Rotary shooting method, device, electronic device and storage medium

Abstract

An embodiment of the present application discloses a rotation shooting method, device, electronic device, and storage medium. Among them, the rotation shooting method is applied to an electronic device, and the electronic device includes a rotatable shooting device. The method includes: controlling the shooting device to rotate to perform sub-region shooting and modeling on a text target; obtaining multiple modeling images captured by the shooting device, each modeling image corresponding to a sub-region; splicing the multiple modeling images to obtain a panoramic image of the text target; dividing the text target according to the panoramic image to obtain multiple sub-regions; controlling the shooting device to rotate and shooting each of the sub-regions; during the shooting process, identifying the sub-region with a marker based on the shooting content to track the text content corresponding to the marker. The above solution can solve the technical problem in the prior art that when using an electronic device camera for shooting, it is impossible to balance the clarity and integrity of the shooting content.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of electronic devices, and in particular, to a rotation shooting method, device, electronic device, and storage medium. Background Art

[0002] Currently, artificial intelligence technology is widely used in all walks of life. For example, in the education industry, artificial intelligence technology is applied to electronic devices to be used as learning devices for users during the learning process. When a user answers questions on an exercise book or a test paper, the electronic device can take pictures of the exercises and the answer content written by the user, and use artificial intelligence technology to identify the accuracy of the answers. This can not only save the link of manual marking of the answer content, but also automatically count wrong questions and find weak knowledge points, enabling users to learn targeted.

[0003] In the foregoing process, the camera installed in the electronic device is a key component. The clearer the camera captures, the more conducive it is to the subsequent identification of the accuracy of the answers. However, referring to Figure 1 , when the electronic device 1 is fixed on the desktop 2 and takes pictures of the exercise book or the test paper 3, the camera 4 needs to be tilted to capture the desktop 2. In this way, the depth of field and the field of view angle during the camera shooting will affect the shooting clarity and the shooting range. For example, when the test paper is an A3-sized paper, a wide-angle camera is required to capture the complete test paper content. However, the edge clarity is relatively low when shooting with a wide-angle camera, which is not conducive to subsequent identification processing. To ensure the shooting clarity, a camera with a smaller field of view angle can be used, but a camera with a smaller field of view angle cannot capture the complete test paper content, which is also not conducive to subsequent identification processing.

[0004] In summary, when using the camera of an electronic device for shooting, how to balance the clarity and integrity of the shooting content has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] Embodiments of the present application provide a rotation shooting method, device, electronic device, and storage medium to solve the technical problem that when using the camera of an electronic device for shooting in the prior art, the clarity and integrity of the shooting content cannot be balanced.

[0006] In a first aspect, an embodiment of the present application provides a rotation shooting method, which is applied to an electronic device, and the electronic device includes a rotatable shooting device. The method includes:

[0007] Controlling the rotation of the shooting device to perform regional shooting and modeling on a text target;

[0008] Obtaining multiple modeling images captured by the shooting device, and each modeling image corresponds to a sub-region;

[0009] Stitch multiple of the modeling images to obtain a panoramic image of the text target object;

[0010] Divide the text target object according to the panoramic image to obtain multiple sub-regions;

[0011] Control the shooting device to rotate and shoot each of the sub-regions;

[0012] During the shooting process, identify the sub-regions with markers based on the shooting content to track the text content corresponding to the markers.

[0013] In a second aspect, an embodiment of the present application further provides a rotating shooting device, which is applied to an electronic device. The electronic device includes a rotatable shooting device. The device includes:

[0014] A first shooting unit, configured to control the shooting device to rotate for shooting and modeling the text target object in sub-regions;

[0015] A modeling acquisition unit, configured to acquire multiple modeling images shot by the shooting device, and each of the modeling images corresponds to a sub-region;

[0016] An image stitching unit, configured to stitch multiple of the modeling images to obtain a panoramic image of the text target object;

[0017] A region division unit, configured to divide the text target object according to the panoramic image to obtain multiple sub-regions;

[0018] A second shooting unit, configured to control the shooting device to rotate and shoot each of the sub-regions;

[0019] A marker recognition unit, configured to, during the shooting process, identify the sub-regions with markers based on the shooting content to track the text content corresponding to the markers.

[0020] In a third aspect, an embodiment of the present application further provides a rotating shooting electronic device, including:

[0021] One or more processors;

[0022] A rotatable shooting device, and the rotation and shooting of the shooting device are controlled by the processor;

[0023] A memory, configured to store one or more programs;

[0024] When the one or more programs are executed by the one or more processors, the one or more processors implement the rotating shooting method as described in the first aspect.

[0025] Fourthly, an embodiment of the present application further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute the rotation shooting method as described in the first aspect when executed by a computer processor.

[0026] In the above rotation shooting method, device, electronic device and storage medium, by controlling a rotatable shooting device to perform sub-region shooting on the area where the text target is placed to obtain multiple modeling images, and stitching the multiple modeling images to obtain a panoramic image of the text target. Then, based on the panoramic image, the text target is divided into multiple sub-regions, the shooting device is controlled to rotate to shoot each sub-region, and the sub-region where the marker exists is determined and photographed to track the text content corresponding to the marker. This technical means solves the technical problem that when using the camera of an electronic device to shoot in the prior art, it is impossible to balance the clarity and integrity of the shooting content. By setting a rotatable shooting device, a camera with a smaller field of view can be used to ensure the clarity of shooting, and the shooting range can be expanded by rotation, without setting an additional camera for the electronic device, thus saving the device cost. At this time, the panoramic image obtained by the rotatable shooting device has a high clarity, ensuring the accuracy of modeling. Then, based on the panoramic image, the text target is partitioned, and only the area where the marker exists is photographed, so that the text content corresponding to the marker can be clearly photographed, thereby improving the accuracy of text recognition. Description of the Drawings

[0027] Figure 1 Schematic diagram of the placement of an electronic device in the prior art;

[0028] Figure 2 Schematic diagram of a shooting device provided by an embodiment of the present application;

[0029] Figure 3 Schematic diagram of another shooting device provided by an embodiment of the present application;

[0030] Figure 4 Schematic diagram of a shooting range provided by an embodiment of the present application;

[0031] Figure 5 Flowchart of a rotation shooting method provided by an embodiment of the present application;

[0032] Figure 6 Schematic diagram of a partition provided by an embodiment of the present application;

