Multi-camera focusing method and device, equipment and storage medium

Abstract

The invention relates to the technical field of display equipment, in particular to a multi-camera focusing method and device, equipment and a storage medium, and the method comprises the steps: controlling a second camera to execute a pre-focusing operation when a conference panel displays a first image shot by a first camera, and obtaining the pre-focusing information of a focusing object, obtaining a target picture shot by a second camera; determining real-time focusing information of the focusing object according to the target picture; and controlling the second camera to keep focusing the focusing object according to the real-time focusing information and the pre-focusing information. According to the scheme, when the first camera displays, the second camera is controlled to perform the pre-focusing operation on the jointly collected focusing object in advance, so that on one hand, the current display process of the first camera is not influenced, and on the other hand, the second camera can smoothly and quickly display a clear picture when the switching instruction is received.

Description

Technical Field

[0001] The present invention relates to the technical field of display devices, and in particular to a multi-camera focusing method, device, equipment and storage medium. Background Art

[0002] In a video conference on a conference tablet, it may be necessary to switch the same panoramic image to a local image of the conference participants. In this case, multiple cameras in the conference tablet need to work together.

[0003] In the prior art, after the panoramic display screen is switched from the first camera to the second camera used to display local meeting personnel, the second camera begins to focus on the local meeting personnel. However, this existing method has a slow focusing process and a brief blurring of the screen after switching, resulting in delayed and unclear display of the screen of the local meeting personnel. Summary of the invention

[0004] One purpose of an embodiment of the present invention is to provide a multi-camera focusing method, device, equipment and storage medium, which are used to solve the technical problems of image delay and unclear image when multiple cameras switch conference images in a video conference.

[0005] In a first aspect, an embodiment of the present invention provides a multi-camera focusing method, which is applied to a conference tablet, wherein the conference tablet includes a first camera and a second camera, including:

[0006] When the conference tablet displays the first picture captured by the first camera, the second camera is controlled to perform a pre-focus operation to obtain pre-focus information of a focus object, where the focus object is the focus object collected by the first camera and the second camera together;

[0007] In response to a camera switching command, a target image captured by the second camera is obtained, wherein the camera switching command is used to instruct the conference tablet to switch from displaying the first image captured by the first camera to displaying the target image captured by the second camera;

[0008] Determining real-time focus information of the focus object according to the target picture;

[0009] The second camera is controlled to keep focusing on the focus object according to the real-time focus information and the pre-focus information.

[0010] In combination with the first aspect, in a possible implementation method, when the conference tablet displays the first picture taken by the first camera, the second camera is controlled to perform a pre-focus operation to obtain pre-focus information of the focus object, including: obtaining the second picture taken by the second camera; determining the overlapping area of ​​the pictures based on the first picture and the second picture; and determining the pre-focus information of the focus object based on the overlapping area of ​​the pictures.

[0011] In combination with the first aspect, in a possible implementation method, the conference tablet also includes a motor, which is used to adjust the position of the second camera, and determining the pre-focus information of the focus object based on the picture overlap area includes: judging whether the picture overlap area contains the focus object; if it does, determining the pre-focus information of the focus object; if it does not, controlling the motor to adjust the second camera to re-shoot the second picture.

[0012] In combination with the first aspect, in a possible implementation method, determining whether the overlapping area of ​​the pictures contains a focus object includes: extracting the object in the overlapping area of ​​the pictures; determining whether the object meets a preset focus condition; if so, determining that the object is the focus object; if not, controlling the motor to adjust the second camera to re-shoot the second picture.

[0013] In combination with the first aspect, in a possible implementation method, the pre-focus information includes pre-object information, pre-focus position and pre-rotation position of the focus object, and the determination of the pre-focus information of the focus object includes: recording the pre-object information and pre-focus position of the focus object, the pre-object information including identity information and pre-object size information of the focus object; determining the pre-rotation position of the motor when the second camera obtains the second picture.

[0014] In combination with the first aspect, in a possible implementation method, the real-time focus information includes real-time object information, real-time focus position and real-time rotation position of the focus object, and determining the real-time focus information of the focus object according to the target picture includes: recording the real-time object information and real-time focus position of the focus object at the current time, the real-time object information including identity information and real-time object size information of the focus object; determining the real-time rotation position of the motor at the current time.

