Video processing method, device, equipment and computer readable storage medium

Abstract

This invention discloses a video processing method, comprising the following steps: acquiring first person information and first coordinate information corresponding to the main venue, and acquiring second person information and second coordinate information corresponding to the sub-venues; based on the first person information, first coordinate information, second person information, and second coordinate information, synthesizing the second person information into a first video to obtain a first synthesized video; if the first person information is located at the starting position, determining whether there is first overlapping person information in the first synthesized video; if so, allocating the first overlapping person information to the outer track of the main venue in the first synthesized video to obtain a target video. This invention also discloses a video processing apparatus, device, and computer-readable storage medium. By synthesizing the person information from the main venue and the sub-venues, this invention enables competitions that cannot be played simultaneously to be displayed through synthesis, thereby facilitating the organization of clustered competitions across multiple venues.

Description

Technical Field

[0001] The present invention relates to the field of video processing technology, and in particular to a video processing method, device, equipment and computer-readable storage medium. Background Art

[0002] The broadcast of competitive matches is based on a real competitive match at the same venue. It uses multi-angle video shooting to broadcast or rebroadcast the video stream, and loads some professional game skills instructions and professional commentary content during the broadcast.

[0003] At present, there are various restrictions that prevent competitions from being organized in the same venue. For example, due to the impact of the COVID-19 pandemic, many gathering activities cannot be held, which makes it impossible to organize gatherings, resulting in the cancellation or postponement of gatherings.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a video processing method, device, equipment and computer-readable storage medium, aiming to solve the technical problem that collective competitions cannot be organized when collective activities cannot be carried out.

[0006] To achieve the above object, the present invention provides a video processing method, which comprises the following steps:

[0007] Acquire the first character information in the first video corresponding to the main arena and the first coordinate information corresponding to the first character information, and acquire the second character information in the second video corresponding to the sub-arena and the second coordinate information corresponding to the second character information;

[0008] Based on the first character information, the first coordinate information, the second character information and the second coordinate information, synthesizing the second character information into the first video to obtain a first synthesized video;

[0009] If it is determined based on the first coordinate information that the first character information is located at the starting position of the main stadium, determining whether there is overlapping first overlapping character information between the first character information and the second character information of the first composite video;

[0010] If the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video to obtain the target video.

[0011] Furthermore, after the step of synthesizing the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain the first synthesized video, the step further includes:

[0012] If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information between the first character information and the second character information of the first composite video, then obtaining a first speed corresponding to the first character information and a second speed corresponding to the second character information;

[0013] If it is determined based on the first speed and the second speed that there is a predicted overlap between the person corresponding to the first person information and the person corresponding to the second person information at the preset moment, then second overlapping person information is determined in the first person information and the second person information of the first composite video based on the predicted overlap;

[0014] The first slow-motion character information in the second overlapping character information is obtained, and the first slow-motion character information is adjusted in the first composite video to obtain the target video.

[0015] Further, the step of obtaining a first speed corresponding to the first character information and a second speed corresponding to the second character information includes:

[0016] If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information in the first character information and the second character information of the first composite video, then determining whether there is third overlapping character information corresponding to the predicted overlapping phenomenon in the first character information and the second character information;

[0017] If the third overlapping character information exists, obtaining the second slow character information in the third overlapping character information and the first adjustment number corresponding to the second slow character information;

[0018] Adjust the second slow-motion character information in the first composite video based on the first adjustment number to obtain the target video;

[0019] If the third overlapping character information does not exist, a first speed corresponding to the first character information and a second speed corresponding to the second character information are acquired.

[0020] Furthermore, the step of adjusting the second slow-motion character information in the first composite video based on the first adjustment number to obtain the target video includes:

[0021] When the position of the second slow-motion person information does not reach the overlapping position corresponding to the predicted overlapping phenomenon, based on the first adjustment times and the preset body position, the second slow-motion person information is adjusted toward the outer track in the first synthetic video to obtain the target video;

[0022] When the position reaches the overlapping position, based on the first adjustment times and the preset body position, the second slow-motion character information is adjusted toward the inner track of the main track in the first synthetic video to obtain the target video.

[0023] Furthermore, after the step of determining the second overlapping character information in the first character information and the second character information of the first synthesized video based on the predicted overlapping phenomenon, the method further includes:

[0024] Acquire speed information and coordinate information corresponding to each character information in the second overlapping character information, and determine a target route trajectory in a preset route trajectory based on the speed information and coordinate information;

[0025] Based on the target route trajectory, the first slow-motion character information is adjusted toward the outer track of the main stadium in the first synthetic video to obtain the target video.

[0026] Furthermore, after the step of synthesizing the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain the first synthesized video, the step further includes:

[0027] If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is first overlapping character information in the first character information and the second character information of the first composite video, then obtaining third slow character information in the first overlapping character information and a second adjustment number corresponding to the third slow character information;

[0028] The third slow-motion character information is adjusted toward the inner track in the first synthetic video based on the second integer number and the preset body position to obtain the target video.

