Panoramic view angle control method and device, computer equipment and storage medium

Abstract

The invention relates to a panoramic view angle control method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: in response to detection of a first target, displaying a panoramic image containing the first target in a panoramic preview picture of a panoramic camera; determining a first moving track generated by the panoramic camera in the current shooting process, and determining a second moving track at the next moment in the shooting process based on the first moving track; determining a second target based on the second moving track and the panoramic image, and determining a transition mode between the first target and the second target based on the second moving track and the panoramic image; and in response to the shooting process of the panoramic camera, in which a second target is in a preset range of a second moving track, based on a transition mode, transitioning the panoramic image containing the first target to a panoramic image containing the second target. By adopting the method, the targets can be accurately locked, so that transition between the targets is realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data image processing, and particularly to a panoramic view control method, apparatus, computer device, and storage medium. Background Art

[0002] With the continuous development of panoramic cameras, users will use panoramic cameras to record various contents in more and more scenarios. However, during the shooting process, due to the changes in the user's hand and the shooting angle of the panoramic camera being 360° panoramic, it is impossible to accurately lock the target that the user needs to shoot, and it is impossible to achieve the transition between different targets, which will cause difficulties in subsequent editing. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a panoramic view control method, apparatus, computer device, and storage medium.

[0004] In a first aspect, the present disclosure provides a panoramic view control method. Applied to a panoramic camera, the method includes:

[0005] In response to detecting a first target during the shooting process of the panoramic camera, a panoramic image containing the first target is displayed in the panoramic preview screen of the panoramic camera, and the first target is located in a first area of the panoramic image;

[0006] Determine a first movement trajectory generated during the current shooting process of the panoramic camera, and determine a second movement trajectory at the next moment during the shooting process based on the first movement trajectory;

[0007] Determine a second target based on the second movement trajectory and the panoramic image, and determine a transition method between the first target and the second target based on the second movement trajectory and the panoramic image;

[0008] In response to the second target being within a preset range of the second movement trajectory during the shooting process of the panoramic camera, based on the transition method, transition the panoramic image containing the first target to a panoramic image containing the second target, and the second target is located in the first area of the panoramic image.

[0009] In one embodiment, the response to detecting a first target during the shooting process of the panoramic camera includes:

[0010] Identify each frame of panoramic image captured by the panoramic camera during the shooting process;

[0011] Determine the movement speed of the panoramic camera corresponding to each frame of panoramic image, and determine multiple frames of panoramic images less than a preset speed threshold according to the preset speed threshold;

[0012] Perform target recognition in the multi-frame panoramic image. In response to the non-empty result of the target recognition, it is determined that a target is detected during the shooting process of the panoramic camera.

[0013] In one embodiment, after displaying the panoramic image containing the first target in the panoramic preview screen of the panoramic camera, the method further includes:

[0014] Determine the first position of the first target in the first movement trajectory of the panoramic camera, and determine the target holding area based on the first position and a preset position distance threshold;

[0015] During the shooting process of the panoramic camera, in response to the panoramic camera being located in the target holding area, display the panoramic image containing the first target in the panoramic preview screen of the panoramic camera, and the first target is located in the first area of the panoramic image.

[0016] In one embodiment, the determining the second movement trajectory at the next moment during the shooting process based on the first movement trajectory includes:

[0017] Determine the speed information that matches the first movement trajectory of the panoramic camera;

[0018] Determine the change amplitude of the speed information. In response to the change amplitude of the speed information not being a linear change, based on the first movement trajectory, use the particle filter algorithm to determine the second movement trajectory at the next moment during the shooting process;

[0019] In response to the change amplitude of the speed information being a linear change, use the speed information, the first movement trajectory, and the Kalman filter to determine the second movement trajectory at the next moment during the shooting process.

[0020] In one embodiment, the determining the second target based on the second movement trajectory and the panoramic image includes:

[0021] Based on the second movement trajectory, determine the shooting direction of the panoramic camera;

[0022] According to the shooting direction, determine the second target search direction in the panoramic image;

[0023] Determine the second target at least based on the first target and the scene style of the panoramic image along the second target search direction of the panoramic image.

[0024] In one embodiment, the determining the transition method between the first target and the second target based on the second movement trajectory and the panoramic image includes:

[0025] Determine the transition distance between the first target and the second target based on the positions of the first target and the second target in the second movement trajectory;

[0026] In response to the transition distance being less than a preset distance threshold, directly transition the first target to the second target;

[0027] In response to the transition distance being greater than a preset distance threshold, determine the speed information that matches the first movement trajectory of the panoramic camera;

[0028] Determine the change amplitude of the speed information, based on the change amplitude, determine the transition type, and according to the transition type and the panoramic image in the second movement trajectory, determine the transition method.

[0029] In one embodiment of the device, the transition types include: linear transition type and non-linear transition type. The determining the transition type based on the change amplitude includes:

[0030] In response to the change amplitude being a uniform change, determine that the transition type is a linear transition type;

[0031] In response to the change amplitude not being a uniform change, determine that the transition type is a non-linear transition type.

