Motion trajectory generation method, apparatus, device, and medium

Abstract

A motion trajectory generation method, device, equipment and medium are disclosed, the method comprising: determining the pixel displacement amount of adjacent frames of a to-be-processed video frame in each picture region based on the reverse direction of the video playback timing, the picture region being obtained by region division of the to-be-processed video frame; determining a target region in the to-be-processed video frame according to the pixel displacement amount; and determining the motion trajectory of a motion target according to the target region in each frame of the to-be-processed video frame. The present application improves the accuracy of the generated motion trajectory.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a motion trajectory generation method, device, equipment and medium. BACKGROUND

[0002] Computer vision refers to machine vision of using a camera and a computer to replace human eyes to identify, track and measure a target, and further performing image processing, so that the computer processing becomes an image more suitable for human observation or transmission to an instrument detection. In an existing scheme, motion trajectory capture depends on multiple angle capture devices, however, a large amount of calculation and a high motion speed can result in low accuracy of the motion trajectory. SUMMARY

[0003] The main purpose of the present application is to provide a motion trajectory generation method, device, equipment and medium, and aims to solve the problem of low accuracy of a target trajectory.

[0004] To achieve the above purpose, the present application provides a motion trajectory generation method, which comprises the following steps:

[0005] Based on the reverse direction of the video playing time sequence, a pixel displacement amount of adjacent frames of a to-be-processed video frame in each picture area is determined, the picture area being obtained by region division of the to-be-processed video frame;

[0006] A target area in the to-be-processed video frame is determined according to the pixel displacement amount;

[0007] A motion trajectory of a motion target is determined according to the target area in each frame of the to-be-processed video frame.

[0008] In an embodiment, the step of determining the target area in the to-be-processed video frame according to the pixel displacement amount comprises:

[0009] When the pixel displacement amount of the picture area of the adjacent frame is greater than a preset threshold value, the picture area greater than the preset threshold value is taken as a high-value area;

[0010] An object shape of the motion target in the high-value area is determined;

[0011] When the object shape meets a preset condition, a circumscribed area of the object shape is determined as the target area.

[0012] In an embodiment, after the step of taking the picture area greater than the preset threshold value as the high-value area, the method further comprises:

[0013] If the number of the high-value regions is multiple, an object shape of a moving target in the high-value region is determined, and a circumscribed region of the object shape is determined as the target region.

[0014] If the number of the high-value regions is one, an object shape of a moving target in the high-value region is determined, and a circumscribed region of the object shape is determined as the target region.

[0015] In an embodiment, the step of determining the target region in the video frame to be processed according to the pixel displacement amount comprises:

[0016] When the pixel displacement amount of the picture region of the adjacent frame is less than or equal to a preset threshold, the target region of the latter frame in the adjacent frame is enlarged, and a target video frame is determined in a forward direction based on a video playing time sequence.

[0017] An object shape in the enlarged target region in the target video frame is determined.

[0018] If the object shape meets a preset condition, a circumscribed region of the object shape is determined as the target region.

[0019] In an embodiment, the step of determining the object shape of the moving target in the high-value region comprises:

[0020] The high-value region is input into a preset recognition model to obtain the object shape, and the recognition model is obtained by training a neural network model.

[0021] In an embodiment, the step of determining the pixel displacement amount of each picture region of the adjacent frame of the video frame to be processed comprises:

[0022] A pixel difference value of each pixel point of two frames of the video frame to be processed in the adjacent frame in each picture region is determined.

[0023] The pixel displacement amount of the picture region is determined according to an average value of the pixel difference value in the picture region.

[0024] In an embodiment, the step of determining the motion trajectory of the moving target according to the target region in each frame of the video frame to be processed comprises:

[0025] A center pixel point of the target region in each frame of the video frame to be processed is determined.

[0026] The motion trajectory of the moving target is determined according to the center pixel point.

[0027] To achieve the above object, the application further provides a motion trajectory generation device, which comprises:

[0028] The computing module is configured to determine the pixel displacement amount of the adjacent frame of the to-be-processed video frame in each picture region based on the reverse direction of the video playing time sequence, wherein the picture region is obtained by region division of the to-be-processed video frame.

[0029] The determining module is configured to determine the target region in the to-be-processed video frame according to the pixel displacement amount.

[0030] The generating module is configured to determine the motion trajectory of the motion target according to the target region in each frame of the to-be-processed video frame.