[0029] Furthermore, if the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video, and the step of obtaining the target video includes:

[0030] If the first overlapping character information exists, assigning the first overlapping character information to the outer track of the main stadium in the first composite video to obtain a second composite video;

[0031] If there is a difference between the synthesized character information corresponding to the second character information in the second synthesized video and the second character information, obtaining the difference character information;

[0032] Acquire a plurality of character information to be replaced corresponding to the difference character information, and determine character information to be synthesized based on the character information to be replaced;

[0033] Based on the coordinate information to be replaced of the character information to be synthesized, the difference character information in the second synthesized video is replaced with the character information to be synthesized to obtain the target video.

[0034] In addition, to achieve the above object, the present invention further provides a video processing device, the video processing device comprising:

[0035] An acquisition module, used to acquire first character information in a first video corresponding to a main venue and first coordinate information corresponding to the first character information, and acquire second character information in a second video corresponding to a sub-venue and second coordinate information corresponding to the second character information;

[0036] A synthesis module, configured to synthesize the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain a first synthesized video;

[0037] a determination module, configured to determine whether there is overlapping first overlapping character information between the first character information and the second character information of the first composite video if it is determined based on the first coordinate information that the first character information is located at the starting position of the main playing field;

[0038] The adjustment module is used to allocate the first overlapping character information to the outer track of the main stadium in the first composite video if the first overlapping character information exists, so as to obtain a target video.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also provides a video processing device, which includes: a memory, a processor, and a video processing program stored in the memory and executable on the processor, and the video processing program implements the steps of the aforementioned video processing method when executed by the processor.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned video processing method are implemented.

[0041] The present invention obtains the first character information in the first video corresponding to the main stadium and the first coordinate information corresponding to the first character information, obtains the second character information in the second video corresponding to the sub-stadium and the second coordinate information corresponding to the second character information; then based on the first character information, the first coordinate information, the second character information and the second coordinate information, the second character information is synthesized into the first video to obtain the first synthesized video; then if it is determined based on the first coordinate information that the first character information is located at the starting position of the main stadium, it is determined whether there is overlapping first overlapping character information in the first synthesized video and the second character information; then if the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first synthesized video to obtain the target video, and the character information of the main stadium and the character information of the sub-stadium are synthesized, so that the competition that cannot compete in the same field can be displayed through synthesis, and then the gathering competition can be organized through multiple stadiums. At the same time, by re-adjusting the track position of the first overlapping character information in the first synthesized video, the overlapping character information in the first synthesized video is avoided, and the viewing experience of the target video is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a structural diagram of a video processing device in a hardware operating environment involved in an embodiment of the present invention;

[0043] Figure 2 It is a flowchart of a first embodiment of a video processing method of the present invention;

[0044] Figure 3 FIG. 4 is a schematic diagram of functional modules of a video processing device according to an embodiment of the present invention.

[0045] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0047] like Figure 1 As shown, Figure 1 It is a structural diagram of a video processing device in a hardware operating environment involved in an embodiment of the present invention.

[0048] The video processing device of the embodiment of the present invention can be a PC, or it can be a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a portable computer, or other portable terminal devices with display function.

[0049] like Figure 1 As shown, the video processing device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0050] Optionally, the video processing device may also include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, etc. Among them, the sensor may be a light sensor, a motion sensor, and other sensors. Of course, the video processing device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be described in detail here.

[0051] Those skilled in the art will understand that Figure 1 The terminal structure shown in the figure does not constitute a limitation on the video processing device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0052] like Figure 1 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a video processing program.

[0053] exist Figure 1In the video processing device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the video processing program stored in the memory 1005.

[0054] In this embodiment, the video processing device includes: a memory 1005, a processor 1001, and a video processing program stored in the memory 1005 and executable on the processor 1001, wherein the processor 1001 calls the video processing program stored in the memory 1005 and executes the steps of the video processing method in each of the following embodiments.

[0055] The present invention also provides a video processing method, referring to Figure 2 , Figure 2 FIG. 4 is a flow chart of a first embodiment of a video processing method according to the present invention.

[0056] In this embodiment, the video processing method includes the following steps:

[0057] Step S101, obtaining first character information in a first video corresponding to a main venue and first coordinate information corresponding to the first character information, and obtaining second character information in a second video corresponding to a sub-venue and second coordinate information corresponding to the second character information;

[0058] In this embodiment, before the competition, the competition venue image modeling is performed for multiple remote venues implemented in the same competition. For example, there are X players participating in a formal competition field at the same time, but due to other reasons, multiple players cannot compete in the same venue and need to compete in a remote place at the same time. It is assumed that there are N remote competition venues. Because it is the same type of competition, the venue standards of the main competition field and the sub-venues are consistent, and the standard parameters of the main competition field and the sub-venues are the same. The standard parameters include track length, track width, track shape, track area, track curvature, etc., and multiple video content acquisition points (cameras) are arranged in each venue. For example: multiple cameras are set at specific points such as the southeast, northwest, and bends of the track. The main competition field is the first camera, and the sub-venue is the second camera. The camera includes a 3D camera. The center point of the main track is used as the zero-point coordinate axis, the length of the venue is X, the width is Y, and the maximum range of X and Y is the surrounding guardrail of the venue. The sub-venues use the same coordinate system and zero-point coordinate axis as the main venue. The camera parameters of a camera at a certain coordinate in the first camera and the camera at the same coordinate in the second camera are the same, including angle parameters, height parameters, width parameters, etc.

