Camera image angle detection and calibration method and device
By combining image angle prediction and human pose estimation models into an automatic calibration scheme, the problem of AI detection accuracy caused by camera installation angle deviation is solved, achieving efficient image calibration and user guidance, and improving the accuracy of AI detection and user experience.
Patent Information
- Application Number
- CN202410195389.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-02-22
AI Technical Summary
In existing technologies, camera installation angle deviations lead to a decrease in the accuracy of AI detection tasks. Existing hardware sensor solutions are costly and have limited accuracy, while manual adjustment solutions rely on user intervention and have unstable results.
By combining image angle prediction models and human pose estimation models, the system automatically detects camera image tilt and performs multiple rotation calibrations to generate calibration suggestions, thereby improving the accuracy of AI detection.
It improves the accuracy of AI detection, reduces false alarms and false negatives, and enhances user experience and satisfaction.
Smart Images

Figure CN118015087B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing technology, and in particular relates to a method and device for detecting and calibrating a camera image angle. Background Art
[0002] In today's security and other fields, artificial intelligence (AI) detection tasks such as face recognition, human posture detection, and target detection are increasingly widely used in various smart devices and systems to provide users with convenient and safe services. However, in actual applications, the installation angle of the camera has a crucial impact on the quality and recognition effect of the image. Incorrect installation or rotation of the camera may cause problems such as image tilt and flipping, which in turn affects the accuracy of AI detection tasks. Users may inadvertently produce such deviations during camera installation. In this case, it is difficult for the AI system to accurately identify objects or humans, resulting in false positives or false negatives. These problems will not only reduce the user experience and satisfaction, but also bring security risks to users.
[0003] To solve this problem, the existing solution is to use hardware sensors to detect the installation angle of the user's camera, but this solution will bring additional costs and space occupation, and the accuracy and stability of the sensor are also limited, and it cannot guarantee real-time and accurate feedback of the camera angle. Another solution may be to adjust the installation angle of the camera through manual intervention, but this solution requires the user's active participation and operation, and the user may not know how to properly install and adjust the camera, resulting in inconsistent and unstable picture angles. Summary of the invention
[0004] In order to solve the above technical problems, the present application provides a camera picture angle detection and calibration method and device. Before the user's video stream enters AI detection and other tasks, the picture angle of the user is repeatedly identified and the picture is calibrated through the picture angle prediction model and the human posture estimation model. At the same time, the user is reminded that there is a deviation in the camera installation angle and calibration suggestions are provided.
[0005] The first aspect of the present application is a camera image angle detection and calibration method, which mainly includes:
[0006] Step S1, obtaining an image from a user video stream;
[0007] Step S2, determining a first rotation angle of the image due to the tilt based on a pre-trained picture angle prediction model;
[0008] Step S3, rotating the image according to the first rotation angle;
[0009] Step S4, performing human posture estimation on the rotated image, obtaining the neck joint and left and right hip joints of the human body, taking the vector between the neck joint and the middle point of the left and right hip joints as the vector in the vertical direction of the human body, determining the angle between the vector and the longitudinal axis of the image coordinate system, and taking the angle as the second rotation angle;
[0010] Step S5, performing a secondary rotation transformation on the image according to the second rotation angle;
[0011] Step S6: input the image into the AI detection model for recognition and analysis of the corresponding task;
[0012] Step S7: Generate a reminder message for reminding the user to perform camera installation calibration according to the first rotation angle and the second rotation angle.
[0013] Preferably, step S4 further comprises:
[0014] Step S41, determining the vertical vectors of multiple human bodies through multiple images of the video stream or multiple human bodies in one image, and calculating multiple angles based on the corresponding vertical axes of the image coordinate system;
[0015] Step S42: Calculate an average value of the multiple angles and use it as the second rotation angle.
[0016] Preferably, when the first rotation angle is outside the set range, the image is rotated, and correspondingly, when the second rotation angle is outside the set range, the image is subjected to a secondary rotation transformation, and the set range is [-10°, 10°].
