping module (cropping the corresponding image or video based on the calculated actual coordinates and outputting the cropped close-up image).

[0052] like Figure 1C As shown, Figure 1C The image shown is displayed on the screen panel of the conference tablet. For example, in a remote meeting, the conference tablet's display screen would look like this: Figure 1C As shown in A, the content within the dashed box in A can be the content of the PowerPoint presentation or other meeting materials. Area a in A is the independent display area for participants A, B, and C. Area B shows an enlarged view of area a. Area C is the specific image of participant C obtained by cutting out the person in area a when participant C is selected as the target person to speak. Area D is the final display effect of presenting the specific image of area C on the conference tablet.

[0053] In view of this, this application proposes an image smoothing method for close-up shots to solve the above problems. The details are described below.

[0054] Please see Figure 2 , Figure 2 A flowchart illustrating an image smoothing method for close-up shots provided in an embodiment of the present invention is shown. The method includes the following steps:

[0055] S10. Obtain the first pixel position of the display screen and the existing close-up screen captured by the conference tablet. The existing close-up screen is used to track the target person. The existing close-up screen corresponds to a capture box.

[0056] The displayed screen shows a live feed of the event captured by the conference tablet.

[0057] The conference tablet may have its own camera module, which is controlled to capture the display image. 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 aforementioned conference tablet can be connected to an external camera device. The external camera receives control commands from the conference tablet to capture the current space. The camera device can communicate with the conference tablet to transmit audio and video. The external camera device needs to cover the area where the conference tablet is located. It can be placed above the area where the conference tablet is located or on both sides parallel to the conference tablet, etc. There is no single limitation on the external camera.

[0059] The aforementioned close-up shots, which are images of the target person displayed on the conference tablet, have been shown through the display panel.

[0060] The aforementioned first pixel position is the focal point position of the cropping frame corresponding to the close-up image. The specific steps for obtaining this focal point are as follows: obtain the midpoint of the horizontal line of the cropping frame and the three-point lines perpendicular to the horizontal line; determine the intersection of the midpoint of the horizontal line and the three-point lines as the focal point; the position of this focal point is the position of the first pixel, as shown below. Figure 3A As shown.

[0061] The first pixel position includes a first horizontal coordinate and a first vertical coordinate. These first horizontal coordinates and first vertical coordinates can be obtained through the coordinate system configured on the display screen. The configuration of the display coordinate system usually follows a standard screen or image coordinate system. The following are examples of common display coordinate configuration methods. The first type is the top-left origin coordinate system, where the origin is located at the top-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. In 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 top boundary. The second type is the bottom-left origin coordinate system, where the origin is located at the bottom-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. In 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. In this coordinate system, the positive directions of the horizontal and vertical coordinates are 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 the coordinate system configured for the display screen is provided. The top left corner of the display screen is taken as the origin. A Y-axis with the vertical downward direction as positive and an X-axis with the right direction as positive are established. Area A is the display screen and area B is a specific screen. The current position of the first pixel can be obtained as (X1, Y1).

[0063] The cropping box corresponding to the aforementioned close-up shot can automatically track the target person and ultimately make the target person appear in focus. This cropping box is the area set in the conference tablet for selecting the target person, and the selection steps for the target person are not limited here.

[0064] As can be seen, by acquiring existing close-up images and corresponding capture frames, it is possible to track the target person. The acquisition of the first pixel position can be used to stabilize the display, reduce image jitter and unnecessary movement, and make the meeting screen smoother and easier to view.

[0065] S20. Determine the target person area corresponding to the target person and the second pixel position of the target person area on the display screen based on the display screen.

[0066] The target character area refers to any character area in the display screen. The target character area must contain the complete character area of ​​each character, and other characters besides the target character may also be present in this area.

[0067] The target person area may include the target person or other items or people besides the target person. Irrelevant people can be processed by Gaussian blur or virtualization.

[0068] For example, such as Figure 1C The system identifies person C speaking from region a, selects person C as the target, and selects the region corresponding to person C.

[0069] The aforementioned second pixel position is the reference point position corresponding to the target person's movement position before the close-up image is displayed. This reference point can be obtained through the following steps: generating a face recognition bounding box for the target person's area; obtaining the midpoint of the horizontal line of the face recognition bounding box and the trisection lines perpendicular to the horizontal line; determining the intersection of the midpoint and the trisection lines as the reference point; the position of this reference point is the second pixel position, which can be referenced. Figure 3C .

