Target frame anti-shake method and device, product and medium

Abstract

The embodiment of the invention provides a target frame anti-shake method and device, a product and a medium, and the method comprises the steps: obtaining target object detection frame information of a preset number of continuous frame images; based on the target object detection frame information, determining display parameter change of a target frame corresponding to the same target object, and judging whether the target frame shakes or not; and if the jitter exists, correcting the display parameter of the target frame in the current frame image based on the display parameter of the target frame in the previous frame image. The problem that the target frame jitters frequently due to the fact that the pixel coordinates of the target object detection frame are not accurate enough can be solved, and the display experience feeling of the target object display frame on a screen is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of image target detection, and in particular to a target frame anti-shake method, a target detection device, a computer program product, and a computer-readable storage medium. Background Art

[0002] With the development of autonomous driving technology, in the field of target perception and detection, the target identification frame display based on image detection and tracking algorithms has been widely used. At present, affected by the pixel coordinate accuracy of the target detection frame, the display frame of the target object will frequently jitter within a certain pixel range. After being displayed on the screen, this jitter of the target display frame seriously affects the driver's driving experience. Therefore, on the display screen, improving the stability of the target display frame has become an urgent problem to be solved in the autonomous driving system. Summary of the invention

[0003] In order to solve the existing technical problems, the present application provides a target frame anti-shake method, a target detection device, a computer program product and a computer-readable storage medium that can avoid target frame jitter.

[0004] In a first aspect, a target frame anti-shake method is provided, comprising:

[0005] Obtaining target object detection frame information for a preset number of consecutive frame images;

[0006] Based on the target object detection frame information, determining the display parameter change of the target frame corresponding to the same target object, and judging whether the target frame is shaking;

[0007] If jitter exists, the display parameters of the target frame in the current frame image are corrected based on the display parameters of the target frame in the previous frame image.

[0008] In a second aspect, a target detection device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory;

[0009] When the computer program is executed by the processor, the target frame anti-shake method as described in any embodiment of the present application is implemented.

[0010] In a third aspect, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the target frame anti-shake method as described in any embodiment of the present application is implemented.

[0011] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the target frame anti-shake method as described in any embodiment of the present application is implemented.

[0012] The target frame anti-shake method provided in the above embodiment obtains the target detection frame information of a preset number of consecutive frame images, uses the target detection frame information to determine the display parameter changes of the target frame corresponding to the same target, and judges whether there is jitter in the target frame. If jitter exists, the display parameters of the target frame in the current frame image are corrected based on the display parameters of the target frame in the previous frame image. In this way, the problem of frequent jitter of the target frame caused by inaccurate pixel coordinates of the target detection frame can be solved, and the experience of displaying the target frame on the screen can be effectively improved.

[0013] The target detection device, computer program product, and computer-readable storage medium provided in the above embodiments belong to the same concept as the corresponding target frame anti-shake method embodiments, and thus have the same technical effects as the corresponding target frame anti-shake method embodiments, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of a flow chart of a target frame anti-shake method in one embodiment.

[0015] Figure 2 Schematic diagram of a flow chart of a target frame anti-shake method in one embodiment.

[0016] Figure 3 Schematic diagram of the display of the target box in the previous frame image.

[0017] Figure 4 Schematic diagram of the display of the target frame in the current frame image, wherein the red frame is the target frame in the current frame image, and the blue frame is the target frame in the current frame image after the target frame is corrected.

[0018] Figure 5 The figure is a flowchart of a target frame anti-shake method in an optional specific example.

[0019] Figure 6 for Figure 5 Logic diagram of the target box stabilization method in the example shown.

[0020] Figure 7 Schematic diagram of the structure of a target detection device in one embodiment. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0022] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0023] In the following description, the expression "some embodiments" is involved, which describes a subset of all possible embodiments. It should be noted that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0024] It should also be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may also be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "inside", "outside", "left", "right" and similar expressions used herein are only for the purpose of explanation in conjunction with the embodiments of the accompanying drawings and do not represent the only implementation method.

[0025] With the development of autonomous driving technology, there is an increasing demand for applications that use image recognition to assist in improving driving safety. Figure 1 , which is a schematic diagram of an optional application scenario of the target frame anti-shake method provided in an embodiment of the present application. The target frame anti-shake method can be applied to a vehicle-mounted assisted driving system, including a vehicle-mounted electronic device 21 and a vehicle-mounted camera 22. The vehicle-mounted electronic device 21 mainly includes a host 211 and a display screen 212 installed in the cab. The host 211 can be loaded with a computer program for executing the target frame anti-shake method provided in an embodiment of the present application. During the driving of the vehicle, the vehicle-mounted camera 22 collects image data of the vehicle scene in real time and sends the image data to the host 211. The host 211 can detect the target object contained in the image through a target recognition algorithm, and use a target frame to highlight the target object in the picture and display it, and execute the target frame anti-shake method to keep the target frame of the target object more stably displayed in the picture.