[0032] In a second aspect, the present disclosure also provides a panoramic view control device. The device includes:

[0033] A view adjustment module, configured to, in response to detecting a first target during the shooting process of the panoramic camera, display a panoramic image containing the first target in the panoramic preview screen of the panoramic camera, where the first target is located in a first area of the panoramic image;

[0034] A trajectory prediction module, configured to determine a first movement trajectory generated during the current shooting process of the panoramic camera, and based on the first movement trajectory, determine a second movement trajectory at the next moment during the shooting process;

[0035] A transition method determination module, configured to determine a second target based on the second movement trajectory and the panoramic image, and determine a transition method between the first target and the second target based on the second movement trajectory and the panoramic image;

[0036] A view switching module, configured to, in response to the second target being within a preset range of the second movement trajectory during the shooting process of the panoramic camera, based on the transition method, transition the panoramic image containing the first target to a panoramic image containing the second target, where the second target is located in a first area of the panoramic image.

[0037] In a third aspect, the present disclosure further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in any of the above method embodiments are implemented.

[0038] In a fourth aspect, the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0039] In a fifth aspect, the present disclosure further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0040] In the above embodiments, when the first target is detected, the panoramic image containing the target can be displayed in the panoramic preview screen in time, and the target can be placed in a specific area (first area), so that the user can quickly focus and track the target and avoid missing important shooting content. By determining the first moving trajectory of the camera and predicting the second moving trajectory at the next moment, the movement trend of the camera can be effectively analyzed and predicted. This makes the movement of the camera smoother and more natural during shooting, and the panoramic image captured maintains good coherence in the time dimension, reduces the abrupt changes in the picture, and brings a more comfortable viewing experience to the audience. Based on the second moving trajectory and the panoramic image, the second target is determined, and the transition method is determined. When the second target enters the preset range, the image can be switched according to the preset transition method. This intelligent switching function can automatically guide the user's attention without frequent manual adjustments, ensuring that the important target is always focused during the shooting process. The identification, positioning and transition processing of the first target and the second target help the system manage the shooting objects more efficiently. Whether it is shooting multiple targets in a static scene or constantly changing targets in a dynamic scene, they can be accurately presented, which improves the shooting ability and adaptability of the panoramic camera in complex scenes. It reduces the time for users to manually search and switch targets during shooting, making shooting more automated and intelligent. Users can focus more on composition, creativity, etc., improving shooting efficiency, especially for shooting tasks that require rapid capture of multiple targets or frequent scene changes. Always place the target (first target or second target) in the first area of the panoramic image, making the picture layout more standardized and reasonable, and making it easier for users and viewers to quickly identify and focus on key content. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings required for the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the panoramic view control method in an embodiment;

[0043] Figure 2 It is a flowchart of detecting the target in step S102 in an embodiment;

[0044] Figure 3 It is a flowchart after step S102 in an embodiment;

[0045] Figure 4 It is a flowchart of step S104 in an embodiment;

[0046] Figure 5 It is a flowchart of a part of step S106 in an embodiment;

[0047] Figure 6 It is a flowchart of another part of step S106 in an embodiment;

[0048] Figure 7 It is a flowchart of step S607 in an embodiment;

[0049] Figure 8 It is a structural schematic block diagram of the panoramic view control device in an embodiment;

[0050] Figure 9 It is an internal structural schematic diagram of a computer device in an embodiment. Specific Embodiments

[0051] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the following further details the present disclosure in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present disclosure and are not used to limit the present disclosure.

[0052] It should be noted that the terms "first", "second", etc. in the specification, claims and the above drawings of this article are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this article described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or equipment.

[0053] In this article, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0054] In one embodiment, as Figure 1 shown, a panoramic view control method is provided. In this embodiment, an example is given where this method is applied to a panoramic camera. In this embodiment, the method includes the following steps:

[0055] S102, in response to detecting a first target during the panoramic camera shooting process, adjust the first target to the first area of the panoramic image to obtain a first panoramic image.

[0056] When the panoramic camera has a preview screen, a panoramic image containing the first target can be displayed in the panoramic preview screen of the preview screen of the panoramic camera, and the first target is located in the first area of the panoramic image.

[0057] When the panoramic camera does not have a preview screen, the panoramic camera can be connected to other electronic devices, and the screen of the other camera can be used to preview the picture during panoramic shooting. At this time, a panoramic image containing the first target can be displayed in the panoramic preview screen of the panoramic camera, and the first target is located in the first area of the panoramic image.

[0058] Among them, the shooting process generally refers to the entire process from when the panoramic camera starts to prepare for shooting (such as opening the camera application, setting shooting parameters, etc.) to actually capturing images and then to the completion of shooting (image data processing, storage, etc.). The preview screen generally refers to the screen on the panoramic camera device for real-time display of the shooting scene. Before shooting, users can view the shooting scene through the preview screen and adjust the shooting angle and parameters, etc. The first area can usually be a specific range or position preset in the panoramic image or determined according to the object detection algorithm. After the first object is detected, it will be displayed within this area so that users can quickly find and focus on the first object.

[0059] Specifically, during the shooting process, the panoramic camera will detect according to the captured scene. When the first object is detected, a panoramic image containing the first object will be displayed in real time on the panoramic preview screen of the camera, and the first object will be accurately presented within the first area of the panoramic image. In this way, users can see the objects they are concerned about in a timely manner during the shooting process without having to search and view after the shooting is completed.

[0060] It should be noted that the detection of the first object can be implemented according to certain algorithms or certain conditions. For example, during the shooting process of the current user, if the user stays at a certain place for a relatively long time and a target is directly in front of the lens of the panoramic camera, this target can be determined as the first object. Those skilled in the art can flexibly determine the detection method of the first object according to the actual situation, and the detection method of the first object is not limited in some embodiments of the present disclosure.

[0061] S104, determine the first movement trajectory generated by the panoramic camera during the current shooting process, and determine the second movement trajectory at the next moment during the shooting process based on the first movement trajectory.