[0070] In the coordinate system described in step 10, such as Figure 3D As shown in the figure, the position of the second pixel (X2, Y2) can be represented as shown in the figure.

[0071] As can be seen, this solution can automatically adjust the camera's focal length and viewing angle based on the target person's position to ensure that the target person appears in focus, reducing the need for manual camera adjustments. Furthermore, obtaining the second pixel position enables 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 a timely manner to ensure that they are visible in the image.

[0072] S30. Calculate the position of the third pixel that satisfies the pixel alignment constraint based on the first pixel position and the second pixel position.

[0073] The aforementioned third pixel position refers to the pixel movement position of the cropping box that satisfies the pixel alignment constraint at the i+1th time in the close-up image during the i-th movement.

[0074] For example, given a close-up shot of the (i-1)th frame, assuming the focal point of the (i-1)th close-up shot has coordinates (Xi-1, Yi-1), and the character moves, the coordinates of the i-th close-up shot (Xi, Yi) are calculated using the movement speed v1 of the first frame. The i-th close-up shot is then output, but the target character area is not yet at the focal point. Next, the tablet uses the movement speed v2 of the second frame to calculate the coordinates of the (i+1)th close-up shot (Xi+1, Yi+1), and outputs the (i+1)th close-up shot. Again, the target character area is not yet at the focal point. Finally, the tablet uses the movement speed v3 of the third frame to calculate the coordinates of the (i+2)th close-up shot (Xi+2, Yi+2), and outputs the (i+2)th close-up shot. At this point, the target character area is at the focal point in the (i+2)th close-up shot. Meanwhile, since d=0, the movement speed v4=0, this embodiment will not move the capture frame to capture close-up shots.

[0075] The aforementioned pixel alignment constraint is a constraint in image processing or movement operations. It requires that image elements or objects be aligned or adjusted pixel by pixel when moved, scaled, or resized 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. Pixel alignment constraints typically include the following aspects: position alignment, size alignment, rotation alignment, and pixel grid alignment. In this scheme, a preset pixel alignment constraint value of 2 can be set to satisfy the pixel alignment constraint, rounded down to the nearest integer, with a maximum multiple of 2. The pixel alignment constraint value is not uniquely defined here; the specific pixel alignment constraint value can depend on various factors, including image processing requirements, application design, and specific image processing tasks.

[0076] For example, given the coordinates of the first pixel (X1, Y1) and the second pixel (X2, Y2), calculate the movement vector (ΔX, ΔY) from the first pixel to the second pixel, where ΔX = X2 - X1 and ΔY = Y2 - Y1. Obtain the preset pixel alignment constraint value that satisfies the pixel alignment condition, which can be calculated using the formula: X3 = X1 +

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

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

[0079] S40. Move the cropping box according to the position of the third pixel to obtain the moved cropping box.

[0080] The aforementioned moved capture box is a relative concept. For the capture box displayed on the conference tablet, its position does not change, nor does it jump from a fixed display area to another area. However, for the target person that the capture box needs to capture, it is not in a fixed position. The capture box will track the target person according to its movement speed. That is, the size of the capture box remains unchanged, but the content of the capture box will dynamically move with the target person as the target to ensure that the capture box can completely capture the target person area.

[0081] Optionally, moving the cropping box according to the third pixel position to obtain the moved cropping box includes: determining the coordinates of four vertices according to the third pixel position, and moving the cropping box according to the coordinates of the four vertices to obtain the moved cropping box.

[0082] The specific steps for determining the coordinates of the four vertices based on the position of the third pixel are as follows: Based on the information from the positions of the first and second pixels, determine the coordinates of the center point of the cropping box. These center point coordinates will be used as the center point of the cropping box. Then, calculate the width and height of the cropping box. Typically, the width and height can be determined by the distance from the first pixel position to the third pixel position, calculated using the following formulas: 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. The coordinates of the four vertices of the cropping box can be calculated using the following formulas: Top left vertex coordinates: (center point x - width / 2, center point y - height / 2); Top right vertex coordinates: (center point x + width / 2, center point y - height / 2); Bottom left vertex coordinates: (center point x - width / 2, center point y + height / 2); Bottom right vertex coordinates: (center point x + width / 2, center point y + height / 2). Based on the coordinates of the third pixel, the coordinates of the four vertices of the cropping box are calculated, thus moving the cropping box and obtaining the moved cropping box.

