CN113888588A - Target tracking method, device, equipment and storage medium - Google Patents
Target tracking method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113888588A CN113888588A CN202111035847.XA CN202111035847A CN113888588A CN 113888588 A CN113888588 A CN 113888588A CN 202111035847 A CN202111035847 A CN 202111035847A CN 113888588 A CN113888588 A CN 113888588A
- Authority
- CN
- China
- Prior art keywords
- tracking
- target
- range
- position information
- video frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000001514 detection method Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000001960 triggered effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006748 scratching Methods 0.000 description 2
- 230000002393 scratching effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a target tracking method, a device, equipment and a storage medium, which relate to the technical field of computer vision, and the method comprises the following steps: acquiring a tracking range and a moving target in the tracking range in a video frame image; determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target; predicting a motion track according to a current video frame image and a next video frame image so as to track a first tracking target in real time or stop tracking; and after the first tracking target is stopped tracking, triggering to continue tracking, returning to the step of determining the tracking target according to the position information of the moving target and the position information of the tracking range so as to obtain a second tracking target, and tracking the second tracking target in real time. The invention solves the problem of lower tracking accuracy when the target tracking method in the prior art tracks athletes in a sports field, and realizes the effects of improving the tracking accuracy and preventing invalid tracking.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a target tracking method, a target tracking device, target tracking equipment and a storage medium.
Background
The target tracking technology is always one of the hot spots in the field of computer vision, and has a wide application prospect in many aspects. Currently, in the aspect of intelligent video monitoring, such as monitoring for players in sports events, target tracking technology is also introduced, and especially in the aspect of playing against sports events, such as football, basketball, ice hockey and other events, the motion state of each player needs to be monitored.
At present, the method for tracking the players in the sports field is easy to identify the spectators at the field as the players by mistake, track the targets of the spectators at the field, and also easily cause the situation that the tracked targets are lost when the speeds of the players are too fast or the players are crowded together. Therefore, the target tracking method in the prior art has the problem of low tracking accuracy.
Disclosure of Invention
The main purposes of the invention are as follows: the invention provides a target tracking method, a target tracking device, target tracking equipment and a storage medium, and aims to solve the technical problem that tracking accuracy is low when a sportsman in a sports field is tracked by a target tracking method in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a target tracking method, including:
acquiring a tracking range in a video frame image and a moving target in the tracking range;
determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target;
predicting a motion track according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking;
and after the first tracking target is stopped tracking, triggering to continue tracking, returning the position information according to the moving target and the position information of the tracking range, determining the tracking target to obtain a second tracking target, and tracking the second tracking target in real time.
Optionally, in the target tracking method, the step of acquiring the moving target within the tracking range specifically includes:
and detecting in the tracking range by using a target detection model to obtain the moving target and the position information thereof.
Optionally, in the target tracking method, the step of determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target specifically includes:
obtaining a central point of the tracking range according to the position information of the tracking range;
obtaining a distance ratio corresponding to the moving target according to the distance from a first vertex of the moving target detection frame to the central point and the distance from a second vertex of the tracking range to the central point, wherein the first vertex and the second vertex are located at the same position;
judging whether the distance ratio is smaller than a preset threshold value or not, wherein the preset threshold value is obtained based on the aspect ratio of the tracking range;
and if the distance ratio is smaller than a preset threshold value, determining that the moving target is a first tracking target.
Optionally, in the target tracking method, after the step of determining a tracking target according to the position information of the moving target and the position information of the tracking range and obtaining a first tracking target, the method further includes:
classifying the first tracking targets to obtain different types of first tracking targets;
and carrying out differential display on the tracking frames of the first tracking targets of different types in the video frame images.
Optionally, in the target tracking method, the step of classifying the first tracking targets to obtain different categories of first tracking targets specifically includes:
expanding the preset multiple of the tracking frame of the first tracking target to obtain an expanded tracking frame;
picking out the first tracking target from the expanded tracking frame to obtain a picked-out target;
and inputting the scratched targets into a target classification model, outputting the categories corresponding to the scratched targets, and obtaining first tracking targets of different categories.
Optionally, in the target tracking method, the step of predicting a motion trajectory according to a current video frame image and a next video frame image to perform real-time tracking or stop tracking on the first tracking target specifically includes:
obtaining a motion offset according to a central point of the tracking frame of the first tracking target in the current video frame image and a central point of the tracking frame of the first tracking target in the next video frame image;
judging whether the motion offset is within a preset threshold range or not and whether the distance ratio corresponding to the first tracking target is smaller than a preset threshold or not;
if the motion offset is within a preset threshold range and the distance ratio corresponding to the first tracking target is smaller than a preset threshold, judging that the motion trail prediction result of the first tracking target is that the first tracking target normally moves within the tracking range, and tracking the first tracking target in real time;
if the motion offset is within a preset threshold range, but the distance ratio corresponding to the first tracking target is not smaller than a preset threshold value, judging that the motion trail prediction result of the first tracking target is that the first tracking target is not within the tracking range, and stopping tracking the first tracking target;
if the motion offset is not within the preset threshold range, but the distance ratio corresponding to the first tracking target is smaller than the preset threshold, determining that the motion trajectory prediction result of the first tracking target is that the first tracking target is tracking abnormally within the tracking range, and stopping tracking the first tracking target.
Optionally, in the target tracking method, the step of triggering continuous tracking specifically includes:
identifying special events occurring in the tracking range and corresponding event duration;
when the special event is identified to be ended or the event duration is identified to be ended, judging whether the current timing duration is within a preset duration range or not and whether the number of first tracking targets in the tracking range reaches a preset target number or not;
if the current timing duration is within a preset duration range and the number of the first tracking targets in the tracking range reaches a preset target number, judging that a continuous tracking triggering condition is met, and triggering continuous tracking;
and if the current timing duration is within a preset duration range, but the number of the first tracking targets in the tracking range does not reach the preset target number, returning to the step of identifying the special events occurring in the tracking range, and continuously monitoring the special events.