[0015] In combination with the first aspect, in a possible implementation manner, controlling the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information includes: calculating the object offset of the focus object according to the real-time focus information and the pre-focus information; determining whether the object offset is less than a preset offset threshold; if less than, controlling the second camera to keep focusing on the focus object according to the pre-focus information; if greater than, controlling the second camera to refocus on the focus object.

[0016] In combination with the first aspect, in a possible implementation, the object offset includes a position offset and / or an object size offset, the real-time focus information includes a real-time focus position and real-time object size information, the pre-focus information includes a pre-focus position and a pre-object size information, and calculating the object offset of the focus object based on the real-time focus information and the pre-focus information includes: calculating the difference between the real-time focus position and the pre-focus position to obtain a position offset, and / or calculating the difference between the real-time object size information and the pre-object size information to obtain an object size offset.

[0017] In a second aspect, an embodiment of the present invention provides a multi-camera focusing device, which is applied to a conference tablet, characterized in that the conference tablet includes a first camera and a second camera, including:

[0018] A control unit, configured to control the second camera to perform a pre-focus operation and obtain pre-focus information of a focus object when the conference tablet displays a first picture captured by the first camera, wherein the focus object is a focus object collected jointly by the first camera and the second camera;

[0019] An acquisition unit, configured to respond to a camera switching command to acquire a target image captured by the second camera, wherein the camera switching command is configured to instruct the conference tablet to switch from displaying the first image captured by the first camera to displaying the target image captured by the second camera;

[0020] A determination unit, configured to determine real-time focus information of the focus object according to the target picture;

[0021] The control unit is further used to control the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information.

[0022] In a third aspect, a conference tablet is characterized by comprising:

[0023] case;

[0024] A first camera, disposed on the housing;

[0025] a second camera, disposed on the housing, wherein a position of the second camera on the housing is different from a position of the first camera on the housing;

[0026] Motors, connected to the first camera and the second camera respectively;

[0027] A controller is electrically connected to the first camera, the second camera and the motor, respectively, and is used to control the motor to adjust the position of the second camera, wherein the controller includes a memory and a processor, the memory is connected to the processor, and 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 above.

[0028] 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.

[0029] 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.

[0030] In the scheme implemented by the above-mentioned multi-camera focusing method, device, equipment and storage medium, when the conference tablet displays the first picture taken by the first camera, the second camera is first controlled to perform a pre-focus operation to obtain the pre-focus information of the focus object, and the focus object is the focus object collected by the first camera and the second camera together. Secondly, in response to the camera switching command, the target picture taken by the second camera is obtained. The camera switching command is used to instruct the conference tablet to switch from displaying the first picture taken by the first camera to displaying the target picture taken by the second camera. Then, the real-time focus information of the focus object is determined according to the target picture. Finally, the second camera is controlled to keep focusing on the focus object according to the real-time focus information and the pre-focus information. Through this scheme, when the first camera is displayed, the second camera can be controlled to perform a focus operation on the focus object collected together in advance, and then the target picture can be focused on at the same time in the background without affecting the current display picture of the first camera. When switching to the target picture, the focus target picture is further dynamically adjusted according to the real-time focus and pre-focus information of the target picture to achieve a smooth and clear display of the target picture. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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.

[0032] Figure 1A This is a hardware architecture diagram of a conference tablet in one embodiment of the present invention;

[0033] Figure 1B This is a module diagram of a conference tablet in one embodiment of the present invention;

[0034] Figure 1C It is a scene diagram of a conference tablet in one embodiment of the present invention;

[0035] Figure 2 is a flow chart of a multi-camera focusing method in one embodiment of the present invention;

[0036] Figure 3 is a schematic diagram of a screen overlap area in one embodiment of the present invention;

[0037] Figure 4 is a schematic structural diagram of a multi-camera focusing device in one embodiment of the present invention;

[0038] Figure 5 It is a schematic diagram of the structure of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] 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.

[0041] The technical solution of this application can be applied to various conference scenarios, such as remote conferences, etc.

[0042] 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.

[0043] 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 1A As shown, the conference tablet 10 includes a display panel 101, a microphone array 102, a camera module 103, a controller 104, and a motor 105. The display panel 101 is used to display the video stream image collected by the conference tablet 10 through the camera module 103; 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 an integration of the two. In this solution, the camera module 102 may include a first camera and a second camera, wherein the first camera is set as a main camera and the second camera is set as a secondary camera; the controller 104 is electrically connected to the first camera, the second camera and the motor 105 respectively, and is used to control the motor to adjust the position of the second camera, wherein the controller 104 includes a memory and a processor, and the memory and the processor 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. The motor 106 is used to adjust the position of the camera module 103 in the conference tablet 10 .