[0033] Figure 7 Schematic diagram of a marker provided by an embodiment of the present application;

[0034] Figure 8 Flowchart of a rotation shooting method provided by an embodiment of the present application;

[0035] Figure 9 A schematic diagram of the structure of a rotating camera device provided by one embodiment of the present application;

[0036] Figure 10 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0037] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0038] An embodiment of the present application provides a rotating shooting method, which can be performed by a rotating shooting device, which can be implemented by software and / or hardware and integrated in a rotating shooting electronic device. Among them, the rotating shooting electronic device can be composed of two or more physical entities, or it can be composed of one physical entity, and the embodiment does not limit this. Currently, the rotating shooting electronic device can be an electronic device such as a mobile phone, a tablet computer, a laptop computer, a learning device, etc. Among them, the electronic device is described as a learning device as an example. The learning device is an auxiliary device for user learning, which can formulate a learning plan, display teaching courses, recommend exercises, shoot the user's learning process or problem-solving process, and correct the exercises answered by the user, etc. The learning device can also be recorded as a learning machine, a learning terminal, etc.

[0039] The electronic device is installed with at least one operating system, and at least one application can be installed under the operating system. Among them, the application can be an application that comes with the operating system, and can also be an application downloaded from a third-party device or server, which is not currently limited. The electronic device is also installed with a display screen, which can have a touch function. The electronic device is also installed with a communication device, through which online courses, answers to exercises, etc. can be obtained. In one embodiment, the electronic device also includes a rotatable shooting device.

[0040] Optional, reference Figure 2, the rotatable shooting device includes a single camera 11 and a rotating assembly 12 for controlling the rotation of the single camera. Taking the learning scenario as an example, after the electronic device 13 is fixed, the single camera directly shoots the paper learning materials used by the user (the materials are placed on the desktop 14). Currently, the rotating assembly for controlling the rotation of the single camera is denoted as the first rotating assembly. It can be understood that the components and structures included in the first rotating assembly are not limited currently, as long as the single camera can be controlled to rotate. For example, the first rotating assembly includes a motor, gears, and other components. Optionally, the single camera can replace the original front camera of the electronic device. Additionally, with reference to Figure 3 , the rotatable shooting device includes a single camera 11, a reflector 15, and a rotating assembly 16 for controlling the rotation of the reflector. At this time, the position of the single camera is fixed. Taking the learning scenario as an example, after the electronic device 13 is fixed, the reflector 15 reflects the paper learning materials used by the user to the single camera for shooting. Currently, the rotating assembly for controlling the rotation of the reflector is denoted as the second rotating assembly. It can be understood that the components and structures included in the second rotating assembly are not limited currently, as long as the reflector can be controlled to rotate. The rotating assembly mentioned above can accept the control of the electronic device. It can be understood that when the shooting device includes a reflector, the camera used can be the original front camera of the electronic device. At this time, the reflector is used to reflect external light to the front camera for imaging. Optionally, the component composed of the reflector and the second rotating assembly can be a part of the electronic device or can be detachably installed in the electronic device to cooperate with the front camera of the electronic device.

[0041] Furthermore, the single camera refers to one camera, and the parameters of the camera can be set according to the actual situation. Currently, taking the camera as an auto-focus camera as an example for description, and the camera has a relatively small field of view (FOV), which is generally smaller than the commonly used field of view of the camera. It can be understood that when the resolution of the camera is fixed, the smaller the field of view, the smaller the area that the camera can shoot, and the more detailed the information expressed by each pixel in the captured image, that is, the higher the clarity of the image and the reduction of image distortion. After applying the single camera to the rotatable shooting device, clear images can be guaranteed and the shooting range of the single camera can be expanded by rotation. For example, with reference to Figure 4 , which shows the range 17 that the single camera 11 can shoot without rotation, and the range 18 that the single camera can shoot after adding rotation. The shooting range 18 after adding rotation can completely cover the object to be shot 19 (such as paper learning materials, etc.).

[0042] The installation method of the rotatable shooting device in the electronic device is not limited currently.

[0043] Exemplarily, Figure 5The flowchart of a rotation shooting method provided by an embodiment of the present application.

[0044] Refer to Figure 5 , the rotation shooting method executed by the electronic device includes:

[0045] Step 110, control the shooting device to rotate to perform sub-region shooting and modeling on the text target.

[0046] Exemplarily, every time the shooting device rotates to a position, it can shoot the current region within the field of view angle (i.e., the maximum region that can be shot during one shooting). The union of the regions corresponding to each position can be understood as the shooting region of the shooting device. A paper text target is placed within the shooting region. The text target refers to a book or paper containing text content. Currently, the text target is a book or a test paper. Generally, the electronic device is fixed on the desktop of a desk (which can also be referred to as a table, a school desk, etc.), and the text target on the desktop is shot through the shooting device.

[0047] Since the field of view angle of a single camera is small, therefore, control the shooting device to rotate and shoot during the rotation to ensure that the entire text target is shot. Currently, the shooting device can perform sub-region shooting on the text target after each rotation to obtain partial content of the text target, and the entire content of the text target can be obtained based on each partial content. That is, the purpose of rotation shooting is to obtain the entire content of the text target to achieve modeling of the text target. After modeling, the text target can be reasonably partitioned. Optionally, the regions shot each time by the shooting device can be combined to form the shooting region, and there is an intersection between adjacent regions to avoid missing some regions of the text target.

[0048] When controlling the shooting device to perform sub-region shooting on the text target, the rotation logic of the shooting device can be set according to actual needs. In one embodiment, this step can be specifically: control the shooting device to rotate multiple times according to the received rotation instruction, and control the shooting device to perform sub-region shooting on the text target after each rotation, and each shooting corresponds to a sub-region.

[0049] Currently, the rotation instruction is used to control the shooting device to rotate, and the rotation instruction can be automatically generated or manually generated.

[0050] When the rotation instruction is automatically generated, the rotation rule of the photographing device is preset in the electronic device. Through the rotation rule, the rotation angle of the photographing device each time it rotates or the position of the photographing device after each rotation can be determined, and the number of rotations of the photographing device can also be determined optionally. After obtaining the rotation rule, a rotation instruction is generated according to the rotation rule, and the photographing device is controlled to rotate based on the rotation instruction. And after each rotation, the photographing device is controlled to take a picture. At this time, the area that can be photographed after each rotation can be understood as the sub-region when photographing the text target object by sub-regions.