In a second aspect, the present invention provides a target tracking apparatus, the apparatus comprising:
the tracking range acquisition module is used for acquiring a tracking range in a video frame image and a moving target in the tracking range;
the tracking target determining module is used for determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target;
the real-time tracking module is used for predicting a motion trail according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking;
and the association tracking module is used for triggering continuous tracking after the first tracking target stops tracking, returning the step of determining the tracking target according to the position information of the moving target and the position information of the tracking range so as to obtain a second tracking target, and tracking the second tracking target in real time.
In a third aspect, the present invention provides an object tracking device comprising a processor and a memory, the memory having stored therein a computer program which, when executed by the processor, implements an object tracking method as described above.
In a fourth aspect, the present invention provides a storage medium having stored thereon a computer program executable by one or more processors to implement a target tracking method as described above.
One or more technical solutions provided by the present invention may have the following advantages or at least achieve the following technical effects:
according to the target tracking method, the target tracking device, the target tracking equipment and the storage medium, the tracking range and the moving target in the tracking range are obtained, and personnel in the moving field and the moving field are identified; determining a first tracking target according to the position information of the moving target and the position information of the tracking range, identifying athletes in the sports field, and preventing the audience from being identified as the athletes by mistake; then, according to the current video frame image and the next video frame image, motion trail prediction is carried out, real-time tracking or stopping tracking is carried out on the athletes, so that the situation that the athletes leave the sports ground due to error tracking can be prevented, the system calculation power is wasted, the tracking of the athletes leaving the sports ground can be stopped in time, the system calculation amount is prevented from being increased, and the system resources are prevented from being wasted; and a second tracking target is obtained by triggering continuous tracking, and the second tracking target is tracked in real time, so that the tracking target is prevented from being lost. The invention screens the moving target which meets the condition, and then carries out real-time tracking after determining the tracking target, thereby improving the tracking accuracy and preventing invalid tracking.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of a first embodiment of a target tracking method according to the present invention;
FIG. 2 is a schematic diagram of a hardware configuration of a target tracking device according to the present invention;
FIG. 3 is a graph illustrating the effectiveness of a prior art tracking method in tracking an athlete;
FIG. 4 is a diagram of another effect of a prior art tracking method on tracking an athlete;
FIG. 5 is a flowchart illustrating a second embodiment of a target tracking method according to the present invention;
fig. 6 is an effect diagram of the step S10 of obtaining the tracking range in the second embodiment of the target tracking method according to the present invention;
fig. 7 is a diagram illustrating an effect when the tracking target is determined at step S30 in the second embodiment of the target tracking method according to the present invention;
FIG. 8 is a simplified schematic of FIG. 7;
fig. 9 is a functional block diagram of the target tracking apparatus according to the first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, in the embodiment of the present invention, all the directional indications (such as up, down, left, right, front, and rear … …) are only used to explain the relative positional relationship between the components, the movement condition, and the like in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indication is changed accordingly.
In the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element. In addition, in the present invention, unless explicitly stated or limited otherwise, the terms "connected," "fixed," and the like are to be construed broadly, e.g., "connected" may be fixedly connected, or detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium; either internally or in interactive relation.
In the present invention, if there is a description referring to "first", "second", etc., the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicit indication of the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the present invention, suffixes such as "module", "part", or "unit" used to represent elements are used only for facilitating the description of the present invention, and have no specific meaning in themselves. Thus, "module", "component" or "unit" may be used mixedly.
The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations. In addition, the technical solutions of the respective embodiments may be combined with each other, but must be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should be considered to be absent and not be within the protection scope of the present invention.
The analysis of the prior art shows that the current method for tracking athletes in a sports field generally comprises the steps of acquiring a first frame of a video, detecting a target and acquiring a tracking target and a boundary frame thereof; then obtaining the image characteristics and the motion characteristics of each tracking target, calculating the similarity, and judging the probability that the two tracking targets belong to the same target; and finally, associating the tracking targets, assigning a numerical ID to each tracking target, and performing tracking display, wherein the tracking effect is as shown in FIG. 3 and FIG. 4. As can be seen from fig. 3, when the prior tracking method tracks the athlete, the spectator at the court is easily identified as the athlete by mistake, and the spectator at the court is also tracked, which easily causes the problems of increasing the system computing power and wasting resources. As can be seen from fig. 4, athletes in a sports event may be crowded together due to their fast movement speed, and at this time, it is difficult to distinguish the team to which the athlete belongs, and the tracking target is easily lost, and only after the tracking target is staggered, target recognition and tracking may be resumed, but during this period, the data of the target may not be synchronized, and thus, there may be an error in the subsequent monitoring data of the target.
In view of the technical problem that the tracking accuracy is low when the target tracking method in the prior art is used for tracking athletes in a sports field, the invention provides a target tracking method, which has the following general idea:
acquiring a tracking range in a video frame image and a moving target in the tracking range; determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target; predicting a motion track according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking; and after the first tracking target is stopped tracking, triggering to continue tracking, returning the position information according to the moving target and the position information of the tracking range, determining the tracking target to obtain a second tracking target, and tracking the second tracking target in real time.
By the technical scheme, the tracking range and the moving target in the tracking range are obtained, and the moving field and personnel in the moving field are identified; determining a first tracking target according to the position information of the moving target and the position information of the tracking range, identifying athletes in the sports field, and preventing the audience from being identified as the athletes by mistake; then, according to the current video frame image and the next video frame image, motion trail prediction is carried out, real-time tracking or stopping tracking is carried out on the athletes, so that the situation that the athletes leave the sports ground due to error tracking can be prevented, the system calculation power is wasted, the tracking of the athletes leaving the sports ground can be stopped in time, the system calculation amount is prevented from being increased, and the system resources are prevented from being wasted; and a second tracking target is obtained by triggering continuous tracking, and the second tracking target is tracked in real time, so that the tracking target is prevented from being lost. The invention screens the moving target which meets the condition, and then carries out real-time tracking after determining the tracking target, thereby improving the tracking accuracy and preventing invalid tracking.