[0083] As can be seen, by moving the cropping box to the third pixel position that meets the pixel alignment constraints, the smoothness of the image can be ensured.

[0084] S50. Capture a close-up image of the target containing the target person area in the display screen according to the moved capture frame.

[0085] For example, in a remote meeting, the meeting tablet only displays... Figure 3A The left image shows a cropped frame, which is the border of the right image. The close-up view of the target is... Figure 3A The image on the right in the text.

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

[0087] The aforementioned close-up shots can be shots that include the target person's area or shots that only include the target person's area.

[0088] The aforementioned conference tablet can display close-up images in a specific area or display close-up images in the entire display panel of the conference tablet; this is not a unique limitation.

[0089] For example, if the conference tablet displays a close-up image in a specific area, it can be done according to... Figure 1C The D area in the text displays a specific region.

[0090] In existing technologies, at specific speeds, image movement is not smooth over time, exhibiting jerky or stuttering motion. Figure 3E As shown in the image, when the image attempts to move right at a speed of 3 pixels per frame, there will be intermediate coordinates that are not multiples of 2. In these cases, forced alignment is required to ensure the coordinates are multiples of 2. During the first movement, the coordinates that should be (123, 40) are forcibly aligned to (122, 40). During the second movement, the expected coordinates (126, 40) are aligned and retained. Therefore, the actual speed during the first movement is 2 pixels per frame, and the actual speed during the second movement is 4 pixels per frame. This repeated speed fluctuation between 2 and 4 causes uneven movement, resulting in image jitter.

[0091] This solution calculates the third pixel position that satisfies the pixel alignment constraint by using the first pixel position of the close-up image and the second pixel position of the target person. This ensures that the corresponding cropping box in the close-up image continuously approaches the target person and puts them in focus while tracking the target person. During this process, the close-up image is displayed smoothly while tracking, thus 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 constraint 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 constraint value; and calculating the third pixel position that satisfies the pixel alignment constraint value based on the moving speed, the first pixel position, and the preset pixel alignment constraint value.

[0093] The aforementioned movement speed refers to the movement speed of the capture box relative to the target person. Moving the capture box according to the movement speed can achieve the purpose of tracking the target person.

[0094] The aforementioned movement speed can be divided into horizontal and vertical velocity components. The horizontal velocity component (Vx) = (x-coordinate of the second pixel position - x-coordinate of the first pixel position) / time interval; the vertical velocity component (Vy) = (y-coordinate of the second pixel position - y-coordinate of the first pixel position) / time interval, where the time interval is the time taken for the movement between the two pixel positions.

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

[0096] The preset pixel alignment limit is a parameter set according to user needs or the conference tablet settings, which determines the alignment rules for pixel positions. For example, if the preset pixel alignment limit is 2, it means that the system expects pixels to move a maximum of 2 pixels at a time. The choice of the preset pixel alignment limit depends on the specific application scenario and requirements. It can control the granularity of pixel alignment, thereby affecting the smoothness and stability of the image.

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

[0098] As can be seen, by calculating the difference between the first pixel position and the second pixel position, the direction and speed of the target object's movement can be accurately determined. By obtaining the preset pixel alignment limit value, the pixel alignment behavior of the image can be adjusted according to the requirements, ensuring that the image can be adjusted according to the specified pixel alignment rules when moving, thus 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, and the third pixel position includes a second horizontal coordinate and a second vertical coordinate. Calculating the third pixel position that satisfies the pixel alignment constraint based on the moving speed, the first pixel position, and the preset pixel alignment constraint value includes: determining the horizontal velocity of the moving speed along the x-axis and the vertical velocity along the y-axis in the coordinate system; calculating the second horizontal coordinate that satisfies the pixel alignment constraint based on the horizontal velocity, the first horizontal coordinate, and the preset pixel alignment constraint value; and calculating the second vertical coordinate that satisfies the pixel alignment constraint based on the vertical velocity, the first vertical coordinate, and the preset pixel alignment constraint value.

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

[0101] Wherein, 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] As can be seen, by adjusting the movement speed, the first pixel position, and the preset pixel alignment limit, the conditions for pixel alignment are ensured to be met. During the tracking process, the position of the cropping box is adjusted based on the relative motion between the close-up image and the face recognition box to achieve the effect of pixel alignment.