[0062] Among them, the first movement trajectory can usually be the actual movement path generated by the panoramic camera during the currently ongoing shooting process as time goes by. This trajectory can obtain the position and orientation change information of the camera in space through the built-in sensors of the camera (such as accelerometers, gyroscopes, etc.), and then determine its movement trajectory. For example, the movement information such as the horizontal translation, vertical lifting, and rotation around an axis of the camera can all constitute a part of the first movement trajectory. The next moment generally refers to a specific time point following the current shooting time point in chronological order. The second movement trajectory can be the movement trajectory obtained by predicting the movement path of the panoramic camera at the next moment using certain algorithms (such as kinematic models, machine learning prediction algorithms, etc.) based on the already determined first movement trajectory. It reflects the estimation of the future short-term movement trend of the camera based on its current movement state.

[0063] Specifically, when the panoramic camera is taking pictures, the system will obtain and analyze various motion data of the camera in real time to determine its current first movement trajectory. For example, when the camera is panned and rotated continuously during hand-held shooting, the system can record the position and attitude changes of the camera in three-dimensional space through sensor data to form the first movement trajectory. Then, based on this determined first movement trajectory, a specific algorithm is used to analyze and predict the movement trend of the camera to obtain the possible movement path of the camera at the next moment, that is, the second movement trajectory.

[0064] S106. Determine the second target based on the second movement trajectory and the panoramic image, and determine the transition method between the first target and the second target based on the second movement trajectory and the panoramic image.

[0065] Among them, the transition method usually refers to the way of connection and conversion presented between the first target and the second target in the panoramic image as the camera moves according to the second movement trajectory. For example, the switching effect of the picture, the relative position change of the first target and the second target in the picture, etc. The second target can be another specific object or element in the panoramic image determined through comprehensive analysis of the second movement trajectory and the panoramic image. It may be a new target that is about to enter the shooting field of view due to the change of the camera's movement trajectory, or an important object related to the scene under the current movement trend.

[0066] Specifically, after determining the second movement trajectory of the panoramic camera and combining the current panoramic image, the system will analyze and judge the image content. On the one hand, by analyzing information such as the movement direction and speed of the camera, as well as the scene elements in the panoramic image, the second target that is about to appear in the field of view or is related to the current movement trend is identified. For example, when the panoramic camera moves along a certain path, an object (the second target) originally outside the picture will gradually enter the picture as the camera moves, and the system determines it as the second target through image processing and analysis.

[0067] On the other hand, according to the second movement trajectory and information such as the positions and sizes of the first target and the second target in the panoramic image, the transition method between them is determined. For example, the system can adopt a smooth fade-in and fade-out effect, making the first target gradually disappear from the picture while the second target gradually appears clearly in the picture; or through operations such as panning and rotating the picture, naturally transfer the viewer's attention from the first target to the second target. This transition method can make the presentation of the panoramic image more smooth and natural, improve the user viewing experience, and can better guide the viewer's line of sight and highlight key targets and content.

[0068] S108. In response to the second target being within the preset range of the second movement trajectory during the shooting process of the panoramic camera, based on the transition method, transition the panoramic image containing the first target to a panoramic image containing the second target, where the second target is located in the first area of the panoramic image.

[0069] Among them, the preset range generally refers to a pre-set area range, with the second movement trajectory as a reference, used to determine whether the second target is in a suitable position. When the second target enters this range, the system will trigger corresponding operations.

[0070] Specifically, during the shooting process of the panoramic camera, the system continuously monitors the relative position relationship between the second target and the second movement trajectory. When it is detected that the second target enters the preset range set based on the second movement trajectory, the system will perform a screen switching operation on the preview screen of the panoramic camera according to the previously determined transition method between the first target and the second target. Specifically, the originally displayed panoramic image containing the first target will gradually change to a panoramic image containing the second target according to the set transition method (such as smooth fade-in and fade-out, screen rotation and translation, etc.). Moreover, in the switched panoramic image, the second target will be placed in the pre-set first area, so that users can clearly and quickly see and focus on the second target on the preview screen, and the entire switching process is smooth and natural.

[0071] In the above panoramic view control method, when the first target is detected, the panoramic image containing the target can be displayed in the panoramic preview screen in time, and the target can be placed in a specific area (first area), so that the user can quickly focus and track the object of interest to avoid missing important shooting content. By determining the first moving trajectory of the camera and predicting the second moving trajectory at the next moment, the movement trend of the camera can be effectively analyzed and predicted. This makes the movement of the camera smoother and more natural during shooting, and the panoramic image captured maintains good coherence in the time dimension, reduces the abrupt changes in the picture, and brings a more comfortable viewing experience to the audience. Based on the second moving trajectory and the panoramic image, the second target is determined, and the transition method is determined. When the second target enters the preset range, the image can be switched according to the preset transition method. This intelligent switching function can automatically guide the user's attention without frequent manual adjustments, ensuring that the important target is always focused during the shooting process. The identification, positioning and transition processing of the first target and the second target help the system manage the shooting objects more efficiently. Whether it is shooting multiple targets in a static scene or constantly changing targets in a dynamic scene, they can be accurately presented, which improves the shooting ability and adaptability of the panoramic camera in complex scenes. It reduces the time for users to manually search and switch targets during shooting, making shooting more automated and intelligent. Users can focus more on composition, creativity, etc., improving shooting efficiency, especially for shooting tasks that require rapid capture of multiple targets or frequent scene changes. Always place the target (first target or second target) in the first area of the panoramic image, making the picture layout more standardized and reasonable, and making it easier for users and viewers to quickly identify and focus on key content.