Example one
Referring to the flowchart illustration of fig. 1, a first embodiment of the target tracking method of the present invention is proposed, which is applied to a target tracking device.
The target tracking device is a terminal device or a network device capable of realizing network connection, and may be a terminal device such as a mobile phone, a computer, a tablet computer, a portable computer, or a network device such as a server and a cloud platform.
Fig. 2 is a schematic diagram of a hardware structure of the target tracking device. The apparatus may include: a processor 1001, such as a CPU (Central Processing Unit), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.
Those skilled in the art will appreciate that the hardware configuration shown in FIG. 2 is not intended to be limiting of the subject tracking device and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
Specifically, the communication bus 1002 is used for realizing connection communication among these components;
the user interface 1003 is used for connecting a client and performing data communication with the client, the user interface 1003 may include an output unit, such as a display screen, an input unit, such as a keyboard, and optionally, the user interface 1003 may further include other input/output interfaces, such as a standard wired interface and a wireless interface;
the network interface 1004 is used for connecting to the backend server and performing data communication with the backend server, and the network interface 1004 may include an input/output interface, such as a standard wired interface, a wireless interface, such as a Wi-Fi interface;
the memory 1005 is used for storing various types of data, which may include, for example, instructions of any application program or method in the target tracking device and application program-related data, and the memory 1005 may be a high-speed RAM memory, or a stable memory such as a disk memory, and optionally, the memory 1005 may be a storage device independent of the processor 1001;
specifically, with continued reference to fig. 2, the memory 1005 may include an operating system, a network communication module, a user interface module, and a computer program, wherein the network communication module is mainly used for connecting to a server and performing data communication with the server;
the processor 1001 is used to call up a computer program stored in the memory 1005 and perform the following operations:
acquiring a tracking range in a video frame image and a moving target in the tracking range;
determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target;
predicting a motion track according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking;
and after the first tracking target is stopped tracking, triggering to continue tracking, returning the position information according to the moving target and the position information of the tracking range, determining the tracking target to obtain a second tracking target, and tracking the second tracking target in real time.
Based on the above target tracking device, the target tracking method of the present embodiment is described in detail below with reference to the flowchart shown in fig. 1. The method may comprise the steps of:
step S10: and acquiring a tracking range in a video frame image and a moving target in the tracking range.
Specifically, a video stream is obtained, a tracking range is marked in a video frame image of the video stream according to the shape characteristics of a motion field, and position information of the tracking range is obtained, namely the motion field is identified; then, in the tracking range, the target detection model is used to detect the moving target, for example, in the moving field, there are not only the players, but also the articles such as the billboard and the moving equipment, and the articles need to be excluded to ensure that the identified moving target is a person, that is, to identify the person in the moving field.
Step S30: and determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target.
Specifically, in the video frame image, after the tracking range is identified, the tracking range may be framed by using the corresponding detection frame, and after the moving object is identified, the moving object may also be framed by using the object frame. The method comprises the steps of calculating the center point of a tracking range after a frame is determined, calculating the distance between the vertex of a target frame and the center point and the distance between the vertex of a detection frame and the center point, wherein the detection frame and the vertex of the target frame are positioned in the same direction, judging whether the ratio of the two distances is smaller than a preset value or not, if so, indicating that the moving target in the target frame is the tracking target, namely identifying a sportsman in a sports field, preventing audience from being identified as the sportsman by mistake, otherwise, indicating that the moving target can be a judge or a scorer and the like, and non-sportsman persons positioned in the tracking range cannot track the persons subsequently. In this way, all players in the sports field, i.e. the first tracked object in the tracking range, can be obtained.
Step S50: and predicting a motion trail according to the current video frame image and the next video frame image so as to track the first tracking target in real time or stop tracking.
Specifically, after the first tracking target is identified, the tracking range and the first tracking target identification of the next video frame image are not needed, the first tracking target of the current video frame image is directly associated with the tracking target of the next video frame image to obtain a predicted tracking frame of the tracking target, namely, the motion track prediction is performed, then the motion offset between the tracking frame of the first tracking target in the current video frame image and the predicted tracking frame in the next video frame image is calculated, so that whether the tracking target corresponding to the prediction frame is the same as the first tracking target marked by the current video frame image is judged, and therefore, the first tracking target is continuously tracked, namely, the real-time tracking of the first tracking target is realized, the situation that the tracking is mistakenly tracked to the audience is avoided, and the system calculation power is wasted.
When a player needs to leave the sports field, for example, replace the player, the position of the first tracking target predicted according to the motion track is within the tracking range, and if the position of the first tracking target is not within the tracking range, the player leaves the sports field, and the tracking of the player is stopped, namely the tracking of the first tracking target is stopped. The tracking of the athletes leaving the sports ground is stopped in time, thereby preventing the increase of system calculation amount and the waste of system resources.
Step S70: and after the first tracking target is stopped tracking, triggering to continue tracking, returning the position information according to the moving target and the position information of the tracking range, determining the tracking target to obtain a second tracking target, and tracking the second tracking target in real time.
Specifically, for the condition of stopping tracking, whether the trigger condition for continuing tracking is met is judged, if yes, the tracking range does not need to be identified, and only the step S30 needs to be returned, the tracking target is determined according to the moving target in the tracking range, and the second tracking target is obtained. Then, the steps S50 and S70 are executed in a recycling manner, so that the loss of the tracking target does not occur. That is, under the condition of replacing the athlete, when the previous athlete leaves the field, the tracking of the previous athlete is stopped, and when the replacement athlete leaves the field, the tracking is triggered to continue, the replacement athlete and the corresponding tracking frame are determined, the tracking is carried out in real time, and the tracking target is prevented from being lost.