[0044] Among them, Figure 1B As shown, the conference tablet 10 includes four major functional modules: a camera image acquisition module: mainly collects original video information through more than two cameras; a target position calculation module: calculates the position and rough distance of the target according to the original audio and video information; an electronic focus module: focuses the camera according to the position of the target; and a camera switching module: switches between different cameras as needed.

[0045] like Figure 1C As shown, Figure 1C For example, in a video conference, the control of the first camera of the conference tablet collects a panoramic picture of the current conference room. Figure 1CAs shown in the left figure, when a switching command is received, the second camera will be controlled to switch the screen. The second camera will shoot an area such as Figure 1C As shown in the middle picture in the figure, the screen captured by the second camera is finally displayed on the conference flat panel as follows Figure 1C As shown in the right figure.

[0046] The present invention is described in detail below through specific embodiments.

[0047] See also Figure 2 , Figure 2 A flowchart of a multi-camera focusing method provided by an embodiment of the present invention is applied to a conference tablet, wherein the conference tablet includes a first camera and a second camera, and the method includes the following steps:

[0048] S10. When the conference tablet displays the first picture taken by the first camera, control the second camera to perform a pre-focus operation to obtain pre-focus information of a focus object, where the focus object is a focus object captured by the first camera and the second camera together.

[0049] The conference tablet further includes a motor, which can adjust the position of the second camera and the position of the first camera.

[0050] Specifically, the motor as a camera control device can be controlled by the camera user or automation system to adjust the direction, focal length, stability and other parameters of the camera to achieve different shooting needs and functions. For example, the motor can rotate, tilt or translate the camera to change the shooting angle and field of view; the motor can also adjust the position of the camera according to the camera's posture to reduce shaking and blur, which is conducive to shooting stable videos or clear photos; the motor is also used to automatically adjust the direction of the camera to track moving targets.

[0051] For example, in this solution, the conference tablet displays the first picture taken by the first camera on the display panel, starts the second camera, determines the common collection area of ​​the second camera and the first camera, obtains the focus object within the common collection area, and the second camera locks the focus object. The controller in the conference tablet uses a motor to control the second camera to change the focal length or lens position to ensure that the focus object is always within the focus range.

[0052] Among them, the shooting range of the first camera is larger than the shooting range of the second camera.

[0053] Optionally, the commonly collected focus objects are multiple focus objects, and the second camera is controlled to perform pre-focus operations on the multiple focus objects in sequence to obtain pre-focus information of each of the multiple focus objects.

[0054] The above-mentioned pre-focus operation means that while the conference tablet keeps the first camera displaying the first screen, the second camera can be pre-operated in the background to focus on the focus object captured by the first camera and the second camera. The pre-focus operation can be started by the conference tablet issuing a pre-focus operation instruction, which can be manually input by the user or automatically started when the conference tablet is turned on. There is no sole restriction here.

[0055] The above-mentioned focus information refers to various information and data used to help the camera module achieve correct focus. This information helps to ensure that the photographed target remains clear and sharp. The above-mentioned focus information may include but is not limited to focus point position information, contrast information, depth information, autofocus algorithm output, tracking information, rotation position, etc. Among them, the focus position information refers to the focus position in the image measured or calculated by the camera, usually expressed in pixel coordinates or focal distance. The focus position information is used to adjust the lens position or focal length to ensure accurate focus; the rotation position refers to the rotation position corresponding to the motor after focusing.

[0056] The pre-focus information in the present scheme refers to various information and data for pre-achieving correct focus. The above-mentioned pre-focus information can be a pre-focus position and a pre-rotation position, and can also include identity information of the focus object. The identity information is used to distinguish each focus object among multiple focus objects, and the pre-focus position and pre-rotation position corresponding to each focus object are combined into sub-pre-focus information.

[0057] Optionally, the focus object may be a plurality of objects, that is, the obtained sub-pre-focus information of each object in the plurality of objects constitutes the pre-focus information.

