Motion track generation method and device, electronic equipment and storage medium

Abstract

The invention provides a motion trail generation method and device, electronic equipment and a storage medium, and relates to the technical field of text processing. The method comprises the following steps: extracting semantic features from a description text of motion of a target object, and generating an initial motion track according to the semantic features; according to the target trajectory signal of the motion of the target object, determining spatial association between key points, and according to the spatial association, constructing a topological graph used for representing a topological relation between the key points of the target object, the spatial association including homogeneous points or heterogeneous points; and updating the initial motion track by using the topological graph to obtain a processed motion track. According to the method, the spatial correlation among the key points of all the parts of the body is determined, and the topological graph for indicating the topological relation of the spatial correlation is constructed, so that the position dependency relation among the key points is better described, the coordination degree among the actions of different body parts is increased for the trajectory, and the signal propagation precision and the control capability are improved.

Description

Technical Field

[0001] This disclosure relates to the field of text processing technology, and in particular to a method, apparatus, electronic device, and storage medium for generating motion trajectories. Background Technology

[0002] Trajectory-guided human motion generation has attracted much attention due to its potential applications in virtual character animation, human-computer interaction, and assistive medical care.

[0003] Trajectory-guided motion generation is becoming a research hotspot due to its ability to finely control the generated results. Users define the semantics of the generated action through text descriptions and provide trajectories of specific human key points (such as the pelvis, wrist, and ankle), thereby providing fine-grained guidance for the generated action and efficiently fulfilling user intentions. Considering the interaction cost, the trajectory signals provided by users are usually sparse, i.e., containing only a few key points. Therefore, coordinating the body under trajectory guidance in interactive motion generation tasks, and the coordination between movements of different body parts, is the core challenge of trajectory generation. Summary of the Invention

[0004] In view of this, the purpose of this disclosure is to provide a method, apparatus, electronic device and storage medium for generating motion trajectories, which can specifically solve existing problems.

[0005] Based on the above objectives, in a first aspect, this disclosure proposes a motion trajectory generation method, comprising: extracting semantic features from descriptive text of the motion of a target object; generating an initial motion trajectory based on the semantic features; determining the spatial association between key points of the target trajectory signal of the motion of the target object; constructing a topological graph to characterize the topological relationship between key points of the target object based on the spatial association, wherein the spatial association includes homogeneous points or heterogeneous points; and updating the initial motion trajectory using the topological graph to obtain a processed motion trajectory.

[0006] Secondly, an extraction unit is also provided, configured to extract semantic features from the descriptive text of the target object's motion, and generate an initial motion trajectory based on the semantic features; a determination unit is configured to determine the spatial association between key points on the target trajectory signal of the target object's motion, and construct a topological graph to characterize the topological relationship between the key points of the target object based on the spatial association, wherein the spatial association includes homogeneous points or heterogeneous points; and an update unit is configured to update the initial motion trajectory using the topological graph to obtain a processed motion trajectory.

[0007] Thirdly, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor running the computer program to implement the method of the first aspect.

[0008] Fourthly, a computer-readable storage medium is also provided, on which a computer program is stored, the computer program being executed by a processor to implement the method described in any one of the first aspects.

[0009] Fifthly, a computer program product is also provided, comprising a computer program that is executed by a processor to implement the method described in any one of the first aspects.

[0010] In summary, this disclosure has at least the following beneficial effects: it determines the spatial relationships between key points of various body parts and constructs a topological graph that indicates the topological relationships of these spatial relationships, thereby better describing the positional dependencies between key points, increasing the coordination between the movements of different body parts in the trajectory, and thus improving the accuracy and control capability of signal propagation. Attached Figure Description

[0011] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this disclosure and should not be construed as limiting the scope of this disclosure.

[0012] Figure 1 A flowchart of a motion trajectory generation method according to an embodiment of the present disclosure is shown;

[0013] Figure 2 Another flowchart of a motion trajectory generation method based on a TCMG model according to an embodiment of the present disclosure is shown;

[0014] Figure 3 A schematic diagram of a motion trajectory generation apparatus according to an embodiment of the present disclosure is shown;

[0015] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure is shown;

[0016] Figure 5 A schematic diagram of a storage medium provided according to an embodiment of the present disclosure is shown. Detailed Implementation

[0017] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0018] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] Figure 1 A motion trajectory generation method of this disclosure is illustrated. In embodiments of this disclosure, the method includes:

[0020] Step S101: Extract semantic features from the descriptive text of the target object's motion, and generate an initial motion trajectory based on the semantic features.