According to the target tracking method provided by the embodiment, the moving field and personnel in the moving field are identified by acquiring the tracking range and the moving target in the tracking range; determining a first tracking target according to the position information of the moving target and the position information of the tracking range, identifying athletes in the sports field, and preventing the audience from being identified as the athletes by mistake; then, according to the current video frame image and the next video frame image, motion trail prediction is carried out, real-time tracking or stopping tracking is carried out on the athletes, so that the situation that the athletes leave the sports ground due to error tracking can be prevented, the system calculation power is wasted, the tracking of the athletes leaving the sports ground can be stopped in time, the system calculation amount is prevented from being increased, and the system resources are prevented from being wasted; and a second tracking target is obtained by triggering continuous tracking, and the second tracking target is tracked in real time, so that the tracking target is prevented from being lost. The invention screens the moving target which meets the condition, and then carries out real-time tracking after determining the tracking target, thereby improving the tracking accuracy and preventing invalid tracking.
Example two
Based on the same inventive concept, referring to fig. 5, a second embodiment of the target tracking method of the present invention is proposed, which is applied to a target tracking apparatus.
The following describes the target tracking method in detail with reference to the flowchart shown in fig. 5. The method may comprise the steps of:
step S10: and acquiring a tracking range in a video frame image and a moving target in the tracking range.
Specifically, the step S10 may include:
step S11: acquiring a video frame image;
step S12: and according to the video frame image, carrying out range identification to obtain a tracking range and position information thereof in the video frame image.
Specifically, a sports field in the video frame image is identified, a corresponding tracking range is obtained by using a circumscribed polygon, such as a rectangle or an ellipse, of the sports field according to the shape characteristics of the sports field, a detection frame of the tracking range in the video frame image is also obtained, and position information, such as coordinate information, of four vertexes of a rectangle corresponding to the minimum circumscribed rectangle or the minimum inscribed ellipse of the tracking range is recorded. Fig. 6 is a diagram showing the effect of the tracking range obtained in the present embodiment, in which the sports field is rectangular, and after the sports field in the image is recognized, the rectangular tracking range is obtained as shown in the figure.
Step S13: and detecting in the tracking range by using a target detection model to obtain the moving target and the position information thereof.
Specifically, after the moving object is obtained, a detection frame corresponding to the moving object in the video frame image is also obtained. After the sports ground is determined, the interference of obstacles in the sports ground, such as articles like sports equipment and advertising boards, is eliminated, people in the articles, such as athletes, scorers, referees and the like in the tracking range, are identified, the sports target is obtained, and position information of the sports target, such as coordinate information, is obtained. The target detection model is actually an object recognition model, a lightweight model module can be selected for building, the existing deep learning recognition algorithm is used for training, the trained recognition model is directly used, namely, a video frame image of a detection frame marking a tracking range is input into the target detection model, all moving targets in the tracking range in the video frame image are output, and the video frame image of the detection frame marking all people is obtained.
Step S30: and determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target.
In order to track the athlete in real time and prevent the target from being lost, the athlete is detected within the tracking range obtained in step S10.
Specifically, the step S30 may include:
step S31: obtaining a central point of the tracking range according to the position information of the tracking range;
step S32: obtaining a distance ratio corresponding to the moving target according to the distance from a first vertex of the moving target detection frame to the central point and the distance from a second vertex of the tracking range to the central point, wherein the first vertex and the second vertex are located at the same position;
step S33: judging whether the distance ratio is smaller than a preset threshold value or not, wherein the preset threshold value is obtained based on the aspect ratio of the tracking range;
step S34: and if the distance ratio is smaller than a preset threshold value, determining that the moving target is a first tracking target.
In this embodiment, moving object detection is performed on the video frame image of fig. 6, a tracking object is determined, and an obtained effect graph is shown in fig. 7. For ease of viewing, the tracking range and the moving object in the video frame image of fig. 7 are simplified, resulting in a simplified schematic diagram as shown in fig. 8. In the figure, I denotes a detection frame of a moving object, and S denotes a detection frame of a tracking range.
According to the steps, a central point O of the sports field is obtained, then, whether the moving target is a tracking target or not is determined according to the top left corner vertex position information of I and the top left corner vertex position information of S, and specifically, according to the distance L from the top left corner vertex of I to the central point O and the distance L from the top left corner vertex of S to the central point O, a distance ratio corresponding to the moving target is obtained; then, whether the distance ratio is smaller than a preset value is judged, the preset value is obtained based on the aspect ratio of the tracking range, and because the tracking range may be larger than the actual sports field, a preset threshold value can be set based on the actual situation, the detection area is reduced, an ROI (Region of Interest) is obtained, and the detection speed can be improved. If the calculated distance ratio is smaller than the preset threshold value, the moving target is in the ROI area and is an athlete in the actual moving field, and if the calculated distance ratio is not smaller than the preset threshold value, the moving target is not the athlete and does not need to be tracked subsequently.
Step S40: the first tracking target is classified to be displayed distinctively in the video frame image.
Specifically, after all athletes in the sports field are identified, the existing method is to directly mark all athletes in a unified way.
Specifically, the step S40 may include:
step S41: and classifying the first tracking targets to obtain different types of first tracking targets.
More specifically, the step S41 may include:
step S41.1: expanding the preset multiple of the tracking frame of the first tracking target to obtain an expanded tracking frame;
step S41.2: picking out the first tracking target from the expanded tracking frame to obtain a picked-out target;
step S41.3: and inputting the scratched targets into a target classification model, outputting the categories corresponding to the scratched targets, and obtaining first tracking targets of different categories.
Step S42: and carrying out differential display on the tracking frames of the first tracking targets of different types in the video frame images.