[0026] See also Figure 2 , a target frame anti-shake method provided by an embodiment, can be applied to but not limited to Figure 1 The vehicle-mounted electronic device shown includes the following steps.

[0027] S101, obtaining target object detection frame information of a preset number of consecutive frame images.

[0028] In this embodiment, the continuous preset number of frame images refers to greater than or equal to three continuous frame images. The target object detection frame information refers to the relevant information of the detection frame for highlighting the target object detected in each frame image in the picture. For example, for target A, it is marked with detection frame A. The target object detection frame information may include the position information and size information of detection frame A.

[0029] S103, based on the target object detection frame information, determining a change in display parameters of a target frame corresponding to the same target object, and judging whether the target frame is shaking.

[0030] The number of targets in each frame may include one or more. For each target detected in each frame, a detection frame is used to highlight and identify the target. For the same target that appears in multiple consecutive frames, the detection frame of the target is called a target frame for ease of description and distinction. The display parameters of the display frame of the target frame of the same target are determined when it appears and is displayed in multiple consecutive frames. According to the change of the display parameters of the display frame of the same target, it is determined whether the target frame is jittering. The display parameters of the target frame usually mainly include the position parameters and size parameters of the target frame.

[0031] S105: If jitter exists, modify the display parameters of the target frame in the current frame image based on the display parameters of the target frame in the previous frame image.

[0032] If it is determined that the target frame is jittery, the display parameters of the target frame in the current frame image are corrected based on the display parameters of the target frame in the previous frame image. The correction can be various known ways of adjusting the display parameters of the target frame in the current frame image so that it does not appear to be jittery when switching between enlargement and reduction, such as directly using the display parameters of the target frame in the previous frame image to display it in the current frame image, or using the display parameters of the target frame in the previous frame image and the display parameters of the target frame in the current frame image to calculate the deviation between the two, and using the deviation value to appropriately compensate the display parameters of the target frame in the current frame image.

[0033] The target frame anti-shake method provided in the above embodiment obtains the target detection frame information of a preset number of consecutive frame images, uses the target detection frame information to determine the display parameter changes of the target frame corresponding to the same target, and judges whether there is jitter in the target frame. If jitter exists, the display parameters of the target frame in the current frame image are corrected based on the display parameters of the target frame in the previous frame image. In this way, the problem of frequent jitter of the target frame caused by inaccurate pixel coordinates of the target detection frame can be solved, and the experience of displaying the target frame on the screen can be effectively improved.

[0034] In some embodiments, step S103 includes:

[0035] Based on the target object detection frame information, determining a size change trend of a target frame corresponding to the same target object;

[0036] According to the size change trend, it is determined whether the target frame is shaking.

[0037] The target object detection frame information at least includes the size of the target frame. According to the target object detection frame information in the continuous multiple frames of images, the change of the size of the target frame corresponding to the same target object is determined. And according to the change of the size of the target frame of the same target object in the continuous multiple frames of images, it is determined whether the target frame has jitter.

[0038] For example, taking three consecutive frames of images as an example, the size of the target frame of the same target object A in the first frame is w1, h1; the size of the target frame in the second frame is w2, h2; and the size of the target frame in the third frame is w3, h3. The change in the size of the target frame can be determined based on the sizes of (w1, h1), (w2, h2), and (w3, h3).

[0039] Optionally, judging whether the target frame has jitter according to the size change trend includes:

[0040] If the size of the target frame increases or decreases continuously, it means that the size change of the target frame is an actual size change, and there is no jitter in the target frame;

[0041] If the size change of the target frame includes switching between enlarging and reducing, the target frame is jittery.

[0042] Among them, according to the change of the size of the target frame of the same target object in multiple consecutive frames of images, it is judged whether the size change trend of the target frame is a continuous change or a jitter change. If the size of the target frame continuously increases or decreases, it is considered that the size of the actual imaging area of ​​the same target object in multiple consecutive frames of images is a continuous change, that is, the size change of the target frame is normal and not jitter. If the size change of the target frame corresponding to the same target object in multiple consecutive frames of images includes switching between enlargement and reduction, that is, it first increases and then decreases, or first decreases and then increases, it is considered that the size change of the target frame is not caused by the change of the actual imaging area of ​​the same target object in multiple frames of images, and it is confirmed that the target frame is currently jittering.