[0031] To achieve the above object, the present application further provides a motion trajectory generation device, which comprises a memory, a processor and a motion trajectory generation program stored in the memory and executable on the processor, and each step of the motion trajectory generation method is realized when the motion trajectory generation program is executed by the processor.

[0032] To achieve the above object, the present application further provides a computer readable storage medium, which stores a motion trajectory generation program, and each step of the motion trajectory generation method is realized when the motion trajectory generation program is executed by a processor.

[0033] The present application provides a motion trajectory generation method, device, equipment and medium, which determines the pixel displacement amount of the adjacent frame of the to-be-processed video frame in each picture region based on the reverse direction of the video playing time sequence, wherein the picture region is obtained by region division of the to-be-processed video frame; determines the target region in the to-be-processed video frame according to the pixel displacement amount; and determines the motion trajectory of the motion target according to the target region in each frame of the to-be-processed video frame. Through the reverse direction of the video playing time sequence, the target region in the adjacent frame of the to-be-processed video is determined, and the motion trajectory of the motion target is determined, which avoids the situation that the target region is difficult to determine or the accuracy is low due to the large motion speed of the motion target, and improves the accuracy of the motion trajectory of the motion target. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 It is a hardware structure schematic diagram of the motion trajectory generation device related to the embodiment of the present application;

[0035] Figure 2 It is a flowchart of the first embodiment of the motion trajectory generation method of the present application;

[0036] Figure 3 It is a schematic diagram of the picture region of the to-be-processed video division of the motion trajectory generation method of the present application;

[0037] Figure 4 It is a schematic diagram of the motion trajectory of the motion trajectory generation method of the present application;

[0038] Figure 5 A schematic diagram of a target region for the motion trajectory generation method of the present application;

[0039] Figure 6 A schematic diagram of a target region for the motion trajectory generation method of the present application;

[0040] Figure 7 A detailed flowchart of step S20 of the second embodiment of the motion trajectory generation method of the present application;

[0041] Figure 8 A schematic diagram of the logical structure of the motion trajectory generation device of the present application.

[0042] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0044] The main solution of the embodiments of the present application is: based on the reverse direction of the video playing timing, determining the pixel displacement amount of the adjacent frames of the to-be-processed video frame in each picture region, the picture region being obtained by region division of the to-be-processed video frame; determining the target region in the to-be-processed video frame according to the pixel displacement amount; and determining the motion trajectory of the motion target according to the target region in each to-be-processed video frame.

[0045] By determining the target region in the adjacent frames of the to-be-processed video in the reverse direction of the video playing timing, and determining the motion trajectory of the motion target, the situation that the target region is difficult to determine or has low accuracy due to the large motion speed of the motion target is avoided, and the accuracy of the motion trajectory of the motion target is improved.

[0046] As an implementation scheme, the motion trajectory generation device can be as shown in Figure 1 .

[0047] The embodiments of the present application relate to a motion trajectory generation device, which comprises a processor 101, such as a CPU, a memory 102, and a communication bus 103. The communication bus 103 is used to realize the connection and communication between the components.

[0048] The memory 102 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. As Figure 1As shown, the memory 102 can include a motion trajectory generation program as a computer readable storage medium; and the processor 101 can be configured to invoke the motion trajectory generation program stored in the memory 102 and perform the following operations:

[0049] Based on the inverse direction of the video playing time sequence, determine the pixel displacement amount of the adjacent frames of the to-be-processed video frame in each picture region, wherein the picture region is obtained by region division of the to-be-processed video frame;

[0050] Determine a target region in the to-be-processed video frame according to the pixel displacement amount;

[0051] Determine the motion trajectory of the motion target according to the target region in each frame of the to-be-processed video frame.

[0052] In an embodiment, the processor 101 can be configured to invoke the motion trajectory generation program stored in the memory 102 and perform the following operations:

[0053] When the pixel displacement amount of the picture region of the adjacent frame is greater than a preset threshold, the picture region greater than the preset threshold is regarded as a high-value region;

[0054] Determine the object shape of the motion target in the high-value region;

[0055] When the object shape meets a preset condition, determine the circumscribed region of the object shape as the target region.