[0058] It can be seen that when the conference tablet displays the first picture taken by the first camera, the second camera is controlled to perform a pre-focus operation. Since the pre-focus operation is performed before the second camera actually shoots, the focusing time can be significantly reduced, which is conducive to quickly switching cameras or capturing important moments without waiting for the camera to actually focus. The pre-focus operation helps to reduce the problem of blurred or unclear images caused by incorrect camera focal length or inaccurate focus, which further reflects the degree of automation of the present solution and improves the automation and intelligence of the conference tablet.

[0059] S20. Respond to a camera switching command to obtain a target image captured by the second camera, wherein the camera switching command is used to instruct the conference tablet to switch from displaying the first image captured by the first camera to displaying the target image captured by the second camera.

[0060] For example, the switching process in step S20 can refer to the above Figure 1C .

[0061] The camera switching command is used to switch multiple cameras in the conference tablet. The switching command is issued to ensure that the conference, live broadcast or recorded images can be switched and adjusted as needed, such as displaying different images taken by different cameras on the display panel of the conference tablet. The camera switching command is issued by a variety of different entities or devices, depending on the application scenario and system design. For example, the camera switching command can be manually issued in the display panel or the camera switching can be controlled by voice commands, such as using the verbal command of "Hey, Assistant" is not the only limitation here.

[0062] Optionally, after responding to a camera switching command, the conference tablet switches from displaying the first picture taken by the first camera to displaying the target picture taken by the second camera. At this time, the first picture is not presented in the display panel of the conference tablet, and the display panel only presents the target picture taken by the second camera.

[0063] It can be seen that by responding to the switching command and switching the conference tablet from displaying the screen of the first camera to the target screen of the second camera, the screen switching can be made smoother. Further, by switching to the screen of the second camera, the audience can obtain information from different angles and perspectives, highlighting the richness of multiple cameras and providing more comprehensive information. It can also be further concluded that the visual content of the meeting can be flexibly controlled according to the operation of switching cameras, so as to dynamically adjust the camera display according to the progress or needs of the meeting.

[0064] S30: Determine real-time focus information of the focus object according to the target image.

[0065] The real-time focus information may be real-time object information, real-time focus position and real-time rotation position at the current time, and the real-time object information includes identity information and real-time object size information of the focus object, and the identity information may distinguish each focus object.

[0066] It can be seen that before implementing step S40, by acquiring the real-time focus information in the target image, immediate feedback can be obtained during the shooting process to ensure the focus processing method for the target image in subsequent steps.

[0067] S40: Control the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information.

[0068] Among them, the object offset of the two focus positions can be calculated by the focus position in the real-time focus information and the focus position of the same focus object in the pre-focus information, and it is determined whether the object offset is less than a preset offset threshold. If it is less than, the second camera is controlled to keep focusing on the focus object according to the pre-focus information; if it is greater, the second camera is controlled to refocus on the focus object.

[0069] Among them, the object offset is usually expressed in pixels or other units, which is used to measure whether the focus object deviates from the expected position. It can be calculated through the real-time focus position and pre-focus position of the same focus object. If the object offset is less than or equal to the preset offset threshold, it will be considered that the focus object is still within an acceptable range and no major focus adjustment is required. If the offset is greater than the preset threshold, it will be considered that the focus object has deviated from the ideal position and a major focus adjustment is required.

[0070] The preset offset threshold may be 0-5 mm, which may be set manually and is not limited here.

[0071] Specifically, there are multiple focus objects A, B, and C. If the object offset between the real-time focus position and the pre-focus position of the focus object A is greater than the preset object offset, it is determined that A has a large position change and has exceeded the position range where the pre-focus position can be focused clearly, and then A is re-focused in real time, and the pre-focus information corresponding to A is deleted and replaced with the focus information of the real-time focus of A. If the object offset between the real-time focus position and the pre-focus position of B and C is less than the preset object offset, it is determined that B and C do not have a large position change, and the pre-focus information corresponding to B and C is directly used for focusing, which can achieve a fast focusing effect.

[0072] It can be seen that by comparing the difference between the real-time focus information and the pre-focus information of the focus object, it is possible to quickly obtain which focus objects in the target picture are offset and have exceeded the range of the pre-focus record. If the pre-focus information is used for the focus object that has already offset, it may cause the picture to become blurred or distorted. At this time, re-focusing the offset focus object in real time can obtain a clear picture, and hiding the focus action to ensure the viewing experience.

[0073] In one embodiment, when the conference tablet displays the first picture taken by the first camera, the second camera is controlled to perform a pre-focus operation to obtain pre-focus information of the focus object, including: obtaining the second picture taken by the second camera; determining the overlapping area of ​​the pictures based on the first picture and the second picture; and determining the pre-focus information of the focus object based on the overlapping area of ​​the pictures.