[0043] For example, still taking the continuous multi-frame image as referring to continuous 3-frame image, the size of the target frame of the same target object A in the first frame image is w1, h1; the size of the target frame in the second frame image is w2, h2; the size of the target frame in the third frame image is w3, h3. According to the relative sizes of (w1, h1), (w2, h2), and (w3, h3), if (w2, h2)-(w1, h1) and (w3, h3)-(w2, h2) are both positive values, it means that the size of the target frame is continuously increasing; if (w2, h2)-(w1, h1) and (w3, h3)-(w2, h2) are both negative values, it means that the size of the target frame is continuously decreasing; if (w2, h2)-(w1, h1) and (w3, h3)-(w2, h2) have both positive and negative values, it means that the size change of the target frame includes switching between increasing and decreasing.

[0044] In some embodiments, step S103 includes:

[0045] Based on the target object detection frame information, determining the change of the corner point coordinates of the target frame corresponding to the same target object;

[0046] According to the change of the corner point coordinates, it is determined whether the target frame is jittering.

[0047] The target object detection frame information at least includes the position of the target frame, such as the coordinates of the four corner points of the target frame. According to the target object detection frame information in the continuous multiple frames, the change of the position of the target frame corresponding to the same target is determined. And according to the change of the position of the target frame of the same target in the continuous multiple frames, it is determined whether the target frame is jittering.

[0048] For example, still taking the continuous multi-frame image as referring to continuous 3-frame image as an example, the position of the target frame of the same target object A in the first frame image includes corner point coordinates tl1, bl1, tr1, br1 of the upper left corner, lower left corner, upper right corner, and lower right corner; the position of the target frame in the second frame image is tl2, bl2, tr2, br2; the position of the target frame in the third frame image is tl3, bl3, tr3, br3, and the corner point with the smallest coordinate difference can be selected according to the difference between the pixel coordinates of the four corner points of the target frame of target object A in the current frame image and the pixel coordinates of the four corner points of the target frame of target object A in the previous frame image, as the stable corner point of the target frame in the current frame image, and the coordinate change of the corner point is determined based on the coordinate difference of the stable corner point.

[0049] Optionally, judging whether the target frame has jitter according to the change of the corner point coordinates includes:

[0050] According to the pixel coordinates of the four corner points of the target frame in the current frame image and the pixel coordinates of the four corner points of the target frame in the previous frame image, the corner point with the smallest coordinate difference is selected as the most stable corner point;

[0051] If the coordinate change of the most stable corner point is greater than or equal to the preset value, it means that the position change of the target frame is an actual position change, and there is no jitter in the target frame;

[0052] If the coordinate change of the most stable corner point is less than the preset value, the target frame is jittery.

[0053] According to the change of pixel coordinates of the four corner points of the target frame of the same target object in multiple consecutive frames, the corner point with the smallest change in corner point coordinates is selected as the most stable corner point. The coordinate difference change of the most stable corner point is used to determine whether the position change of the target frame belongs to the normal position movement of the target object or to jitter. If the coordinate change of the most stable corner point of the target frame is greater than or equal to the preset value, it is considered that the position of the actual imaging area of ​​the same target object in the current frame image has changed, that is, the current position change of the target frame is normal and not jitter. If the coordinate change of the most stable corner point of the target frame is less than the preset value, it is considered that the current position change of the target frame is not caused by the change of the actual imaging area of ​​the same target object in the current frame image, and it is confirmed that the target frame is currently jittering.

[0054] For example, still taking the continuous multi-frame images as 3 consecutive frames of images as an example, the position of the target box of the same target object A in the first frame of image is tl1, bl1, tr1, br1; the position of the target box in the second frame of image is tl2, bl2, tr2, br2; the position of the target box in the third frame of image is tl3, bl3, tr3, br3, according to the deviation between the position of the target box in the current frame image (tl2, bl2, tr2, br2) and the position in the previous frame image (tl1, bl1, tr1, br1), the coordinate deviations of the upper left corner point (tl2-tl1), the lower left corner point (bl2-bl1), the upper right corner point (tr2-tr1), and the lower right corner point (br2-br1) are calculated respectively, and the corner point with the smallest coordinate difference is selected as the most stable corner point, such as the upper left corner point. When the pixel coordinate change of the most stable corner point is greater than or equal to the preset value, the position change of the target frame of the current frame belongs to the actual position change; when the pixel coordinate change of the most stable corner point is less than the preset value, the position change of the target frame of the current frame belongs to jitter.

[0055] It should be noted that judging whether the target frame is jittering according to the size change trend of the target frame in multiple consecutive image frames and judging whether the target frame is jittering according to the position change of the target frame can be combined.