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

[0104] The candidate x-coordinates mentioned above represent the next x-coordinate position based on the velocity estimate.

[0105] For example, the horizontal velocity = 4.5 pixels / frame; the first horizontal coordinate = 23.8 pixels; the preset pixel alignment limit = 10 pixels; the candidate horizontal coordinate = the horizontal velocity + the first horizontal coordinate, i.e., 4.5 + 23.8 = 28.3 pixels. To determine the closest second horizontal coordinate that satisfies the pixel alignment limit, in this case, the closest horizontal coordinate that satisfies the pixel alignment limit is 30 pixels, because it is an integer multiple of the closest candidate horizontal coordinate 28.3 pixels, and also an integer multiple of the preset pixel alignment limit of 10 pixels. Therefore, based on the horizontal velocity, the first horizontal coordinate, and the preset pixel alignment limit, the second horizontal coordinate that satisfies the pixel alignment limit is calculated to be 30 pixels.

[0106] As can be seen, by calculating the candidate horizontal coordinate by the sum of the horizontal velocity and the first horizontal coordinate, the next horizontal coordinate position estimated based on the velocity is reflected, ensuring that the new position is aligned with the current pixel. Among all possible horizontal coordinates, the one closest to the candidate horizontal coordinate is selected, and this horizontal coordinate must meet the pixel alignment constraint condition, that is, it must be an integer multiple of the preset pixel alignment constraint 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 the horizontal coordinate that is smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and 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 the horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and an integer multiple of the preset pixel alignment limit value as the second horizontal coordinate.

[0108] In the section where the second horizontal coordinate is selected if the decimal value of the candidate horizontal coordinate is less than 0.5, the horizontal coordinate closest to the candidate horizontal coordinate, and is an integer multiple of the preset pixel alignment limit, is chosen as the second horizontal coordinate. Assume the following values: horizontal speed = 6 pixels / second, first horizontal coordinate = 28 pixels, preset pixel alignment limit = 10 pixels. The 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 choose a horizontal coordinate smaller than the candidate horizontal coordinate and an integer multiple of the preset pixel alignment limit. The preset pixel alignment limit is 10 pixels, so we need to choose an integer that is closest to 34 pixels and is an integer multiple of 10, thus obtaining a second horizontal coordinate of 30 pixels that satisfies the pixel alignment limit.

[0109] In the process of selecting 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, the horizontal coordinate that is larger than the candidate horizontal coordinate, closest to the candidate horizontal coordinate, and an integer multiple of the preset pixel alignment limit value is chosen. 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), the horizontal coordinate that is larger than the candidate horizontal coordinate and an integer multiple of the preset pixel alignment limit value is chosen. The preset pixel alignment limit value is 12 pixels, so we need to choose an integer that is closest to 53 pixels and an integer multiple of 12. Therefore, the second horizontal coordinate that satisfies the pixel alignment limit condition is 60 pixels.

[0110] As can be seen, on the one hand, when the value of the candidate x-coordinate is less than 0.5, it means that it is closer to the previous integer pixel. By selecting a x-coordinate that is smaller than the candidate x-coordinate, the closest, and an integer multiple of the preset pixel alignment limit, it is ensured that the second x-coordinate is closer to the previous integer pixel than the candidate x-coordinate, which helps to maintain the alignment of the image. On the other hand, when the value of the candidate x-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 x-coordinate that is larger than the candidate x-coordinate, the closest, and an integer multiple of the preset pixel alignment limit, it is ensured that the second x-coordinate is closer to the next integer pixel than the candidate x-coordinate, which helps to maintain the alignment of the image.

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

[0112] When the horizontal velocity is less than the preset pixel alignment limit, it indicates that the horizontal velocity 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. Due to pixel alignment requirements, it cannot move to the next integer pixel position and therefore must remain at the current pixel position.

[0113] Specifically, when the horizontal velocity is greater than or equal to a preset pixel alignment limit, it indicates that the horizontal velocity is fast enough to span one or more integer pixel units. In this case, the sum of the horizontal velocity and the first horizontal coordinate is calculated to obtain a candidate horizontal coordinate, ensuring that even at a relatively high speed, the movement can meet the pixel alignment requirements without misalignment.

[0114] As can be seen, this step ensures that the final second horizontal coordinate can meet the pixel alignment constraint, regardless of the speed.

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

[0116] Among them, longitudinal velocity is used to describe the value of the movement speed in the vertical direction.