[0074] For example, see Figure 3 ,like Figure 3 As shown, the first camera image in the figure is the first image of this solution, and the second camera image is the second image of this solution. As shown in the figure, the overlapping area is the second image, and the jointly captured focus object can be obtained in the overlapping area.

[0075] The above processes of acquiring the second screen and determining the overlapping area are unknown to the user, that is, they are run in the background of the conference tablet, and therefore will not affect the display effect of the currently displayed first screen.

[0076] It can be seen that by determining the overlapping area of ​​the screen, it is possible to quickly respond to changes in the meeting and adjust the focus accordingly, which helps to adapt to different shooting needs, such as switching the focal length or focusing on different focus objects.

[0077] In one embodiment, the conference tablet also includes a motor, which is used to adjust the position of the second camera. The pre-focus information of the focus object determined based on the picture overlap area includes: judging whether the picture overlap area contains the focus object; if it does, determining the pre-focus information of the focus object; if it does not, controlling the motor to adjust the second camera to re-shoot the second picture.

[0078] The motor is a mechanical device used to change the position or direction of the second camera, that is, to adjust the direction or angle of the second camera to ensure that it can be aimed at a specific area of ​​the subject or picture.

[0079] Among them, in the overlapping area of ​​the picture, it can be determined whether there is a focused object based on image recognition and detection algorithms.

[0080] It can be seen that by judging whether the overlapping area of ​​the pictures contains the focus object, the motor is controlled to adjust the position of the second camera to avoid misfocusing.

[0081] In one embodiment, determining whether the overlapping area of ​​the pictures contains a focus object includes: extracting the object in the overlapping area of ​​the pictures; determining whether the object satisfies a preset focus condition; if so, determining that the object is the focus object; if not, controlling the motor to adjust the second camera to re-shoot the second picture.

[0082] The objects in the overlapping area of ​​the pictures can be extracted by conventional image recognition or image detection technology.

[0083] The preset focus condition is used to perform focus evaluation on the extracted object to determine whether the preset focus condition is met. The focus condition may include the clarity, distance, position or other visual attributes of the object.

[0084] If the focus condition is not met, it may mean that the object is blurred, moved out of the picture, or is no longer in focus. In this case, the motor control measures will be taken to adjust the position or angle of the second camera to retake the second picture and find the focus object again.

[0085] It can be seen that by detecting the focus conditions of objects in the overlapping area of ​​the picture, timely adjustments can be made to correct focus errors and ensure that the camera provides a clear image.

[0086] In one embodiment, the pre-focus information includes pre-object information, pre-focus position and pre-rotation position of the focus object, and determining the pre-focus information of the focus object includes: recording the pre-object information and pre-focus position of the focus object, the pre-object information including identity information and pre-object size information of the focus object; determining the pre-rotation position of the motor when the second camera obtains the second picture.

[0087] Among them, the above-mentioned identity information includes the identification of the focused object, such as the name or label of the object, so as to be able to identify and track the specific object; the pre-object size information can describe the relative size of the object in the picture, which helps the conference tablet to better compare the characteristics of the focused object.

[0088] It can be seen that during the pre-focus process, the identity information, size information and motor rotation position of each focus object when the focus is successful are saved, so that during subsequent switching, the pre-focus information can be quickly retrieved to focus on the focus object, which reduces the delay in screen switching and improves the smoothness of multi-camera switching.

[0089] In one embodiment, the real-time focus information includes real-time object information, real-time focus position and real-time rotation position of the focus object, and determining the real-time focus information of the focus object based on the target picture includes: recording the real-time object information and real-time focus position of the focus object at the current time, the real-time object information includes identity information and real-time object size information of the focus object; determining the real-time rotation position of the motor at the current time.

[0090] Among them, the above-mentioned identity information includes the identification of the focused object, such as the name or label of the object, so as to be able to identify and track a specific object; the real-time object size information can describe the relative size of the object in the picture, which helps the conference tablet to better compare the characteristics of the focused object.

[0091] It can be seen that through real-time focus information, adjustments can be made quickly when the scene or focus object changes to ensure that the focus will not be lost. Regardless of whether the focus object is moving or changing, the focus can be adjusted quickly to ensure that the picture remains clear, thus ensuring the picture display quality after switching the screen.