[0056] In an embodiment, the processor 101 can be configured to invoke the motion trajectory generation program stored in the memory 102 and perform the following operations:

[0057] If the number of high-value regions is multiple, determine whether there is an object shape of the motion target in the high-value region, and when there is the object shape in the high-value region, determine the circumscribed region of the object shape as the target region;

[0058] If the number of high-value regions is one, determine the object shape of the motion target in the high-value region, and determine the circumscribed region of the object shape as the target region.

[0059] In an embodiment, the processor 101 can be configured to invoke the motion trajectory generation program stored in the memory 102 and perform the following operations:

[0060] When the pixel displacement amount of the picture region of the adjacent frame is less than or equal to a preset threshold, expand the target region in the latter frame of the adjacent frame, and determine the target video frame based on the inverse direction of the video playing time sequence and the target video frame moved forward by a preset number of frames;

[0061] Determine the object shape in the expanded target region in the target video frame.

[0062] If the object shape satisfies a preset condition, an outer region of the object shape is determined as the target region.

[0063] In an embodiment, the processor 101 can be configured to invoke a motion trajectory generation program stored in the memory 102, and perform the following operations:

[0064] inputting the high-value region into a preset recognition model to obtain the object shape, the recognition model being obtained by training a neural network model.

[0065] In an embodiment, the processor 101 can be configured to invoke a motion trajectory generation program stored in the memory 102, and perform the following operations:

[0066] determining a pixel difference value of each pixel point in each picture region in two adjacent frames of the to-be-processed video frames;

[0067] determining the pixel displacement amount of the picture region according to an average value of the pixel difference values in the picture region.

[0068] In an embodiment, the processor 101 can be configured to invoke a motion trajectory generation program stored in the memory 102, and perform the following operations:

[0069] determining a center pixel point of a target region in each of the to-be-processed video frames;

[0070] determining a motion trajectory of the moving target according to the center pixel point.

[0071] Based on the hardware architecture of the motion trajectory generation device, embodiments of the motion trajectory generation method are provided.

[0072] Reference Figure 2 , Figure 2 For a first embodiment of the motion trajectory generation method, the motion trajectory generation method comprises the following steps:

[0073] Step S10, determining a pixel displacement amount of each picture region in adjacent frames of the to-be-processed video frames in a reverse direction of a video playback time sequence, the picture region being obtained by region division of the to-be-processed video frames;

[0074] Specifically, the video playback time sequence is played in a time sequence, for example, the first frame is played at 00:01, the second frame is played at 00:11, and the nth frame is played at 01:01. The reverse direction of the video playback time sequence is to arrange the video frames in the later time in the front, for example, the reverse direction of the video playback time sequence of the first frame to the nth frame is from the nth frame to the first frame.

[0075] determine a pixel displacement amount of the adjacent frames of the to-be-processed video frame in each picture region according to a reverse direction of a video playing time sequence. For example, the adjacent frames are the nth frame and the (n-1)th frame. The picture region is obtained by dividing the to-be-processed video frame. For example, each to-be-processed video frame is divided according to a preset size of a grid to obtain the picture region of each to-be-processed video frame. For example, as shown in FIG. 6, the picture region is marked by rows and columns, for example, the picture region of the fifth row and the fifth column is a picture region of a player, and the picture regions of the fifth row and the sixth column and the fifth row and the seventh column are picture regions of a shuttlecock. Alternatively, each to-be-processed video frame is divided by bisection, and each to-be-processed video frame is divided into two picture regions, and the picture region with a large pixel displacement amount is further divided until the smallest picture region is the preset size. Figure 3

[0076] The pixel displacement amount of the adjacent frames of the to-be-processed video frame in each picture region is determined. For example, the pixel difference of each pixel point in each picture region of two to-be-processed video frames in the adjacent frames is determined, and the pixel displacement amount of the picture region is determined according to the average value of the pixel difference in the picture region. Figure 3

[0077] Step S20: determining a target region in the to-be-processed video frame according to the pixel displacement amount.

[0078] For example, the target region is a picture region of a moving target, and the size of the target region corresponding to each to-be-processed video frame can be different. For example, the moving target is a shuttlecock, and the target region of the shuttlecock is longer in a high-speed state and is close to the size of the shuttlecock in a low-speed state.