[0117] Specifically, the vertical velocity is rounded down to an integer multiple of the preset pixel alignment limit. For example, if the preset pixel alignment limit is 2 pixels and the calculated velocity is 3.5 pixels per frame, the rounding operation will constrain it to 4 pixels per frame.

[0118] As can be seen, this step ensures pixel alignment in the vertical direction, improving the stability and accuracy of movement.

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

[0120] In this process, if the decimal value of the vertical speed is less than 0.5, the speed closest to the vertical speed and an integer multiple of the preset pixel alignment limit is selected as the reference speed. For example: the first vertical coordinate is 85 pixels; the vertical speed is 2.3 pixels / frame; the preset pixel alignment limit is 4 pixels; the decimal part of the vertical speed is 0.3, which is less than 0.5. Therefore, we will select a speed that is less than 2.3 pixels / frame and an integer multiple of 4 pixels. The closest speed that meets the condition is 0 pixels / frame, because 0 is an integer multiple of 4. Therefore, the reference speed is 0 pixels / frame, and the second vertical coordinate = 85 pixels + 0 pixels / frame = 85 pixels; which meets the pixel alignment limit condition.

[0121] In this process, if the decimal value of the vertical speed is greater than or equal to 0.5 and less than 1, then the speed that is greater than the vertical speed, closest to the vertical speed, and an integer multiple of the preset pixel alignment limit is selected as the reference speed. For example: the first vertical coordinate is 125 pixels; the vertical speed is 3.7 pixels / frame; and the preset pixel alignment limit is 5 pixels. The decimal part of the vertical 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 an integer multiple of 5 pixels. The closest speed that meets the condition is 5 pixels / frame because 5 is an integer multiple of 5. Therefore, the reference speed is 5 pixels / frame, resulting in the second vertical coordinate = 125 pixels + 5 pixels / frame = 130 pixels.

[0122] As can be seen, by rounding the vertical velocity, the reference velocity is ensured to be an integer. This makes it easier to perform pixel alignment when calculating the second vertical coordinate. Furthermore, by selecting the closest integer velocity, the error introduced by velocity calculation and rounding is reduced, thereby improving the accuracy of pixel alignment.

[0123] Based on the above steps, an example can be given: Assume the preset pixel alignment limit is 2, meaning 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 velocity V on the x-axis. fx The moving speed V on the y-axis is 7.3. fy It 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 coordinates are 107.3. After aligning downwards, we get X. i The value is 106. On the y-axis, the actual instantaneous velocity 4.2 is taken down to the largest integer multiple of 2, resulting in 4. Therefore, V... y If the velocity is taken downwards as 4, then the Y-axis coordinate of the next step is obtained. i The coordinates are 104. Therefore, the coordinates of the first step are (106, 104).

[0124] Repeat the above steps. If the calculated velocity is V on the current x-axis... fx The moving speed V on the y-axis is 5.8. fy It is 2.4. On the x-axis, based on the recorded coordinates X... i-1 It is 107.3, plus the instantaneous velocity V fx To obtain the latest X f The coordinates are 113.1, and after downward alignment, we get X. i It is 112. On the y-axis, it is determined by Y. i-1 The actual instantaneous velocity 2.4 is taken down to the largest integer multiple of 2, resulting in 2. Therefore, V...y If the velocity is taken downwards as 2, then the Y-axis coordinate of the next step is obtained. i The value is 106. Therefore, the coordinates for the second step are (112, 106). If further image processing is needed, repeat the above steps. For example, when the calculation speed yields a new V... fx For 5.8 and V fy When the value is 2.4, the coordinate positions on the X and Y axes are repeatedly calculated and the coordinates are updated sequentially.

[0125] In summary, this section describes an algorithm or method that processes image coordinates according to pixel alignment requirements (align=2), ensuring they are always integer multiples of 2, and updates the coordinate positions based on computation speed information, thereby achieving smooth image processing. 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 this application has been described above; the apparatus of this application will be described below.

[0127] See Figure 4 , Figure 4 This is a schematic diagram of the structure of an image smoothing device for close-up shots provided in an embodiment of this application. Figure 4 As shown, the image smoothing device for this close-up shot includes:

[0128] The acquisition unit 401 is used to acquire the first pixel position of the display screen and the existing close-up screen captured by the conference tablet. The existing close-up screen is used to track the target person, and the existing close-up screen corresponds to the capture box.