[0051] In one embodiment, a rotation rule is preset. Each time the rotation photographing method is executed, a rotation instruction is generated according to the rotation rule to control the rotation of the photographing device. It can be understood that when the photographing device is controlled to rotate according to this rotation rule, the maximum photographing range can be obtained.

[0052] In one embodiment, multiple rotation rules are preset, and the sizes of the text target objects corresponding to each rotation rule are different. At this time, controlling the photographing device to rotate multiple times according to the received rotation instruction may include: obtaining the size information of the text target object; obtaining the corresponding rotation rule according to the size information, and generating a rotation instruction according to the rotation rule; controlling the photographing device to rotate multiple times according to the rotation instruction. It can be understood that for the text target object, its size generally includes several fixed sizes such as A3, A4, B5 or A5. For example, the size of a test paper is generally A3. Therefore, a reasonable rotation rule can be set for each size. For example, the number of rotations specified in the rotation rule for the A3 size can be more than the number of rotations specified in the rotation rule for the A4 size to ensure that the number of rotations of the photographing device is more reasonable when photographing the entire text target object. Each time the rotation photographing method is executed, the size information of the text target object (the size of the text target object is recorded in the size information) can be obtained. Among them, the size information can be input by the user, or automatically obtained by the electronic device, such as identifying the type of the text target object (test paper or book) through machine learning and obtaining the size information corresponding to the type. Then, the rotation rule corresponding to the size information is called, and a rotation instruction is generated according to the rotation rule to control the rotation of the photographing device. Optionally, the positions of text target objects of different sizes may be different. At this time, the user can control the photographing device to rotate to the accurate position, and then the electronic device generates a rotation instruction according to the rotation rule to control the rotation of the photographing device, or the electronic device rotates the photographing device and generates a rotation instruction according to the rotation rule to control the rotation of the photographing device when identifying the corner position (such as the upper left corner position) of the text photographing object. Among them, the identification of the corner position can be realized through machine learning or other means. It can be understood that when the photographing device is controlled to rotate according to the rotation rule, the entire text target object can be photographed by the photographing device.

[0053] When the rotation instruction is automatically generated, the rotation instruction is input manually in the electronic device. The rotation instruction can be specifically used to limit the rotation angle or the position reached by the photographing device during a rotation process, that is, each rotation requires a rotation instruction to drive. The input method of the rotation instruction is not limited currently. After obtaining the rotation instruction, the photographing device is controlled to rotate to perform sub-region photographing on the text target.

[0054] Step 120: Obtain multiple modeling images taken by the photographing device, and each modeling image corresponds to a sub-region.

[0055] Exemplarily, the image obtained after the photographing device performs sub-region photographing on the text target is denoted as the modeling image. At this time, there is a corresponding modeling image after each photographing, and the modeling image can be considered to correspond to a sub-region.

[0056] Step 130: Stitch the multiple modeling images to obtain a panoramic image of the text target.

[0057] In one embodiment, when performing sub-region photographing on the text target, the electronic device can determine the relative position relationship between the sub-regions. Then, based on the relative position relationship, the modeling images are stitched.

[0058] Optionally, there is an overlapping area between adjacent sub-regions, that is, there is some repeated content in the modeling images corresponding to adjacent sub-regions. Therefore, based on the repeated content, the modeling images can be accurately stitched. It can be understood that image stitching based on the repeated content is an already implemented technology and will not be described separately currently.

[0059] It can be understood that after stitching, an image including the complete photographing area can be obtained, and the complete text target is included in this image. In the embodiment, the image obtained after stitching is denoted as the panoramic image. The panoramic image can be understood as the image obtained after modeling the text target.

[0060] Step 140: Divide the text target according to the panoramic image to obtain multiple sub-regions.

[0061] Exemplarily, the multiple regions obtained after dividing the text target are denoted as sub-regions.

[0062] It can be understood that after the electronic device is fixed on the desktop, the relative positional relationship between the shooting device and the shooting area in the desktop can be determined. At this time, according to the relative positional relationship (which can be regarded as the external parameters of a single camera) and the parameters of the single camera (such as the field of view angle, focal length, etc., the internal parameters of the single camera), each pixel when the shooting device takes a picture can be associated with the actual position of the content displayed by the pixel in the desktop. Therefore, after obtaining the panoramic image, the pixels where the text target objects are located in the panoramic image can be recognized, and the actual positions of the text target objects can be determined according to the association relationship between the pixels and the actual positions. This actual position can also be understood as the area where the text target object is located. After that, the area where the text target object is located can be divided to obtain sub-areas, or, first, the text target objects in the panoramic image are divided to obtain multiple sub-areas, and then, the actual positions of the multiple sub-areas are determined, and the actual positions are determined as the positions where the sub-areas are located. It can be understood that the sub-areas can be regarded as the areas when the user operates on the text target object (such as writing, indicating, etc.).

[0063] It should be noted that determining the association relationship between the image coordinates and the physical space coordinates according to the external and internal parameters of the camera is an implemented technology and will not be described separately here.

[0064] When dividing the text target object, an equal division method can be used, or it can be divided in combination with the text content of the text target object, or other division methods can also be used.

[0065] In one embodiment, when using the equal division method to divide the text target object, this step can be specifically: dividing the text target object according to the panoramic image to obtain multiple sub-areas of equal size.

[0066] Exemplarily, the text target object is usually rectangular. When dividing, the area where the text target object is located can be divided into multiple rectangular areas of equal size and used as sub-areas. Optionally, the number of rectangular areas can be preset in advance. This number can be the specific number of rectangular areas or the number of rows and columns of the matrix area. Then, according to the preset number, the area where the text target object is located is equally divided. Optionally, text target objects with different size information can share the same number. At this time, regardless of the size of the text target object, a fixed number of sub-areas can be obtained. Or, text target objects with different size information correspond to different numbers. At this time, the numbers corresponding to different size information can be preset in advance, and the larger the size information, the more the corresponding number. Then, the corresponding number is obtained according to the size information of the text target object, and the area where the text target object is located is divided according to this data. It can be understood that each sub-area after equal division can be completely photographed by the shooting device.

[0067] In one embodiment, the division is performed in combination with the text content of the text target. At this time, this step may be specifically: performing text recognition on the panoramic image, and dividing the text target according to the recognized text content to obtain a plurality of sub-regions.