[0059] In this embodiment, there is a central server connected to the first camera, and multiple edge servers connected to the second cameras of each sub-venue, that is, each sub-venue can correspond to an edge server; the video shot by the first camera (first video) is obtained through the central server, and the video shot by the second camera (second video) is obtained through the edge servers.

[0060] In this embodiment, the central server obtains the first character information in the first video corresponding to the main venue and the first coordinate information corresponding to the first character information, and obtains the second character information in the second video corresponding to the sub-venue and the second coordinate information corresponding to the second character information.

[0061] Specifically, the central server performs image recognition on the first video to obtain the first character information in each frame of the first video and the coordinate information of the first character information in the corresponding main stadium (first coordinate information). At the same time, the central server can also obtain each second video through the edge server, perform image recognition on the second video, obtain the second character information in each frame of the second video and the coordinate information of the second character information in the corresponding main stadium (second coordinate information), or the edge server performs image recognition on the second video to obtain the second character information in each frame of the second video and the coordinate information of the second character information in the corresponding main stadium (second coordinate information), and send the second character information and the second coordinate information corresponding to the second character information to the central server, and also include the shooting time corresponding to each second character information.

[0062] The first character information and the second character information are images of athletes.

[0063] Step S102, based on the first character information, the first coordinate information, the second character information and the second coordinate information, synthesizing the second character information into the first video to obtain a first synthesized video;

[0064] In this embodiment, after obtaining the first character information, the first coordinate information, the second character information and the second coordinate information, the central server synthesizes the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain the first synthesized video, that is, the central server adds the second character information to the position corresponding to the second coordinate information in the first video to obtain the first synthesized video. Specifically, in the image frame of the first video with the same shooting time as the second character information, the central server adds the second character information to the position corresponding to the second coordinate information to obtain the image frame in the first synthesized video.

[0065] Step S103, if it is determined based on the first coordinate information that the first character information is located at the starting position of the main stadium, determining whether there is overlapping first overlapping character information between the first character information and the second character information of the first composite video;

[0066] In this embodiment, the central server first determines that the first character information is located at the starting position of the main stadium based on the first coordinate information or the second coordinate information, that is, whether the current stage is the beginning of the game. If the first character information is determined to be located at the starting position of the main stadium based on the first coordinate information, then it is determined whether there is overlapping first overlapping character information between the first character information and the second character information in the first composite video; specifically, it is determined whether there is overlap between the regional coordinates of the areas where the character information in the first composite video is located. If there is overlap between the regional coordinates, it is determined that there is first overlapping character information.

[0067] Step S104: if the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video to obtain a target video.

[0068] In this embodiment, if there is first overlapping character information, the central server will assign the first overlapping character information to the outer track of the main stadium in the first composite video to obtain the target video. Specifically, if the first character information in the first composite video overlaps with a certain character information in the second character information, then a certain character information in the second character information is used as the first overlapping character information. If two character information in the second character information overlap, then any character information of the two overlapping character information is used as the first overlapping character information. If there is N overlapping character information, then N-1 overlapping character information is used as the first overlapping character information. When allocating the outer track, each character information in the first overlapping character information is assigned a track to obtain the target video.

[0069] In other implementations, if the first overlapping character information does not exist, the first composite video is used as the target video.

[0070] It should be noted that the collective competition in this embodiment may be short track speed skating, sprinting, long distance running, swimming, or other competitions that require multiple tracks for competition.

[0071] The video processing method proposed in this embodiment obtains the first character information in the first video corresponding to the main stadium and the first coordinate information corresponding to the first character information, obtains the second character information in the second video corresponding to the sub-stadium and the second coordinate information corresponding to the second character information; then based on the first character information, the first coordinate information, the second character information and the second coordinate information, the second character information is synthesized into the first video to obtain the first synthesized video; then if it is determined based on the first coordinate information that the first character information is located at the starting position of the main stadium, it is determined whether there is overlapping first overlapping character information in the first synthesized video and the second character information; then if the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first synthesized video to obtain the target video, and the character information of the main stadium and the character information of the sub-stadium are synthesized, so that the competition that cannot compete in the same stadium can be displayed through synthesis, and then a concentrated competition can be organized through multiple stadiums. At the same time, by re-adjusting the track position of the first overlapping character information in the first synthesized video, overlapping character information in the first synthesized video is avoided, and the viewing experience of the target video is improved.

[0072] Based on the first embodiment, a second embodiment of the video processing method of the present invention is proposed. In this embodiment, after step S102, the video processing method further includes:

[0073] Step S201, if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information between the first character information and the second character information of the first composite video, then obtaining a first speed corresponding to the first character information and a second speed corresponding to the second character information;

[0074] Step S202, if it is determined based on the first speed and the second speed that there is a predicted overlap between the person corresponding to the first person information and the person corresponding to the second person information at the preset time, then second overlapping person information is determined in the first person information and the second person information of the first composite video based on the predicted overlap;

[0075] Step S203, obtaining the first slow-motion character information in the second overlapping character information, adjusting the first slow-motion character information in the first composite video, and obtaining the target video.

