Object motion trail generation method and device based on camera visual angle

Abstract

The invention provides an object motion trail generation method and device based on a camera visual angle, and relates to the technical field of image processing.The object motion trail generation method based on the camera visual angle comprises the steps that world space coordinates of an observation target are obtained, and a transformation matrix between the world space and a camera space is utilized to generate a motion trail of the observation target; converting the world space coordinates into corresponding camera space coordinates; adjusting the first timestamp corresponding to each camera space coordinate based on a preset speed curve of the observation target to generate a second timestamp, and fusing the second timestamp with the camera space coordinates to generate an initial movement track of the observation target in the camera space; and smoothing the initial movement track to generate a target movement track. According to the method, the position information of the observation target under the visual angle of the camera is ensured to be accurate through coordinate conversion, and then the movement track capable of accurately reflecting the actual movement state of the observation target is generated through adjustment of the timestamp.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method and device for generating an object motion trajectory based on a camera view. Background Art

[0002] In animation production, the global motion path of an object in a three-dimensional space cannot directly reflect its projected trajectory from a specific camera view, which makes it difficult for animators to intuitively adjust the motion performance of the object within the shot. This is especially true for complex animations that require precise control of the trajectory within the shot, such as character close-ups and camera tracking. The global three-dimensional trajectory cannot be dynamically associated with the camera view, resulting in the lack of visualization of the trajectory within the shot, and thus it is difficult to intuitively judge the actual motion performance of the object in the final rendered image. On the other hand, due to hardware effects and some accidental human factors, the object trajectory data often has jitter or incoherence, seriously affecting the smoothness and visual quality of the animation. Existing tools cannot intelligently correct or artistically process the motion trajectory according to the animation performance requirements, limiting the improvement of animation expressiveness. Summary of the Invention

[0003] In view of this, the present invention provides a method and device for generating an object motion trajectory based on a camera view.

[0004] The technical solution of the present invention is implemented as follows: In a first aspect of the present invention, a method for generating an object motion trajectory based on a camera view is provided, including:

[0005] Obtaining the world space coordinates of an observation target, and using the transformation matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates;

[0006] Adjusting the first timestamp corresponding to each camera space coordinate based on a preset speed curve of the observation target to generate a second timestamp, and fusing the second timestamp with the camera space coordinates to generate an initial motion trajectory of the observation target in the camera space;

[0007] Smoothing the initial motion trajectory to generate a target motion trajectory.

[0008] Based on the above technical solution, preferably, the step of obtaining the world space coordinates of an observation target and using the transformation matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates includes:

[0009] Obtaining the first coordinate of a sample observation point in the world space and the second coordinate in the camera space;

[0010] Determine the transformation matrix between the world space and the camera space based on the mapping relationship between the first coordinate and the second coordinate.

[0011] Based on the above technical solutions, preferably, the method of adjusting the first timestamp corresponding to each camera space coordinate based on the preset velocity curve of the observation target to generate a second timestamp, and fusing the second timestamp with the camera space coordinate to generate the initial motion trajectory of the observation target in the camera space further includes:

[0012] Determine the target time interval in which the motion speed of the observation target is greater than the preset threshold based on the preset velocity curve;

[0013] Perform time interpolation processing on multiple second timestamps located in the target time interval to generate third timestamps; the number of the third timestamps is greater than the number of the second timestamps;

[0014] Generate the initial motion trajectory of the observation target in the camera space based on the camera space coordinates corresponding to the third timestamps.

[0015] Based on the above technical solutions, preferably, the method of performing time interpolation processing on multiple second timestamps located in the target time interval to generate third timestamps further includes:

[0016] Generate a first motion trajectory based on multiple camera space coordinates and the second timestamps;

[0017] Perform time interpolation processing on at least some adjacent two second timestamps to generate third timestamps, and determine the camera space coordinates corresponding to the newly added timestamps from the first motion trajectory based on the preset velocity curve and the third timestamps.

[0018] Based on the above technical solutions, preferably, the observation target includes a first observation target and a second observation target; the multiple second timestamps corresponding to the first observation target are the same as the multiple second timestamps corresponding to the second observation target.

[0019] Based on the above technical solutions, preferably, the method of fusing the second timestamp with the camera space coordinate to generate the initial motion trajectory of the observation target in the camera space includes:

[0020] Fuse the second timestamp of the first observation target with the camera space coordinate corresponding to the first observation target, and fuse the second timestamp of the second observation target with the camera space coordinate corresponding to the second observation target to generate the relative motion trajectory of the first observation target and the second observation target in the camera space.

[0021] Based on the above technical solutions, preferably, the smoothing process of the initial motion trajectory to generate a target motion trajectory includes:

[0022] Performing curvature analysis on the initial motion trajectory to obtain key feature points in the initial motion trajectory;

[0023] Using the key feature points as control points of a uniform B-spline curve, and generating a target motion trajectory by iteratively adjusting the tension parameter of the uniform B-spline curve.

[0024] More preferably, in the second aspect of the present invention, there is provided an apparatus for generating an object motion trajectory based on a camera view, including: a coordinate conversion module, an adjustment and fusion module, and a smoothing process module; wherein,

[0025] The coordinate conversion module is configured to obtain the world space coordinates of an observation target, and use the conversion matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates;

[0026] The adjustment and fusion module is configured to adjust the first timestamp corresponding to each camera space coordinate based on a preset speed curve of the observation target to generate a second timestamp, and fuse the second timestamp with the camera space coordinates to generate an initial motion trajectory of the observation target in the camera space;

[0027] The smoothing process module is configured to perform a smoothing process on the initial motion trajectory to generate a target motion trajectory.

[0028] More preferably, in the third aspect of the present invention, there is provided an electronic device including a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the method for generating an object motion trajectory based on a camera view according to the first aspect.

[0029] More preferably, in the fourth aspect of the present invention, there is provided a computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for generating an object motion trajectory based on a camera view according to the first aspect.

[0030] The method and apparatus for generating an object motion trajectory based on a camera view of the present invention have the following beneficial effects compared with the prior art:

[0031] 1. Coordinate transformation ensures the accuracy of the position information of the observed target from the camera's perspective. The global motion path of the observed target in three-dimensional space can be directly reflected from a specific camera perspective, facilitating intuitive adjustment by animators of the object's motion performance within the lens. On this basis, the motion trajectory is adjusted through timestamps, improving the accuracy of motion trajectory measurement and enabling precise control of the object's motion speed, thus meeting the requirements of different animation scenarios.

[0032] 2. By separately monitoring different position points on the observed target, the relative motion trajectories at the same timestamp are obtained, enabling the presentation of the relative motions of different positions on the observed target and facilitating a deeper understanding of the overall motion pattern of the observed target and the relative motion relationships between its various parts.

[0033] 3. Through curvature analysis of the initial motion trajectory, key feature points in the initial motion trajectory are obtained and used as control points for a uniform B-spline curve. By iteratively adjusting the tension parameter of the uniform B-spline curve, while ensuring the continuity and smoothness of the trajectory curve, the loss of details due to over-smoothing is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0035] Figure 1 It is a schematic flowchart of a method for generating an object motion trajectory based on a camera perspective provided by an embodiment of the present invention;

[0036] Figure 2 It is a schematic structural diagram of a device for generating an object motion trajectory based on a camera perspective provided by an embodiment of the present invention;

[0037] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0039] In some embodiments, such as Figure 1 shown, Figure 1 is a schematic flowchart of a method for generating an object motion trajectory based on a camera view provided by an embodiment of the present invention; a method for generating an object motion trajectory based on a camera view provided by the present invention includes:

[0040] S110, obtain the world space coordinates of the observation target, and use the transformation matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates.

[0041] The coordinates of the observation target in the world space coordinate system can be three-dimensional coordinates. The transformation matrix between the world space and the camera space is a 4x4 matrix that contains rotation and translation information. By expanding the world coordinates into homogeneous coordinate form and then multiplying by the transformation matrix, the corresponding coordinates in the camera space can be obtained.

[0042] In some embodiments, S110, obtain the world space coordinates of the observation target, and use the transformation matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates, including:

[0043] Obtain the first coordinates of the sample observation points in the world space and the second coordinates in the camera space;

[0044] Determine the transformation matrix between the world space and the camera space based on the mapping relationship between the first coordinates and the second coordinates.