[0068] Exemplarily, the technical means used for text recognition of the panoramic image is not limited at present. For example, a neural network for text recognition is trained. After that, the panoramic image is input into the neural network to obtain the text content. Another example is to process the panoramic image through optical character recognition (OCR) to obtain the text content included in the panoramic image. Generally speaking, in the panoramic image, only the text (which may include Chinese characters, English, numbers, and symbols, etc.) appears in the text target. Therefore, the text content of the panoramic image can also be used as the text content of the text target. Or, first identify the text target in the panoramic image, and then perform text recognition on the text target to obtain the text content of the text target.

[0069] After that, the text target is divided according to the text content to obtain a plurality of sub-regions. Among them, when dividing according to the text content, the text content used to describe the same event may be divided into one sub-region. For example, when the text content is an exercise question, the same exercise question can be divided into one sub-region, or the same type of exercise questions (such as multiple-choice questions, fill-in-the-blank questions, or subjective questions, etc.) can be divided into one sub-region. At this time, if the sub-regions of the same type exceed the maximum range that can be photographed by a single camera, the sub-regions can be further divided to ensure that each sub-region can be completely photographed by the photographing device in a single shot. The sizes of the sub-regions divided based on the text content may be the same or different.

[0070] Step 150: Control the photographing device to rotate and photograph each sub-region.

[0071] Exemplarily, after dividing each sub-region, control the photographing device to photograph each sub-region to identify the markers in each sub-region. Among them, the user can perform corresponding operations on the text target through the markers, such as writing on the text target, or indicating a part of the text content in the text target. Optionally, after dividing the sub-regions, the position of the photographing device when photographing the sub-region can be determined according to the actual position where the sub-region is located. After that, control the photographing device to rotate to this position and photograph the sub-region. When photographing, automatic focusing can be performed.

[0072] In one embodiment, the shooting order between sub-regions is preset in advance, and each sub-region is shot in sequence according to the shooting order. At this time, this step may be specifically: according to the preset regional shooting order, control the shooting device to rotate, and after each rotation, control the shooting device to shoot the corresponding sub-region currently.

[0073] The regional shooting order is used to define the shooting order when shooting each sub-region. The sorting logic used for the regional shooting order can be set according to the actual situation, such as setting the regional shooting order according to the user's writing habit, reading habit or answering habit, etc. For example, in the answering scenario, the habitual order for the user to answer questions is to start answering from the upper left. Therefore, the regional shooting order can be in the order from left to right and from top to bottom or in the order from top to bottom and from left to right. For example, referring to Figure 6 , a text target 19 is placed on the desktop 14, and the text target 19 is evenly divided into 12 sub-regions ( Figure 6 respectively numbered 1-12 in ), at this time, control the shooting device to shoot each sub-region in the order of numbers from 1 to 12 (that is, in the order from top to bottom and from left to right), or control the shooting device to shoot each sub-region in the order of numbers 1, 5, 9, 2, 6, 10, 3, 7, 11, 4, 8, 12 (that is, in the order from top to bottom and from left to right).

[0074] It should be noted that the position limitations related to the text target mentioned in this embodiment, such as "left" in the upper left corner of the text target, "left", "right", "top", "bottom" in from left to right or from top to bottom, are all limited from the user's perspective.

[0075] When the shooting device shoots each sub-region, it can identify the captured image to determine whether it contains a marker.

[0076] Step 160: During the shooting process, identify the sub-regions with markers based on the shooting content to track the text content corresponding to the markers.

[0077] Exemplarily, after the imaging device captures an image of a sub-region, it can identify the captured image to determine whether it contains a marker. Currently, the number of images captured by the imaging device for each sub-region is not limited. If a marker is identified in the image, it is determined that the user may have performed an operation in this sub-region. At this time, the operation of the user and the text content corresponding to the operation can be identified based on the marker. If no marker is identified in the image, it is determined that the user has not performed an operation in this sub-region. Therefore, the imaging device can be controlled to rotate to capture another sub-region and continue to identify the marker until a sub-region with a marker is identified. If it is determined that all sub-regions do not contain a marker after capturing all sub-regions, it is determined that the user has not performed an operation currently. At this time, the imaging device can continue to capture each sub-region until a sub-region with a marker is identified. For example, referring to Figure 7 , when the marker is a writing pen and the imaging device captures an image of sub-region No. 6, the writing pen is detected. Therefore, it is determined that the number of the sub-region where the current operation is performed is 6. It can be understood that identifying certain required objects in the captured image is an already implemented technology and will not be described separately here.

[0078] In one embodiment, the marker is a pen and / or a human hand. It can be understood that when the user operates on a text target, it is generally achieved by a pen (which can be a writing pen, a point-reading pen, etc.) or a human hand. When the marker is a pen, it can specifically be the pen tip and the pen head. The pen tip refers to the part of the pen that contacts the text target, and the pen head is the part that connects the pen tip and the pen barrel.

[0079] In one embodiment, the user can indicate the text content corresponding to the text target based on the marker, so that the electronic device can obtain the text content for subsequent processing, such as generating and playing an audio file containing the text content, or translating the text content into a set language, or searching for similar content based on the text content (for example, when the text content is an exercise question, searching for other exercise questions similar to this exercise question). At this time, the marker includes a pen and / or a human hand, and the marker is used to indicate the text content in the text target. The tracking of the text content corresponding to the marker includes: controlling the imaging device to capture an image of the sub-region where the marker exists to obtain a captured image; identifying the text content pointed to by the marker in the text target based on the captured image.

[0080] Exemplarily, after determining the sub-region where the marker is located, capturing an image of this sub-region can determine the position indicated by the marker, and then use the text content corresponding to the position indicated by the marker in the text target as the text content pointed to by the marker. That is, the text content currently tracked. Optionally, when the marker is a human hand, the position of the fingertip can be used as the position indicated by the marker; when the marker is a pen, the position of the pen tip can be used as the position indicated by the marker.