In this embodiment, the first tracked targets of different categories are athletes belonging to different teams. The tracking frame of the first tracking target is expanded, for example, the expansion is 1.4 times on the original basis, and the external rectangular frame of the original tracking target is expanded into the expanded tracking frame which completely contains the tracking target. And then, based on the tracking frame, carrying out character image extraction on the athletes in the frame, inputting the extracted character images into a target classification model, and obtaining the belonged class of the tracking target, namely the belonged team of the athletes. After the categories of all the first tracking targets are identified and classified, the first tracking targets with different categories are obtained, namely athletes belonging to different teams are obtained, and tracking frames of the tracking targets are displayed in a distinguishing mode, namely the athletes of different teams are represented in different colors. The players belonging to one team are marked by the tracking frames with the same color, so that the players of the same team can be better tracked for the competition-type game, the players of the other team can be distinguished, and the tracking loss can be prevented. When the tracking frames of the athletes are overlapped in the video frame images, the tracking frames can be distinguished according to the identity information of the athletes, namely the team.
Step S50: and predicting a motion trail according to the current video frame image and the next video frame image so as to track the first tracking target in real time or stop tracking.
Specifically, the athlete position information and the athlete classification information in the first frame of video frame image can be used to associate the corresponding athlete in the next frame of video frame image, so as to predict the movement track, and thus, the athlete can be tracked in real time or stopped tracking.
Specifically, the step S50 may include:
step S51: and obtaining the motion offset according to the central point of the tracking frame of the first tracking target in the current video frame image and the central point of the tracking frame of the first tracking target in the next video frame image.
And calculating to obtain the movement offset according to the distance between the center point of the athlete tracking frame in the current video frame image and the center point of the corresponding athlete tracking frame in the next video frame image.
Step S52: and judging whether the motion offset is within a preset threshold range or not and whether the distance ratio corresponding to the first tracking target is smaller than a preset threshold or not.
The preset threshold range of the motion offset can be determined for different motion types according to actual conditions.
Step S53: if the motion offset is within a preset threshold range and the distance ratio corresponding to the first tracking target is smaller than a preset threshold, judging that the motion trail prediction result of the first tracking target is that the first tracking target normally moves within the tracking range, and tracking the first tracking target in real time.
Specifically, the distance ratio here is a ratio of a distance between a first vertex of the tracking frame of the first tracking target and the center point of the tracking range to a distance between a second vertex of the tracking range, which is at the same orientation as the first vertex, and the center point of the tracking range. If the motion offset is within the preset threshold range, the athlete in the current video frame image and the athlete in the next video frame image belong to the same athlete, tracking is normal, if the distance ratio corresponding to the athlete is smaller than the preset threshold value, the athlete moves within the tracking range, namely, a motion track prediction result of the first tracking target moving normally within the tracking range is obtained, and correspondingly, the first tracking target is tracked in real time.
Step S54: if the motion offset is within a preset threshold range, but the distance ratio corresponding to the first tracking target is not smaller than a preset threshold, determining that the motion trail prediction result of the first tracking target is that the first tracking target is not within the tracking range, and stopping tracking the first tracking target.
Specifically, the tracking can be stopped when the motion trail prediction result determined for a plurality of times continuously indicates that the first tracking target is not in the tracking range, so that the condition that the athlete temporarily leaves the sports field to perform penalty ball and the like can be avoided, and the athlete can be prevented from stopping tracking. The number of times may be set according to a specific motion category.
Step S55: if the motion offset is not within the preset threshold range, but the distance ratio corresponding to the first tracking target is smaller than the preset threshold, determining that the motion trajectory prediction result of the first tracking target is that the first tracking target is tracking abnormally within the tracking range, and stopping tracking the first tracking target.
Specifically, if the motion offset is not within the preset threshold range, it indicates that the tracking frame may be misaligned or the tracked targets tracked before and after the tracking frame are inconsistent, but if the athlete corresponding to the tracking frame is still in the field, that is, the current situation indicates that the tracking is abnormal, the tracking of the tracking target is prevented from being continuously tracked incorrectly or influenced, and the tracking of the tracking target is stopped in time.
Specifically, if the motion offset is not within the preset threshold range, and the distance ratio corresponding to the first tracking target is not smaller than the preset threshold, at this time, a situation that tracking is abnormal or the athlete leaves the sports field may exist, and the tracking of the first tracking target is also stopped.
Step S70: and after the first tracking target is stopped tracking, triggering to continue tracking, returning the position information according to the moving target and the position information of the tracking range, determining the tracking target to obtain a second tracking target, and tracking the second tracking target in real time.
In the process of competition, the reason for stopping tracking the athlete is mainly due to the fact that some special events occur, such as the situations of half-time rest, active pause, athlete replacement and the like, when the special events are finished and the athlete returns to the court, the traditional method needs to execute the whole tracking method again, the stopping tracking of the method is not needed to be in a pause state, when the special events are finished, only the step of determining the athlete needs to be returned, the step of identifying the sports field and the like does not need to be executed, and therefore computing power and system resources are saved.
Specifically, the step S70 may include:
step S71: and after the first tracking target is stopped tracking, identifying a special event and a corresponding event duration which occur in the tracking range.
The competition items relate to the competition duration, trigger conditions for continuing tracking can be started by combining the timing condition of the competition duration, and the special events with time limit such as midcourt rest, active pause and the like can be directly judged to end by the corresponding event duration. For some emergencies, such as replacing replacement athletes, the end of the special events can be directly and manually monitored.
Step S72: when the special event is identified to be ended or the event duration is identified to be ended, judging whether the current timing duration is within a preset duration range or not and whether the number of the first tracking targets in the tracking range reaches the preset target number or not.
The preset time length range is different according to different sports items and is generally set by a conventional time length or allowable time supplement. Is an interval value, for example, the minimum value may be the regular time length of the game, and the maximum value may be the sum of the regular time length and the time length allowing time compensation. If the current special event is ended or the half time is reached, judging whether the continuous timing time is in the preset time range or not, namely judging whether the competition is ended or not, and judging whether the number of the athletes in the sports field reaches the preset target number or not, namely judging whether the number of the athletes in the field accords with the set number or not. The preset target number is determined according to an actual motion item.