[0017] Preferably, step S7 further comprises:
[0018] Step S71, calculating the sum of the first rotation angle and the second rotation angle;
[0019] Step S72: When the sum of the first rotation angle and the second rotation angle exceeds a threshold, a reminder message is generated, wherein the reminder message includes a total rotation angle value and a calibrated image, and a carrier of the reminder message includes but is not limited to voice, text, and graphics.
[0020] In a second aspect of the present application, a camera image angle detection and calibration device mainly comprises:
[0021] An image acquisition module, used to acquire images from a user video stream;
[0022] A first rotation angle prediction module, used to determine a first rotation angle of an image due to tilt based on a pre-trained picture angle prediction model;
[0023] An image rotation module, used for rotating the image according to the first rotation angle;
[0024] The second rotation angle prediction module is used to estimate the human body posture of the rotated image, obtain the neck joint and left and right hip joints of the human body, use the vector between the neck joint and the middle point of the left and right hip joints as the vector in the vertical direction of the human body, determine the angle between the vector and the longitudinal axis of the image coordinate system, and use the angle as the second rotation angle;
[0025] A secondary rotation transformation module, used for performing a secondary rotation transformation on the image according to the second rotation angle;
[0026] The task processing module is used to input images into the AI detection model for identification and analysis of corresponding tasks;
[0027] The calibration information generating module is used to generate reminder information for reminding the user to perform camera installation calibration according to the first rotation angle and the second rotation angle.
[0028] Preferably, the second rotation angle prediction module includes:
[0029] An angle calculation unit, used to determine the vectors of the vertical direction of multiple human bodies through multiple images of the video stream or multiple human bodies in one image, and calculate multiple angles based on the corresponding vertical axes of the image coordinate system;
[0030] The second rotation angle calculation unit is used to calculate an average value of the multiple angles and use the average value as the second rotation angle.
[0031] Preferably, when the first rotation angle is outside the set range, the image is rotated, and correspondingly, when the second rotation angle is outside the set range, the image is subjected to a secondary rotation transformation, and the set range is [-10°, 10°].
[0032] Preferably, the calibration information generating module comprises:
[0033] a total rotation angle calculation unit, configured to calculate the sum of the first rotation angle and the second rotation angle;
[0034] The reminder information generating unit is used to generate a reminder information when the sum of the first rotation angle and the second rotation angle exceeds a threshold value. The reminder information includes a total rotation angle value and a calibrated image. The carrier of the reminder information includes but is not limited to voice, text, and graphics.
[0035] In a third aspect of the present application, a computer device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the camera picture angle detection and calibration method as described above.
[0036] In a fourth aspect of the present application, a readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the camera picture angle detection and calibration method as described above.
[0037] This application improves the recognition accuracy of tasks such as AI detection, avoids the problem of false positives or false negatives, and enhances user experience and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a flowchart of a preferred embodiment of the camera image angle detection and calibration method of the present application.
[0039] Figure 2 It is a schematic diagram of the structure of a control terminal suitable for implementing the implementation mode of the present application. DETAILED DESCRIPTION
[0040] In order to make the purpose, technical scheme and advantages of the implementation of this application clearer, the technical scheme in the implementation of this application will be described in more detail in combination with the drawings in the implementation of this application. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described implementation is a part of the implementation of this application, not all of the implementations. The implementation described below with reference to the drawings is exemplary and is intended to be used to explain this application, and cannot be understood as a limitation on this application. Based on the implementation in this application, all other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The implementation of this application is described in detail below in combination with the drawings.
[0041] The first aspect of the present application provides a camera image angle detection and calibration method, such as Figure 1 As shown, it mainly includes:
[0042] Step S1, obtaining an image from a user video stream;
[0043] Step S2, determining a first rotation angle of the image due to the tilt based on a pre-trained picture angle prediction model;
[0044] Step S3, rotating the image according to the first rotation angle;
[0045] Step S4, performing human posture estimation on the rotated image, obtaining the neck joint and left and right hip joints of the human body, taking the vector between the neck joint and the middle point of the left and right hip joints as the vector in the vertical direction of the human body, determining the angle between the vector and the longitudinal axis of the image coordinate system, and taking the angle as the second rotation angle;
[0046] Step S5, performing a secondary rotation transformation on the image according to the second rotation angle;
[0047] Step S6: input the image into the AI detection model for recognition and analysis of the corresponding task;
[0048] Step S7: Generate a reminder message for reminding the user to perform camera installation calibration according to the first rotation angle and the second rotation angle.