[0081] In one embodiment, the user can write on the text object based on the marker. At this time, when the user operates on the text object, it is necessary to issue a writing action, and the marker is related to the writing action, that is, by detecting the marker, it can be determined whether there is a writing action. It can be understood that when the user writes on paper, he needs to use his hand to hold the pen to write, so the writing action can be detected by the pen and / or the human hand. After the sub-area where the marker is detected, the sub-area is continuously photographed to determine the user's writing content based on the content of the continuous shooting, and the writing content is the tracked text content. Among them, when the sub-area is continuously photographed, the sub-area can be photographed at a certain frequency to obtain multiple images, and the frequency can be set according to actual conditions. Optionally, after each image is taken, the image is compared with the previous image taken, and the writing track written by the user during the current shooting can be determined. For example, the current image shows "干" and the previous image shows "丅". After comparing the two images, it can be determined that the current writing track is "一". According to the above method, the writing tracks of the user can be identified in turn based on multiple images, and the stroke order of the user's writing can be obtained according to the writing order of each writing track. Afterwards, the writing content of the user is determined in combination with the writing track and the stroke order. It should be noted that determining the corresponding text content according to the writing track (i.e. handwriting) and the stroke order is an already implemented technology. For example, the handwriting input in the mobile phone determines the corresponding text content based on the writing track and the stroke order. Optionally, after shooting the sub-area at a certain frequency, the captured image can be processed by OCR to obtain the text content in the image (which includes the writing content).

[0082] Optionally, after photographing the sub-area at a certain frequency, the moving trajectory of the marker can be identified based on the position of the marker in multiple images, and then the writing trajectory and stroke order corresponding to the marker can be obtained based on the moving trajectory. After that, the corresponding writing content can be determined based on the writing trajectory and stroke order. Optionally, the writing content can be obtained by combining the writing trajectory, stroke order and OCR technology. For example, when a user writes the word "计", the writing content obtained by combining the writing trajectory and stroke order is the word "计", and the writing content obtained by combining the OCR technology is the word "汁". At this time, after comparing the two writing contents, it can be determined that the word "汁" and the word "计" are inconsistent texts. Afterwards, the correct text can be selected based on the semantic recognition results of the text content before and after the text, or it can be displayed to the user, and the user selects the correct text. This can improve recognition accuracy.

[0083] As described above, by controlling a rotatable photographing device to photograph a text target in sub-regions to obtain multiple modeling images, and stitching the multiple modeling images to obtain a panoramic image of the text target. Then, based on the panoramic image, the region where the text target is located is divided into multiple sub-regions, the photographing device is controlled to rotate to photograph each sub-region, and the sub-region where a marker exists is determined, and this sub-region is photographed to track the text content corresponding to the marker. This technical means solves the technical problem in the prior art that when using the camera of an electronic device for photographing, it is impossible to take into account both the clarity and integrity of the photographed content. By setting a rotatable photographing device, a camera with a smaller field of view can be used to ensure the clarity of the photographing, and the photographing range can be expanded by rotation, without setting an additional camera for the electronic device, thus saving the device cost. At this time, the panoramic image obtained by the rotatable photographing device has a higher clarity, ensuring the accuracy of the modeling. Then, based on the panoramic image, the text target is partitioned, and only the region where the marker exists is photographed, so that the text content corresponding to the marker can be clearly photographed, thereby improving the accuracy of text recognition.

[0084] In an embodiment of the present application, after a user writes in a sub-region and then moves to another sub-region to continue writing, the electronic device needs to track and photograph the writing process of the user. At this time, after step 160, steps 170 to 180 are further included:

[0085] Step 170, when it is detected that the marker leaves the currently photographed sub-region, determine the alternative sub-regions where the marker may appear.

[0086] Exemplarily, when controlling the photographing device to photograph the sub-region where the marker exists, the marker in the sub-region can be continuously recognized. If the marker is not recognized in a certain photographing or in the images obtained by a continuous number of times (this value can be set according to the actual situation) of photographing, it is determined that the marker has left the sub-region, that is, the user has not performed an operation in the sub-region. Then, the sub-regions where the marker may exist are determined. In the embodiment, the sub-regions where the marker may exist are denoted as alternative sub-regions.

[0087] The determination method of the alternative sub-regions can be set according to the actual situation. In one embodiment, determining the alternative sub-regions where the marker may appear can be specifically: determining the alternative sub-regions according to the preset regional photographing order; or, obtaining each adjacent sub-region of the currently photographed sub-region and determining the alternative sub-regions among the adjacent sub-regions.

[0088] Exemplarily, when it is detected that the marker leaves the currently photographed sub-region, determine the sub-region located after the currently photographed sub-region according to the region photographing order. It can be understood that since the region photographing order is determined according to the user's habitual order when writing, reading or answering questions, therefore, the possibility that there is a marker in the sub-region located after the currently photographed sub-region is high, and it can be determined as an alternative sub-region. Optionally, one sub-region located after the currently photographed sub-region can be determined as the alternative sub-region or all sub-regions located after the currently photographed sub-region can be determined as the alternative sub-regions.

[0089] Exemplarily, when the user is writing, reading or answering questions, generally, it is carried out in a certain order. In this case, the sub-regions operated by the user in sequence are generally adjacent. Therefore, when it is detected that the marker leaves the currently photographed sub-region, it is also possible to obtain the sub-regions adjacent to the currently photographed sub-region, and determine the adjacent sub-regions as the alternative sub-regions, or determine the sub-regions that have not been operated by the user among the adjacent sub-regions as the alternative sub-regions.

[0090] Step 180, control the photographing device to rotate to photograph the alternative sub-region, and during the photographing process, identify the marker based on the photographed content.

[0091] Exemplarily, after determining the alternative sub-region, rotate the photographing device so that the photographing device photographs the alternative sub-region, and detect whether there is a marker in the alternative sub-region based on the photographed content. If there is a marker, determine the alternative sub-region as the currently operated sub-region, and track the text content corresponding to the marker. If there is no marker, determine that the alternative sub-region is not the currently operated sub-region. At this time, other sub-regions can be photographed until a sub-region with a marker is detected, and then, track the text content corresponding to the marker.

[0092] As described above, when it is detected that the marker leaves the currently photographed sub-region, the photographing device can be controlled to rotate to photograph other sub-regions to continue identifying the marker, and based on the marker, determine the currently operated writing sub-region, and then track the text content corresponding to the marker, so as to achieve accurate follow-up photographing of the operation process, and then obtain accurate and clear text content.

[0093] Figure 8 The flowchart of a rotation photographing method provided by an embodiment of the present application. This embodiment is a concretization based on the above embodiment. In this embodiment, the text target object includes the questions of multiple exercises. Among them, the multiple exercises can be one or more of multiple-choice questions, fill-in-the-blank questions, true-or-false questions, application questions, and subjective questions. When the user answers questions, the electronic device determines the user's writing area by identifying the pen and / or the human hand used by the user, that is, the marker is the pen and / or the human hand. Refer to Figure 8 , the method includes:

[0094] Step 210: Control the rotation of the photographing device to perform sub-region photographing and modeling on the text target object.