[0076] In this embodiment, after obtaining the first composite video, if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, the central server determines whether there is first overlapping character information in the first character information and the second character information of the current first composite video. If not, the first speed corresponding to the first character information and the second speed corresponding to the second character information are obtained. When performing image recognition on the first video, the first speed corresponding to the first character information can be obtained, and when performing image recognition on the second video, the second speed corresponding to the second character information can be obtained. The first speed and the second speed can be instant speeds, that is, the first speed is the current speed of the first character information, and the second speed is the current speed of the second character information.

[0077] Next, the central server determines whether there is a predicted overlap between the person corresponding to the first character information and the person corresponding to the second character information at the preset moment based on the first speed and the second speed. If so, the second overlapping character information is determined in the first character information and the second character information of the first composite video based on the predicted overlap. Specifically, the first position information of the first character information in the track of the first composite video after a preset time and the second position information of the second character information in the track of the first composite video can be determined based on the first speed and the second speed. For each character information, the estimated sliding distance length L(s,nt)+δ is calculated based on its instantaneous speed and n time units (after the preset time), where s is the average speed (first speed or second speed) in a number of consecutive time units, and δ is the error value. Combined with the shape of the forward track, the position of the track is calculated and predicted as Anew(x, y) = Aold(x', y') + δ, where x' and y' are the coordinates of the point S (L, Lstraight, Large), where L is the predicted sliding distance, Lstraight is the calculated length of the track straight line, and Large is the calculated length of the track arc n×π×r / 180. Where n is the degree of the center angle (degree system), r is the radius, and L is the arc length of the center angle. Furthermore, the first position information and the second position information can be predicted according to the prediction method of the position Anew (x, y), and then, it is determined whether the character corresponding to the first character information and the character corresponding to the second character information overlap when they are synthesized after a preset time period. If it is determined based on the first position information and the second position information that there is a predicted overlap between the character corresponding to the first character information and the character corresponding to the second character information at the preset moment, the first position area coordinates of the character corresponding to the first character information in the predicted video are determined according to the first position information, and the second position area coordinates of the character corresponding to the second character information in the predicted video are determined according to the second position information. If the first position area coordinates overlap with the second position area coordinates, it is determined that there is a predicted overlap, and then based on the predicted overlap, the second overlapping character information is determined in the first character information and the second character information of the first synthesized video, that is, the second overlapping character information is the character information corresponding to the overlapping area coordinates.

[0078] Finally, the first slow character information in the second overlapping character information is obtained, and the character speed of the second overlapping character information is obtained from the first speed and the second speed. If the second overlapping character information includes two, the character information with a smaller character speed in the second overlapping character information is used as the first slow character information. If the second overlapping character information is greater than two, the character information in the second overlapping character information except the character information with the largest character speed is used as the first slow character information. Then, based on the preset body position, the first slow character information is adjusted in the first composite video toward the outer track of the main stadium, that is, the first slow character information in the first composite video is adjusted toward the direction of the outer track by a preset body position to obtain the target video, wherein the preset body position can be a track width of the main stadium or the sub-stadium. If the target video has overlapping character information, the first slow character information in the first composite video is adjusted toward the direction of the outer track by a preset body position again until there is no overlapping character information in the target video.

[0079] The video processing method proposed in this embodiment is as follows: if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information in the first character information and the second character information of the first composite video, then a first speed corresponding to the first character information and a second speed corresponding to the second character information are obtained; then if it is determined based on the first speed and the second speed that there is a predicted overlap between the character corresponding to the first character information and the character corresponding to the second character information at the preset moment, the second overlapping character information is determined in the first character information and the second character information of the first composite video based on the predicted overlap; then the first slow character information in the second overlapping character information is obtained, the first slow character information is adjusted in the first composite video, and the target video is obtained. By adjusting the character information that may overlap in advance, it can be gradually adjusted outward by several time units in advance, so that the movement trajectory of the character information in continuous video frames is an arc, thereby avoiding the existence of overlapping character information in the first composite video and improving the viewing experience of the target video.

[0080] Based on the second embodiment, a third embodiment of the video processing method of the present invention is proposed. In this embodiment, step S201 includes:

[0081] Step S301, if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information in the first character information and the second character information of the first composite video, then determining whether there is third overlapping character information corresponding to a predicted overlapping phenomenon in the first character information and the second character information;

[0082] Step S302, if the third overlapping character information exists, obtaining the second slow character information in the third overlapping character information and the first adjustment number corresponding to the second slow character information, and adjusting the second slow character information in the first composite video based on the first adjustment number to obtain the target video;

[0083] Step S303: If the third overlapping character information does not exist, obtain a first speed corresponding to the first character information and a second speed corresponding to the second character information.

[0084] In this embodiment, after obtaining the first composite video, if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, it is determined whether there is first overlapping character information in the first character information and the second character information of the current first composite video. If not, it is determined whether there is third overlapping character information corresponding to the predicted overlapping phenomenon in the first character information and the second character information. The third overlapping character information is character information that has been adjusted due to overlap when the video was synthesized before the current moment.