[0049] This application adopts a joint optimization strategy of picture angle prediction and human posture estimation and calibration, and proposes a camera picture angle detection and calibration scheme to improve the accuracy of AI detection and recognition tasks. First, in steps S1-S3, the first picture angle detection and calibration are performed based on the picture angle prediction model. In steps S4-S5, the second picture angle detection and calibration are performed based on the human posture estimation model. The above two processes can be iterated multiple times to improve the accuracy of AI detection and recognition tasks. In step S7, an intelligent reminder mechanism is introduced to inform users whether there are deviations in the camera installation by sending accurate calibration suggestions to users, thereby improving the reliability of AI detection tasks in practical applications.
[0050] In step S1, an image is obtained from a user video stream as input. The image may be in color or grayscale and may be of any resolution and format.
[0051] In step S2, the input image is sent to a pre-trained picture angle prediction model, which is trained to predict the rotation angle of the image and output the rotation angle value of the image in the range of [-180°, 180°].
[0052] It should be noted that the training method of the picture angle prediction model is: use the training set to supervise the model and optimize the loss function to improve the model's ability to accurately recognize the picture angle. Among them, the training set collects camera picture data from various scenes to ensure that different rotation angles and environments are covered, and accurate angle information is annotated for each picture as the training target of supervised learning. The model adopts a neural network structure, and can use ResNet, VGG, MobileNet and other models to extract image features from the input camera picture image, and the model output is the angle of the picture. The loss function is designed to measure the difference between the angle output by the model and the actual angle, and the mean square error (MSE) is used as the loss function. The formula is as follows:
[0053]
[0054] Where N is the number of training samples, θ i is the real angle, is the angle predicted by the model.
[0055] In step S3, the input image is subjected to a corresponding rotation transformation according to the output rotation angle value to obtain a calibrated image.
[0056] In step S4, if the model of the AI detection task is a model of the human posture estimation task, such as OpenPose, AlphaPose, etc., and there are key points of multiple people in the calibrated image, then the coordinates of the neck joint points and the coordinates of the middle points of the left and right hip joints output by the human posture estimation model are connected to form a vector in the vertical direction of the human body. The rotation angle of the picture is determined by calculating the angle between the vector in the vertical direction of the human body and the longitudinal axis of the image coordinate system.
[0057] It should be noted that the human pose estimation task is an important problem in the field of computer vision. Its goal is to infer the key joint positions and posture information of the human body from images or videos. This task involves locating and tracking the positions of each joint of the human body to restore the two-dimensional posture of the human body in the plane (2D pose estimation) or the three-dimensional posture of the human body in space (3D pose estimation). Specifically, the human pose estimation model analyzes the input image or video to identify the key points of the human body, such as the head, shoulders, elbows, knees and other joints, and establishes the relationship between these joints to restore the overall human pose. This task has broad practical significance for many applications, including but not limited to human-computer interaction, virtual reality, security monitoring, motion capture and other fields. In terms of implementation, deep learning technology is often used to enable the model to automatically learn and infer complex human pose information by training a large amount of labeled human pose data.
[0058] In some optional implementations, step S4 further includes:
[0059] Step S41, determining the vertical vectors of multiple human bodies through multiple images of the video stream or multiple human bodies in one image, and calculating multiple angles based on the corresponding vertical axes of the image coordinate system;
[0060] Step S42: Calculate an average value of the multiple angles and use it as the second rotation angle.
[0061] This embodiment determines the rotation angle of the picture by calculating the average value of the angles between a plurality of vectors in the vertical direction of the human body and the longitudinal axis of the image coordinate system.
[0062] Step S5 is used to perform a secondary rotation transformation on the image. If the image rotation angle value is not within the set range, the calibrated image is further rotated to obtain a further calibrated image. Similarly, for step S3, the set range can also be considered when performing the first rotation transformation. Specifically, in some optional implementations, when the first rotation angle is outside the set range, the image is rotated, and correspondingly, when the second rotation angle is outside the set range, the image is subjected to a secondary rotation transformation, and the set range is [-10°, 10°].