[0045] In this embodiment, for each sample observation point, obtain the first coordinates in the world space and the second coordinates in the camera space. According to the transformation relationship between the world space and the camera space, establish a system of linear equations. This system of equations contains unknown parameters of the rotation matrix and the translation vector. Use the least squares method or other optimization algorithms to solve this system of linear equations to obtain the optimal solutions of the rotation matrix and the translation vector. The rotation matrix is a 3x3 matrix that describes the rotation relationship from the world coordinate system to the camera coordinate system. The translation vector is a 3x1 vector that describes the translation relationship from the world coordinate system to the camera coordinate system. Combine the rotation matrix and the translation vector into a 4x4 transformation matrix.

[0046] S120, adjust the first timestamp corresponding to each camera space coordinate based on the preset velocity curve of the observation target to generate a second timestamp, and fuse the second timestamp with the camera space coordinates to generate the initial motion trajectory of the observation target in the camera space.

[0047] In this embodiment, the preset speed curve describes the speed change of the observed target over time and may include parameters such as the starting speed, acceleration, maximum speed, deceleration rate, etc. Each camera spatial coordinate has a corresponding first timestamp indicating the time when the coordinate is observed. According to the preset speed curve, the time interval required to travel from the starting point to the current camera spatial coordinate is calculated. This can be achieved by integrating (or numerically integrating) the speed curve to obtain the cumulative distance from the starting time to the current time and matching it with the actually observed distance (calculated from the camera spatial coordinate). The calculated time interval is added to the starting time or the previous adjusted timestamp to obtain a new second timestamp. Adjusting the motion trajectory by the timestamp improves the accuracy of motion trajectory measurement and enables precise control of the object's motion speed.

[0048] In some embodiments, S120, based on the preset speed curve of the observed target, adjusts the first timestamp corresponding to each camera spatial coordinate to generate a second timestamp, and fuses the second timestamp with the camera spatial coordinate to generate an initial motion trajectory of the observed target in the camera space. It further includes:

[0049] Determine a target time interval during which the motion speed of the observed target is greater than a preset threshold based on the preset speed curve;

[0050] Perform time interpolation processing on multiple second timestamps located in the target time interval to generate third timestamps; the number of third timestamps is greater than the number of second timestamps;

[0051] Generate an initial motion trajectory of the observed target in the camera space based on the camera spatial coordinates corresponding to the third timestamps.

[0052] In this embodiment, the target time interval during which the motion speed is greater than the preset threshold is a high-speed motion interval. At this time, the motion speed of the observed target is relatively large. If the detection device collects data at a fixed acquisition frequency, there may be a large distance span, resulting in missing trajectory details and not being able to well reflect the actual motion of the observed target. Therefore, when the motion speed of the observed target is relatively large, time interpolation processing can be performed on the time intervals between multiple second timestamps to generate new trajectory points, ensuring the continuity and smoothness of the motion trajectory.

[0053] In some embodiments, performing time interpolation processing on multiple second timestamps located in the target time interval to generate third timestamps further includes:

[0054] Generate a first motion trajectory based on multiple camera spatial coordinates and second timestamps;

[0055] Perform time interpolation on at least partially adjacent two second timestamps to generate a third timestamp, and determine the camera space coordinates corresponding to the newly added timestamp from the first motion trajectory based on a preset speed curve and the third timestamp.

[0056] Inserting new timestamps between two adjacent second timestamps can generate a finer time resolution. For each newly added timestamp, use the preset speed curve and the spatial coordinates at the adjacent second timestamps to calculate the interpolation coordinates.

[0057] In some embodiments, the observation targets include a first observation target and a second observation target; the multiple second timestamps corresponding to the first observation target are the same as the multiple second timestamps corresponding to the second observation target.

[0058] Through synchronous observation, it can be ensured that the first observation target and the second observation target are observed within the time window at the same time point, thereby providing a consistent data set. When the size of the observation target is large, the motion trajectories of individual observation points are not sufficient to describe the overall dynamics and local dynamics of the observation target. By analyzing the trajectories of the first observation target and the second observation target, it is possible to understand how different parts of the observation target work together and their relative motion, and capture the overall and local dynamics of the target.