[0085] Then, if the third overlapping character information exists, the second slow character information in the third overlapping character information and the first adjustment number corresponding to the second slow character information are obtained. Since the first character information is located at a non-starting position of the main stadium and the third overlapping character information exists, the third overlapping character information is currently in the middle stage of position adjustment, that is, the third overlapping character information has been position adjusted in the previous video. Therefore, the second slow character information in the third overlapping character information is obtained. The second slow character information is the character information with a slower speed in the third overlapping character information, specifically the character information other than the character information with the fastest speed in the third overlapping character information, and the first adjustment number corresponding to the second slow character information is obtained, that is, the number of times each second slow character information has been adjusted. Then, based on the first adjustment number, the second slow character information is adjusted in the first synthetic video to obtain the target video.

[0086] Specifically, step S302 includes:

[0087] Step S3021, when the position of the second slow-motion person information does not reach the overlapping position corresponding to the predicted overlapping phenomenon, based on the first adjustment times and the preset body position, the second slow-motion person information is adjusted toward the outer track in the first synthetic video to obtain the target video;

[0088] Step S3022, when the position reaches the overlapping position, based on the first adjustment times and the preset body position, the second slow-motion character information is adjusted toward the inner track of the main track in the first synthetic video to obtain the target video.

[0089] In this embodiment, the central server first determines whether the position of the second slow-moving person information reaches the overlapping position corresponding to the predicted overlapping phenomenon, that is, determines whether the position reaches the overlapping position corresponding to the predicted overlapping phenomenon according to the coordinate information of the second slow-moving person information.

[0090] If the overlapping position is not reached, the central server adjusts the second slow-motion character information in the first composite video toward the outer track based on the first adjustment times and the preset body position to obtain the target video. Specifically, the first slow-motion character information in the first composite video is adjusted toward the outer track by the preset body position of the first adjustment times + 1, so that the first slow-motion character information in the current target video differs from the first slow-motion character information in the previous target video by a preset body position.

[0091] If the overlapping position is reached, the central server adjusts the second slow-motion character information in the first composite video toward the inner track of the main track based on the first adjustment times and the preset body position to obtain the target video. Specifically, the first slow-motion character information in the first composite video is adjusted toward the inner track by the preset body position of the first adjustment times-1, so that the first slow-motion character information in the current target video differs from the first slow-motion character information in the previous target video by a preset body position, so that the motion trajectory of the character information in the continuous video frames is an arc, thereby avoiding the existence of overlapping character information in the first composite video and improving the viewing experience of the target video.

[0092] The video processing method proposed in this embodiment determines whether the first character information is located at a non-starting position of the main stadium based on the first coordinate information, and whether there is first overlapping character information in the first character information and the second character information of the first composite video. The method determines whether there is third overlapping character information corresponding to the predicted overlapping phenomenon in the first character information and the second character information; then, if the third overlapping character information exists, the second slow character information in the third overlapping character information and the first adjustment number corresponding to the second slow character information are obtained, and the second slow character information is adjusted in the first composite video based on the first adjustment number to obtain the target video; and then, if the third overlapping character information does not exist, the first speed corresponding to the first character information and the second speed corresponding to the second character information are obtained, and the third overlapping character information is adjusted again, so that the first slow character information in the current target video differs from the first slow character information in the previous target video by a preset body position, so that the movement trajectory of the character information in the continuous video frames is an arc, thereby avoiding the existence of overlapping character information in the first composite video and improving the viewing experience of the target video.

[0093] Based on the second embodiment, a fourth embodiment of the video processing method of the present invention is proposed. In this embodiment, after step S203, the video processing method further includes:

[0094] Step S401, obtaining speed information and coordinate information corresponding to each character information in the second overlapping character information, and determining a target route trajectory in a preset route trajectory based on the speed information and coordinate information;

[0095] Step S402: Based on the target route trajectory, the first slow-motion character information is adjusted toward the outer track of the main stadium in the first synthetic video to obtain the target video.

[0096] It should be noted that by taking N number of overtaking routes in similar real competitions, the trajectories are analyzed and counted in advance to form various different trajectory routes, and the trajectory routes are combined with the coordinate positions of the main venue for competition, and the regular function of parameter changes between various trajectories is calculated F(s, t, l, x, y) + δ, where s is speed, t is time, l is track length, and x and y are coordinate series items.

[0097] In this embodiment, speed information and coordinate information corresponding to each character information in the second overlapping character information are obtained, and based on the speed information and coordinate information, a target route trajectory is determined in the preset route trajectory, and then a regular function of the target route trajectory is determined, and finally based on the target route trajectory, the first slow character information is adjusted toward the outer track of the main stadium in the first synthetic video to obtain the target video, that is, the first slow character information is adjusted according to the regular function of the target route trajectory, and the first slow character information is adjusted toward the outer track in the first synthetic video according to the adjusted position.