[0063] Step S6 is used to send the re-calibrated image to the model of AI detection, recognition and other tasks for corresponding recognition and analysis. The AI detection here belongs to the prior art. The invention point of the present application is that before performing the AI detection, the image is pre-processed through steps S1 to S5 to achieve image tilt correction.
[0064] Finally, in step S7, the output results of the picture angle value of the comprehensive picture angle prediction model and the human posture estimation model are combined. If the output picture angle value is not within the preset reasonable range, the system sends a reminder message to the user to remind the user that there is a deviation in the camera installation and recommends re-calibration.
[0065] In some optional implementations, step S7 further includes:
[0066] Step S71, calculating the sum of the first rotation angle and the second rotation angle;
[0067] Step S72: When the sum of the first rotation angle and the second rotation angle exceeds a threshold, a reminder message is generated, wherein the reminder message includes a total rotation angle value and a calibrated image, and a carrier of the reminder message includes but is not limited to voice, text, and graphics.
[0068] This embodiment is used to guide the user to adjust the camera installation angle to improve the accuracy of tasks such as AI detection.
[0069] The second aspect of the present application provides a camera picture angle detection and calibration device corresponding to the above method, mainly comprising:
[0070] An image acquisition module, used to acquire images from a user video stream;
[0071] A first rotation angle prediction module, used to determine a first rotation angle of an image due to tilt based on a pre-trained picture angle prediction model;
[0072] An image rotation module, used for rotating the image according to the first rotation angle;
[0073] The second rotation angle prediction module is used to estimate the human body posture of the rotated image, obtain the neck joint and left and right hip joints of the human body, use the vector between the neck joint and the middle point of the left and right hip joints as the vector in the vertical direction of the human body, determine the angle between the vector and the longitudinal axis of the image coordinate system, and use the angle as the second rotation angle;
[0074] A secondary rotation transformation module, used for performing a secondary rotation transformation on the image according to the second rotation angle;
[0075] The task processing module is used to input images into the AI detection model for identification and analysis of corresponding tasks;
[0076] The calibration information generating module is used to generate reminder information for reminding the user to perform camera installation calibration according to the first rotation angle and the second rotation angle.
[0077] In some optional implementations, the second rotation angle prediction module includes:
[0078] An angle calculation unit, used to determine the vectors of the vertical direction of multiple human bodies through multiple images of the video stream or multiple human bodies in one image, and calculate multiple angles based on the corresponding vertical axes of the image coordinate system;
[0079] The second rotation angle calculation unit is used to calculate an average value of the multiple angles and use the average value as the second rotation angle.
[0080] In some optional embodiments, when the first rotation angle is outside the set range, the image is rotated, and correspondingly, when the second rotation angle is outside the set range, the image is subjected to a secondary rotation transformation, and the set range is [-10°, 10°].
[0081] In some optional implementations, the calibration information generation module includes:
[0082] a total rotation angle calculation unit, configured to calculate the sum of the first rotation angle and the second rotation angle;
[0083] The reminder information generating unit is used to generate a reminder information when the sum of the first rotation angle and the second rotation angle exceeds a threshold value. The reminder information includes a total rotation angle value and a calibrated image. The carrier of the reminder information includes but is not limited to voice, text, and graphics.
[0084] In a third aspect of the present application, a computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the camera picture angle detection and calibration method as described above.
[0085] In a fourth aspect of the present application, a readable storage medium stores a computer program, which, when executed by a processor, is used to implement the camera image angle detection and calibration method as described above.
[0086] Reference below Figure 2 , which shows a schematic structural diagram of a control terminal 400 suitable for implementing the embodiments of the present application. Figure 2 The computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0087] like Figure 2 As shown, the computer device 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the computer device 400 are also stored. The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0088] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.
[0089] In particular, according to the embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above functions defined in the method of the present application are executed. It should be noted that the computer storage medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0090] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0091] The modules or units involved in the embodiments described in this application may be implemented by software or hardware. The modules or units described may also be set in a processor, and the names of these modules or units do not constitute limitations on the modules or units themselves in some cases.