[0021] In this embodiment, the execution entity of the motion trajectory generation method can extract semantic features from the descriptive text and generate an initial motion trajectory based on these features. The descriptive text is the text that describes the motion of the target object. The aforementioned semantic features can be used to guide the sampling of random noise motion processes.

[0022] The motion trajectory refers to the position of multiple key points at various points in time as the target object moves.

[0023] Step S102: For the target trajectory signal of the target object's movement, determine the spatial association between key points, and construct a topological graph to characterize the topological relationship table between key points of the target object based on the spatial association. The spatial association includes homogeneous points or heterogeneous points.

[0024] Step S103: Using the topology graph, update the initial motion trajectory to obtain the processed motion trajectory.

[0025] For example, the aforementioned executing entity can input the initial motion trajectory and topology map into a preset model to obtain the processed motion trajectory. Spatial association is also known as spatial dependency.

[0026] This disclosure identifies the spatial relationships between key points in different parts of the body and constructs a topological graph that indicates the topological relationships of these spatial relationships, thereby better describing the positional dependencies between key points, increasing the coordination between the movements of different body parts in the trajectory, and thus improving the accuracy and control of signal propagation.

[0027] In some optional implementations of any embodiment of this disclosure, the topology graph includes a homogeneous topology graph and a heterogeneous topology graph; constructing a topology graph to characterize the topological relationships between key points of the target object based on the spatial association includes: constructing a homogeneous topology graph to characterize homogeneous associations between key points based on the homogeneous points, wherein the homogeneous topology graph is used to characterize short-distance dependencies between key points; and constructing a heterogeneous topology graph to characterize heterogeneous associations between key points based on the heterogeneous points, wherein the heterogeneous topology graph is used to characterize long-distance dependencies between key points.

[0028] Based on the strength of the correlation between different points on the body, we categorize key points into homogeneous points (such as shoulders, elbows, and wrists, which influence each other during movement, and the magnitude of this influence can be greater than a preset large influence factor) and heterogeneous points (which have minimal mutual influence during movement; specifically, the magnitude of this influence can be less than a preset small influence factor). We model these dependencies by constructing topological graphs for homogeneous and heterogeneous points.

[0029] Optionally, determining the spatial association between key points in the target trajectory signal of the target object's movement includes: for joints in the initial motion trajectory where the minimum number of jumps between key points is less than or equal to a first value, determining the key points in that joint as homogeneous points; for joints in the initial motion trajectory where the minimum number of jumps between key points is greater than 1 and not greater than a second value, determining the key points in that joint as heterogeneous points, wherein the first value is less than the second value.

[0030] The minimum number of connections between two keypoints is defined as the minimum hop count. The minimum hop count is less than or equal to the first value s. ij Keypoint pairs in a joint are defined as homogeneous points, and the minimum jump count is greater than 1 but does not exceed the second value d. ij Keypoint pairs in a joint are defined as heterogeneous points. Therefore, it is possible to base them on s ij and d ij The value of is used to generate different topological embeddings based on semantic features.

[0031] s ij Set to 1 (that is, s) ij Using values ​​of 1 or near 1 can yield better FID and R-precision scores. When d ij When the setting range is small (i.e., d) ij ≤3), the model performs well, while when d ij When the range is large, the R-accuracy and error indicators will decrease.

[0032] Optionally, updating the initial motion trajectory using the topology graph to obtain the processed motion trajectory includes: fusing the homogeneous topology graph and the heterogeneous topology graph to obtain a cooperative topology graph; and updating the initial motion trajectory using the cooperative topology graph to obtain the processed motion trajectory.

[0033] Specifically, the above-mentioned updating of the initial motion trajectory using the collaborative topology graph to obtain the processed motion trajectory may include: fusing the collaborative topology graph and the initial motion trajectory to obtain a fused trajectory, wherein the fusion adopts the dependency ratio between key points.

[0034] Specifically, fusing the homogeneous topology map and the heterogeneous topology map to obtain a cooperative topology map includes: adding the homogeneous topology map, the heterogeneous topology map, and the target trajectory signal to obtain the cooperative topology map.