[0072] In one embodiment, Figure 2 As shown, the response to detecting the first target during the panoramic camera shooting process includes:

[0073] S202, identifying each frame of the panoramic image captured by the panoramic camera during the capturing process.

[0074] S204, determining the moving speed of the panoramic camera corresponding to each frame of the panoramic image, and determining a plurality of panoramic image frames that are less than the preset speed threshold according to a preset speed threshold.

[0075] Among them, the moving speed generally refers to the distance moved or the position change generated by the panoramic camera within a unit time during the shooting process. The motion data of the camera can be obtained through built-in sensors of the camera (such as accelerometers, gyroscopes, etc.), and combined with time information to calculate the moving speed of the camera at the corresponding moment of each frame of panoramic image. The preset speed threshold is usually a preset speed value standard as the basis for judgment. It is used to compare the moving speed of the panoramic camera with this value to distinguish different motion states. Among them, multiple frames of panoramic images usually refer to panoramic images that are continuous in time.

[0076] Specifically, when the panoramic camera is in the shooting state, each frame of panoramic image captured by it can be identified and processed. The moving speed of the camera at the corresponding moment of each frame of panoramic image is analyzed in real time. By processing and calculating the data of the built-in sensors of the camera, the moving speed value of the camera at the corresponding moment of each frame of image is obtained. Then, these calculated speed values are compared with the preset speed threshold. When it is found that the moving speed of the camera corresponding to a certain frame of panoramic image is less than the preset speed threshold, this frame of image is screened out. Finally, multiple frames of panoramic images that meet the conditions (that is, the moving speed of the camera is less than the preset speed threshold) will be determined.

[0077] S206, perform target recognition on the multiple frames of panoramic images, and in response to the result of the target recognition not being empty, determine that a target is detected during the shooting process of the panoramic camera.

[0078] Among them, target recognition generally uses computer vision techniques and algorithms to analyze and process various elements in multiple frames of panoramic images, find target objects (such as people, vehicles, specific signs, etc.) that meet specific conditions or features, and determine their positions, sizes, categories, etc. in the images.

[0079] Specifically, when multiple frames of panoramic images (that is, those images with the moving speed of the camera less than the preset speed threshold) are obtained, the system will perform target recognition operations on these images in sequence. The system will use various target recognition algorithms (such as object detection algorithms based on deep learning, etc.) to analyze each part of the image and try to find objects that meet the preset target features. If the recognition result is not empty after performing target recognition on these multiple frames of panoramic images, that is, at least one target object that meets the conditions is successfully detected in these images. At this time, the system will determine that a target is detected during the shooting process of the panoramic camera.

[0080] In this embodiment, each frame of panoramic image captured by the panoramic camera is first recognized, then multiple frames of panoramic images with a speed less than a preset speed threshold are filtered out by determining the camera movement speed, and finally target recognition is performed on these images. Such a process can preferentially process the images captured when the camera movement is relatively stable, reducing the interference of problems such as image blurring and distortion caused by camera jitter and rapid movement on target recognition, thereby improving the accuracy and reliability of target recognition. For example, in a security monitoring scenario, abnormal targets can be detected more accurately, reducing the false alarm and missed alarm rates. In addition, target recognition is not performed on all captured panoramic images, but multiple frames of images with a slower camera movement speed are first filtered out. Since such images are relatively stable, they are more likely to contain clear and recognizable targets, reducing the unnecessary amount of image analysis calculations, concentrating computing resources on more valuable images, improving the processing efficiency, and saving computing resources.

[0081] In one embodiment, as Figure 3 shown, after the panoramic image containing the first target is displayed in the panoramic preview screen of the panoramic camera, the method further includes:

[0082] S302, determining a first position of the first target in a first movement trajectory of the panoramic camera, and determining a target holding area based on the first position and a preset position distance threshold.

[0083] Among them, the target holding area is generally an area in which the position of the first target displayed in the panoramic camera does not change. Generally, the target holding area can be a spatial area formed with the first position as the center and a preset position distance threshold as the radius (or side length, etc., depending on the shape of the area).

[0084] Specifically, during the shooting process of the panoramic camera, when the first target is detected, the system will determine the first position of the first target in the first movement trajectory by analyzing the camera movement trajectory and the position of the target in the image. For example, then, based on this first position and a preset position distance threshold, the system will construct a target holding area. For example, if the set position distance threshold is 5 meters, then a circular target holding area is formed with the first position as the center and 5 meters as the radius (it may also be other shapes, such as a square, depending on the specific setting).

[0085] S304, during the shooting process of the panoramic camera, in response to the panoramic camera being located in the target holding area, displaying the panoramic image containing the first target in the panoramic preview screen of the panoramic camera, where the first target is located in a first area of the panoramic image.

[0086] Specifically, when it is detected that the panoramic camera enters the previously determined target holding area, the system will respond. At this time, a panoramic image containing the first target will be displayed in real time on the panoramic preview screen of the panoramic camera, and the first target will be accurately placed within the first area of the panoramic image.

[0087] In this embodiment, by determining the target holding area, the first image can be continuously placed within the first area in the target holding area, so that the first target will not move back and forth, reducing the interference caused by camera jitter.

[0088] In one embodiment, as Figure 4 shown, determining the second movement trajectory at the next moment during the shooting process based on the first movement trajectory includes:

[0089] S402, determining the speed information of the panoramic camera that matches the first movement trajectory.