[0095] Step 220: Obtain multiple modeling images taken by the photographing device, and each modeling image corresponds to a sub-region.

[0096] Step 230: Stitch the multiple modeling images to obtain a panoramic image of the text target object.

[0097] Step 240: Perform text recognition on the panoramic image to obtain the text content of the text target object, and the text content is the title content.

[0098] Exemplarily, the technical means for performing text recognition on the panoramic image is not currently limited. For example, the panoramic image is processed by OCR to obtain the text content of the panoramic image. It can be understood that the text content can reflect the title content in the text target object.

[0099] Step 250: In a preset exercise question bank, search for the answer content corresponding to the text content.

[0100] The exercise question bank contains a large number of exercise questions and corresponding answer contents. The exercise question bank can be stored in an electronic device or in the background server of the electronic device. Optionally, the exercise question bank can be classified according to disciplines and grades.

[0101] Exemplarily, after obtaining the title content, access one or more exercise question banks to find the exercises with the same title content in the exercise question bank. In one embodiment, by calculating the similarity of the questions, find one or more exercises in the exercise question bank that are most similar to the title content, and then obtain the answer content of the found exercises as the answer content corresponding to the title content. At this time, the obtained answer content can be used to judge the accuracy of the user's current answer.

[0102] Step 260: Divide the text target object according to the panoramic image to obtain multiple sub-regions.

[0103] Step 270: Control the rotation of the photographing device and photograph each sub-region.

[0104] Step 280: During the photographing process, identify the sub-regions with markers based on the photographed content.

[0105] Step 290: Control the photographing device to perform real-time photographing on the sub-regions with markers to obtain multiple photographed images.

[0106] Exemplarily, the effect of real-time photographing can be achieved by setting an appropriate photographing frequency for the photographing device. It can be understood that after each photographing, a photographed image can be obtained, and after real-time photographing, multiple photographed images can be obtained.

[0107] Step 2100: determine the writing trajectory and stroke sequence of the marker when performing the writing action based on the multiple captured images.

[0108] For example, after each captured image is obtained, the captured image is compared with the previous captured image to determine the newly written writing track in the current captured image. For example, the current image shows "干", and the previous image shows "丅". After comparing the two images, the currently written writing track "一" can be determined. By comparing multiple captured images in sequence, all written writing tracks can be obtained, and the stroke order written by the user can be determined based on the recognition order of the writing tracks.

[0109] Step 2110: Determine the first writing content corresponding to the writing action according to the writing trajectory and stroke sequence.

[0110] Exemplarily, the writing content corresponding to the writing action can be obtained according to the writing trajectory and the stroke sequence, and the currently determined writing content is recorded as the first writing content.

[0111] Optionally, a text library is constructed, in which the trajectory and stroke order of each text are recorded. Afterwards, the currently recognized writing trajectory and stroke order are compared with the trajectory and stroke order of each text in the text library to determine the text represented by the currently recognized writing trajectory and stroke order, and then obtain the first writing content. It can be understood that when a user continuously inputs multiple texts, it can be determined whether to write a new text based on the position interval of the writing trajectory and the pause time of the writing trajectory. For example, when the user writes "we", after the word "I" is written, there is a certain position interval between the first stroke of the word "们" and the last stroke of the word "我", and a pause time will be generated. Therefore, based on the position interval and the pause time, it can be determined that a new text "们" has been written.

[0112] Optionally, a neural network for text recognition is constructed, and after the writing trajectory and stroke sequence are input into the neural network, the first writing content output by the neural network can be obtained.

[0113] Optionally, based on the stroke sequence, it can also be determined whether the stroke sequence written by the user is correct.

[0114] In one embodiment, the above operation may be performed each time a captured image is obtained, so as to identify the real-time first writing content during the writing process.

[0115] Step 2120: Process the captured image using optical character recognition technology to obtain second writing content corresponding to the writing action.

[0116] Exemplarily, each captured image is processed using OCR to obtain the written content corresponding to each captured image. Currently, this written content is denoted as the second written content. It can be understood that after each captured image is obtained, the corresponding first written content and second written content can be obtained.

[0117] It can be understood that the first written content and the second written content can be recognized simultaneously or successively, and there is no current limitation.

[0118] Step 2130: Obtain the final written content based on the first written content and the second written content.

[0119] Exemplarily, based on the first written content and the second written content corresponding to each captured image, the final written content corresponding to this captured image can be obtained. Optionally, the determination method of the final written content can be to compare the first written content and the second written content. If the two are the same, then determine the final written content as the first written content or the second written content. If the two are different, then find the different texts. After that, perform semantic recognition on the first written content and the second written content to determine the accurate text among the different texts, or display it to the user and let the user select the accurate text, so as to obtain the final written content. Or, build a neural network that outputs the final text, and then input the first written content and the second written content into the neural network to obtain the final written content.

[0120] It can be understood that since there are some identical texts in the continuously captured images, when determining the final written content, it can be to only determine the newly written content, and then merge the currently determined written content with the previously determined written content to obtain the current final written content.

[0121] Step 2140: Compare the final written content with the corresponding answer content to determine whether the final written content is correct.

[0122] Exemplarily, after obtaining the final written content, compare the final written content with the corresponding answer content. If they are the same, then determine that the written content is correct; otherwise, determine that the written content is incorrect. This process can be regarded as the process of grading the answer. It can be understood that since the final written content is determined in real time during the writing process, comparing the real-time determined final written content with the answer content can achieve real-time grading during the answering process.

[0123] As described above, by setting a rotatable photographing device, a camera with a smaller field of view can be used to ensure the clarity of the photograph, and the photographing range can be expanded by rotation to balance clarity and integrity. Moreover, based on the writing trajectory, stroke order, and OCR technology, the final written content can be obtained, which can further improve the accuracy of text recognition. Additionally, by photographing the area with markers in real time, the real-time written content can be parsed, and then the real-time written content can be compared with the answer content to achieve real-time marking during the answering process.

[0124] Figure 9 FIG. 4 is a schematic structural diagram of a rotary photographing device provided by an embodiment of the present application. This device is applied to an electronic device, and the electronic device includes a rotatable photographing device. Refer to Figure 9 , this device includes: a first photographing unit 301, a modeling acquisition unit 302, an image stitching unit 303, a region division unit 304, a second photographing unit 305, and a marker recognition unit 306.