[0092] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
[0093] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A camera image angle detection and calibration method, characterized in that: include: Step S1, obtaining an image from a user video stream; Step S2, determining a first rotation angle of the image due to the tilt based on a pre-trained picture angle prediction model; Step S3, rotating the image according to the first rotation angle; Step S4, performing human posture estimation on the rotated image, obtaining the neck joint and left and right hip joints of the human body, taking the vector between the neck joint and the middle point of the left and right hip joints as the vector in the vertical direction of the human body, determining the angle between the vector and the longitudinal axis of the image coordinate system, and taking the angle as the second rotation angle; Step S5, performing a secondary rotation transformation on the image according to the second rotation angle; Step S6: input the image into the AI detection model for recognition and analysis of the corresponding task; Step S7: Generate a reminder message for reminding the user to perform camera installation calibration according to the first rotation angle and the second rotation angle.
2. The camera image angle detection and calibration method as claimed in claim 1, characterized in that: Step S4 further comprises: Step S41, determining the vertical vectors of multiple human bodies through multiple images of the video stream or multiple human bodies in one image, and calculating multiple angles based on the corresponding vertical axes of the image coordinate system; Step S42: Calculate an average value of the multiple angles and use it as the second rotation angle.
3. The camera image angle detection and calibration method as claimed in claim 1, characterized in that: When the first rotation angle is outside the set range, the image is rotated, and correspondingly, when the second rotation angle is outside the set range, the image is subjected to a secondary rotation transformation, and the set range is [-10°, 10°].
4. The camera image angle detection and calibration method as claimed in claim 1, characterized in that: Step S7 further comprises: Step S71, calculating the sum of the first rotation angle and the second rotation angle; Step S72: When the sum of the first rotation angle and the second rotation angle exceeds a threshold, a reminder message is generated, wherein the reminder message includes a total rotation angle value and a calibrated image, and a carrier of the reminder message includes but is not limited to voice, text, and graphics.
5. A camera image angle detection and calibration device, characterized in that: include: An image acquisition module, used to acquire images from a user video stream; A first rotation angle prediction module, used to determine a first rotation angle of an image due to tilt based on a pre-trained picture angle prediction model; An image rotation module, used for rotating the image according to the first rotation angle; The second rotation angle prediction module is used to estimate the human body posture of the rotated image, obtain the neck joint and left and right hip joints of the human body, use the vector between the neck joint and the middle point of the left and right hip joints as the vector in the vertical direction of the human body, determine the angle between the vector and the longitudinal axis of the image coordinate system, and use the angle as the second rotation angle; A secondary rotation transformation module, used for performing a secondary rotation transformation on the image according to the second rotation angle; The task processing module is used to input images into the AI detection model for identification and analysis of corresponding tasks; The calibration information generating module is used to generate reminder information for reminding the user to perform camera installation calibration according to the first rotation angle and the second rotation angle.
6. The camera image angle detection and calibration device as claimed in claim 5, characterized in that: The second rotation angle prediction module comprises: An angle calculation unit, used to determine the vectors of the vertical direction of multiple human bodies through multiple images of the video stream or multiple human bodies in one image, and calculate multiple angles based on the corresponding vertical axes of the image coordinate system; The second rotation angle calculation unit is used to calculate an average value of the multiple angles and use the average value as the second rotation angle.
7. The camera image angle detection and calibration device as claimed in claim 5, characterized in that: When the first rotation angle is outside the set range, the image is rotated, and correspondingly, when the second rotation angle is outside the set range, the image is subjected to a secondary rotation transformation, and the set range is [-10°, 10°].
8. The camera image angle detection and calibration device as claimed in claim 5, characterized in that: The calibration information generation module comprises: a total rotation angle calculation unit, configured to calculate the sum of the first rotation angle and the second rotation angle; The reminder information generating unit is used to generate a reminder information when the sum of the first rotation angle and the second rotation angle exceeds a threshold value. The reminder information includes a total rotation angle value and a calibrated image. The carrier of the reminder information includes but is not limited to voice, text, and graphics.
9. A computer device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the camera picture angle detection and calibration method as described in any one of claims 1 to 4.
10. A readable storage medium storing a computer program, wherein the computer program, when executed by a processor, is used to implement the camera picture angle detection and calibration method according to any one of claims 1 to 4.