[0092] In one embodiment, controlling the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information includes: calculating an object offset of the focus object according to the real-time focus information and the pre-focus information; determining whether the object offset is less than a preset offset threshold; if less than, controlling the second camera to keep focusing on the focus object according to the pre-focus information; if greater than, controlling the second camera to refocus on the focus object.

[0093] The object offset refers to the difference between the actual focus position of the object and the predetermined focus position, and can be calculated by comparing the real-time focus position and the pre-focus position.

[0094] The preset offset threshold may be 0-5 mm and may be manually set. The preset offset threshold is used to determine whether the object is close enough to the predetermined focus position. If the object offset is less than the threshold, it means that the object is not far from the predetermined focus position and can be considered to be well focused. If the object offset is greater than the preset offset threshold, it means that the object has deviated from the predetermined focus position, and the second camera will be controlled to refocus the object. The control process may include adjusting the focal length, angle or position of the camera to bring the object back into focus.

[0095] It can be seen that by comparing the object offset and the offset threshold, it can be determined whether each focused object should maintain the current focus or refocus, so as to ensure that the focused object always remains clear.

[0096] In one embodiment, the object offset includes a position offset and / or an object size offset, the real-time focus information includes a real-time focus position and real-time object size information, the pre-focus information includes a pre-focus position and pre-object size information, and calculating the object offset of the focus object based on the real-time focus information and the pre-focus information includes: calculating the difference between the real-time focus position and the pre-focus position to obtain a position offset, and / or calculating the difference between the real-time object size information and the pre-object size information to obtain an object size offset.

[0097] The object offset can be calculated by mathematical calculation or image processing technology. For example, a coordinate system is used to represent the real-time focus position and the pre-focus position, and then the distance between them is calculated to obtain the position offset. For the object size offset, image processing technology can be used to measure the actual size of the object and compare it with the expected size.

[0098] For example, the difference between the real-time focus position and the pre-focus position is calculated to obtain the position offset, which can be calculated by the following formula:

[0099] X-coordinate offset = X-coordinate of real-time focus position - X-coordinate of pre-focus position

[0100] Y coordinate offset = Y coordinate of real-time focus position - Y coordinate of pre-focus position. If the pre-focus position is (120, 180) and the real-time focus position is (100, 200), we can get:

[0101] X coordinate offset = 100-120 = -20;

[0102] Y coordinate offset = 200-180 = 20;

[0103] Thus, the position offset is (-20, 20), which means that the current position is 20 units away from the expected position on the X axis (to the left), and 20 units away from the expected position on the Y axis (upward).

[0104] It can be seen that by calculating the object offset, whether it is the position offset or the object size offset, a more precise focus adjustment can be made according to the offset result, thereby ensuring that the focused object always remains clear.

[0105] In the scheme implemented by the above-mentioned multi-camera focusing method, device, equipment and storage medium, when the conference tablet displays the first picture taken by the first camera, the second camera is first controlled to perform a pre-focus operation to obtain the pre-focus information of the focus object, and the focus object is the focus object collected by the first camera and the second camera together. Secondly, in response to the camera switching command, the target picture taken by the second camera is obtained. The camera switching command is used to instruct the conference tablet to switch from displaying the first picture taken by the first camera to displaying the target picture taken by the second camera. Then, the real-time focus information of the focus object is determined according to the target picture. Finally, the second camera is controlled to keep focusing on the focus object according to the real-time focus information and the pre-focus information. Through this scheme, when the first camera is displayed, the second camera can be controlled to perform a focus operation on the focus object collected together in advance, and then the target picture can be focused on at the same time in the background without affecting the current display picture of the first camera. When switching to the target picture, the focus target picture is further dynamically adjusted according to the real-time focus and pre-focus information of the target picture to achieve a smooth and clear display of the target picture.

[0106] The method of the present application is introduced above, and the device of the present application is introduced below.

[0107] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a multi-camera focusing device provided in an embodiment of the present application. Figure 4As shown, the multi-camera focusing device is applied to a conference tablet, characterized in that the conference tablet includes a first camera and a second camera, including:

[0108] The control unit 401 is used to control the second camera to perform a pre-focus operation when the conference tablet displays the first picture captured by the first camera, and obtain pre-focus information of a focus object, where the focus object is the focus object collected by the first camera and the second camera together;

[0109] An acquisition unit 402 is used to respond to a camera switching command to acquire a target image captured by the second camera, wherein the camera switching command is used to instruct the conference tablet to switch from displaying the first image captured by the first camera to displaying the target image captured by the second camera;

[0110] A determining unit 403 is used to determine the real-time focus information of the focus object according to the target picture;

[0111] The control unit 401 is further configured to control the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information.