[0079] ​​Optionally, when the pixel displacement of the adjacent frame picture region is greater than the preset threshold, the picture region greater than the preset threshold is taken as a high value region; if the number of the high value regions is multiple, since the motion in the to-be-processed video frame is not only the moving target but also other moving objects, for example, the moving target is a shuttlecock, but the player will also follow the moving target to move accordingly, thus it is necessary to identify the high value region in one step. Optionally, the object shape of the moving target in the high value region is determined, and the circumscribed region of the object shape is taken as the target region; if the number of the high value regions is one, the object shape of the moving target in the high value region is determined, and the circumscribed region of the object shape is taken as the target region.

[0080] Optionally, when the pixel displacement of the adjacent frame picture region is greater than the preset threshold, the picture region greater than the preset threshold is taken as a high value region; since the motion in the to-be-processed video frame is not only the moving target but also other moving objects, for example, the moving target is a shuttlecock, but the player will also follow the moving target to move accordingly, thus it is necessary to identify the high value region in one step. The object shape of the moving target in the high value region is determined, and the circumscribed region of the object shape is taken as the target region.

[0081] Step S30, the motion trajectory of the moving target is determined according to the target region in each frame of the to-be-processed video frame.

[0082] Specifically, the motion trajectory of the moving target is determined according to the target region in each frame of the to-be-processed video frame, wherein the size of the target region in different to-be-processed video frames can be different. Optionally, the center pixel point of the target region in each frame of the to-be-processed video frame is determined; the motion trajectory of the moving target is determined according to the center pixel point, as shown in FIG. 1. Figure 4 As shown in FIG. 1, trajectories 1-5 are the motion trajectories of the moving target in different time periods.

[0083] Based on the to-be-processed video frame in the video playing time sequence, the speed of the moving target in the previous video frame can be too fast, resulting in that the target region in the video frame is too large, as shown in FIG. 2. Figure 5 As shown in FIG. 3, the speed of the moving target in the latter video frame is smaller, and the size of the target region is normal. Figure 6As shown, it is difficult to determine the target region in the to-be-processed video frame based on the video playing time sequence. In the reverse direction of the video playing time sequence, the speed of the moving target in the to-be-processed video frame is small, and it is easier to determine the target region of the to-be-processed video frame. According to the target region, the determination of the moving track of the moving target is realized. For example, for a typical badminton route, the speed of the badminton at the end of the flight is greatly reduced due to the special shape and material, and therefore, the image features obtained in the reverse direction of the playing time sequence are superior to those obtained in the forward direction.

[0084] In the technical scheme of the embodiment, the pixel displacement amount of the adjacent frame of the to-be-processed video frame in each picture region is determined based on the reverse direction of the video playing time sequence, the picture region is obtained by region division of the to-be-processed video frame, the target region in the to-be-processed video frame is determined according to the pixel displacement amount, and the moving track of the moving target is determined according to the target region in each to-be-processed video frame. By determining the target region in the adjacent frame of the to-be-processed video in the reverse direction of the video playing time sequence and determining the moving track of the moving target, the situation that the target region is difficult to determine or the accuracy is low due to the large speed of the moving target is avoided, and the accuracy of the moving track of the moving target is improved.

[0085] Reference Figure 7 , Figure 7 For the second embodiment of the moving track generation method, based on the first embodiment, the step S20 comprises:

[0086] In step S21, when the pixel displacement amount of the picture region of the adjacent frame is less than or equal to a preset threshold, the target region of the latter frame in the adjacent frame is enlarged, and the target video frame is determined to be moved forward by a preset number of frames based on the reverse direction of the video playing time sequence.

[0087] In step S22, the shape of the object in the enlarged target region in the target video frame is determined.

[0088] In step S23, if the object shape meets the preset condition, the circumscribed region of the object shape is determined as the target region.

[0089] Specifically, in the case that the image features of the to-be-processed video frame are blocked, deformed or missing, the pixel displacement amount of the adjacent frame will decrease significantly. The position of the previous frame in the adjacent frame can be moved forward based on the reverse direction of the video playing time sequence, for example, the nth to-be-processed video frame becomes the (n-1)th to-be-processed video frame after moving forward by one frame. If the pixel displacement amount still decreases significantly, the position of the previous frame is continuously moved forward by one frame, and the size of the target region of the latter frame is appropriately enlarged. The shape of the object in the enlarged target region in the target video frame is determined, and if the object shape meets the preset condition, the circumscribed region of the object shape is determined as the target region.