[0129] Determining unit 402 is used to determine, based on the display screen, the target person area corresponding to the target person and the second pixel position of the target person area on the display screen;

[0130] The calculation unit 403 is used to calculate the position of the third pixel that satisfies the pixel alignment constraint based on the first pixel position and the second pixel position;

[0131] The moving unit 404 is used to move the cropping box according to the position of the third pixel to obtain the moved cropping box;

[0132] The cropping unit 405 is used to crop a close-up image of the target person area in the display screen according to the moved cropping frame;

[0133] Display unit 406 is used to control the conference tablet to display the close-up image of the target.

[0134] In one embodiment, in the step of calculating the third pixel position that satisfies the pixel alignment constraint based on the first pixel position and the second pixel position, the calculation unit 403 is further configured to: calculate the moving speed based on the first pixel position and the second pixel position; obtain a preset pixel alignment constraint value; and calculate the third pixel position that satisfies the pixel alignment constraint based on the moving speed, the first pixel position and the preset pixel alignment constraint 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, and the third pixel position includes a second horizontal coordinate and a second vertical coordinate. In the process of calculating the third pixel position that satisfies the pixel alignment constraint based on the moving speed, the first pixel position, and the preset pixel alignment constraint value, the calculation unit 403 is further configured to: determine the horizontal velocity of the moving speed in the x-axis direction and the vertical velocity in the y-axis direction of the coordinate system; calculate the second horizontal coordinate that satisfies the pixel alignment constraint based on the horizontal velocity, the first horizontal coordinate, and the preset pixel alignment constraint value; and calculate the second vertical coordinate that satisfies the pixel alignment constraint based on the vertical velocity, the first vertical coordinate, and the preset pixel alignment constraint value.

[0136] In one embodiment, in the step of calculating the second horizontal coordinate that satisfies the pixel alignment constraint based on the horizontal velocity, the first horizontal coordinate, and the preset pixel alignment constraint value, the calculation unit 403 is further configured to: calculate the sum of the horizontal velocity 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 constraint value as the second horizontal coordinate.

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

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

[0139] In one embodiment, in the step of calculating the second ordinate that satisfies the pixel alignment constraint based on the vertical speed, the first ordinate, and the preset pixel alignment constraint value, the calculation unit 403 is further configured to: perform a rounding operation on the vertical speed according to the preset pixel alignment constraint value to obtain an integer reference speed, wherein the reference speed is an integer multiple of the preset pixel alignment constraint value; and calculate the sum of the reference speed and the first ordinate to obtain the second ordinate.

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

[0141] This solution calculates the third pixel position that satisfies the pixel alignment constraint by using the first pixel position of the close-up image and the second pixel position of the target person. This ensures that the corresponding cropping box in the close-up image continuously approaches the target person and puts them in focus while tracking the target person. During this process, the close-up image is displayed smoothly while tracking, thus ensuring image stability, reducing image jitter, and providing a better visual experience.

[0142] See Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this 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] Processor 501 is configured to support the computer device 50 in performing the corresponding functions in the methods described in the above method embodiments. Processor 501 may be a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof. The aforementioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The aforementioned PLD may 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 transmitting card, a receiving card, and a driver chip.

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

[0146] Processor 501 can call the program code to perform the following operations:

[0147] The first pixel position of the display screen and the existing close-up screen captured by the conference tablet is obtained. The existing close-up screen is used to track the target person. The existing close-up screen corresponds to the capture box.

[0148] Determine the target person area corresponding to the target person and the second pixel position of the target person area on the display screen based on the display screen;

[0149] Based on the first pixel position and the second pixel position, calculate the third pixel position that satisfies the pixel alignment constraint.

[0150] The cropping box is moved according to the third pixel position to obtain the moved cropping box;

[0151] Based on the moved capture frame, a close-up image of the target person area is captured in the display screen;

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

[0153] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the method described in the foregoing embodiments.

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

[0155] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. An image smoothing method for a close-up picture applied to a conference panel, characterized by, The method comprises the following steps: acquiring a first pixel position of a display picture captured by the conference tablet and an existing close-up picture, the existing close-up picture being used for tracking a target person, and the existing close-up picture corresponding to a clipping frame; determining 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; calculating a third pixel position satisfying a pixel alignment restriction condition according to the first pixel position and the second pixel position; moving the clipping frame according to the third pixel position to obtain a moved clipping frame; clipping a target close-up picture containing the target person region in the display picture according to the moved clipping frame; controlling the conference tablet to display the target close-up picture.

