KR20220086940A - A Hybrid Object Tracking System and Method therefor - Google Patents

Abstract

The present invention relates to a system and method for tracking an object, comprising: an object information receiver configured to receive information on an object to be tracked in video data composed of a plurality of frames; and a location and a current frame of the object to be tracked in a previous frame of the video data A non-recognition tracking unit for tracking the movement of the object to be tracked using The present invention relates to an object tracking system and an object tracking method including a comprehensive tracking unit for generating a comprehensive tracking result based on a result and the tracking result of the non-recognized tracking unit.

Description

A Hybrid Object Tracking System and Method therefor

The present invention relates to a system and method for tracking an object, and to a system and method for enabling efficient and accurate movement tracking of an object in a process of tracking an object selected in an image.

As the technology for analyzing an image and providing a service based on it increases, the demand for a technology for recognizing a specific object in an image and tracking the movement of the recognized object in the image is increasing.

Among the conventional object tracking technologies in an image, a widely used technology is an object detection based tracking technology, which continuously recognizes an area having the characteristics of an object to be tracked in each of a plurality of frames constituting an image. By doing so, it is a technology that tracks how the object moves according to the time series flow in the image.

The prior art, Korean Patent Application Laid-Open No. 10-2016-0123647, "An apparatus and method for providing additional video information using object tracking" is a technology that enables various services to be provided using such an object recognition-based tracking technology. However, in the case of using such an object recognition tracking technology, it is necessary to perform a pre-learning operation on an object so that the characteristics of the object to be recognized can be identified. There is a problem that

In order to solve this problem, recently, non-recognition tracking technology that does not use object recognition has been developed. This technology, also called Visual Object Tracking (VOT), compares the image of the current frame with the previous frame. , a technology that checks how an object in the previous frame moved in the current frame based on artificial intelligence There is a problem that it is impossible to restore.

Korean Patent Publication No. 10-2016-0123647

The present invention uses a non-recognized tracking technology to effectively track the movement of an object, while tracking the movement of an object again even when the tracking of the object is stopped, such as when the object goes out of the screen and comes in. do.

An object of the present invention is to enable effective object tracking by using the object recognition tracking method supplementally when the reliability is low while tracking the object using the non-recognition tracking method.

An object of the present invention is to enable an object-recognized tracking method to be used only when the reliability of the non-recognized tracking method is low based on a reliability value, thereby enabling effective object tracking while minimizing computation.

When the non-recognition tracking method and the object recognition tracking method are simultaneously applied, an object of the present invention is to maximize tracking performance by creating a comprehensive tracking result by assigning weights to the tracking results of each method based on a reliability value.

In order to achieve this object, an object tracking system according to an embodiment of the present invention includes an object information receiving unit that receives information about an object to be tracked in video data composed of a plurality of frames, A non-recognition tracking unit for tracking the movement of the object to be tracked by using the location of the object and the current frame, an object recognition tracking unit for tracking the movement of the object by recognizing the object to be tracked for each frame of the video data, and and a comprehensive tracking unit for generating a comprehensive tracking result based on the tracking result of the object recognition tracking unit and the tracking result of the non-recognition tracking unit.

At this time,

The object recognition tracking unit and the non-recognition tracking unit calculate a tracking reliability value, respectively, and the comprehensive tracking unit obtains the weight of the tracking result of the object recognition tracking unit and the tracking result of the non-recognition tracking unit using the tracking reliability value, respectively , it is possible to create a comprehensive tracking result by reflecting this.

In addition, the comprehensive tracking unit obtains the weight of the tracking result of the non-recognition tracking unit based on the tracking reliability value of the non-recognition tracking unit, and based on the difference between the tracking reliability value of the object recognition tracking unit and the tracking reliability value of the non-recognition tracking unit The weight of the tracking result of the object recognition tracking unit may be obtained.

In addition, the object recognition tracking unit tracks the movement of the object to be tracked only when the tracking reliability value of the non-recognition tracking unit is less than or equal to a predetermined reference value, and the comprehensive tracking unit tracks the movement of the object recognition tracking unit when the object recognition tracking unit does not track the movement. The tracking result of the recognition tracking unit may be generated as a comprehensive tracking result.

In addition, the object recognition tracking unit checks whether the object to be tracked is a learned type of object based on the information on the object to be tracked, and tracks the movement of the object to be tracked only in the case of the learned type of object, and the synthesis The tracking unit may generate the non-recognition tracking unit tracking result as a comprehensive tracking result when the object recognition tracking unit does not track movement.