[0098] The video processing method proposed in this embodiment obtains the speed information and coordinate information corresponding to each character information in the second overlapping character information, and determines the target route trajectory in the preset route trajectory based on the speed information and coordinate information; then, based on the target route trajectory, the first slow character information is adjusted to the outer track of the main stadium in the first composite video to obtain the target video. The preset route trajectory can be used to quickly adjust the first slow character information, thereby improving the viewing experience of the target video while avoiding overlapping character information in the first composite video.

[0099] Based on the first embodiment, a fifth embodiment of the video processing method of the present invention is proposed. In this embodiment, after step S102, the video processing method further includes:

[0100] Step S501, if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is first overlapping character information in the first character information and the second character information of the first composite video, then obtaining third slow character information in the first overlapping character information and a second adjustment number corresponding to the third slow character information;

[0101] Step S502: adjusting the third slow-motion person information toward the inner track in the first synthetic video based on the second integer number and the preset body position to obtain the target video.

[0102] In this embodiment, each time the position of the first overlapping character information is adjusted, the number of adjustments is increased by 1; if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is first overlapping character information in the first character information and the second character information of the first synthetic video, then the third slow character information in the first overlapping character information and the second number of adjustments corresponding to the third slow character information are obtained, and the second number of adjustments is the number of adjustments currently used to adjust the third slow character information to the outermost side of the arc in the continuous target video.

[0103] Then, based on the second integer number and the preset body position, the third slow-motion character information is adjusted toward the inner track in the first composite video to obtain the target video. Specifically, the first slow-motion character information in the first composite video is adjusted toward the inner track by the preset body position of the first adjustment number - 1, so that the first slow-motion character information in the current target video differs from the first slow-motion character information in the previous target video by a preset body position.

[0104] The video processing method proposed in this embodiment is as follows: if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is first overlapping character information in the first character information and the second character information of the first composite video; then the third slow character information in the first overlapping character information and the second adjustment number corresponding to the third slow character information are obtained, and based on the second integer number and the preset body position, the third slow character information is adjusted toward the inner track in the first composite video to obtain the target video, so that the first slow character information in the current target video differs from the first slow character information in the previous target video by a preset body position, so that the movement trajectory of the character information in continuous video frames is an arc, thereby avoiding overlapping character information in the first composite video and improving the viewing experience of the target video.

[0105] Based on the above embodiments, a sixth embodiment of the video processing method of the present invention is proposed. In this embodiment, step S104 includes:

[0106] Step S601: if the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video to obtain a second composite video;

[0107] Step S602, if there is a difference between the synthesized character information corresponding to the second character information in the second synthesized video and the second character information, obtaining the difference character information;

[0108] Step S603, obtaining a plurality of character information to be replaced corresponding to the difference character information, and determining character information to be synthesized based on the character information to be replaced;

[0109] Step S604: based on the coordinate information to be replaced of the character information to be synthesized, the difference character information in the second synthesized video is replaced with the character information to be synthesized, so as to obtain the target video.

[0110] In this embodiment, if the first overlapping character information exists, the first overlapping character information is assigned to the outer track of the main stadium in the first composite video to obtain the second composite video. Specifically, the central server assigns the fourth slow character information in the first overlapping character information to the outer track of the main stadium to obtain the second composite video.

[0111] Then, determine whether there is a difference between the synthesized character information corresponding to the second character information in the second synthesized video and the second character information, that is, the difference caused by the distortion, stretching or shrinkage of the character image in the synthesized character information. Specifically, the area of ​​the synthesized character information can be determined, and the ratio of the area of ​​the synthesized character information to the area of ​​the corresponding second character information can be calculated to obtain multiple area ratios. If there is an area ratio in the area ratio whose absolute difference with 1 (the absolute value of the difference) is greater than a preset value, it is determined that there is a difference. The preset value can be set to 20%.

[0112] If there is no difference between the synthesized character information corresponding to the second character information in the second synthesized video and the second character information, the second synthesized video is used as the target video.

[0113] If the synthesized character information corresponding to the second character information in the second synthesized video differs from the second character information, then the difference character information is obtained, a plurality of character information to be replaced corresponding to the difference character information is obtained, and the character information to be synthesized is determined based on the character information to be replaced; specifically, the difference character information is character information that differs from the second character information, and the central server obtains a plurality of character information to be replaced corresponding to the difference character information and coordinate information to be replaced corresponding to the character information to be replaced, that is, each difference character information corresponds to a plurality of character information to be replaced, and the difference between the coordinates of the character information to be replaced and the coordinates of the difference character information is less than the preset coordinate difference. Determine the character information to be synthesized that does not differ from the character information to be replaced, that is, after the difference character information in the second synthesized video is replaced with the character information to be synthesized, there is no difference in the new synthesized video, and the synthesized character information corresponding to the second character information in the new synthesized video does not differ from the second character information.

[0114] Finally, based on the coordinate information to be replaced of the character information to be synthesized, the difference character information in the second synthesized video is replaced with the character information to be synthesized to obtain the target video.