[0090] In the technical scheme of the embodiment, when the pixel displacement amount of the adjacent frame picture area is less than or equal to a preset threshold, the target area of the latter frame in the adjacent frame is enlarged, the inverse direction based on the video playing time sequence is determined, the target video frame of the preset frame number is moved forward, the object shape in the enlarged target area in the target video frame is determined, and if the object shape meets a preset condition, the circumscribed area of the object shape is determined as the target area. In the case that the image features of the to-be-processed video frame are blocked, deformed or missing, the target area in the adjacent frame of the to-be-processed video is accurately determined, and the motion trajectory of the moving target is accurately determined.

[0091] With reference to Figure 8 The application further provides a motion trajectory generation device, which comprises:

[0092] A calculation module 100 is configured to determine the pixel displacement amount of each picture area of the adjacent frame of the to-be-processed video frame based on the inverse direction of the video playing time sequence, wherein the picture area is obtained by region division of the to-be-processed video frame.

[0093] A determination module 200 is configured to determine a target area in the to-be-processed video frame according to the pixel displacement amount.

[0094] A generation module 300 is configured to determine the motion trajectory of the moving target according to the target area in each frame of the to-be-processed video frame.

[0095] In an embodiment, in the aspect of determining the target area in the to-be-processed video frame according to the pixel displacement amount, the determination module 200 is specifically configured to:

[0096] When the pixel displacement amount of the picture area of the adjacent frame is greater than a preset threshold, the picture area greater than the preset threshold is regarded as a high-value area.

[0097] The object shape of the moving target in the high-value area is determined.

[0098] When the object shape meets a preset condition, the circumscribed area of the object shape is determined as the target area.

[0099] In an embodiment, after the picture area greater than the preset threshold is regarded as the high-value area, the determination module 200 is specifically configured to:

[0100] If the number of the high-value areas is multiple, whether the object shape of the moving target exists in the high-value area is determined, and when the object shape exists in the high-value area, the circumscribed area of the object shape is determined as the target area.

[0101] If the number of the high-value areas is one, the object shape of the moving target in the high-value area is determined, and the circumscribed area of the object shape is determined as the target area.

[0102] In an embodiment, in determining the target region in the video frame to be processed according to the pixel displacement amount, the determining module 200 is specifically configured to:

[0103] When the pixel displacement amount of the picture region of the adjacent frame is less than or equal to a preset threshold, the target region of the latter frame in the adjacent frame is enlarged, and a target video frame that is forward by a preset frame number based on the reverse direction of the video playing time sequence is determined.

[0104] The object shape in the enlarged target region in the target video frame is determined.

[0105] If the object shape satisfies a preset condition, the circumscribed region of the object shape is determined as the target region.

[0106] In an embodiment, in determining the object shape of the moving target in the high-value region, the determining module 200 is specifically configured to:

[0107] The high-value region is input into a preset recognition model to obtain the object shape, and the recognition model is obtained by training a neural network model.

[0108] In an embodiment, in determining the pixel displacement amount of each picture region of adjacent frames of the video frame to be processed, the calculating module 200 is specifically configured to:

[0109] The pixel difference value of each pixel point of two frames of video frames to be processed in the adjacent frames in each picture region is determined.

[0110] The average value of the pixel difference value in the picture region is determined as the pixel displacement amount of the picture region.

[0111] In an embodiment, in determining the motion trajectory of the moving target according to the target region in each frame of the video frame to be processed, the generating module 300 is specifically configured to:

[0112] The center pixel point of the target region in each frame of the video frame to be processed is determined.

[0113] The motion trajectory of the moving target is determined according to the center pixel point.

[0114] The application further provides a motion trajectory generation device, which comprises a memory, a processor, and a motion trajectory generation program stored in the memory and executable on the processor, and each step of the motion trajectory generation method is implemented when the motion trajectory generation program is executed by the processor.

[0115] The application further provides a computer readable storage medium storing a motion trajectory generation program, the motion trajectory generation program being executed by a processor to implement each step of the motion trajectory generation method according to the above embodiment.

[0116] The above-mentioned embodiment numbers of the application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0117] It should be noted that, in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, system, article or apparatus that includes a series of elements not only includes those elements, but also includes other elements not explicitly listed, or inherent to such a process, system, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, system, article or apparatus that includes the element.

[0118] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment system can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a computer readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for making a terminal device (which can be a mobile phone, computer, parking management device, air conditioner, or network device, etc.) execute the system described in each embodiment of the present application.