[0090] Among them, the speed information may include relevant data regarding the moving speed of the panoramic camera, including but not limited to the moving rate (the distance moved per unit time), the speed change situation (acceleration, deceleration), and the speed components in different directions, etc. In some embodiments of the present disclosure, the speed information may refer to the moving rate.

[0091] Specifically, during the shooting process of the panoramic camera, various sensors (such as accelerometers, gyroscopes, etc.) built in the panoramic camera are used to collect the motion data of the camera in real time. Through the analysis and processing of these data, the position changes of the camera at different moments are calculated. Then, based on the relationship between the position change and time, the moving speed of the camera is determined.

[0092] S404, determining the change amplitude of the speed information. In response to the change amplitude of the speed information not being a linear change, based on the first movement trajectory, a particle filter algorithm is used to determine the second movement trajectory at the next moment during the shooting process.

[0093] Among them, linear change usually means that the change of speed information follows a linear law, that is, the change of speed with time is uniform, and its change curve appears as a straight line on the coordinate graph. For example, the speed increasing or decreasing at a constant acceleration belongs to linear change. The particle filter algorithm is usually a recursive Bayesian filtering algorithm based on the Monte Carlo method (random sampling method). It approximates the probability distribution by using a set of random samples (particles), updates and adjusts the weights of the particles according to the observed data and the system model, so as to realize the estimation and prediction of the target state (such as position, speed, etc.).

[0094] Specifically, during the shooting process of the panoramic camera, the system continuously monitors and records the speed information of the camera. Then, it calculates the change amplitude of the speed information and determines whether it is a linear change. For example, if the speed increases or decreases uniformly over a period of time, then the change amplitude is linear; if the speed changes non-uniformly, sometimes fast and sometimes slow, or the direction changes frequently, then the change amplitude is not a linear change. When it is detected that the change amplitude of the speed information is not a linear change, it indicates that the motion state of the camera is relatively complex and difficult to predict using a simple linear model. At this time, based on the already determined first movement trajectory, the system uses the particle filter algorithm to predict the second movement trajectory of the camera at the next moment. The particle filter algorithm first generates a set of randomly distributed particles according to the first movement trajectory and some current prior information. Each particle represents the possible position and state of the camera at the next moment. Then, according to the current observation data (such as the sensor data of the camera) and the system model (the physical model describing the camera motion), each particle is evaluated and its weight is adjusted. Particles with higher weights indicate a higher probability of being the state of the camera at the next moment. Finally, by sampling and updating these particles, a new set of particles is obtained, and based on this set, the predicted position and state of the camera at the next moment are determined, thereby generating the second movement trajectory.

[0095] S406, in response to the change amplitude of the speed information being a linear change, use the speed information, the first movement trajectory, and the Kalman filter to determine the second movement trajectory at the next moment during the shooting process.

[0096] Among them, the Kalman filter is usually an algorithm that uses the linear system state equation to optimally estimate the system state through the system input-output observation data. Based on the minimum mean square error criterion, it can accurately predict and estimate the state of the system in the presence of noise and is widely used in the state estimation and prediction of various dynamic systems.

[0097] Specifically, when the panoramic camera is in the process of shooting, the system continuously monitors and analyzes its speed information. When it is found that the change amplitude of the speed information shows a linear change, it indicates that the motion state of the camera is relatively stable and predictable, meeting the characteristics of a linear system. At this time, the system will utilize the obtained speed information (including the magnitude and direction of the speed, etc.) and the first moving trajectory (the path the camera has traveled), and combine the Kalman filtering algorithm to predict the position and motion state of the camera at the next moment. The Kalman filtering algorithm will first make a prior prediction of the state (position, speed, etc.) of the camera at the next moment based on the current speed information and the first moving trajectory. Then, the actually observed data (such as the position and speed of the camera measured by the sensor) is compared with the predicted value, and the prior prediction is corrected by calculating the error between the two, obtaining a more accurate posterior estimate. This posterior estimate is the predicted state of the camera at the next moment, and based on this state, the second moving trajectory can be determined.

[0098] In this embodiment, by using the particle filtering algorithm, even in the case of complex camera motion states and irregular changes in speed information, it is possible to relatively accurately predict the future moving trajectory of the camera, providing a more reliable basis for subsequent shooting control, image analysis, etc. When the camera motion state is linearly changing, using the Kalman filtering algorithm can relatively accurately predict the future moving trajectory of the camera, providing guidance for subsequent shooting. For example, when shooting a fixed scene and the camera is moving at a constant speed, this method can accurately predict the position of the camera, enabling the captured image to stably cover the target area, and at the same time, it also helps to perform stable processing and analysis on the captured images.

[0099] In one embodiment, as Figure 5 shown, determining the second target based on the second moving trajectory and the panoramic image includes:

[0100] S502, based on the second moving trajectory, determine the shooting direction of the panoramic camera.

[0101] S504, according to the shooting direction, determine the second target search direction in the panoramic image.

[0102] S506, at least based on the first target and the scene style of the panoramic image, along the second target search direction of the panoramic image, determine the second target.

[0103] Among them, the shooting direction generally refers to the direction in which the lens of the panoramic camera is aimed during shooting. Determining the shooting direction based on the second moving trajectory is to clarify the viewing angle orientation of the camera during subsequent shooting. The scene style generally refers to the characteristics and styles of the scene presented by the panoramic image, such as whether it is an indoor or outdoor scene, a bustling city or a quiet countryside, a modern style or a retro style, etc.