The present invention uses a non-recognized tracking technology to effectively track the movement of an object, while tracking the movement of an object again even when the tracking of the object is stopped, such as when the object goes out of the screen and then comes in.

The present invention enables effective object tracking by using the object recognition tracking method supplementally when the reliability is low while tracking the object using the non-recognition tracking method.

The present invention allows the object recognition tracking method to be used only when the reliability of the non-recognition tracking method is low based on the reliability value, thereby enabling effective object tracking while minimizing computation.

In the present invention, when the non-recognition tracking method and the object recognition tracking method are simultaneously applied, the tracking performance is maximized by assigning a weight to the tracking result of each method based on the reliability value to generate a comprehensive tracking result.

1 is a configuration diagram illustrating an internal configuration of an object tracking system according to an embodiment of the present invention.
2 is a diagram illustrating an example in which non-recognition tracking and object recognition tracking are applied according to an embodiment of the present invention.
3 is a flowchart illustrating a flow of an object tracking method according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, in describing the embodiments of the present invention, specific numerical values are merely examples and the scope of the invention is not limited thereby.

The object tracking system according to the present invention may be configured in the form of a server including a central processing unit (CPU) and a memory (Memory) and connectable to other terminals through a communication network such as the Internet. In addition, it may be implemented in a mobile terminal, an Internet of Things (IoT) device, etc., and independent operation is possible even in an environment in which a communication network such as the Internet is not connected. However, the present invention is not limited by the configuration of the central processing unit and the memory. In addition, the object tracking system according to the present invention may be physically configured as one device or may be implemented in a distributed form among a plurality of devices.

1 is a configuration diagram illustrating an internal configuration of an object tracking system according to an embodiment of the present invention.

As shown in the drawing, the object tracking system 101 according to an embodiment of the present invention includes an object information receiving unit 110 , a non-recognizing tracking unit 120 , an object recognition tracking unit 130 , and a comprehensive tracking unit 140 . ) may be included. Each component may be a software module operating in the same computer system physically, and may be configured so that two or more physically separated computer systems can operate in conjunction with each other. Embodiments fall within the scope of the present invention.

The object information receiving unit 110 receives information about an object to be tracked in video data composed of a plurality of frames. The moving image data provides a moving image by arranging a plurality of still image frames in time series and rapidly reproducing the still image according to the passage of time. In order to analyze such moving picture data, it is necessary to recognize an object included in the moving picture. For example, when CCTV detects an intruder, it is necessary to select the intruder as an object to track and identify the movement.

The information about the object to be tracked received by the object information receiving unit 110 may include location information where the object to be tracked is located in an image or range information indicating a range in which it exists, and additionally relates to the property of the object to be tracked. may contain information. For example, when the object to be tracked is a human face, by providing attribute information that the object to be tracked is a face, more accurate recognition may be possible when tracking an object through object recognition.

In order to receive information about an object to be tracked from the object information receiving unit 110, when a user tracks a desired object using an application, the user's mouse click or touch input is received to track the object at the corresponding location. Alternatively, when applied to intelligent CCTV, etc., an object in which abnormal behavior such as an intruder is detected may be automatically identified and selected as an object to be tracked, and information about the object may be received from the object information receiving unit 110 .

The non-recognition tracking unit 120 tracks the movement of the object to be tracked using the location of the object to be tracked in the previous frame of the video data and the current frame. Most of the conventional object tracking technologies have been to recognize an object in every frame of a video and track the location of the object. Because this is set, the tracking performance of tracking moving objects is not high. For example, in the case of tracking a human face, when the front of the face is exposed, it is possible to recognize that the part is a human face, but in the next scene, if the face rotates sideways or backwards, Since the face cannot be recognized in the frame of the scene in which the next face is turned back, tracking will fail.

Therefore, the non-recognition tracking unit 120 designs a network focusing on tracking, not recognition, and when an object exists in a certain position or range in the previous frame, how the object moves in the next frame By checking, it is possible to accurately determine the movement of objects between frames. That is, if the conventional object recognition-based tracking technology enables tracking by using a recognition technology, the technology of detecting the movement of an object in the previous frame and the current frame in the non-recognition tracking unit 120 is optimized for tracking the object. Therefore, it can be said that it is a technology that maximizes the tracking performance.

The technology for tracking by using the location information of the object in the previous frame and the current frame information in the non-recognition tracking unit 120 can be implemented through artificial intelligence, and various artificial intelligence algorithms for implementing this are being developed, In the present invention, it does not matter which method is applied. In general, such a technology for tracking objects without recognizing them is called Visual Object Tracking (VOT).