Step S73: and if the current timing duration is within a preset duration range and the number of the first tracking targets in the tracking range reaches the preset target number, judging that a continuous tracking triggering condition is met, triggering continuous tracking, returning to the step of determining the tracking targets according to the position information of the moving targets and the position information of the tracking range to obtain second tracking targets, and tracking the second tracking targets in real time.
If the current timing duration is within the preset duration range, the competition is not finished, the number of players in the sports field accords with the set number, the players are in the sports field, namely the replacement players are on the field, at the moment, the condition of continuous tracking triggering is met, continuous tracking is triggered, the step S30 is returned, the tracking target is continuously determined, namely the second tracking target is obtained, and real-time tracking of the replacement players is realized.
Step S74: and if the current timing duration is within a preset duration range, but the number of the first tracking targets in the tracking range does not reach the preset target number, returning to the step of identifying the special events occurring in the tracking range, and continuously monitoring the special events.
If the current timing duration is within the preset duration range, the competition is not finished, but the number of players in the sports field does not accord with the set number, the players are not all in the sports field, namely, the replacement players may not get on the sports field, and other pages of special time may be available. At this point, the process may return to step S71 to continue listening for special events.
Specifically, if the current timing duration exceeds the preset duration range, the tracking is finished no matter whether the number of the first tracking targets reaches the preset target number, that is, the tracking is not required to be triggered to continue.
According to the target tracking method provided by the embodiment, the first tracking targets are classified, and the tracking frames of the first tracking targets of different categories are displayed in a distinguishing manner, so that athletes of different teams can be tracked better; according to the current video frame image and the next video frame image, motion trail prediction is carried out, and tracking of athletes leaving a sports ground or abnormal tracking conditions is stopped in time, so that the waste of computing power is avoided; and in the process of competition, when the number of athletes in the field is identified to reach the set number, the tracking is triggered to continue, so that the tracking target is prevented from being lost. The real-time tracking method and the real-time tracking system can accurately identify the athletes in the field, are high in real-time performance, and can quickly track the target.
EXAMPLE III
Based on the same inventive concept, referring to fig. 9, a first embodiment of the target tracking apparatus of the present invention is provided, which may be a virtual apparatus applied to a target tracking device.
The following describes in detail the target tracking apparatus provided in this embodiment with reference to a schematic functional block diagram shown in fig. 9, where the apparatus may include:
the tracking range acquisition module is used for acquiring a tracking range in a video frame image and a moving target in the tracking range;
the tracking target determining module is used for determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target;
the real-time tracking module is used for predicting a motion trail according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking;
and the association tracking module is used for triggering continuous tracking after the first tracking target stops tracking, returning the step of determining the tracking target according to the position information of the moving target and the position information of the tracking range so as to obtain a second tracking target, and tracking the second tracking target in real time.
Further, the tracking range acquisition module may include:
and the moving target detection unit is used for detecting in the tracking range by using a target detection model to obtain a moving target and position information thereof.
Further, the tracking target determination module may include:
the central point acquisition unit is used for acquiring the central point of the tracking range according to the position information of the tracking range;
a distance ratio obtaining unit, configured to obtain a distance ratio corresponding to the moving target according to a distance from a first vertex of the moving target detection frame to the central point and a distance from a second vertex of the tracking range to the central point, where the first vertex and the second vertex are located in the same direction;
the first judging unit is used for judging whether the distance ratio is smaller than a preset threshold value, wherein the preset threshold value is obtained based on the aspect ratio of the tracking range;
and the target determining unit is used for determining the moving target as a first tracking target if the distance ratio is smaller than a preset threshold value.
Further, the apparatus may further include:
the target classification module is used for classifying the first tracking targets to obtain different types of first tracking targets;
and the distinguishing display module is used for distinguishing and displaying the tracking frames of the first tracking targets of different types in the video frame image.
Still further, the object classification module may include:
the tracking frame processing unit is used for expanding the preset multiple of the tracking frame of the first tracking target to obtain an expanded tracking frame;
the object scratching unit is used for scratching the first tracking object from the expanded tracking frame to obtain a scratched object;
and the classification unit is used for inputting the scratched target into a target classification model, outputting the category corresponding to the scratched target and obtaining first tracking targets of different categories.
Further, the real-time tracking module may include:
the offset calculation unit is used for obtaining a motion offset according to the central point of the tracking frame of the first tracking target in the current video frame image and the central point of the tracking frame of the first tracking target in the next video frame image;
the second judging unit is used for judging whether the motion offset is within a preset threshold range or not and whether the distance ratio corresponding to the first tracking target is smaller than a preset threshold or not;
the real-time tracking unit is used for judging that the motion trail prediction result of the first tracking target is that the first tracking target normally moves in the tracking range and tracking the first tracking target in real time if the motion offset is within a preset threshold range and the distance ratio corresponding to the first tracking target is smaller than a preset threshold;
a stopping tracking unit, configured to, if the motion offset is within a preset threshold range, but a distance ratio corresponding to the first tracking target is not smaller than a preset threshold, determine that a motion trajectory prediction result of the first tracking target is that the first tracking target is not within the tracking range, and stop tracking the first tracking target;
and the tracking abnormity unit is used for judging that the motion trail prediction result of the first tracking target is that the first tracking target is abnormally tracked in the tracking range and stopping tracking the first tracking target if the motion offset is not in the preset threshold range but the distance ratio corresponding to the first tracking target is smaller than the preset threshold value.