[0112] In one embodiment, when the conference tablet displays the first picture taken by the first camera, the second camera is controlled to perform a pre-focus operation to obtain pre-focus information of the focus object, and the control unit 401 is also used to: obtain the second picture taken by the second camera; determine the picture overlap area based on the first picture and the second picture; and determine the pre-focus information of the focus object based on the picture overlap area.

[0113] In one embodiment, the conference tablet also includes a motor, which is used to adjust the position of the second camera. In determining the pre-focus information of the focus object based on the overlapping area of ​​the pictures, the determination unit 403 is also used to: determine whether the overlapping area of ​​the pictures contains the focus object; if so, determine the pre-focus information of the focus object; if not, control the motor to adjust the second camera to re-shoot the second picture.

[0114] In one embodiment, in the determination of whether the overlapping area of ​​the pictures contains a focus object, the determination unit 403 is further used to: extract the object in the overlapping area of ​​the pictures; determine whether the object satisfies a preset focus condition; if so, determine that the object is a focus object; if not, control the motor to adjust the second camera to re-shoot the second picture.

[0115] In one embodiment, the pre-focus information includes pre-object information, pre-focus position and pre-rotation position of the focus object. In the determination of the pre-focus information of the focus object, the determination unit 403 is also used for: the pre-object information and pre-focus position of the focus object, the pre-object information includes the identity information and pre-object size information of the focus object; and determining the pre-rotation position of the motor when the second camera obtains the second picture.

[0116] In one embodiment, the real-time focus information includes real-time object information, real-time focus position and real-time rotation position of the focus object. In determining the real-time focus information of the focus object according to the target image, the determination unit 403 is further used to: record the real-time object information and real-time focus position of the focus object at the current time, the real-time object information including the identity information and real-time object size information of the focus object; determine the real-time rotation position of the motor at the current time.

[0117] In one embodiment, in controlling the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information, the control unit 401 is further used to: calculate the object offset of the focus object according to the real-time focus information and the pre-focus information; determine whether the object offset is less than a preset offset threshold; if less than, control the second camera to keep focusing on the focus object according to the pre-focus information; if greater than, control the second camera to refocus on the focus object.

[0118] In one embodiment, the object offset includes a position offset and / or an object size offset, the real-time focus information includes a real-time focus position and real-time object size information, the pre-focus information includes a pre-focus position and pre-object size information, and in calculating the object offset of the focus object based on the real-time focus information and the pre-focus information, the control unit 401 is further used to: calculate the difference between the real-time focus position and the pre-focus position to obtain the position offset, and / or calculate the difference between the real-time object size information and the pre-object size information to obtain the object size offset.

[0119] In the scheme implemented by the above-mentioned multi-camera focusing method, device, equipment and storage medium, when the conference tablet displays the first picture taken by the first camera, the second camera is first controlled to perform a pre-focus operation to obtain the pre-focus information of the focus object, and the focus object is the focus object collected by the first camera and the second camera together. Secondly, in response to the camera switching command, the target picture taken by the second camera is obtained. The camera switching command is used to instruct the conference tablet to switch from displaying the first picture taken by the first camera to displaying the target picture taken by the second camera. Then, the real-time focus information of the focus object is determined according to the target picture. Finally, the second camera is controlled to keep focusing on the focus object according to the real-time focus information and the pre-focus information. Through this scheme, when the first camera is displayed, the second camera can be controlled to perform a focus operation on the focus object collected together in advance, and then the target picture can be focused on at the same time in the background without affecting the current display picture of the first camera. When switching to the target picture, the focus target picture is further dynamically adjusted according to the real-time focus and pre-focus information of the target picture to achieve a smooth and clear display of the target picture.

[0120] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, and the computer device may be a display. 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.

[0121] 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.

[0122] Specifically, the processor 501 may include a sending card, a receiving card and a driving chip.

[0123] 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.