In the method of tracking an object in the non-recognized tracking unit 120, relatively accurate tracking is possible even when an object moving within the screen is deformed or rotated, and tracking performance is maximized by tracking using a network optimized for tracking. While there is an advantage of being able to do it, there is a problem that there is no way to track when an object goes out of the screen and then comes back.

The object recognition tracking unit 130 tracks the movement of the object by recognizing the object to be tracked for each frame of the video data. As described above, an object moving out of the screen cannot be tracked by the tracking method of the non-recognition tracking unit 120, but if an object is recognized every frame, when the object that has moved out of the screen returns, the object is recognized again. There are advantages to be found. Therefore, the object tracking system of the present invention uses the tracking technology of the non-recognition tracking unit 120 and the tracking technology based on frame-by-frame object recognition at the same time to compensate for each other's shortcomings.

In order for the object recognition tracking unit 130 to recognize an object for each frame, it is necessary to learn the characteristics of the object by using the learning data for the object to be recognized in advance. If a human face is selected as an object to be tracked, it is necessary to learn various human face images as learning data so that the human face part and other objects can be distinguished in the image. Accordingly, the object recognition tracking unit 130 checks information about the object to be tracked, determines whether the object to be tracked is a learned type of object, and tracks the movement of the object to be tracked only in the case of the learned type of object. can do.

The non-recognition tracking unit 120 and the object recognition tracking unit 130 may calculate a tracking reliability value together with a result of tracking an object, respectively. The object tracking algorithm using the position of the object in the previous frame and the current frame of the non-recognition tracking unit 120 and the object recognition-based tracking algorithm for each frame of the object recognition tracking unit 130 are all tracking reliability values according to the tracking results. can provide The tracking reliability value is a number indicating how accurate the tracking result is, and may be calculated to have a value between 0 and 1.

For example, in the algorithm of YOLO, which is one of the object recognition-based tracking methods in the object recognition tracking unit 130, the probability that the recognized object belongs to the class (classification) of the object is obtained, and the accuracy of the area where the object is located The reliability value can be obtained by obtaining the IOU (Intersection over Union) value representing , and multiplying these two. Since both the probability that the recognized object belongs to the class of the object and the accuracy of the area have values between 0 and 1, the final tracking reliability value has a value between 0 and 1. In this example, the tracking reliability may be calculated by Equation 1 below.

[Formula 1]

The comprehensive tracking unit 140 generates a comprehensive tracking result based on the tracking result of the object recognition tracking unit 130 and the tracking result of the non-recognition tracking unit 120 . When the tracking reliability of the tracking result of the non-recognized tracking unit 120 is high, the comprehensive tracking result may be generated using the tracking result of the non-recognized tracking unit 120 entirely, and the tracking of the non-recognized tracking unit 120 is When the reliability is low and the tracking reliability of the object recognition tracking unit 130 is high, the tracking result of the object recognition tracking unit 130 may be used as a comprehensive tracking result. In addition, in the middle, a weight may be given to each and the summed tracking result may be generated as a comprehensive tracking result.

To this end, the comprehensive tracking unit 140 obtains the weights of the tracking result of the object recognition tracking unit 130 and the tracking result of the non-recognition tracking unit 120 by using the tracking reliability value, and reflects them to perform comprehensive tracking. results can be generated. In addition, the weight of the tracking result of the non-recognition tracking unit 120 is obtained based on the tracking reliability value of the non-recognition tracking unit 120, and the tracking reliability value of the object recognition tracking unit 130 and the non-recognition tracking unit The weight of the tracking result of the object recognition tracking unit 130 may be obtained based on the difference in the tracking reliability value of 120 . The weight may have a value between 0 and 1, and when only one tracking result is used, the weight of the method may be set to 1, and the weight of the other method may be set to 0.

More specifically, the comprehensive tracking unit 140 may obtain the weight of the tracking result of the non-recognized tracking unit 120 by Equation 2 below.

[Equation 2]

At this time, wt is the weight of the tracking result of the unrecognized tracking unit 120 .

ct is the tracking reliability of the unrecognized tracking unit 120 (a value between 0 and 1)

,

는 신뢰도를 구분하기 위한 소정의 기준 값

,

is a predetermined reference value for classifying reliability

,

는 추적 알고리즘을 무엇으로 적용하는지에 따라서, 변경될 수 있다.Depending on the tracking method, the meaning of the reliability value may be slightly different,

,

can be changed depending on what the tracking algorithm is applied to.