[0104] Specifically, based on the predicted second movement trajectory, the movement trend of the panoramic camera at the next moment can be analyzed, thereby determining the shooting direction of the camera. For example, if the second movement trajectory shows that the camera will move forward to the right, then the shooting direction will be adjusted accordingly to the front right. According to different second movement trajectories, the shooting directions of the panoramic camera are also different. According to the determined shooting direction, a reasonable search direction is set in the panoramic image. For example, if the shooting direction is to the front right, then the second target search direction may be carried out in the front right area of the panoramic image. This can narrow the search range and improve the search efficiency. When searching along the second target search direction, the system will comprehensively consider the first target and the scene style of the panoramic image. If the first target is a person wearing bright clothes and the scene style of the panoramic image is a bustling market, then when searching for the second target, it may be more inclined to find objects that match the market atmosphere and are equally eye-catching, such as special goods on the stalls, artists performing, etc.

[0105] In some exemplary embodiments, for example, in a cycling scenario, a certain cycling person is used as the first target. Usually, the movement direction of the panoramic camera can be along the direction of the cycling track. At this time, another cycling person can be searched along the cycling track direction, and another cycling person is usually a person close to the first target. Thus, the competitive effect of the two cycling persons can be demonstrated.

[0106] In one embodiment, as Figure 6 shown, the method for determining the transition manner between the first target and the second target based on the second movement trajectory and the panoramic image includes:

[0107] S602, determining a transition distance between the first target and the second target based on the positions of the first target and the second target in the second movement trajectory.

[0108] S604, in response to the transition distance being less than a preset distance threshold, directly transitioning the first target to the second target.

[0109] S606, in response to the transition distance being greater than the preset distance threshold, determining speed information matching the first movement trajectory of the panoramic camera.

[0110] S608, determining a change amplitude of the speed information, determining a transition type based on the change amplitude, and determining a transition manner according to the transition type and the panoramic image in the second movement trajectory.

[0111] Among them, the transition distance generally refers to the position interval distance between the first target and the second target on the second movement trajectory, which is used to measure the spatial relationship between the two targets. The transition type is generally the type of way for the first target to transition to the second target determined according to the change range of the speed information, such as rapid switching, smooth transition, etc.

[0112] Specifically, the positions of the first target and the second target on the second movement trajectory can be analyzed to calculate the transition distance between the two. When the transition distance is less than the preset distance threshold, it means that the first target and the second target are relatively close in space, and the first target can be directly transitioned to the second target. In the panoramic preview screen or the final shooting screen, it may directly switch from displaying the first target to displaying the second target, giving a simple switching effect. For example, when the two targets are very close in the screen, a rapid switch will not make the audience feel abrupt. When the transition distance is greater than the preset distance threshold, the system will first determine the speed information matching the first movement trajectory of the panoramic camera. For example, data such as the movement speed and direction change of the camera are obtained through sensors such as the accelerometer and gyroscope of the camera. Then, the change range of the speed information is calculated to judge the change situation of the movement state of the camera. The transition type is determined according to the change range of the speed information. If the speed change range is small, it may be determined as the smooth transition type, and the first target will be transitioned to the second target in a more natural and slow way in the screen, such as through effects like fade-in and fade-out, panning of the screen, etc. If the speed change range is large, it may be determined as the rapid switching type, and quickly switch from the first target to the second target in the screen. The system will transition the first target to the second target according to the determined transition type and the panoramic image in the second movement trajectory. This can make the transition of the screen more in line with the movement state of the camera and the actual scene, improve the viewing experience, and make the connection of the shooting content more smooth and natural. According to different change ranges, those skilled in the art can select appropriate transition methods, and the transition methods are not limited in some embodiments of the present disclosure.

[0113] In this embodiment, the transition distance is determined according to the positions of the first target and the second target in the second movement trajectory, and different transition methods are selected accordingly. When the transition distance is small, it is directly transitioned, which is simple and efficient; when the transition distance is large, the transition type is determined according to the change range of the speed information, making the transition more natural and smooth. This can avoid a sense of abruptness when the screen is switched, improve the viewing experience, and enable the audience to obtain a more comfortable visual feeling whether for the shot video or the real-time preview screen. By judging the transition distance and combining the camera speed information to determine the target transition method, the switch from the first target to the second target is more in line with the actual scene and the movement state of the camera. This avoids the chaos of the screen caused by blindly switching targets, ensuring that the audience's attention can be accurately and reasonably guided during the shooting process, highlighting the key target.

[0114] In one embodiment, as Figure 7 shown, the transition types include: linear transition type and non-linear transition type. Among them, the linear transition type usually characterizes that during the process of transitioning from the first target to the second target, the relevant changes are uniform, regular, and linearly related. Linear transitions include: linear transition of the screen, linear transition of screen parameters, and appropriate linear transition methods can be selected according to different scenarios. Non-linear transition means that during the process of transitioning from the first target to the second target, the changes are not uniform and regular, but exhibit complex and irregular characteristics. The non-linear transition type can include: non-linear transition of the screen, non-linear transition of screen parameters. Determining the transition type based on the change amplitude includes:

[0115] S702, in response to the change amplitude being a uniform change, determining that the transition type is a linear transition type;

[0116] S704, in response to the change amplitude not being a uniform change, determining that the transition type is a non-linear transition type.