[0125] The first photographing unit 301 is configured to control the rotation of the photographing device to perform sub-region photographing and modeling on a text target object; the modeling acquisition unit 302 is configured to acquire multiple modeling images photographed by the photographing device, and each modeling image corresponds to a sub-region; the image stitching unit 303 is configured to stitch the multiple modeling images to obtain a panoramic image of the text target object; the region division unit 304 is configured to divide the text target object according to the panoramic image to obtain multiple sub-regions; the second photographing unit 305 is configured to control the rotation of the photographing device and photograph each sub-region; the marker recognition unit 306 is configured to, during the photographing process, recognize the sub-region with a marker based on the photographed content to track the text content corresponding to the marker.

[0126] In one embodiment, the first photographing unit 301 may specifically be configured to: control the photographing device to rotate multiple times according to the received rotation instruction, and control the photographing device to perform sub-region photographing on the text target object after each rotation, and each photographing corresponds to a sub-region.

[0127] In one embodiment, when the first photographing unit 301 is configured to control the photographing device to rotate multiple times according to the received rotation instruction, it may specifically include: acquiring the size information of the text target object; obtaining the corresponding rotation rule according to the size information, and generating a rotation instruction according to the rotation rule; controlling the photographing device to rotate multiple times according to the rotation instruction.

[0128] In one embodiment, the region division unit 304 may specifically be: evenly dividing the text target object according to the panoramic image to obtain a plurality of sub-regions of equal size; or, performing text recognition on the panoramic image and dividing the text target object according to the recognized text content to obtain a plurality of sub-regions.

[0129] In one embodiment, it further includes: an alternative determination unit, configured to, after identifying a sub-region with a marker based on the shooting content to track the text content corresponding to the marker, when it is detected that the marker leaves the currently shot sub-region, determine an alternative sub-region where the marker may appear; a third shooting unit, configured to control the rotation of the shooting device to shoot the alternative sub-region, and during the shooting process, identify the marker based on the shooting content.

[0130] In one embodiment, the alternative determination unit may specifically be: when it is detected that the marker leaves the currently shot sub-region, determining the alternative sub-region according to the preset region shooting order; or, when it is detected that the marker leaves the currently shot sub-region, obtaining each adjacent sub-region of the currently shot sub-region and determining the alternative sub-region among the adjacent sub-regions.

[0131] In one embodiment, the marker includes a pen and / or a human hand, and the marker is used to indicate the text content in the text target object; the marker recognition unit 306 includes: a first recognition subunit, configured to, during the shooting process, recognize the sub-region with the marker based on the shooting content; a first real-time shooting subunit, configured to control the shooting device to shoot the sub-region with the marker to obtain a shooting image; a pointing recognition subunit, configured to recognize the text content pointed to by the marker in the text target object based on the shooting image

[0132] In one embodiment, the marker includes a pen and / or a human hand, and the marker is related to a writing action, and the writing action is used to write on the text target object. The marker recognition unit 306 includes: a second recognition subunit, configured to, during the shooting process, recognize the sub-region with the marker based on the shooting content; a second real-time shooting subunit, configured to control the shooting device to perform real-time shooting on the sub-region with the marker to obtain a plurality of shooting images; a stroke determination subunit, configured to determine the writing trajectory and stroke order when the marker performs the writing action according to the plurality of shooting images; a first content subunit, configured to determine the first writing content corresponding to the writing action according to the writing trajectory and stroke order; a second content subunit, configured to process the shooting image using optical character recognition technology to obtain the second writing content corresponding to the writing action; a third content subunit, configured to obtain the final writing content according to the first writing content and the second writing content.

[0133] In one embodiment, the text target includes the topics of multiple exercises; it further includes: a topic recognition unit, which is used to splice multiple pieces of the modeling images to obtain a panoramic image of the text target, and then perform text recognition on the panoramic image to obtain the text content of the text target, where the text content is the topic content; an answer search unit, which is used to search for the corresponding answer content in a preset exercise question bank; a content comparison unit, which is used to compare the final written content with the corresponding answer content after obtaining the final written content based on the first written content and the second written content to determine whether the final written content is correct.

[0134] The rotary shooting device provided in this embodiment is included in a rotary shooting device and is used to execute the rotary shooting method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0135] It should be noted that in the embodiments of the above rotary shooting device, the various units included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of this application.

[0136] Figure 10 This is a schematic structural diagram of an electronic device provided in an embodiment of this application. As Figure 10 shown, this electronic device is a rotary shooting electronic device, and this electronic device includes a processor 30, a memory 31, an input device 32, an output device 33, and a rotatable shooting device 34; the number of processors 30 in the electronic device can be one or more, Figure 10 here, one processor 30 is taken as an example; the processor 30, the memory 31, the input device 32, the output device 33, and the rotatable shooting device 34 in the electronic device can be connected through a bus or other means, Figure 10 here, connection through a bus is taken as an example.

[0137] The memory 31, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules in the rotary shooting method in the embodiments of this application (for example, the first shooting unit 301, the modeling acquisition unit 302, the image splicing unit 303, the area division unit 304, the second shooting unit 305, and the marker recognition unit 306 in the rotary shooting device). The processor 30 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 31, that is, implements the rotary shooting method provided in any of the above embodiments.

[0138] The memory 31 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the electronic device and the like. In addition, the memory 31 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 31 may further include a memory remotely provided with respect to the processor 30, and these remote memories may be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0139] The input device 32 can be used to receive input digital or character information, and generate key signal inputs related to the user settings and function controls of the electronic device. The output device 33 may include devices such as a display screen and a speaker. The rotatable photographing device 34 is controlled by the processor 30 to rotate and photograph. Refer to Figure 2 and Figure 3 , the photographing device includes a single camera and a first rotating component, the single camera is a zoom camera, and the first rotating component is used to control the zoom camera to rotate, or, the photographing device includes a single camera, a second rotating component and a reflector, the second rotating component is used to control the reflector to rotate, the single camera is the front camera of the electronic device, and the reflector is used to reflect external light to the front camera for imaging. The electronic device may further include a communication device (not shown in the figure), which can be used to perform data communication with other devices.