[0056] In some embodiments, step S101 includes:

[0057] Obtain target object detection frame information of three or more consecutive frames of images; the target object detection frame information includes the width, height, and corner point coordinates of the detection frame.

[0058] The target detection frame information includes at least the width, height, and corner point coordinates of the detection frame. The target detection frame information in at least three consecutive frames of images can be used to determine changes in size and position of the same target appearing in multiple consecutive frames of images, and the changes can be used to determine whether it is a normal change or jitter.

[0059] Optionally, step S103 includes:

[0060] Based on the target object detection frame information, determining a size change trend of a target frame corresponding to the same target object;

[0061] If it is determined that the target frame is jittering according to the size change trend, the size of the target frame in the current frame image is equal to the size of the target frame in the previous frame image;

[0062] Based on the target object detection frame information, determining the change of the corner point coordinates of the target frame corresponding to the same target object;

[0063] According to the change of the corner point coordinates, if it is determined that the target frame is jittered, the coordinates of the corresponding corner points of the target frame in the current frame image are equal to the coordinates of the corresponding corner points of the target frame in the previous frame image.

[0064] In this embodiment, by recording the target frame information in multiple consecutive frames of images and judging the width and height change trends of the target frame, the width and height of the target frame can be effectively corrected to avoid target frame jitter caused by inaccurate width and height of the target frame; by selecting the pixel coordinate changes of the four corner points of the target frame, the corner point positions of the target frame can be effectively corrected to effectively avoid target frame jitter introduced by corner point coordinate jitter.

[0065] In some embodiments, the target frame anti-shake method further includes:

[0066] If there is no jitter, the target frame is displayed based on the display parameters of the target frame in the current frame image; the display parameters include size and / or position.

[0067] If the width and height of the target frame of the same target object do not shake in the current frame image, or the corner position of the target frame in the current frame image does not shake, the size and position of the target frame in the current frame image are equal to the size and position of the target frame in the previous frame image.

[0068] In order to ensure a more comprehensive understanding of the target frame anti-shake method provided in the embodiment of the present application, please refer to Figure 5and Figure 6 , taking an optional specific example as an example, the target frame anti-shake method is described. The target frame anti-shake method includes:

[0069] S11, obtaining detection frame data.

[0070] The target detection frame information in the previous 6 consecutive frames before the current frame image can be recorded through the recording queue, where each detection frame has the width and height of the detection frame, and the pixel coordinates of the four corner points of the upper left corner, lower left corner, lower right corner, and upper right corner.

[0071] S12, judging the width and height change trend of the target frame of the same target object.

[0072] Based on the recorded information of all target object detection frames in the previous 6 consecutive frames of the current frame image, such as the width and height information of the detection frame, and all target object detection frame information in the current frame image, for the detection frame of the same target object, in order to distinguish the description, it is called the target frame, and the width and height change values ​​of the target frame between each two frames are calculated. If there are 6 consecutive changes, both positive and negative values, it means that the width and height are shaking back and forth. Otherwise, if it is continuously positive, it means that the width and height have indeed increased, and if it is continuously negative, it means that the width and height have indeed decreased.

[0073] S13, based on the determination of the width and height change trend of the target frame, setting the width and height of the target frame in the current frame image.

[0074] If the width and height are jittered, the width and height of the target box in the current frame image are directly equal to the width and height of the target box in the previous frame image.

[0075] If the width and height of the detection frame tend to increase or decrease, the width and height of the target frame in the current frame image are equal to the width and height of the target frame in the current frame image.

[0076] S14, the most stable corner point selection of the target box.

[0077] The pixel coordinates of the four corner points of the target box in the current frame image are used to calculate the difference with the pixel coordinates of the four corner points of the target box in the previous frame image, and then the corner point with the smallest coordinate difference is selected as the most stable corner point of the target box in the current frame image.

[0078] S15, corner point coordinate correction.

[0079] When the coordinate change of the most stable corner point is greater than 5 pixel values, the coordinate of the corner point of the target frame in the current frame image is equal to the coordinate of the corner point of the target frame in the current frame image; otherwise, the coordinate of the corner point of the target frame in the current frame image is equal to the coordinate of the corner point of the target frame in the previous frame image.

[0080] S16, based on selecting the most stable corner point and correcting the width and height, obtain the target frame in the current frame image.

[0081] Based on the selected most stable corner point, that is, the one with the smallest difference in corner coordinates among the upper left corner, lower left corner, lower right corner, and upper right corner, and the corrected width and height, the coordinates of each corner point and the width and height of the final target box are calculated.