[0115] The video processing method proposed in this embodiment is as follows: if the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video to obtain a second composite video; then, if there is a difference between the composite character information corresponding to the second character information in the second composite video and the second character information, the difference character information is obtained; then, a plurality of character information to be replaced corresponding to the difference character information is obtained, and the character information to be composited is determined based on the character information to be replaced; then, based on the coordinate information to be replaced of the character information to be composited, the difference character information in the second composite video is replaced with the character information to be composited to obtain the target video. By replacing the difference character information, distortion, stretching or shrinkage of the character information in the target video can be avoided, thereby further improving the viewing experience of the target video.

[0116] The present invention also provides a video processing device, referring to Figure 3 , the video processing device comprises:

[0117] An acquisition module 10 is used to acquire first character information in a first video corresponding to a main venue and first coordinate information corresponding to the first character information, and acquire second character information in a second video corresponding to a sub-venue and second coordinate information corresponding to the second character information;

[0118] A synthesis module 20, configured to synthesize the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain a first synthesized video;

[0119] A determination module 30, configured to determine whether there is overlapping first overlapping character information between the first character information and the second character information of the first composite video if it is determined based on the first coordinate information that the first character information is located at the starting position of the main stadium;

[0120] The adjustment module 40 is configured to allocate the first overlapping character information to the outer track of the main stadium in the first composite video if the first overlapping character information exists, so as to obtain a target video.

[0121] Furthermore, the video processing device further includes:

[0122] a speed acquisition module, configured to acquire a first speed corresponding to the first character information and a second speed corresponding to the second character information if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium and there is no first overlapping character information between the first character information and the second character information of the first composite video;

[0123] an overlapping character information determining module, configured to determine second overlapping character information in the first character information and the second character information of the first composite video based on the predicted overlapping phenomenon if it is determined based on the first speed and the second speed that there is a predicted overlapping phenomenon between the character corresponding to the first character information and the character corresponding to the second character information at the preset moment;

[0124] The first video adjustment module is used to obtain the first slow-motion character information in the second overlapping character information, and adjust the first slow-motion character information in the first composite video to obtain the target video.

[0125] Furthermore, the speed acquisition module is also used for:

[0126] If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information in the first character information and the second character information of the first composite video, then determining whether there is third overlapping character information corresponding to the predicted overlapping phenomenon in the first character information and the second character information;

[0127] If the third overlapping character information exists, obtaining the second slow character information in the third overlapping character information and the first adjustment number corresponding to the second slow character information, and adjusting the second slow character information in the first composite video based on the first adjustment number to obtain the target video;

[0128] If the third overlapping character information does not exist, a first speed corresponding to the first character information and a second speed corresponding to the second character information are acquired.

[0129] Furthermore, the speed acquisition module is also used for:

[0130] When the position of the second slow-motion person information does not reach the overlapping position corresponding to the predicted overlapping phenomenon, based on the first adjustment times and the preset body position, the second slow-motion person information is adjusted toward the outer track in the first synthetic video to obtain the target video;

[0131] When the position reaches the overlapping position, based on the first adjustment times and the preset body position, the second slow-motion character information is adjusted toward the inner track of the main track in the first synthetic video to obtain the target video.

[0132] Furthermore, the video processing device further includes:

[0133] A route trajectory acquisition module, used to acquire speed information and coordinate information corresponding to each character information in the second overlapping character information, and determine a target route trajectory in a preset route trajectory based on the speed information and coordinate information;

[0134] The second video adjustment module is used to adjust the first slow-motion character information toward the outer track of the main stadium in the first synthetic video based on the target route trajectory to obtain the target video.

[0135] Furthermore, the video processing device further includes:

[0136] an adjustment number acquisition module, configured to acquire third slow character information in the first overlapping character information and a second adjustment number corresponding to the third slow character information if it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and first overlapping character information exists between the first character information and the second character information of the first composite video;

[0137] The third video adjustment module is used to adjust the third slow-motion character information toward the inner track in the first synthetic video based on the second integer number and the preset body position to obtain the target video.

[0138] Furthermore, the adjustment module is also used to:

[0139] If the first overlapping character information exists, assigning the first overlapping character information to the outer track of the main stadium in the first composite video to obtain a second composite video;

[0140] If there is a difference between the synthesized character information corresponding to the second character information in the second synthesized video and the second character information, obtaining the difference character information;

[0141] Acquire a plurality of character information to be replaced corresponding to the difference character information, and determine character information to be synthesized based on the character information to be replaced;

[0142] Based on the coordinate information to be replaced of the character information to be synthesized, the difference character information in the second synthesized video is replaced with the character information to be synthesized to obtain the target video.

[0143] The methods executed by the above-mentioned program units can refer to the various embodiments of the video processing method of the present invention, and will not be described in detail here.

[0144] The present invention also provides a computer-readable storage medium.

[0145] The computer-readable storage medium of the present invention stores a video processing program, and when the video processing program is executed by a processor, the steps of the video processing method described above are implemented.

[0146] The method implemented when the video processing program running on the processor is executed can refer to the various embodiments of the video processing method of the present invention, and will not be described in detail here.

[0147] In addition, an embodiment of the present invention further provides a computer program product, which includes a video processing program. When the video processing program is executed by a processor, the steps of the video processing method described above are implemented.

[0148] 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 system 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 system. 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 system including the element.