[0117] Specifically, when it is determined that the change amplitude of the speed information is a uniform change, it can be determined that the transition type from the first target to the second target is a linear transition type. In this case, the switching of the screen or the transition of the target can be processed in the way of linear transition, such as using a uniform fade-in and fade-out effect, translating the screen at a fixed speed, etc. When it is determined that the change amplitude of the speed information is not a uniform change, the system determines that the transition type is a non-linear transition type. At this time, the system will select a suitable transition effect according to the characteristics of non-linear transition, such as rapid screen switching, fade-in and fade-out with a gradually changing speed, irregular screen scaling, etc., to adapt to the unstable speed change situation of the camera.

[0118] In this embodiment, determining the transition type according to the change amplitude of the camera speed can make the screen transition effect match the motion state of the camera. When the speed changes uniformly, linear transition is adopted, which can provide a smooth and fluent visual experience, avoid abrupt changes in the screen, and enable the audience to watch the panoramic content more comfortably. When the speed changes non-uniformly, non-linear transition is adopted, which can better adapt to the dynamic changes of the camera and enhance the visual expression through more impactful or unique transition effects. In addition, this method realizes the automatic judgment and selection of the transition type, reducing the need for manual intervention. It can automatically determine the appropriate transition type according to the speed information of the camera in real time, without the need for the shooter to set it manually, improving the shooting efficiency and convenience. Especially in some scenarios that require continuous shooting and rapid target switching, this automated processing method can allow the shooter to focus more on the shooting content and creativity without worrying about the setting of the transition effect.

[0119] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0120] Based on the same inventive concept, an embodiment of the present disclosure also provides a panoramic view control device for implementing the panoramic view control method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the panoramic view control device provided below can refer to the limitations on the panoramic view control method in the above text, and will not be repeated here.

[0121] In one embodiment, as Figure 8 shown, a panoramic view control device 800 is provided, including: a viewing angle adjustment module 802, a trajectory prediction module 804, a transition mode determination module 806, and a viewing angle switching module 808, where:

[0122] The viewing angle adjustment module 802 is configured to, in response to detecting a first target during the shooting process of the panoramic camera, display a panoramic image containing the first target in the panoramic preview screen of the panoramic camera, and the first target is located in a first area of the panoramic image;

[0123] The trajectory prediction module 804 is configured to determine a first movement trajectory generated by the panoramic camera during the current shooting process, and determine a second movement trajectory at the next moment during the shooting process based on the first movement trajectory;

[0124] The transition mode determination module 806 is configured to determine a second target based on the second movement trajectory and the panoramic image, and determine a transition mode between the first target and the second target based on the second movement trajectory and the panoramic image;

[0125] The viewing angle switching module 808 is configured to, in response to the second target being within a preset range of the second movement trajectory during the shooting process of the panoramic camera, transition the panoramic image containing the first target to a panoramic image containing the second target based on the transition mode, and the second target is located in a first area of the panoramic image.

[0126] In one embodiment of the device, the perspective adjustment module 802 includes:

[0127] A target detection module, configured to identify each panoramic image captured by the panoramic camera during the shooting process; determine the moving speed of the panoramic camera corresponding to each panoramic image, and determine multiple frames of panoramic images with a speed less than a preset speed threshold according to the preset speed threshold; perform target recognition on the multiple frames of panoramic images, and in response to the result of the target recognition not being empty, determine that a target is detected during the shooting process of the panoramic camera.

[0128] In one embodiment of the device, the device further includes:

[0129] A target holding area determination module, configured to determine the first position of the first target in the first movement trajectory of the panoramic camera, and determine the target holding area based on the first position and a preset position distance threshold.

[0130] A position holding module, configured to, during the shooting process of the panoramic camera, in response to the panoramic camera being located in the target holding area, display a panoramic image containing the first target in the panoramic preview screen of the panoramic camera, and the first target is located in the first area of the panoramic image.

[0131] In one embodiment of the device, the trajectory prediction module 804 includes:

[0132] A speed information determination module, configured to determine the speed information matching the first movement trajectory of the panoramic camera.

[0133] A first prediction module, configured to determine the change amplitude of the speed information, and in response to the change amplitude of the speed information not being a linear change, determine the second movement trajectory at the next moment during the shooting process based on the first movement trajectory by using a particle filter algorithm.

[0134] A second prediction module, configured to, in response to the change amplitude of the speed information being a linear change, determine the second movement trajectory at the next moment during the shooting process by using the speed information, the first movement trajectory, and Kalman filtering.

[0135] In one embodiment of the device, the transition mode determination module 806 includes:

[0136] A shooting direction determination module, configured to determine the shooting direction of the panoramic camera based on the second movement trajectory.

[0137] A search direction determination module, configured to determine the second target search direction in the panoramic image according to the shooting direction.

[0138] A second target determination module, configured to determine a second target along a second target search direction of the panoramic image at least based on the first target and the scene style of the panoramic image.

[0139] In an embodiment of the device, the transition mode determination module 806 includes:

[0140] A transition distance determination module, configured to determine a transition distance between the first target and the second target based on the positions of the first target and the second target in the second movement trajectory;

[0141] A first transition module, configured to directly transition the first target to the second target in response to the transition distance being less than a preset distance threshold;

[0142] A second transition module, configured to determine speed information matching the first movement trajectory of the panoramic camera in response to the transition distance being greater than the preset distance threshold;

[0143] A mode determination module, configured to determine a change amplitude of the speed information, determine a transition type based on the change amplitude, and determine a transition mode according to the transition type and the panoramic image in the second movement trajectory.

[0144] In an embodiment of the device, the transition types include: a linear transition type and a non - linear transition type. The mode determination module is further configured to determine that the transition type is a linear transition type in response to the change amplitude being a uniform change; and determine that the transition type is a non - linear transition type in response to the change amplitude not being a uniform change.