[0140] The above electronic device includes the rotating photographing device provided in the foregoing embodiment, can be used to execute the rotating photographing method provided in any embodiment, and has corresponding functions and beneficial effects.

[0141] In addition, the embodiment of the present application further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to perform related operations in the rotating photographing method provided in any embodiment of the present application when executed by a computer processor, and have corresponding functions and beneficial effects.

[0142] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product.

[0143] Therefore, the present application can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0144] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory. The memory may include non-permanent memory in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0145] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0146] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0147] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A rotation shooting method, applied to an electronic device, characterized in that, The electronic device includes a rotatable photographing device, and the method includes: Controlling the rotation of the photographing device to perform sub-region photographing and modeling on a text target; Obtaining a plurality of modeling images photographed by the photographing device, each of the modeling images corresponding to a sub-region; Stitching the plurality of modeling images to obtain a panoramic image of the text target; Dividing the text target according to the panoramic image to obtain a plurality of sub-regions; Controlling the rotation of the photographing device and photographing each of the sub-regions, including: controlling the rotation of the photographing device according to a preset region photographing order, and after each rotation, controlling the photographing device to photograph the currently corresponding sub-region; During the photographing process, identifying the sub-region where a marker exists based on the photographed content to track the text content corresponding to the marker; After identifying the sub-region where a marker exists based on the photographed content to track the text content corresponding to the marker, it further includes: When it is detected that the marker leaves the currently photographed sub-region, determining alternative sub-regions where the marker may appear; Controlling the rotation of the photographing device to photograph the alternative sub-regions, and during the photographing process, identifying the marker based on the photographed content; The determining the alternative sub-regions where the marker may appear includes: Determining alternative sub-regions according to a preset region photographing order; or, Obtaining each adjacent sub-region of the currently photographed sub-region, and determining alternative sub-regions among the adjacent sub-regions.

2. The method according to claim 1, wherein The controlling the rotation of the photographing device to perform sub-region photographing and modeling on a text target includes: Controlling the photographing device to rotate multiple times according to a received rotation instruction, and after each rotation, controlling the photographing device to perform sub-region photographing on the text target, with each photographing corresponding to a sub-region.

3. The method according to claim 2, characterized in that, The controlling the photographing device to rotate multiple times according to a received rotation instruction includes: Obtaining the size information of the text target; Obtaining a corresponding rotation rule according to the size information, and generating a rotation instruction according to the rotation rule; Controlling the photographing device to rotate multiple times according to the rotation instruction.

4. The method according to claim 1, wherein The dividing the text target according to the panoramic image to obtain a plurality of sub-regions includes: Dividing the text target evenly according to the panoramic image to obtain a plurality of sub-regions of equal size; or, Performing text recognition on the panoramic image, and dividing the text target according to the recognized text content to obtain a plurality of sub-regions.

5. The method according to claim 1, wherein The marker includes a pen and / or a human hand, and the marker is used to indicate the text content in the text target; The tracking the text content corresponding to the marker includes: Controlling the photographing device to photograph the sub-region where the marker exists to obtain a photographed image; Identifying the text content pointed to by the marker in the text target based on the photographed image.

6. The method according to claim 1, wherein The marker includes a pen and / or a human hand, and the marker is related to a writing action, and the writing action is used to write on the text target; The tracking the text content corresponding to the marker includes: Control the shooting device to perform real-time shooting on the sub-region where the marker exists to obtain multiple shooting images; Determine the writing trajectory and stroke order when the marker performs a writing action based on the multiple shooting images; Determine the first writing content corresponding to the writing action according to the writing trajectory and stroke order; Use optical character recognition technology to process the shooting images to obtain the second writing content corresponding to the writing action; Obtain the final writing content according to the first writing content and the second writing content.

7. The method according to claim 6, wherein The text target object includes the titles of multiple exercises; After stitching the multiple modeling images to obtain the panoramic image of the text target object, it further includes: Perform text recognition on the panoramic image to obtain the text content of the text target object, and the text content is the title content; In a preset exercise question bank, search for the answer content corresponding to the text content; After obtaining the final writing content according to the first writing content and the second writing content, it further includes: Compare the final writing content with the corresponding answer content to determine whether the final writing content is correct.

8. A rotating shooting device, applied to an electronic device, characterized in that, The electronic device includes a rotatable shooting device, and the device includes: A first shooting unit, configured to control the rotation of the shooting device to perform sub-region shooting and modeling on the text target object; A modeling acquisition unit, configured to acquire multiple modeling images captured by the shooting device, and each modeling image corresponds to a sub-region; An image stitching unit, configured to stitch the multiple modeling images to obtain the panoramic image of the text target object; A region division unit, configured to divide the text target object according to the panoramic image to obtain multiple sub-regions; A second shooting unit, configured to control the rotation of the shooting device and shoot each sub-region. Specifically, the second shooting unit is configured to control the rotation of the shooting device according to a preset region shooting order, and control the shooting device to shoot the currently corresponding sub-region after each rotation; A marker recognition unit, configured to, during the shooting process, recognize the sub-region where the marker exists based on the shooting content to track the text content corresponding to the marker; An alternative determination unit, configured to, after detecting that the marker leaves the currently shot sub-region based on the shooting content to track the text content corresponding to the marker, determine the alternative sub-regions where the marker may appear; A third shooting unit, configured to control the shooting device to rotate to shoot the alternative sub-regions, and during the shooting process, recognize the marker based on the shooting content; Specifically, the alternative determination unit is configured to determine the alternative sub-regions according to the preset region shooting order when detecting that the marker leaves the currently shot sub-region; or, when detecting that the marker leaves the currently shot sub-region, obtain each adjacent sub-region of the currently shot sub-region, and determine the alternative sub-regions among the adjacent sub-regions.

9. A rotating shooting electronic device, characterized in that, Includes: One or more processors; A rotatable shooting device, and the rotation and shooting of the shooting device are controlled by the processor; A memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the rotating shooting method according to any one of claims 1-7.

10. The electronic device according to claim 9, wherein The shooting device includes a single camera and a first rotating component, the single camera is a zoom camera, and the first rotating component is used to control the rotation of the zoom camera, or, The shooting device includes a single camera, a second rotating component and a reflector, the second rotating component is used to control the rotation of the reflector, the single camera is a front camera of the electronic device, and the reflector is used to reflect external light to the front camera for imaging.

11. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions are used to execute the rotating shooting method according to any one of claims 1-7 when executed by a computer processor.

Images