[0082] Please refer again Figure 3 and 4 , respectively represent the previous frame image and the current frame image, where the target object does not move in the image. Figure 3 In the figure, the blue box is the target box. Figure 4 In the figure, the red frame is the target frame in the current frame image, and the blue frame is the target frame in the current frame image after the target frame is corrected. The red target frame has a jitter of about 2 pixels relative to the target frame of the previous frame, but after correction, the target frame of the current frame is completely consistent with the target frame of the previous frame without jitter.

[0083] In the above embodiment, the target frame anti-shake method records the target object detection frame information in multiple consecutive frames of images to determine the width and height change trends of the corresponding target frame of the same target object, and can effectively correct the width and height of the target frame. By correcting the width and height of the target frame, the target frame jitter caused by the inaccurate width and height of the target frame of the target object can be effectively avoided. By selecting the corner point with the smallest pixel coordinate change among the four corner points of the target frame, and correcting the position of the target frame within a certain range according to the coordinate change of the corner point with the smallest pixel coordinate change, the target frame jitter introduced by the corner point coordinate jitter can be effectively avoided. In this way, the problem of frequent jitter of the target frame caused by the inaccurate pixel coordinates of the target frame of the target object can be solved, and the experience of the target frame of the target object being displayed on the screen can be effectively improved.

[0084] On the other hand, please refer to Figure 7 , a target detection device is also provided, including a memory 112 and a processor 111, wherein the memory 112 stores a computer program; when the computer program is executed by the processor 111, the target frame anti-shake method described in any embodiment of the present application is implemented. Optionally, the target detection device may refer to a vehicle-mounted device host installed in a vehicle cab.

[0085] In another aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the target anti-shake method described in any embodiment of the present application is implemented.

[0086] On the other hand, the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the target anti-shake method described in any embodiment of the present application is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0087] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0088] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, vehicle-mounted device, etc.) to execute the methods described in each embodiment of the present invention.

[0089] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A target frame anti-shake method, characterized in that: include: Obtaining target object detection frame information for a preset number of consecutive frame images; Based on the target object detection frame information, determining the display parameter change of the target frame corresponding to the same target object, and judging whether the target frame is shaking; If jitter exists, the display parameters of the target frame in the current frame image are corrected based on the display parameters of the target frame in the previous frame image.

2. The target frame anti-shake method according to claim 1, characterized in that: The determining, based on the target object detection frame information, a display parameter change of a target frame corresponding to the same target object, and judging whether the target frame is jittering, includes: Based on the target object detection frame information, determining a size change trend of a target frame corresponding to the same target object; According to the size change trend, it is determined whether the target frame is shaking.

3. The target frame anti-shake method according to claim 2, characterized in that: The determining, according to the size change trend, whether the target frame is jittering includes: If the size of the target frame increases or decreases continuously, it means that the size change of the target frame is an actual size change, and there is no jitter in the target frame; If the size change of the target frame includes switching between enlarging and reducing, the target frame is jittery.

4. The target frame anti-shake method according to any one of claims 1 to 3, characterized in that: The determining, based on the target object detection frame information, a display parameter change of a target frame corresponding to the same target object, and judging whether the target frame is jittering, includes: Based on the target object detection frame information, determining the change of the corner point coordinates of the target frame corresponding to the same target object; According to the change of the corner point coordinates, it is determined whether the target frame is jittering.

5. The target frame anti-shake method according to claim 4, characterized in that: The determining, according to the change of the corner point coordinates, whether the target frame is jittering includes: According to the pixel coordinates of the four corner points of the target frame in the current frame image and the pixel coordinates of the four corner points of the target frame in the previous frame image, the corner point with the smallest coordinate difference is selected as the most stable corner point; If the coordinate change of the most stable corner point is greater than or equal to the preset value, it means that the position change of the target frame is an actual position change, and there is no jitter in the target frame; If the coordinate change of the most stable corner point is less than the preset value, the target frame is jittery.

6. The target frame anti-shake method according to claim 1, characterized in that: Also includes: If there is no jitter, displaying the target frame based on the display parameters of the target frame in the current frame image; The display parameters include size and / or position.

7. The target frame anti-shake method according to claim 1, characterized in that: The step of obtaining target object detection frame information of a preset number of consecutive image frames includes: Obtain target object detection frame information of three or more consecutive frames of images; the target object detection frame information includes the width, height, and corner point coordinates of the detection frame.

8. A target detection device, characterized in that: The device comprises a memory and a processor, wherein the memory stores a computer program; When the computer program is executed by the processor, the target frame anti-shake method according to any one of claims 1 to 7 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the target frame anti-shake method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the target frame anti-shake method according to any one of claims 1 to 7 is implemented.

Images