In addition, the comprehensive tracking unit 140 may obtain the weight of the tracking result of the object recognition tracking unit 130 by Equation 3 below.

[Equation 3]

At this time, wd is the weight of the tracking result of the object recognition tracking unit 130 .

ct is the tracking reliability of the unrecognized tracking unit 120 (a value between 0 and 1)

cd is the tracking reliability of the object recognition tracking unit 130 (a value between 0 and 1)

는 신뢰도를 구분하기 위한 소정의 기준값

is a predetermined reference value for classifying reliability

는 추적 알고리즘을 무엇으로 적용하는지에 따라서 변경될 수 있다.Because the meaning of the reliability value may differ depending on the tracking method,

can be changed depending on what the tracking algorithm is applied to.

In the present invention, unlike the conventional method, since the non-recognition tracking unit 120 and the object recognition tracking unit 130 perform tracking to increase the tracking accuracy, it occupies more resources than the conventional method. will do Accordingly, the object recognition tracking unit 130 does not track the object when the tracking reliability value of the non-recognition tracking unit 120 is greater than or equal to a predetermined reference value, but only performs tracking when the tracking reliability value falls below the reference value. can That is, while the tracking method of the non-recognition tracking unit 120 is applied while the object is moving within the screen, if the tracking reliability is lowered in the non-recognition tracking unit 120 because the object moves out of the screen or moves at high speed, object recognition tracking The unit 130 may execute tracking, and synthesize and utilize the tracking results. In this way, it is possible to maximize the performance of tracing while minimizing the use of computational resources.

2 is a diagram illustrating an example in which non-recognition tracking and object recognition tracking are applied according to an embodiment of the present invention.

As shown in the drawing, when there is an object (a human face in the drawing) to be recognized on the screen, first, the object information receiver 110 receives information about the location and properties of the object.

As in (b), when an object moves, the non-recognition tracking unit 120 and the object recognition tracking unit 130 track the movement of the object, and synthesize them to generate a comprehensive tracking result. As in (b), when the object moves within the screen, since the reliability of the tracking result of the non-recognized tracking unit 120 is highly likely to appear, in this case, only the tracking result of the non-recognized tracking unit can generate a comprehensive tracking result. can

If the object to be tracked moves out of the screen as in (c), it becomes difficult for the non-recognized tracking unit 120 to track the object. Thereafter, even if the object is returned to the screen as in (d), since the location information of the object in the previous frame does not exist in the non-recognized tracking unit 120, it is difficult to track the movement of the object. Therefore, in this case, the object recognition tracking unit 130 recognizes the object in the corresponding frame again so that the tracking can be continued.

3 is a flowchart illustrating a flow of an object tracking method according to an embodiment of the present invention.

The object tracking method according to the present invention is a method of deriving a data boundary in an object tracking system including a central processing unit and a memory, and may be driven in such a computing system.

Accordingly, the object tracking method includes all the characteristic components described for the object tracking system described above, and content not described in the following description can be implemented with reference to the description of the object tracking system described above.

In the object information receiving step (S301), information on an object to be tracked is received from video data composed of a plurality of frames. The moving image data provides a moving image by arranging a plurality of still image frames in time series and rapidly reproducing the still image according to the passage of time. In order to analyze such moving picture data, it is necessary to recognize an object included in the moving picture. For example, when CCTV detects an intruder, it is necessary to select the intruder as an object to track and identify the movement.

The information on the object to be tracked received in the object information receiving step S301 may include location information on which the object to be tracked is located in the image or range information indicating the range in which it exists. It may contain information about For example, when the object to be tracked is a human face, by providing attribute information that the object to be tracked is a face, more accurate recognition may be possible when tracking an object through object recognition.

In the unrecognized tracking step (S302), the movement of the object to be tracked is tracked using the location of the object to be tracked in the previous frame of the video data and the current frame. Most of the conventional object tracking technologies have been to recognize an object in every frame of a video and track the location of the object. Because this is set, the tracking performance of tracking moving objects is not high. For example, in the case of tracking a human face, when the front of the face is exposed, it is possible to recognize that the part is a human face, but in the next scene, if the face rotates sideways or backwards, Since the face cannot be recognized in the frame of the scene in which the next face is turned back, tracking will fail.