[0035] In some optional implementations of any embodiment of this disclosure, the spatial association and the topology graph are obtained using a topology relationship module, and the processed motion trajectory is obtained using a controllable propagation module. The topology relationship module and the controllable propagation module are included in the action generator model.

[0036] The topology module, also known as the homogeneous heterogeneous point topology (HPTR) module, can perform a topology analysis on the target trajectory signal of the target object's motion, determine the spatial association between key points, and construct a topology map to characterize the topological relationship between the key points of the target object based on the spatial association.

[0037] The controllable propagation module, also known as the CP module, can use the topology graph to update the initial motion trajectory and obtain the processed motion trajectory.

[0038] This application also provides another method for generating motion trajectories. This method includes:

[0039] To enhance the coordination of movements between homogeneous and heterogeneous points guided by a trajectory, a simple yet effective motion generation model, called the Trajectory Signal Controlled Motion Generator (TCMG), is introduced. This model focuses on optimizing the propagation of trajectory signals between different body joints, thereby achieving efficient and controllable interactive motion generation. Specifically, we design a homogeneous-heterogeneous point topology mining module, which extracts homogeneous-heterogeneous correlations using body joints. This module builds homogeneous and heterogeneous point graphs and uses a minimum jump count metric to capture the different dependencies of the trajectory signal on homogeneous and heterogeneous points. Furthermore, a controllable propagation module is developed to coordinate the propagation of trajectory signals at key points. This module dynamically establishes appropriate signal propagation strength by utilizing the topological correlation between the trajectory signal and its homogeneous / heterogeneous points. This advantage is reflected in a pair of embeddings representing homogeneous / heterogeneous signal propagation, which guide the motion optimization of each key point, coordinating it with the user-provided trajectory signal, thereby improving the accuracy and controllability of signal propagation.

[0040] Experiments show that this method can optimize the propagation of trajectory signals between human joints and reduce uncoordinated and inefficient movements. The TCMG model outperforms existing methods and introduces a signal propagation perspective into the design of trajectory-based motion generation models.

[0041] This embodiment proposes a Trajectory Signal Controlled Motion Generator (TCMG) model based on a motion diffusion model, which is an efficient motion generation method. TCMG optimizes the propagation of trajectory signals between different body parts, thereby achieving controllable and consistent motion generation. The TCMG framework consists of two main modules: a homogeneous-heterogeneous point topological relationship (HPTR) module and a controllable propagation (CP) module. The HPTR module constructs the spatial dependencies between different body parts, while the CP module coordinates the flow of trajectory signals between these parts to enhance the coordination and efficiency of generated motion. Text is input into the TCMG model for processing to generate the target motion trajectory.

[0042] In the generation process, the text input is first processed by a text encoder to extract semantic features. These features guide the sampling of random noise, thereby generating an initial noisy motion representation, i.e., the initial motion trajectory x. t Then, the model iteratively optimizes x through a denoising process. t This ultimately generates a denoised, clean motion representation, i.e., the processed motion trajectory x0. In each iteration, the noisy motion representation x... t All of them will use the CP module to fully utilize the control effect of the trajectory signal.

[0043] The HPTR module aims to capture the spatial dependencies of trajectory signals between points on the body, providing precise spatial control for motion generation. The target trajectory signal (i.e., the control signal) is directly input into this module. Based on the correlation strength between points on the body, keypoints are categorized into homogeneous points (e.g., shoulders, elbows, wrists, etc., which influence each other during movement) and heterogeneous points (which have minimal mutual influence during movement). The HPTR module models these dependencies by constructing a topological graph for homogeneous and heterogeneous points.

[0044] The minimum number of connections between two keypoints is defined as the minimum hop count. The minimum hop count is less than or equal to s. ij The joint pairs are defined as homogeneous points, and the minimum number of jumps is greater than 1 but does not exceed d. ij Joint pairs are defined as heterogeneous points. The HPTR module quantifies the spatial association between points by calculating the minimum number of hops, counting between key points on the human body based on the user-provided target trajectory signal. ij and d ij The value of is used to generate different feature topology embeddings.

[0045] if distance(x i ,x j )≤s ij (1)

[0046] (i,j∈[0,keypoints.length-1])

[0047] Then x i and x j They form a pair of identical points.