[0059] In some embodiments, fusing the second timestamp with the camera space coordinates to generate an initial motion trajectory of the observation target in the camera space includes:

[0060] Fuse the second timestamp of the first observation target with the camera space coordinates corresponding to the first observation target, and fuse the second timestamp of the second observation target with the camera space coordinates corresponding to the second observation target to generate the relative motion trajectories of the first observation target and the second observation target in the camera space.

[0061] In this embodiment, for the first observation target and the second observation target, the camera space coordinates and the second timestamp at different time points are collected respectively, ensuring that the datasets of each observation target contain the same number of timestamps and camera space coordinates. For the first observation target, a data structure is created, which contains the timestamps and the corresponding camera space coordinates. The same applies to the second observation target. Using the fused data, the motion trajectories of the two observation targets in the camera space can be plotted, that is, a series of three-dimensional points that change over time, and each point is associated with a timestamp. At each time point, the relative position between the first observation target and the second observation target is calculated. Connecting the relative positions at all time points forms the relative motion trajectory between the two observation targets. This trajectory can show the moving path of the second observation target relative to the first observation target in the camera space. By analyzing the relative motion trajectory, useful information such as speed, acceleration, and trajectory length can be extracted. It should be noted that the first observation target and the second observation target are part of the observation targets, and the third observation target, the fourth observation target, etc. can also be included, which is not limited herein.

[0062] Taking animation production as an example, by fusing the collected data (including the second timestamp and the camera space coordinates), the motion trajectory of the character in the three-dimensional space can be automatically generated, which not only shows the overall motion of the character but also includes the local relative motion. These trajectory data can be used to drive the skeletal animation system of the character, making the actions of the character more smooth, realistic, and coordinated.

[0063] S130, smooth the initial motion trajectory to generate the target motion trajectory.

[0064] Smoothing can eliminate the discontinuous points, jitters, or noises in the trajectory, making the motion look more natural and smooth. Common smoothing methods include the moving average method, the least squares method, B-spline curves, and spline interpolation. It should be noted that during the smoothing process, the original motion characteristics such as acceleration changes and direction changes should be maintained as much as possible, and over-smoothing should be avoided to prevent the trajectory from losing its original details and characteristics.

[0065] In some embodiments, S130, smooth the initial motion trajectory to generate the target motion trajectory, including:

[0066] Conduct curvature analysis on the initial motion trajectory to obtain the key feature points in the initial motion trajectory;

[0067] Use the key feature points as the control points of the uniform B-spline curve, and generate the target motion trajectory by iteratively adjusting the tension parameter of the uniform B-spline curve.

[0068] In this embodiment, a discrete curvature calculation method is used to perform curvature analysis on the initial motion trajectory. Curvature reflects the degree of bending of the trajectory at that point and is an important basis for identifying key feature points. The characteristic of a uniform B-spline curve is that the influence degree of each control point on the curve is uniform, which helps to maintain the smoothness and continuity of the curve. The tension parameter determines the "stiffness" or "flexibility" of the B-spline curve. A higher tension value will make the curve closer to the control points, while a lower tension value will make the curve smoother. By iteratively adjusting the tension parameter, the shape of the curve can be gradually optimized to meet the requirements of the key feature points while maintaining overall smoothness.

[0069] In some embodiments, refer to Figure 2 , Figure 2 which is a schematic structural diagram of an object motion trajectory generation device based on the camera view provided by the embodiment of the present invention. The present invention provides an object motion trajectory generation device 200 based on the camera view, including: a coordinate conversion module 210, an adjustment and fusion module 220, and a smoothing processing module 230; wherein,

[0070] The coordinate conversion module 210 is configured to obtain the world space coordinates of the observed target and convert the world space coordinates into corresponding camera space coordinates by using the conversion matrix between the world space and the camera space;

[0071] The adjustment and fusion module 220 is configured to adjust the first timestamp corresponding to each camera space coordinate based on the preset speed curve of the observed target to generate a second timestamp, and fuse the second timestamp with the camera space coordinates to generate the initial motion trajectory of the observed target in the camera space;

[0072] The smoothing processing module 230 is configured to perform smoothing processing on the initial motion trajectory to generate the target motion trajectory.

[0073] In some embodiments, the coordinate conversion module 210 is specifically configured to:

[0074] Obtain the first coordinate of the sample observation point in the world space and the second coordinate in the camera space;

[0075] Determine the conversion matrix between the world space and the camera space based on the mapping relationship between the first coordinate and the second coordinate.

[0076] In some embodiments, the adjustment and fusion module 220 is specifically configured to:

[0077] Determine the target time interval in which the motion speed of the observed target is greater than the preset threshold based on the preset speed curve;

[0078] Perform time interpolation on multiple second timestamps within a target time interval to generate third timestamps; the number of third timestamps is greater than the number of second timestamps;

[0079] Generate an initial motion trajectory of the observation target in the camera space based on the camera space coordinates corresponding to the third timestamps.

[0080] In some embodiments, the adjustment and fusion module 220 is further specifically configured to:

[0081] Generate a first motion trajectory based on multiple camera space coordinates and second timestamps;

[0082] Perform time interpolation on at least some adjacent pairs of second timestamps to generate third timestamps, and determine the camera space coordinates corresponding to the new timestamps from the first motion trajectory based on a preset velocity curve and the third timestamps.

[0083] In some embodiments, the observation target includes a first observation target and a second observation target; the multiple second timestamps corresponding to the first observation target are the same as the multiple second timestamps corresponding to the second observation target.

[0084] In some embodiments, the adjustment and fusion module 220 is further specifically configured to:

[0085] Fuse the second timestamps of the first observation target with the camera space coordinates corresponding to the first observation target, and fuse the second timestamps of the second observation target with the camera space coordinates corresponding to the second observation target to generate a relative motion trajectory of the first observation target and the second observation target in the camera space.

[0086] In some embodiments, the smoothing processing module 230 is specifically configured to:

[0087] Perform curvature analysis on the initial motion trajectory to obtain key feature points in the initial motion trajectory;

[0088] Use the key feature points as control points of a uniform B-spline curve, and generate a target motion trajectory by iteratively adjusting the tension parameter of the uniform B-spline curve.

[0089] It should be noted that the device for generating an object motion trajectory based on a camera view provided in the embodiments of the present application and the method for generating an object motion trajectory based on a camera view provided in the embodiments of the present application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the foregoing method for generating an object motion trajectory based on a camera view, and the repeated parts will not be elaborated.

[0090] In some embodiments, please refer to Figure 3 , Figure 3A schematic structural diagram of an electronic device provided by an embodiment of the present application. An electronic device 300 provided by an embodiment of the present application includes a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program, when executed by the processor, implements the above-mentioned method for generating an object motion trajectory based on a camera view.

[0091] Specifically, the processor 310 may include, for example, a general microprocessor, an instruction set processor, and / or a related chipset and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), and so on. The processor 310 may also include on-board memory for caching purposes. The processor 310 may be a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present application.

[0092] The memory 320 may be, for example, any medium capable of containing, storing, transmitting, propagating, or transporting instructions. For example, the memory 320 may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of the memory 320 include: a magnetic storage device, such as a magnetic tape or a hard disk drive (HDD); an optical storage device, such as a compact disc (CD-ROM); it may also be, for example, a random access memory (RAM) or a flash memory; and / or a wired / wireless communication link.

[0093] The present application also provides a computer-readable medium, on which a computer program is stored, and when the program is executed by the processor, it implements the above-mentioned method for generating an object motion trajectory based on a camera view. The computer-readable medium may be included in the device / device / system described in the above embodiment; or it may exist separately and not be assembled into the device / device / system. The above computer-readable medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiment of the present application is implemented.

[0094] According to an embodiment of the present application, a computer-readable medium may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, 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 that contains or stores a program, and this program may be used by or in combination with an instruction execution system, apparatus, or device. And 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 computer-readable program code. Such a propagated data signal may take various 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, and this computer-readable medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted by any suitable medium, including but not limited to: wireless, wired, optical cable, radio frequency signal, etc., or any suitable combination of the above.

[0095] Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly recited in the present application. In particular, without departing from the spirit and teachings of the present application, the features recited in the various embodiments and / or claims of the present application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present application. Therefore, the scope of the present application should not be limited to the above embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for generating an object motion trajectory based on a camera view, characterized in that, Including: Obtain the world space coordinates of the observation target, and use the transformation matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates; Based on the preset velocity curve of the observation target, adjust the first timestamp corresponding to each camera space coordinate to generate a second timestamp, and fuse the second timestamp with the camera space coordinate to generate the initial motion trajectory of the observation target in the camera space; Smooth the initial motion trajectory to generate a target motion trajectory.

2. The method for generating an object motion trajectory based on a camera view according to claim 1, wherein The obtaining the world space coordinates of the observation target and using the transformation matrix between the world space and the camera space to convert the world space coordinates into corresponding camera space coordinates includes: Obtain the first coordinate of the sample observation point in the world space and the second coordinate in the camera space; Determine the transformation matrix between the world space and the camera space based on the mapping relationship between the first coordinate and the second coordinate.

3. The method for generating an object motion trajectory based on a camera view according to claim 1, wherein The adjusting the first timestamp corresponding to each camera space coordinate based on the preset velocity curve of the observation target to generate a second timestamp, and fusing the second timestamp with the camera space coordinate to generate the initial motion trajectory of the observation target in the camera space further includes: Determine the target time interval in which the motion speed of the observation target is greater than the preset threshold based on the preset velocity curve; Perform time interpolation processing on multiple second timestamps located in the target time interval to generate third timestamps; the number of the third timestamps is greater than the number of the second timestamps; Generate the initial motion trajectory of the observation target in the camera space based on the camera space coordinates corresponding to the third timestamps.

4. The method for generating an object motion trajectory based on a camera view according to claim 3, wherein The performing time interpolation processing on multiple second timestamps located in the target time interval to generate third timestamps further includes: Generate a first motion trajectory based on multiple camera space coordinates and the second timestamps; Perform time interpolation processing on at least some adjacent two second timestamps to generate third timestamps, and determine the camera space coordinates corresponding to the new added timestamps from the first motion trajectory based on the preset velocity curve and the third timestamps.

5. The method for generating an object motion trajectory based on a camera view according to claim 1, wherein, The observation target includes a first observation target and a second observation target; the multiple second timestamps corresponding to the first observation target are the same as the multiple second timestamps corresponding to the second observation target.

6. The method for generating an object motion trajectory based on a camera view as described in claim 5, wherein The fusing the second timestamp with the camera space coordinate to generate the initial motion trajectory of the observation target in the camera space includes: Fuse the second timestamp of the first observation target with the camera space coordinate corresponding to the first observation target, and fuse the second timestamp of the second observation target with the camera space coordinate corresponding to the second observation target to generate the relative motion trajectory of the first observation target and the second observation target in the camera space.

7. The method for generating an object motion trajectory based on a camera view according to claim 1, wherein The smoothing the initial motion trajectory to generate a target motion trajectory includes: Perform curvature analysis on the initial motion trajectory to obtain key feature points in the initial motion trajectory; Using the key feature points as the control points of a uniform B-spline curve, and generating a target motion trajectory by iteratively adjusting the tension parameter of the uniform B-spline curve.

8. An object motion trajectory generation device based on the camera view, characterized in that, Including: A coordinate transformation module, an adjustment and fusion module, and a smoothing processing module; wherein, The coordinate transformation module is configured to obtain the world space coordinates of an observed target, and use the transformation matrix between the world space and the camera space to transform the world space coordinates into corresponding camera space coordinates; The adjustment and fusion module is configured to adjust the first timestamp corresponding to each of the camera space coordinates based on a preset velocity curve of the observed target to generate a second timestamp, and fuse the second timestamp with the camera space coordinates to generate an initial motion trajectory of the observed target in the camera space; The smoothing processing module is configured to perform smoothing processing on the initial motion trajectory to generate a target motion trajectory.

9. An electronic device, comprising a processor and a memory; the memory stores a computer program, wherein, The computer program, when executed by the processor, implements the method for generating an object motion trajectory based on a camera view according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, A computer program is stored thereon, wherein the computer program, when executed by a processor, implements the method for generating an object motion trajectory based on a camera view according to any one of claims 1 to 7.

Images