[0149] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0150] 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 is essentially 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) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0151] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A video processing method, characterized in that: The video processing method comprises the following steps: Acquire the first character information in the first video corresponding to the main arena and the first coordinate information corresponding to the first character information, and acquire the second character information in the second video corresponding to the sub-arena and the second coordinate information corresponding to the second character information; Based on the first character information, the first coordinate information, the second character information and the second coordinate information, synthesizing the second character information into the first video to obtain a first synthesized video; If it is determined based on the first coordinate information that the first character information is located at the starting position of the main stadium, determining whether there is overlapping first overlapping character information between the first character information and the second character information of the first composite video; If the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video to obtain the target video.

2. The video processing method according to claim 1, characterized in that: After the step of synthesizing the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain a first synthesized video, the method further includes: If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information between the first character information and the second character information of the first composite video, then obtaining a first speed corresponding to the first character information and a second speed corresponding to the second character information; If it is determined based on the first speed and the second speed that there is a predicted overlap between the person corresponding to the first person information and the person corresponding to the second person information at the preset moment, then second overlapping person information is determined in the first person information and the second person information of the first composite video based on the predicted overlap; The first slow-motion character information in the second overlapping character information is obtained, and the first slow-motion character information is adjusted in the first composite video to obtain the target video.

3. The video processing method according to claim 2, characterized in that: The step of acquiring a first speed corresponding to the first character information and a second speed corresponding to the second character information comprises: If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is no first overlapping character information in the first character information and the second character information of the first composite video, then determining whether there is third overlapping character information corresponding to the predicted overlapping phenomenon in the first character information and the second character information; If the third overlapping character information exists, obtaining the second slow character information in the third overlapping character information and the first adjustment number corresponding to the second slow character information, and adjusting the second slow character information in the first composite video based on the first adjustment number to obtain the target video; If the third overlapping character information does not exist, a first speed corresponding to the first character information and a second speed corresponding to the second character information are acquired.

4. The video processing method according to claim 3, characterized in that: The step of adjusting the second slow-motion character information in the first composite video based on the first adjustment number to obtain the target video comprises: When the position of the second slow-motion person information does not reach the overlapping position corresponding to the predicted overlapping phenomenon, based on the first adjustment times and the preset body position, the second slow-motion person information is adjusted toward the outer track in the first synthetic video to obtain the target video; When the position reaches the overlapping position, based on the first adjustment times and the preset body position, the second slow-motion character information is adjusted toward the inner track of the main stadium in the first composite video to obtain the target video.

5. The video processing method according to claim 2, characterized in that: After the step of determining the second overlapping character information in the first character information and the second character information of the first synthesized video based on the predicted overlapping phenomenon, the method further includes: Acquire speed information and coordinate information corresponding to each character information in the second overlapping character information, and determine a target route trajectory in a preset route trajectory based on the speed information and coordinate information; Based on the target route trajectory, the first slow-motion character information is adjusted toward the outer track of the main stadium in the first synthetic video to obtain the target video.

6. The video processing method according to claim 1, characterized in that: After the step of synthesizing the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain a first synthesized video, the method further includes: If it is determined based on the first coordinate information that the first character information is located at a non-starting position of the main stadium, and there is first overlapping character information in the first character information and the second character information of the first composite video, then obtaining third slow character information in the first overlapping character information and a second adjustment number corresponding to the third slow character information; The third slow-motion character information is adjusted toward the inner track in the first synthetic video based on the second adjustment number and the preset body position to obtain the target video.

7. The video processing method according to any one of claims 1 to 6, characterized in that: If the first overlapping character information exists, the first overlapping character information is allocated to the outer track of the main stadium in the first composite video, and the step of obtaining the target video includes: If the first overlapping character information exists, assigning the first overlapping character information to the outer track of the main stadium in the first composite video to obtain a second composite video; If there is a difference between the synthesized character information corresponding to the second character information in the second synthesized video and the second character information, obtaining the difference character information; Acquire a plurality of character information to be replaced corresponding to the difference character information, and determine character information to be synthesized based on the character information to be replaced; Based on the coordinate information to be replaced of the character information to be synthesized, the difference character information in the second synthesized video is replaced with the character information to be synthesized to obtain the target video.

8. A video processing device, characterized in that: The video processing device comprises: An acquisition module, used to acquire first character information in a first video corresponding to a main venue and first coordinate information corresponding to the first character information, and acquire second character information in a second video corresponding to a sub-venue and second coordinate information corresponding to the second character information; A synthesis module, configured to synthesize the second character information into the first video based on the first character information, the first coordinate information, the second character information and the second coordinate information to obtain a first synthesized video; a determination module, configured to determine whether there is overlapping first overlapping character information between the first character information and the second character information of the first composite video if it is determined based on the first coordinate information that the first character information is located at the starting position of the main playing field; The adjustment module is used to allocate the first overlapping character information to the outer track of the main stadium in the first composite video if the first overlapping character information exists, so as to obtain a target video.

9. A video processing device, characterized in that: The video processing device comprises: a memory, a processor, and a video processing program stored in the memory and executable on the processor, wherein the video processing program implements the steps of the video processing method according to any one of claims 1 to 7 when executed by the processor.

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

Images