[0048] if 1≤distance(x i ,x j )≤d ij (2)

[0049] Then x i and x j They form a pair of heterogeneous points.

[0050] The HPTR module generates neighborhood and global feature topological embeddings for homogeneous and heterogeneous points based on this topological structure. The neighborhood embedding (hom) captures short-range dependencies between homogeneous points, while the global feature embedding (het) expresses long-range dependencies between heterogeneous points. These embeddings help establish more accurate spatial dependencies during motion generation, enhancing the coordination of generated motion. To effectively utilize spatial dependencies to generate guided motion, we fuse the neighborhood embedding (hom) and the global feature embedding (het) to obtain the trajectory co-embedding (sce). Specifically, the formula for calculating sce is as follows:

[0051]

[0052] This formula allows the HPTR module to fuse the input target trajectory signal `contl` with the spatial dependencies between homogeneous and heterogeneous points obtained through the FeatureTransformer. This fusion enhances the propagation of the trajectory signal. This fusion method effectively combines short-range dependencies `hom` and long-range dependencies `het`, ensuring that the generated motion conforms to local trajectory constraints while maintaining global consistency and natural fluency. Here, `▽` can be addition, multiplication, or concatenation, with addition being preferred.

[0053] The CP module is responsible for managing the propagation of trajectory signals during motion generation to ensure coordination among all points. Based on the embedding of the cooperative trajectory scene generated by the HPTR module, the CP module constructs a feature map to adaptively adjust the flow of trajectory signals between points on the body.

[0054] In each iteration, the noise motion representation x t The cooperative trajectories with the HPTR module are fused in the CP module. We embed the cooperative trajectory into the SCE input to the CP module, along with x... t We perform weighted fusion. We introduce a weight, called the dependency ratio between keypoints, denoted as ω. The fusion process can be expressed as:

[0055] x′ t ←x t Δω*sce (4)

[0056] Specifically, the CP module first uses a homogeneous topology graph to propagate signals between similar moving points to ensure synchronization. Then, a heterogeneous topology graph further propagates the signals to other points, ensuring that the generated motion has global consistency and coordination. Through this multi-level propagation strategy, the module effectively improves the guidance efficiency of trajectory signals, ensuring that the generated motion meets trajectory control requirements while maintaining a natural interactive effect.

[0057] Figure 2 Another flowchart of a motion trajectory generation method based on a TCMG model according to an embodiment of this disclosure is shown. It includes the processing procedures of an HPTR module and a CP module, where the inputs are descriptive text and a target trajectory signal (i.e., a control signal), the processed motion trajectory is generated, and the final motion trajectory is obtained and output.

[0058] This disclosure provides a motion trajectory generation apparatus for executing the motion trajectory generation method described in the above embodiments, such as... Figure 3As shown, the device includes: an extraction unit 301 configured to extract semantic features from descriptive text of the target object's motion, and generate an initial motion trajectory based on the semantic features; a determination unit 302 configured to determine the spatial association between key points of the target object's motion trajectory signal, and construct a topological graph representing the topological relationship between the key points of the target object based on the spatial association, wherein the spatial association includes homogeneous points or heterogeneous points; and an update unit 303 configured to update the initial motion trajectory using the topological graph to obtain a processed motion trajectory.

[0059] The motion trajectory generation device and the motion trajectory generation method provided in the above embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0060] This disclosure also provides an electronic device corresponding to the motion trajectory generation method provided in the foregoing embodiments, for executing the motion trajectory generation method described above. This disclosure does not limit the scope of the embodiments.

[0061] Please refer to Figure 4 This illustrates a schematic diagram of an electronic device provided by some embodiments of the present disclosure. For example... Figure 4 As shown, the electronic device 40 includes: a processor 400, a memory 401, a bus 402, and a communication interface 403. The processor 400, the communication interface 403, and the memory 401 are connected via the bus 402. The memory 401 stores a computer program that can run on the processor 400. When the processor 400 runs the computer program, it executes the method provided in any of the foregoing embodiments of this disclosure.

[0062] The memory 401 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0063] Bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 401 is used to store programs. After receiving an execution instruction, the processor 400 executes the program. The motion trajectory generation method disclosed in any of the foregoing embodiments of this disclosure can be applied to the processor 400, or implemented by the processor 400.