Further, the association tracking module may include:
the special event identification unit is used for identifying special events occurring in the tracking range and corresponding event duration;
the trigger condition judging unit is used for judging whether the current timing time length is within a preset time length range or not and whether the number of first tracking targets in the tracking range reaches the preset target number or not when the special event is identified to be finished or the event time length timing is finished;
the continuous tracking triggering unit is used for judging that a continuous tracking triggering condition is met and triggering continuous tracking if the current timing duration is within a preset duration range and the number of the first tracking targets in the tracking range reaches a preset target number;
and the continuous monitoring event unit is used for returning to the step of identifying the special event occurring in the tracking range and continuously monitoring the special event if the current timing duration is within a preset duration range but the number of the first tracking targets in the tracking range does not reach the preset target number.
It should be noted that, for the functions that can be realized by each module in the target tracking apparatus and the corresponding achieved technical effects provided in this embodiment, reference may be made to the description of the specific implementation manner in each embodiment of the target tracking method of the present invention, and for the sake of brevity of the description, no further description is given here.
Example four
Based on the same inventive concept, the present embodiment provides an object tracking apparatus, which may include a processor and a memory, where the memory stores a computer program, and when the computer program is executed by the processor, the computer program implements all or part of the steps of the embodiments of the object tracking method of the present invention.
Specifically, the target tracking device refers to a terminal device or a network device capable of implementing network connection, and may be a terminal device such as a mobile phone, a computer, a tablet computer, and a portable computer, or may be a network device such as a server and a cloud platform.
It will be appreciated that the device may also include a communications bus, a user interface and a network interface.
Wherein the communication bus is used for realizing connection communication among the components.
The user interface is used for connecting the client and performing data communication with the client, and may include an output unit such as a display screen and an input unit such as a keyboard, and optionally may also include other input/output interfaces such as a standard wired interface and a wireless interface.
The network interface is used for connecting the background server and performing data communication with the background server, and the network interface may include an input/output interface, such as a standard wired interface, a wireless interface, such as a Wi-Fi interface.
The memory is used to store various types of data, which may include, for example, instructions for any application or method in the target tracking device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic or optical disk, or alternatively, the Memory may be a storage device independent of the processor.
The Processor may be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is configured to call a computer program stored in the memory and execute the target tracking method.
EXAMPLE five
Based on the same inventive concept, the present embodiment provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, the computer program being executable by one or more processors, the computer program, when executed by the processors, implementing all or part of the steps of the embodiments of the object tracking method of the present invention.
It should be noted that the above-mentioned serial numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
The above description is only an alternative embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method of target tracking, the method comprising:
acquiring a tracking range in a video frame image and a moving target in the tracking range;
determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target;
predicting a motion track according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking;
and after the first tracking target is stopped tracking, triggering to continue tracking, returning the position information according to the moving target and the position information of the tracking range, determining the tracking target to obtain a second tracking target, and tracking the second tracking target in real time.
2. The target tracking method according to claim 1, wherein the step of acquiring the moving target within the tracking range specifically includes:
and detecting in the tracking range by using a target detection model to obtain the moving target and the position information thereof.
3. The target tracking method according to claim 1, wherein the step of determining a tracking target and obtaining a first tracking target according to the position information of the moving target and the position information of the tracking range specifically includes:
obtaining a central point of the tracking range according to the position information of the tracking range;
obtaining a distance ratio corresponding to the moving target according to the distance from a first vertex of the moving target detection frame to the central point and the distance from a second vertex of the tracking range to the central point, wherein the first vertex and the second vertex are located at the same position;
judging whether the distance ratio is smaller than a preset threshold value or not, wherein the preset threshold value is obtained based on the aspect ratio of the tracking range;
and if the distance ratio is smaller than a preset threshold value, determining that the moving target is a first tracking target.
4. The target tracking method according to claim 1, wherein after the step of determining a tracking target based on the position information of the moving target and the position information of the tracking range and obtaining a first tracking target, the method further comprises:
classifying the first tracking targets to obtain different types of first tracking targets;
and carrying out differential display on the tracking frames of the first tracking targets of different types in the video frame images.
5. The target tracking method according to claim 4, wherein the step of classifying the first tracked target to obtain different classes of first tracked targets specifically comprises:
expanding the preset multiple of the tracking frame of the first tracking target to obtain an expanded tracking frame;
picking out the first tracking target from the expanded tracking frame to obtain a picked-out target;
and inputting the scratched targets into a target classification model, outputting the categories corresponding to the scratched targets, and obtaining first tracking targets of different categories.
6. The target tracking method according to claim 1, wherein the step of predicting the motion trajectory according to the current video frame image and the next video frame image to perform real-time tracking or stop tracking on the first tracking target specifically comprises:
obtaining a motion offset according to a central point of the tracking frame of the first tracking target in the current video frame image and a central point of the tracking frame of the first tracking target in the next video frame image;
judging whether the motion offset is within a preset threshold range or not and whether the distance ratio corresponding to the first tracking target is smaller than a preset threshold or not;
if the motion offset is within a preset threshold range and the distance ratio corresponding to the first tracking target is smaller than a preset threshold, judging that the motion trail prediction result of the first tracking target is that the first tracking target normally moves within the tracking range, and tracking the first tracking target in real time;
if the motion offset is within a preset threshold range, but the distance ratio corresponding to the first tracking target is not smaller than a preset threshold value, judging that the motion trail prediction result of the first tracking target is that the first tracking target is not within the tracking range, and stopping tracking the first tracking target;
if the motion offset is not within the preset threshold range, but the distance ratio corresponding to the first tracking target is smaller than the preset threshold, determining that the motion trajectory prediction result of the first tracking target is that the first tracking target is tracking abnormally within the tracking range, and stopping tracking the first tracking target.