2. The method of claim 1, wherein, The step of calculating the third pixel position satisfying the pixel alignment restriction condition according to the first pixel position and the second pixel position comprises the following steps: calculating a moving speed according to the first pixel position and the second pixel position, wherein the moving speed is the moving speed of the clipping frame relative to the target person when the target person moves; acquiring a preset pixel alignment restriction value; 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.

3. The method of claim 2, wherein, The display picture is configured with a coordinate system, the first pixel position comprises a first horizontal coordinate and a first vertical coordinate, the third pixel position comprises a second horizontal coordinate and a second vertical coordinate, and the step of 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 comprises the following steps: determining a horizontal speed in the x-axis direction and a vertical speed in the y-axis direction of the coordinate system of the moving speed; calculating the second horizontal coordinate satisfying the pixel alignment restriction condition according to the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value; calculating the second vertical coordinate satisfying the pixel alignment restriction condition according to the vertical speed, the first vertical coordinate and the preset pixel alignment restriction value.

4. The method of claim 3, wherein, The step of calculating the second horizontal coordinate satisfying the pixel alignment restriction condition according to the horizontal speed, the first horizontal coordinate and the preset pixel alignment restriction value comprises the following steps: calculating the sum of the horizontal speed and the first horizontal coordinate to obtain a candidate horizontal coordinate; determining the horizontal coordinate closest to the candidate horizontal coordinate and having an integer multiple relationship with the preset pixel alignment restriction value as the second horizontal coordinate.

5. The method of claim 4, wherein, The step of determining the horizontal coordinate closest to the candidate horizontal coordinate and having an integer multiple relationship with the preset pixel alignment restriction value as the second horizontal coordinate comprises the following steps: if the decimal value of the candidate horizontal coordinate is less than 0.5, selecting the horizontal coordinate smaller than the candidate horizontal coordinate, closest to the candidate horizontal coordinate and having an integer multiple relationship with the preset pixel alignment restriction 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, selecting the horizontal coordinate greater than the candidate horizontal coordinate, closest to the candidate horizontal coordinate and having an integer multiple relationship with the preset pixel alignment restriction value as the second horizontal coordinate.

6. The method of claim 4, wherein, Before the step of calculating the candidate horizontal coordinate, the method further comprises the following steps: determining whether the horizontal velocity is less than the preset pixel alignment limit value; if less, setting the value of the second horizontal coordinate as the value of the first horizontal coordinate; if greater than or equal to, calculating the sum of the horizontal velocity and the first horizontal coordinate to obtain a candidate horizontal coordinate.

7. The method of claim 3, wherein, The calculating the second vertical coordinate satisfying the pixel alignment limit condition according to the longitudinal velocity, the first vertical coordinate and the preset pixel alignment limit value comprises: performing an integer operation on the longitudinal velocity according to the preset pixel alignment limit value to obtain an integer type reference velocity, the reference velocity being in an integer multiple relationship with the preset pixel alignment limit value; calculating the sum of the reference velocity and the first vertical coordinate to obtain a second vertical coordinate.

8. The method of claim 7, wherein, The performing an integer operation on the longitudinal velocity according to the preset pixel alignment limit value to obtain an integer type reference velocity comprises: if the decimal value of the longitudinal velocity is less than 0.5, selecting a velocity smaller than the longitudinal velocity, closest to the longitudinal velocity and in an integer multiple relationship with the preset pixel alignment limit value as the reference velocity; if the decimal value of the longitudinal velocity is greater than or equal to 0.5 and less than 1, selecting a velocity greater than the longitudinal velocity, closest to the longitudinal velocity and in an integer multiple relationship with the preset pixel alignment limit value as the reference velocity.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program comprising program instructions, the program instructions causing the processor to execute the close-up picture image smoothing method of any one of claims 1-8 when executed by the processor.

10. A conference panel, characterized by comprise: a camera for collecting a display picture; a microphone array for collecting voice information; a memory; a processor in communication connection with the camera, the microphone array and the memory respectively, wherein the processor is configured to execute one or more computer programs stored in the memory, and the processor, when executing the one or more computer programs, causes the conference tablet to implement the close-up picture image smoothing method of any one of claims 1-8.

Images