[0064] The processor 400 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 400 or by instructions in software form. The processor 400 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 401. The processor 400 reads the information in memory 401 and, in conjunction with its hardware, completes the steps of the above method.

[0065] The electronic device provided in this disclosure and the motion trajectory generation method provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0066] This disclosure also provides a computer-readable storage medium corresponding to the motion trajectory generation method provided in the foregoing embodiments. Please refer to... Figure 5 The computer-readable storage medium shown is an optical disc 50, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the motion trajectory generation method provided in any of the foregoing embodiments.

[0067] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0068] The computer-readable storage medium provided in the above embodiments of this disclosure and the motion trajectory generation method provided in the embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0069] It should be noted that:

[0070] In the foregoing text, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in this disclosure is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0071] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.

[0072] The embodiments of this disclosure have been described above with reference to the accompanying drawings. These are merely specific implementations of this disclosure, but this disclosure is not limited to the specific implementations described above. The specific implementations described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this disclosure without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this disclosure.

Claims

1. A method for generating motion trajectories, characterized in that, include: Semantic features are extracted from the descriptive text of the target object's motion, and an initial motion trajectory is generated based on the semantic features; For the target trajectory signal of the target object's movement, determine the spatial association between key points, and construct a topological map to characterize the topological relationship between key points of the target object based on the spatial association. The spatial association includes homogeneous points or heterogeneous points. Using the aforementioned topology graph, the initial motion trajectory is updated to obtain the processed motion trajectory.

2. The method according to claim 1, characterized in that, The topology graph includes homogeneous topology graphs and heterogeneous topology graphs; The step of constructing a topology graph representing the topological relationships between key points of the target object based on the spatial association includes: Based on the homogeneous points, a homogeneous topological graph is constructed to represent the homogeneous associations between key points, and the homogeneous topological graph is used to represent the short-distance dependencies between key points; Based on the heterogeneous points, a heterogeneous topology graph is constructed to characterize the heterogeneous associations between key points, and the heterogeneous topology graph is used to characterize the long-distance dependencies between key points.

3. The method according to claim 2, characterized in that, The determination of spatial relationships between key points based on the target trajectory signal of the target object's movement includes: For joints in the initial motion trajectory where the minimum number of jumps between key points is less than or equal to the first value, the key points in that joint are determined to be homogeneous points. For joints in the initial motion trajectory where the minimum number of jumps between key points is greater than 1 and not greater than the second value, the key points in that joint are defined as heterogeneous points, where the first value is less than the second value.

4. The method according to claim 2, characterized in that, The step of updating the initial motion trajectory using the topology graph to obtain the processed motion trajectory includes: The homogeneous topology graph and the heterogeneous topology graph are fused to obtain a cooperative topology graph; The initial motion trajectory is updated using the cooperative topology graph to obtain the processed motion trajectory.

5. The method according to claim 4, characterized in that, The step of updating the initial motion trajectory using the cooperative topology graph to obtain the processed motion trajectory includes: The collaborative topology map and the initial motion trajectory are fused to obtain a fused trajectory, wherein the fusion adopts the dependency ratio between key points.

6. The method according to claim 4, characterized in that, The process of fusing the homogeneous topology graph and the heterogeneous topology graph to obtain a cooperative topology graph includes: The homogeneous topology graph, the heterogeneous topology graph, and the target trajectory signal are added together to obtain the cooperative topology graph.

7. The method according to claim 1, characterized in that, The spatial association and the topology graph are obtained using the topology relationship module, and the processed motion trajectory is obtained using the controllable propagation module. The topology relationship module and the controllable propagation module are included in the action generator model.

8. A motion trajectory generation device, characterized in that, include: The extraction unit is configured to extract semantic features from the descriptive text of the target object's motion and generate an initial motion trajectory based on the semantic features; The determining unit is configured to determine the spatial association between key points based on the target trajectory signal of the target object's motion, and construct a topological map to characterize the topological relationship between the key points of the target object based on the spatial association, wherein the spatial association includes homogeneous points or heterogeneous points. The update unit is configured to use the topology graph to update the initial motion trajectory to obtain the processed motion trajectory.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement the method as described in any one of claims 1-7.

Images