Therefore, in the non-recognition tracking step (S302), a network focused on tracking, not recognition, is designed, and when an object exists in a certain position or range in the previous frame, how the object moves in the next frame By checking, it is possible to accurately determine the movement of objects between frames. That is, if the conventional object recognition-based tracking technology enables tracking by using a recognition technology, the technology of detecting the movement of an object in the previous frame and the current frame in the non-recognition tracking step (S302) is optimized for tracking the object. Therefore, it can be said that it is a technology that maximizes the tracking performance.

In the unrecognized tracking step (S302), the tracking technology using the location information of the object in the previous frame and the current frame information can be implemented through artificial intelligence, and various artificial intelligence algorithms for implementing this are being developed, In the present invention, it does not matter which method is applied. In general, such a technology for tracking objects without recognizing them is called Visual Object Tracking (VOT).

In the object recognition tracking step (S303), the object to be tracked is recognized for each frame of the video data and the movement of the object is tracked. As described above, the tracking method of the non-recognized tracking step (S302) cannot track an object moving out of the screen. There are advantages to be found. Therefore, the object tracking system of the present invention uses the tracking technology of the non-recognition tracking step (S302) and the tracking technology based on the object recognition for each frame at the same time to compensate for each other's shortcomings.

In order to recognize an object for each frame in the object recognition tracking step ( S303 ), it is necessary to learn the characteristics of the object by using the learning data for the object to be recognized in advance. If a human face is selected as an object to be tracked, it is necessary to learn various human face images as learning data so that the human face part and other objects can be distinguished in the image. Therefore, in the object recognition tracking step (S303), information on the object to be tracked is checked, the object to be tracked is determined whether the object is a learned type of object, and the movement of the object to be tracked is tracked only in the case of the learned type of object. can do.

In the non-recognition tracking step ( S302 ) and the object recognition tracking step ( S303 ), a tracking reliability value may be calculated together with a result of tracking an object, respectively. The object tracking algorithm using the position of the object in the previous frame and the current frame of the non-recognition tracking step (S302) and the object recognition-based tracking algorithm for each frame of the object recognition tracking step (S303) are all tracking reliability values according to the tracking results. can provide The tracking reliability value is a number indicating how accurate the tracking result is, and may be calculated to have a value between 0 and 1.

The comprehensive tracking step (S304) generates a comprehensive tracking result based on the tracking result of the object recognition tracking step (S303) and the tracking result of the non-recognition tracking step (S302). If the tracking reliability for the tracking result of the non-recognized tracking step (S302) is high, a comprehensive tracking result may be generated using the tracking result of the non-recognized tracking step (S302) entirely, and the tracking of the non-recognized tracking step (S302) When the reliability is low and the tracking reliability of the object recognition tracking step S303 is high, the tracking result of the object recognition tracking step S303 may be used as a comprehensive tracking result. In addition, in the middle, a weight may be given to each and the summed tracking result may be generated as a comprehensive tracking result.

To this end, the comprehensive tracking step (S304) obtains the weights of the tracking result of the object recognition tracking step (S303) and the tracking result of the non-recognition tracking step (S302) by using the tracking reliability value, and reflects them to perform comprehensive tracking results can be generated. In addition, the weight of the tracking result of the non-recognition tracking step (S302) is obtained based on the tracking reliability value of the non-recognition tracking step (S302), and the tracking reliability value of the object recognition tracking step (S303) and the non-recognition tracking step Based on the difference in the tracking reliability value of ( S302 ), the weight of the tracking result of the object recognition tracking step ( S303 ) can be obtained. The weight may have a value between 0 and 1, and when only one tracking result is used, the weight of the method may be set to 1, and the weight of the other method may be set to 0.

In the present invention, unlike the conventional method, since tracking is performed in each of the non-recognition tracking step (S302) and the object recognition tracking step (S303) to increase the tracking accuracy, it occupies more resources than the conventional method. will do Therefore, in the object recognition tracking step (S303), if the tracking reliability value of the non-recognition tracking step (S302) is greater than or equal to a predetermined reference value, the object is not tracked, and only when the tracking reliability value falls below the reference value. can That is, while the tracking method of the non-recognition tracking step (S302) is applied while the object is moving within the screen, when the tracking reliability decreases in the non-recognition tracking step (S302) because the object moves out of the screen or moves at high speed, object recognition tracking In step S303, the tracking may be executed, and the tracking results may be synthesized and utilized. In this way, it is possible to maximize the performance of tracing while minimizing the use of computational resources.

The object tracking method according to the present invention may be recorded in a computer-readable recording medium produced as a program for causing a computer to execute.

Examples of the computer-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CDROM and DVD, and a magneto-optical medium such as a floppy disk. media), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like.

Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules for carrying out the processing according to the present invention, and vice versa.

Although the above has been described with reference to the embodiments, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention described in the claims below.

101: object tracking system
110: object information receiving unit 120: non-recognition tracking unit
130: object recognition tracking unit 140: comprehensive tracking unit

Claims (11)

an object information receiver configured to receive information about an object to be tracked in video data composed of a plurality of frames;
a non-recognized tracking unit for tracking the movement of the object to be tracked using the location of the object to be tracked in the previous frame of the moving picture data and the current frame;
an object recognition tracking unit for recognizing the object to be tracked for each frame of the video data and tracking the movement of the object; and
Comprehensive tracking unit for generating a comprehensive tracking result based on the tracking result of the object recognition tracking unit and the tracking result of the non-recognition tracking unit
An object tracking system comprising a. According to claim 1,
The object recognition tracking unit and the non-recognition tracking unit calculate a tracking reliability value, respectively,
The comprehensive tracking unit
Obtaining the weight of the tracking result of the object recognition tracking unit and the tracking result of the non-recognition tracking unit using the tracking reliability value, respectively, and reflecting this to generate a comprehensive tracking result
Object tracking system, characterized in that. 3. The method of claim 2,
The comprehensive tracking unit
Obtaining the weight of the tracking result of the unrecognized tracking unit based on the tracking reliability value of the non-recognized tracking unit,
Obtaining the weight of the tracking result of the object recognition tracking unit based on the difference between the tracking reliability value of the object recognition tracking unit and the tracking reliability value of the non-recognition tracking unit
Object tracking system, characterized in that. 4. The method of claim 3,
The object recognition tracking unit
tracking the movement of the object to be tracked only when the tracking reliability value of the unrecognized tracking unit is less than or equal to a predetermined reference value;
The comprehensive tracking unit
When the object recognition tracking unit does not track movement, generating the tracking result of the non-recognition tracking unit as a comprehensive tracking result
Object tracking system, characterized in that. According to claim 1,
The object recognition tracking unit
Checking whether the object to be tracked is a learned type of object based on the information about the object to be tracked,
Track the movement of the object to be tracked only if it is a learned type of object,
The comprehensive tracking unit
When the object recognition tracking unit does not track movement, generating the non-recognition tracking unit tracking result as a comprehensive tracking result
Object tracking system, characterized in that. In the object tracking method of the object tracking system having a memory and a central processing unit,
an object information receiving step of receiving information about an object to be tracked in video data composed of a plurality of frames;
a non-recognized tracking step of tracking the movement of the object to be tracked using the current frame and the location of the object to be tracked in the previous frame of the moving picture data;
an object recognition tracking step of recognizing the object to be tracked for each frame of the video data and tracking the movement of the object;
A comprehensive tracking step of generating a comprehensive tracking result based on the tracking result of the object recognition tracking step and the tracking result of the non-recognition tracking step
An object tracking method comprising 7. The method of claim 6,
The object recognition tracking step and the non-recognition tracking step calculate a tracking reliability value, respectively,
The comprehensive tracking step is
Obtaining the weight of the tracking result of the object recognition tracking step and the tracking result of the non-recognition tracking step using the tracking reliability value, respectively, and reflecting this to generate a comprehensive tracking result
An object tracking method, characterized in that 8. The method of claim 7,
The comprehensive tracking step is
Obtaining the weight of the tracking result of the unrecognized tracking step based on the tracking reliability value of the non-recognized tracking step,
Obtaining the weight of the tracking result of the object recognition tracking step based on the difference between the tracking reliability value of the object recognition tracking step and the tracking reliability value of the non-recognition tracking step
An object tracking method, characterized in that 9. The method of claim 8,
The object recognition tracking step is
tracking the movement of the object to be tracked only when the tracking reliability value of the unrecognized tracking step is less than or equal to a predetermined reference value;
The comprehensive tracking step is
When the object recognition tracking step does not track movement, generating the tracking result of the non-recognition tracking step as a comprehensive tracking result
An object tracking method, characterized in that 7. The method of claim 6,
The object recognition tracking step is
Checking whether the object to be tracked is a learned type of object based on the information about the object to be tracked,
Track the movement of the object to be tracked only if it is a learned type of object,
The comprehensive tracking step is
When the object recognition tracking step does not track movement, generating the tracking result of the non-recognition tracking step as a comprehensive tracking result
An object tracking method, characterized in that A computer-readable recording medium in which a program for causing a computer to execute the method of any one of claims 6 to 10 is recorded.

Images