[0145] Each module in the above - mentioned panoramic view control device can be implemented in whole or in part by software, hardware, and their combination. The above - mentioned modules can be embedded in a processor in a computer device in a hardware form or be independent of the processor, or can be stored in a memory in the computer device in a software form, so as to be called by the processor to execute the operations corresponding to the above - mentioned modules.

[0146] In an embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 9As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a panoramic view control method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the computer device housing, or an external keyboard, a touchpad, or a mouse, etc.

[0147] Those skilled in the art can understand that Figure 9 the structure shown in the figure is only a block diagram of some structures related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0148] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0151] It should be noted that the panoramic images obtained by the panoramic cameras involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties.

[0152] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided by the present disclosure can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided by the present disclosure can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0153] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0154] The above-described embodiments merely represent several implementation manners of the present disclosure. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent of the present disclosure. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present disclosure, several modifications and improvements can still be made, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the appended claims.

Claims

1. A panoramic view control method, characterized in that, Applied to a panoramic camera, the method includes: In response to detecting a first target during the shooting process of the panoramic camera, a panoramic image containing the first target is displayed in the panoramic preview screen of the panoramic camera, and the first target is located in a first area of the panoramic image; Determine a first movement trajectory generated by the panoramic camera during the current shooting process, and determine a second movement trajectory at the next moment during the shooting process based on the first movement trajectory; Determine a second target based on the second movement trajectory and the panoramic image, and determine a transition method between the first target and the second target based on the second movement trajectory and the panoramic image; In response to the second target being within a preset range of the second movement trajectory during the shooting process of the panoramic camera, based on the transition method, transition the panoramic image containing the first target to a panoramic image containing the second target, and the second target is located in the first area of the panoramic image.

2. The method according to claim 1, characterized in that, The "In response to detecting a first target during the shooting process of the panoramic camera" includes: Identify each frame of the panoramic image captured by the panoramic camera during the shooting process; Determine the movement speed of the panoramic camera corresponding to each frame of the panoramic image, and determine multiple frames of panoramic images with a speed less than a preset speed threshold according to the preset speed threshold; Perform target recognition on the multiple frames of panoramic images. In response to the result of the target recognition not being empty, determine that a target is detected during the shooting process of the panoramic camera.

3. The method according to claim 1, wherein After displaying the panoramic image containing the first target in the panoramic preview screen of the panoramic camera, the method further includes: Determine a first position of the first target in the first movement trajectory of the panoramic camera, and determine a target holding area based on the first position and a preset position distance threshold; During the shooting process of the panoramic camera, in response to the panoramic camera being within the target holding area, display the panoramic image containing the first target in the panoramic preview screen of the panoramic camera, and the first target is located in the first area of the panoramic image.

4. The method according to claim 1, characterized in that, The "Determine a second movement trajectory at the next moment during the shooting process based on the first movement trajectory" includes: Determine speed information of the panoramic camera matching the first movement trajectory; Determine the change amplitude of the speed information. In response to the change amplitude of the speed information not being a linear change, based on the first movement trajectory, use the particle filter algorithm to determine the second movement trajectory at the next moment during the shooting process; In response to the change amplitude of the speed information being a linear change, use the speed information, the first movement trajectory, and the Kalman filter to determine the second movement trajectory at the next moment during the shooting process.

5. The method according to claim 1, wherein The "Determine a second target based on the second movement trajectory and the panoramic image" includes: Based on the second movement trajectory, determine the shooting direction of the panoramic camera; According to the shooting direction, determine the second target search direction in the panoramic image; Determine the second target at least based on the first target and the scene style of the panoramic image along the second target search direction of the panoramic image.

6. The method according to claim 1, characterized in that, Determining the transition manner between the first target and the second target based on the second movement trajectory and the panoramic image includes: Determining the transition distance between the first target and the second target based on the positions of the first target and the second target in the second movement trajectory; In response to the transition distance being less than a preset distance threshold, directly transitioning the first target to the second target; In response to the transition distance being greater than the preset distance threshold, determining the speed information matching the first movement trajectory of the panoramic camera; Determining the change amplitude of the speed information, determining the transition type based on the change amplitude, and determining the transition manner according to the transition type and the panoramic image in the second movement trajectory.

7. The method according to claim 6, wherein The transition type includes: a linear transition type and a non-linear transition type. Determining the transition type based on the change amplitude includes: In response to the change amplitude being a uniform change, determining the transition type as the linear transition type; In response to the change amplitude not being a uniform change, determining the transition type as the non-linear transition type.

8. A panoramic view control device, characterized in that, Applied to a panoramic camera, the device includes: A perspective adjustment module for, in response to detecting a first target during the shooting process of the panoramic camera, displaying a panoramic image containing the first target in the panoramic preview screen of the panoramic camera, where the first target is located in the first area of the panoramic image; A trajectory prediction module for determining the first movement trajectory generated during the current shooting process of the panoramic camera and determining the second movement trajectory at the next moment during the shooting process based on the first movement trajectory; A transition manner determination module for determining a second target based on the second movement trajectory and the panoramic image and determining the transition manner between the first target and the second target based on the second movement trajectory and the panoramic image; A perspective switching module for, in response to the second target being within a preset range of the second movement trajectory during the shooting process of the panoramic camera, transitioning the panoramic image containing the first target to the panoramic image containing the second target based on the transition manner, where the second target is located in the first area of the panoramic image.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images