[0119] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A motion trajectory generation method characterized by, The motion trajectory generation method comprises: determining pixel displacement of each picture area of adjacent frames of a to-be-processed video frame based on the reverse direction of the video playing time sequence, wherein the picture area is obtained by region division of the to-be-processed video frame, and the speed of a moving target in a later to-be-processed video frame is less than the speed of the moving target in an earlier to-be-processed video frame based on the video playing time sequence; determining a target area in the to-be-processed video frame according to the pixel displacement, wherein the target area is a picture area where the moving target is located; determining a motion trajectory of the moving target according to the target area in each frame of the to-be-processed video frame; wherein the step of determining the target area in the to-be-processed video frame according to the pixel displacement comprises: when the pixel displacement of the picture area of the adjacent frames is greater than a preset threshold, the picture area greater than the preset threshold is regarded as a high-value area; an object shape of the moving target in the high-value area is determined; when the object shape meets a preset condition, the circumscribed area of the object shape is determined as the target area; when the pixel displacement of the picture area of the adjacent frames is less than or equal to the preset threshold, the target area in the later frame of the adjacent frames is expanded, a target video frame is determined by moving forward a preset number of frames based on the reverse direction of the video playing time sequence; an object shape in the expanded target area in the target video frame is determined; if the object shape meets a preset condition, the circumscribed area of the object shape is determined as the target area.

2. The motion trajectory generation method of claim 1, wherein, after the step of regarding the picture area greater than the preset threshold as the high-value area, the method further comprises: if the number of the high-value areas is more than one, it is determined whether there is an object shape of the moving target in the high-value areas; when there is the object shape in the high-value areas, the circumscribed area of the object shape is determined as the target area; if the number of the high-value areas is one, an object shape of the moving target in the high-value area is determined, and the circumscribed area of the object shape is determined as the target area.

3. The motion trajectory generation method of claim 1, wherein, the step of determining the object shape of the moving target in the high-value area comprises: inputting the high-value area into a preset recognition model to obtain the object shape, wherein the recognition model is obtained by training a neural network model.

4. The motion trajectory generation method of claim 1, wherein, the step of determining the pixel displacement of each picture area of the adjacent frames of the to-be-processed video frame comprises: determining the pixel difference value of each pixel point of each picture area of two frames of to-be-processed video frames in the adjacent frames; determining the pixel displacement of the picture area according to the average value of the pixel difference value in the picture area.

5. The motion trajectory generation method of claim 1, wherein, the step of determining the motion trajectory of the moving target according to the target area in each frame of the to-be-processed video frame comprises: determining the center pixel point of the target area in each frame of the to-be-processed video frame; determining the motion trajectory of the moving target according to the center pixel point.

6. A motion trajectory generating apparatus characterized by comprising: the motion trajectory generation device comprises: The computing module is configured to determine the pixel displacement of the adjacent frame of the to-be-processed video frame in each picture region based on the reverse direction of the video playback time sequence, the picture region being obtained by region division of the to-be-processed video frame, and the speed of the moving target in the to-be-processed video frame after the video playback time sequence being less than the speed of the moving target in the to-be-processed video frame before the video playback time sequence; The determining module is configured to determine the target region in the to-be-processed video frame according to the pixel displacement; when the pixel displacement of the adjacent frame of the picture region is greater than a preset threshold, the picture region greater than the preset threshold is regarded as a high-value region; the object shape of the moving target in the high-value region is determined; when the object shape satisfies a preset condition, the circumscribed region of the object shape is determined as the target region; the target region is a picture region where the moving target is located; when the pixel displacement of the adjacent frame of the picture region is less than or equal to the preset threshold, the target region of the frame after the adjacent frame is expanded, the target video frame is determined based on the reverse direction of the video playback time sequence and the forward movement of a preset number of frames, the object shape in the expanded target region of the target video frame is determined, and if the object shape satisfies a preset condition, the circumscribed region of the object shape is determined as the target region; The generating module is configured to determine the motion trajectory of the moving target according to the target region in each to-be-processed video frame.

7. A motion trajectory generation device characterized by comprising: The motion trajectory generation device includes a memory, a processor, and a motion trajectory generation program stored in the memory and executable on the processor, and when the motion trajectory generation program is executed by the processor, each step of the motion trajectory generation method of any one of claims 1-5 is implemented.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a motion trajectory generation program, and when the motion trajectory generation program is executed by the processor, each step of the motion trajectory generation method of any one of claims 1-5 is implemented.

Images