[0124] The processor 501 may call the program code to perform the following operations:

[0125] When the conference tablet displays the first picture captured by the first camera, the second camera is controlled to perform a pre-focus operation to obtain pre-focus information of a focus object, where the focus object is the focus object collected by the first camera and the second camera together;

[0126] In response to a camera switching command, a target image captured by the second camera is obtained, wherein the camera switching command is used to instruct the conference tablet to switch from displaying the first image captured by the first camera to displaying the target image captured by the second camera;

[0127] Determining real-time focus information of the focus object according to the target picture;

[0128] The second camera is controlled to keep focusing on the focus object according to the real-time focus information and the pre-focus information.

[0129] 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.

[0130] 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.

[0131] 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 multi-camera focusing method, applied to a conference tablet, characterized in that: The conference tablet includes a first camera and a second camera, and the method includes: When the conference tablet displays the first picture captured by the first camera, the second camera is controlled to perform a pre-focus operation to obtain pre-focus information of a focus object, where the focus object is the focus object collected by the first camera and the second camera together; In response to a camera switching command, a target image captured by the second camera is obtained, wherein the camera switching command is used to instruct the conference tablet to switch from displaying the first image captured by the first camera to displaying the target image captured by the second camera; Determining real-time focus information of the focus object according to the target picture; The second camera is controlled to keep focusing on the focus object according to the real-time focus information and the pre-focus information.

2. The method according to claim 1, characterized in that When the conference tablet displays the first picture captured by the first camera, controlling the second camera to perform a pre-focus operation to obtain pre-focus information of the focus object includes: Acquire a second picture captured by the second camera; determining a picture overlap area according to the first picture and the second picture; The pre-focus information of the focus object is determined according to the picture overlap area.

3. The method according to claim 2, characterized in that The conference tablet further includes a motor, and the motor is used to adjust the position of the second camera. The pre-focus information of determining the focus object according to the overlap area of ​​the picture includes: Determining whether the overlapping area of ​​the images contains a focus object; If included, determining the pre-focus information of the focus object; If not included, the motor is controlled to adjust the second camera to re-shoot the second picture.

4. The method according to claim 3, characterized in that The determining whether the picture overlap area contains the focus object comprises: Extracting objects in the overlapping area of ​​the pictures; Determining whether the object meets a preset focus condition; If satisfied, determining that the object is a focus object; If not, the motor is controlled to adjust the second camera to re-shoot the second picture.

5. The method according to claim 3, characterized in that: The pre-focus information includes pre-object information, a pre-focus position, and a pre-rotation position of the focus object, and the pre-focus information for determining the focus object includes: Recording pre-object information and a pre-focus position of the focus object, wherein the pre-object information includes identity information and pre-object size information of the focus object; Determine the pre-rotation position of the motor when the second camera obtains the second picture.

6. The method according to claim 1, characterized in that The real-time focus information includes real-time object information, real-time focus position and real-time rotation position of the focus object, and the real-time focus information of the focus object determined according to the target picture includes: Recording the real-time object information and the real-time focus position of the focus object at the current time, wherein the real-time object information includes the identity information and the real-time object size information of the focus object; Determine the real-time rotational position of the motor at the current time.

7. The method according to claim 1, characterized in that The controlling the second camera to keep focusing on the focus object according to the real-time focus information and the pre-focus information includes: Calculating an object offset of the focus object according to the real-time focus information and the pre-focus information; Determining whether the object offset is less than a preset offset threshold; If it is less than, controlling the second camera to keep focusing on the focus object according to the pre-focus information; If it is greater, the second camera is controlled to refocus on the focus object.

8. The method according to claim 7, characterized in that The object offset includes a position offset and / or an object size offset, the real-time focus information includes a real-time focus position and real-time object size information, the pre-focus information includes a pre-focus position and pre-object size information, and calculating the object offset of the focus object according to the real-time focus information and the pre-focus information includes: The difference between the real-time focus position and the pre-focus position is calculated to obtain a position offset, and / or the difference between the real-time object size information and the pre-object size information is calculated to obtain an object size offset.

9. A conference tablet, characterized in that: include: case; A first camera, disposed on the housing; a second camera, disposed on the housing, wherein a position of the second camera on the housing is different from a position of the first camera on the housing; Motors, connected to the first camera and the second camera respectively; A controller is electrically connected to the first camera, the second camera and the motor, respectively, and is used to control the motor to adjust the position of the second camera, wherein the controller includes a memory and a processor, the memory is connected to the processor, and 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 any one of claims 1-8.

10. 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 is caused to perform the method according to any one of claims 1 to 8.

Images