7. The target tracking method of claim 1, wherein the step of triggering the continuation of tracking specifically comprises:
identifying special events occurring in the tracking range and corresponding event duration;
when the special event is identified to be ended or the event duration is identified to be ended, judging whether the current timing duration is within a preset duration range or not and whether the number of first tracking targets in the tracking range reaches a preset target number or not;
if the current timing duration is within a preset duration range and the number of the first tracking targets in the tracking range reaches a preset target number, judging that a continuous tracking triggering condition is met, and triggering continuous tracking;
and if the current timing duration is within a preset duration range, but the number of the first tracking targets in the tracking range does not reach the preset target number, returning to the step of identifying the special events occurring in the tracking range, and continuously monitoring the special events.
8. An object tracking apparatus, characterized in that the apparatus comprises:
the tracking range acquisition module is used for acquiring a tracking range in a video frame image and a moving target in the tracking range;
the tracking target determining module is used for determining a tracking target according to the position information of the moving target and the position information of the tracking range to obtain a first tracking target;
the real-time tracking module is used for predicting a motion trail according to a current video frame image and a next video frame image so as to track the first tracking target in real time or stop tracking;
and the association tracking module is used for triggering continuous tracking after the first tracking target stops tracking, returning the step of determining the tracking target according to the position information of the moving target and the position information of the tracking range so as to obtain a second tracking target, and tracking the second tracking target in real time.
9. An object tracking device, characterized in that the device comprises a memory and a processor, the memory having stored thereon a computer program which, when executed by the processor, carries out the object tracking method according to any one of claims 1 to 7.
10. A storage medium having stored thereon a computer program executable by one or more processors to implement the object tracking method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111035847.XA CN113888588A (en) | 2021-09-03 | 2021-09-03 | Target tracking method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111035847.XA CN113888588A (en) | 2021-09-03 | 2021-09-03 | Target tracking method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113888588A true CN113888588A (en) | 2022-01-04 |
Family
ID=79008238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111035847.XA Pending CN113888588A (en) | 2021-09-03 | 2021-09-03 | Target tracking method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113888588A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114501115A (en) * | 2022-02-12 | 2022-05-13 | 北京蜂巢世纪科技有限公司 | Cutting and reprocessing method, device, equipment and medium for court video |
| CN115475373A (en) * | 2022-09-14 | 2022-12-16 | 浙江大华技术股份有限公司 | Motion data display method and device, storage medium and electronic device |
| US20230148102A1 (en) * | 2021-11-10 | 2023-05-11 | Honda Motor Co., Ltd. | Systems and methods for predicting future data using diverse sampling |
| CN116433709A (en) * | 2023-04-14 | 2023-07-14 | 北京拙河科技有限公司 | Tracking method and device for sports ground monitoring |
-
2021
- 2021-09-03 CN CN202111035847.XA patent/CN113888588A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230148102A1 (en) * | 2021-11-10 | 2023-05-11 | Honda Motor Co., Ltd. | Systems and methods for predicting future data using diverse sampling |
| US11979590B2 (en) * | 2021-11-10 | 2024-05-07 | Honda Motor Co., Ltd. | Systems and methods for predicting future data using diverse sampling |
| CN114501115A (en) * | 2022-02-12 | 2022-05-13 | 北京蜂巢世纪科技有限公司 | Cutting and reprocessing method, device, equipment and medium for court video |
| CN114501115B (en) * | 2022-02-12 | 2023-07-28 | 北京蜂巢世纪科技有限公司 | Cutting and reprocessing method, device, equipment and medium for court video |
| CN115475373A (en) * | 2022-09-14 | 2022-12-16 | 浙江大华技术股份有限公司 | Motion data display method and device, storage medium and electronic device |
| CN115475373B (en) * | 2022-09-14 | 2024-02-02 | 浙江大华技术股份有限公司 | Display method and device of motion data, storage medium and electronic device |
| CN116433709A (en) * | 2023-04-14 | 2023-07-14 | 北京拙河科技有限公司 | Tracking method and device for sports ground monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113888588A (en) | Target tracking method, device, equipment and storage medium | |
| Figueroa et al. | Tracking soccer players aiming their kinematical motion analysis | |
| Chen et al. | Ball tracking and 3D trajectory approximation with applications to tactics analysis from single-camera volleyball sequences | |
| CN104102910B (en) | Sports video tactics Activity recognition method based on space-time local mode | |
| CN105183849B (en) | A kind of match Video Events detection of Snooker and semanteme marking method | |
| US20220198684A1 (en) | Player Trajectory Generation via Multiple Camera Player Tracking | |
| Chen et al. | Recognizing tactic patterns in broadcast basketball video using player trajectory | |
| US20100098307A1 (en) | Method and apparatus for detecting objects of interest in soccer video by color | |
| JP4886707B2 (en) | Object trajectory identification device, object trajectory identification method, and object trajectory identification program | |
| Liu et al. | MonoTrack: Shuttle trajectory reconstruction from monocular badminton video | |
| US20220277463A1 (en) | Tracking dynamics using a computerized device | |
| CN109308456B (en) | Target object information determination method, device, equipment and storage medium | |
| US20180374217A1 (en) | Ball detection and tracking device, system and method | |
| US11962873B2 (en) | Advertisement analysis system and method for sports broadcasting video using artificial intelligence | |
| US20210213351A1 (en) | Billiard monitoring and management system and method | |
| CN115661698A (en) | Escalator passenger abnormal behavior detection method, system, electronic device and storage medium | |
| US20210097289A1 (en) | A method and apparatus for user interaction with a video stream | |
| JP6653423B2 (en) | Play section extracting method and play section extracting apparatus | |
| CN115475373B (en) | Display method and device of motion data, storage medium and electronic device | |
| US20220164974A1 (en) | Information processing device, information processing method, and program | |
| Tahan et al. | A computer vision driven squash players tracking system | |
| CN108854031A (en) | The method and relevant apparatus of exercise data are analyzed by unmanned camera work | |
| Yu et al. | A player-possession acquisition system for broadcast soccer video | |
| Huang et al. | Shot and scoring events identification of basketball videos | |
| Lee et al. | Highlight generation for basketball video using probabilistic excitement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |