KR100837299B1 - Sever system and device and operating method of moving object by using vector graphic - Google Patents

Abstract

A sever system and apparatus for displaying the outline of a moving object, and an operating method thereof are provided to assign and input the object of a person or a thing in a video manually and track the change status of the object by frame, thereby extracting the outline of the object semiautomatically. A method for operating a sever system for displaying the outline of a moving object comprises the following steps of: inputting the assigned object outline of a specific frame from a touchpad manually when the moving object outline information of a video is extracted by an additional information server(S100,S110); converting the manually inputted object outline into a polygon by plural vertexes adjacent to the outline and extracting the outline(S120); comparing the extracted outline with the frame screen of a next order to track the location movement of each vertex as a characteristic of vector from vector graphics(S130); and recording the vector characteristic information of the tracked object outline in a storage unit by frame(S140).

Description

Contour representation of moving objects Server system, device and operation method {SEVER SYSTEM AND DEVICE AND OPERATING METHOD OF MOVING OBJECT BY USING VECTOR GRAPHIC}

1 is a network diagram for explaining a general broadcast communication system;

2 is a functional configuration diagram of a general multimedia terminal for broadcasting communication;

3 is a functional configuration diagram of an outline representation server system apparatus of a moving object according to one embodiment of the present invention;

4 is an explanatory diagram of a vector value extraction state of vertices according to an embodiment of the present invention;

5 is a flowchart illustrating a method of expressing a contour of a moving object according to an embodiment of the present invention;

6 is an exemplary view of a feature tracking result of each vertex according to an embodiment of the present invention.

          ** Explanation of symbols for main parts of drawings **

10: terminal 20: mobile communication network

30: broadcast station 40: additional information server

41: display unit 42: touch pad unit

43: object outline 44: polygon approximation

45: feature tracking unit 46: storage unit

The present invention displays object contours by humans or objects in a vector graphic form in a video. In particular, by using XML in the form of vector graphics, it is possible to easily and quickly track vertices and reduce data throughput. And an apparatus and method.

BROADCASTING is a one-way transmission in which one-way simultaneous transmission of information having the same content to multiple terminals, and communication is a two-way transmission in which one-to-one access is provided to each other.

As the broadcasting and communication convergence is activated, the DMB (DIGITAL MULTIMEDIA BROADCASTING) service is provided to receive and watch a broadcast signal to the communication terminal, and the broadcast communication terminal is a touch pad that recognizes a specific point designated on the display unit. It is common to apply a technique to transmit the control signal to a broadcasting station or the additional information server system.

The additional information server is a system configuration that provides the additional information when a viewer using broadcast communication selects an actor appearing in a TV broadcast or an accessory worn by an actor.

In order to provide additional information as described above, a technology for automatically extracting outlines by accurately recognizing specific objects in a video is required, and a technology for recognizing and extracting outlines is represented by polygonal graphics. (SCALAR VECTOR GRAPHIC) is defined as a specification for POLYGON.

In general, an OBJECT-BASED MOVING IMAGE CODING method is widely used to encode an ultra-low speed video signal in which an actor's motion is slow.

In the object-oriented video encoding method, an input image signal is segmented into a background that does not move and a change region that is generated due to the movement of the object.

The motion objects in the change region are separated into motion compensated objects when motion estimation and motion compensation are possible, and separated into motion failed objects when motion estimation and motion compensation are impossible. .

Movement compensable objects are moving objects with certain principles such as horizontal movement, rotational movement, and linear movement in the state of converting objects in three-dimensional space into images of two-dimensional objects. Does not have a background object.

The additional information service is to automatically track the contour of the movable compensable object in a polygon and provide the associated additional information in association.

In order to track the contour of a moving object, the amount of data to be processed should be small, and if it is displayed as a vertex of a polygon, the movement amount of each vertex can be displayed as data, and the movement by the movement, rotation, and size change of each vertex Not constant with each other

1 is a diagram illustrating a network for explaining a general broadcast communication system.

As shown, the terminal 10 receiving the broadcast communication is subscribed to the mobile communication network 20, and is provided with a communication service while moving.

The mobile communication network 20 receives a program or a VOD from the broadcasting station 30 and broadcasts it to the plurality of terminals 10 in one direction, and the terminal 10 selects and watches one of various broadcast programs or VODs.

Since BROADCASTING is a one-way communication, a user cannot directly provide a response to a questionnaire, a reply to a question, or submit an opinion through a terminal, and other communication means. Internet e-mail, telephone or mail should be used. Since the mobile communication network is bi-directional (TWO-WAY) communication, it is possible to receive and transmit data.

The additional information server 40 receives a program to be broadcast from the broadcasting station 30 in advance, and prepares additional information about the actors on the screen and various clothes and ornaments worn by the actors in a linked state.

When the additional information server 40 requests a specific screen and a specific part from the terminal 10 to provide the additional information, the additional information server 40 searches for the additional information and provides the additional information to the terminal 10 through bidirectional communication.

FIG. 2 is a functional configuration diagram of a general multimedia communication terminal 10. The high frequency unit 11 wirelessly connects to the mobile communication network 20, wirelessly receives a program broadcast by broadcast communication, and controls the controller 12. Display on the display unit 13 under the control of the "

When the user wants to check the information on the actor displayed on the display unit 13, or when the user wants to check the information on the clothes and specific accessories worn by the actor, the touch pad which operates in conjunction with the display unit 13. Touch the corresponding part of the unit 14.

The touch signal detected by the touch pad unit 14 is converted into a designated frame and coordinate value of a program broadcast by the control unit 12, and transmitted to the mobile communication network 20 through the high frequency unit 11. The mobile communication network 20 transmits the frame information and the coordinate information transmitted by the terminal 10 to the additional information server 40. Since the additional information server 40 searches for the additional information and provides the additional information to the terminal, bidirectional broadcast communication is performed.

In this way, the additional information provided by the additional information server 40 includes a text TEXT, an image, a video, a URL address, and the like.

However, the contour of the object is automatically extracted from the broadcast image, and the additional information stored in association is provided, and the standard defined in the POLYGON of the SVG according to the prior art is an arbitrary change out of the polygon's movement, rotation, and size conversion. There is a problem that is not defined for.

The present invention facilitates the automatic tracking of vertices of polygonal vector graphics using XML of the contour data of objects moving or transformed in a broadcast or VOD service image, and tracks any deformation with a small amount of data. It is an object to provide a representation system, apparatus and method.

In addition, an object of the present invention is to approximate and display the outline of a moving object in a moving image as a plurality of vertices, and to express the movement of each vertex as a vector value, so that the amount of data is small.

In order to achieve the above object, the present invention, when extracting the moving object contour information of the video by the additional information server, manually inputting the specified object contour of a specific frame from the touch pad unit; Converting and extracting the manually input object contour into a polygon by a plurality of vertices in proximity to the outline; Comparing the converted contour with the frame screen in the following order and tracking the feature by the position vector of each vertex in a vector graphic; Recording the feature information of the tracked object contour in a storage unit in a frame unit; This presents the included configuration.

In addition, the present invention devised to achieve the above object, the object contour unit for inputting the outline of the object manually selected from the specific frame screen of the video provided by the broadcast station; A polygon approximation unit for converting an outline of an object outline input by the object outline into a polygon of a plurality of vertices; A feature tracking unit tracking each vertex position information of the polygon converted by the polygon approximation unit by comparing with the image of the next frame; A storage unit which records the feature information of the object tracked in units of frames as a vector value; Present a configuration comprising a.

In addition, the present invention devised to achieve the above object is a method for tracking the contour of a specified object from the frame-by-frame screen by the additional information server, A) manually inputting the selected object contour information of the specified screen Wow; B) converting and extracting from the manually input object loop information into a polygon by a plurality of vertices in proximity to a selected contour; C) tracking the positional transformation of each vertex as a vector graphic by comparing the extracted contours of the plurality of vertices with a frame of a next order; D) recording the information of the vector graphic by the contour of the tracked object; Present a configuration comprising a.

In addition, the present invention devised in order to achieve the above object, in the additional information server for tracking the specified object contour of the frame unit screen including a display unit, a touch pad unit, a storage unit, specified manually selected from the frame unit screen An object outline unit for inputting an outline of the object; A polygon approximation unit extracting an outline of an input object as a polygon connected with a plurality of vertices; A feature tracking unit tracking each vertex position of the polygon extracted by the polygon approximation unit by comparing with the next frame image; Present a configuration comprising a.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention having the above-described configuration will be described in detail with reference to the accompanying drawings.

It is attached to illustrate the present invention, Figure 3 is a functional configuration diagram of the server server apparatus for the contour representation of the moving object according to an embodiment of the present invention, Figure 4 is a vector of the vertex according to an embodiment of the present invention 5 is an explanatory diagram of a value extraction state, and FIG. 5 is a flowchart illustrating a method of expressing an outline of a moving object according to an embodiment of the present invention, and FIG. 6 is an exemplary view of a feature tracking result of each vertex according to an embodiment of the present invention.

In describing the embodiments of the present invention, descriptions are omitted for technical contents that are not directly related to the present invention and are well known, and thus, the present invention is clearly transmitted without passing the gist of the present invention.

BROADCASTING AND COMMUNICATION In particular, a technology that combines mobile communication is called broadcasting communication. This broadcasting communication service checks additional information on the actor's personal information or histories while watching TV broadcasting on a terminal. Or, if you request additional information such as the seller, price, etc. of various clothes and accessories worn by the actor, it is a service that provides a quick search for the information.

Such a terminal is provided for selecting an actor appearing on a screen of a selected frame or inputting information for selecting clothes and accessories worn by the actor, and having a touch pad unit.

In addition, the additional information server for providing additional information is provided with program information broadcasted by a broadcasting station in advance, and extracts the actors, costumes and accessories worn by the actors that appear in each frame or time unit of the program, The information is recorded and managed in a linked state.

When the additional information server selects a frame of a program broadcast from a terminal or inputs information for selecting a specific coordinate of the frame, the additional information server should quickly search for the frame or coordinates and information associated with the corresponding time to provide the terminal to the terminal. do.

Since such a broadcast program is composed of a very large number of screen frames or a long time, it is necessary to check and record object location information such as actors, costumes, and accessories for each frame or time unit.

The location information of such an object should be quickly tracked in a frame unit or a time unit, and since the movement direction of each object is not constant, any deformation or movement amount must be accurately tracked.

In addition, since the location information of each object recorded in the frame unit or the time unit is very large, there is a difficulty in management.

The present invention relates to a technique for automatically and precisely tracking an object's frame state or a set unit of time's movement state and movement amount automatically and easily managing a small amount of tracked data.

Referring to FIG. 3, according to an embodiment of the present invention, a contour representation server system of a moving object may include: a display unit 41 displaying a video and a VOD program input from a broadcasting station in units of frames; A touch pad unit 42 for inputting contour extraction information of a selected object in association with the display unit; An object outline part 43 for inputting outline information of an object manually selected from a specific frame screen; A polygon approximation unit 44 for converting the outline of the input outline into a polygon of a plurality of vertices; A feature tracking unit 45 for comparing and tracking vertex position information of the polygon with an image of a next order frame; A storage unit 46 which records the feature information of the object tracked by the feature tracker in units of frames as a vector value; It includes a configuration.

Referring to FIG. 5, according to an embodiment of the present disclosure, a method of operating a system for expressing an outline of a moving object, when extracting moving object contour information of a video, manually extracts a specified object outline from the touch pad unit. Input process; Extracting the contour by converting the contour into a polygon by a plurality of vertices in proximity to the outline; Tracking the feature in vector graphics in comparison with the next frame screen; Recording the vector feature information of the tracked contour in a storage unit on a frame basis; This configuration is included.

According to the present invention having the above-described configuration, the outline representation server system and the operation method of the moving object will be described as an embodiment. The broadcast program or the VOD program is previously provided by the additional information server 40 from the broadcasting station 30. .

As described above, when a user wants to extract an object outline by a specific actor, a costume worn by an actor, an accessory, etc. from a program provided in advance (S100), the program displayed on the display unit 41 is checked by the additional information server operator, and the display unit is checked. Using the touch pad unit 42 that works in conjunction with 41, the contour of the object is manually input (S110).

At this time, in the manual input of the object outline, the touch pad unit 42 inputs coordinate information of several points that can identify the outline of the object.

The object contour information of the video manually inputted as described above is input by the object contour unit 43 and converted by the polygon approximation unit 44 into a polygon by a plurality of vertices adjacent to the outline of the object (S120).

The vertex information of the polygon extracted by the polygon approximation unit 44 is compared with the information on the frame screen in the following order by the feature tracking unit 45, and the positional information of each vertex is converted into a vector value by vector graphics. It is tracked (S130).

Since these vector values represent only the motion values of each vertex, the amount of data is very small.

In this case, each frame may also be expressed as a value of time displacement. As an example, referring to FIG. 4, the position information of the vertices extracted at the time t of the current frame may be represented by t + 1 according to the next frame. The case tracked in time is shown.

According to an embodiment, a method of expressing polygonal vertices according to time variation is as follows.

<polygon id = "1" points = "x1, y1 x2, y1 x2, y2 x1, y2" begin = "tms" dur = "lms" l>

<polygon id = "2" points = "x1 ', y1' x2 ', y1' x2 ', y2' x1 ', y2'" begin = "t + 1ms" dur = "l'ms" l>

In addition, a method of expressing a polygon that changes over time by using a movement vector and a movement of a point is as follows.

<polygon id = "1" points = "x1, y1 x2, y1 x2, y2 x1, y2" begin = "tms" dur = "lms" l>

     <animateMotion begin = "tms" dur = "lms" from = "0,0" to = "d, 0" l>

          <animagePoint order = "2" from = "2" from = "x2, y1" to = "x2 ', y1" "l>

<polygon>

The movement vector value of each vertex expressed as described above has a small amount of data, is shown as a diagram of FIG. 6, and is stored in the storage unit 46.

Referring to FIG. 6 in detail, even though a large number of vertices have moved in a direction defined by a motion vector or a motion vector, a few vertices can move in different directions, and this state is found to find individual data.

In other words, a polygon consisting of m vertices on a screen consisting of n frames is shown as part of moving according to a frame change in the following order.

Since the screen of the first frame has nothing to compare, a polygon is created as a reference frame, and the second frame of the next sequence generates a motion vector or a motion vector of -1 on the x axis because the movement amounts of all vertices are the same.

In the next sequence, the third frame, all vertices are the same except for the third vertex. In this case, a motion vector is generated, and the movement to that point is recorded separately as an exception process for the third vertex.

In the case of the fifth frame, this means that a plurality of vertices have moved in an arbitrary direction, and this case is treated as a reference frame.

The frame-wise feature information for each extracted vertex of the tracked object outline is recorded and managed in the allocated area of the storage unit 46 with a small capacity.

In addition, according to an embodiment of the present invention, the contour representation apparatus of a moving object includes a display unit, a touch pad unit, and a storage unit to track a specified object outline on a frame-by-frame screen. An object outline portion 43 for inputting an outline; Polygonal approximation unit 44 for extracting the outline of the object as a polygon connected a plurality of vertices; Feature tracking unit 45 for tracking the position of the polygon vertex compared to the next frame image; It includes a configuration.

In addition, according to an embodiment of the present invention, a method for operating a contour representation apparatus of a moving object includes: A) manually inputting object contour information; B) transform extraction into polygons by multiple vertices; C) tracking the positional transformation of each vertex in vector graphics as compared to the next order frame; D) recording the vector graphic information; It is configured to include.

According to an embodiment of the present invention having such a configuration, since the contour representation apparatus and the operation method of the moving object have already been described in the system and the operation method, duplicate description thereof will be avoided.

Although the present invention has been described in the embodiments as described above, the present invention is not necessarily limited to these embodiments, and various modifications can be made without departing from the spirit of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention but to describe the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

According to the present invention having the above-described configuration, by manually inputting an object by a person or an object in a video and automatically changing a state of change in units of frames, there is an industrial use effect of extracting an outline in a semi-automatic manner. .

In addition, the frame-based contour tracking of the object is facilitated, and any deformation of each vertex is tracked with a small amount of data, so that data management is easy and there is a convenience in use.

Claims (18)

Manually extracting moving object contour information of a video by the additional information server, manually inputting a specified object contour of a specific frame from the touch pad unit; Converting and extracting the manually input object contour into a polygon by a plurality of vertices in proximity to an outline; Comparing the extracted contour with a frame screen of the next order and tracking the positional movement of each vertex as a feature by a vector in a vector graphic; Recording vector feature information of the tracked object contour in a storage unit in a frame unit; Operation method of the contour representation server system of a moving object configured to include. The method of claim 1, wherein the input of the object contour is, And a method of inputting information on a contour of an object manually designated from a frame unit screen displayed on a display unit provided in the additional information server. The method of claim 1 or 2, wherein the extraction process, And converting each vertex value of the converted polygonal shape into a polygonal shape by a plurality of vertices close to a specified object contour of the selected frame unit screen, and extracting a value of each vertex of the converted polygonal shape. The method of claim 1 or 2, wherein the tracking process, And the contour of the designated object is compared with the next frame screen to track the position movement of each vertex as a vector value. The method of claim 1, The frame is a method of operating a contour representation server system of a moving object, characterized in that the time information is included. An object contour unit for inputting an outline of an object manually selected from a specific frame screen of a video provided by a broadcasting station; A polygon approximation unit for converting an outline of an object outline input by the object outline unit into a polygon of a plurality of vertices; A feature tracking unit tracking each vertex position information of the polygon converted by the polygon approximation unit by comparing with the image of the next frame; A storage unit which records the feature information of the object tracked by the feature tracker in units of frames as a vector value; Contour representation server system of a moving object that is configured to include. The method of claim 6, A display unit for displaying a moving image program input from the broadcasting station in units of frames; A touch pad unit inputting contour extraction information of a selected object in association with the display unit; Contour representation server system of the moving object is configured to further include. The method of claim 7, wherein The program input from the broadcasting station includes a VOD program, the contour representation server system of the moving object. The method of claim 6, wherein the object contour portion, And an object is extracted from the selected frame of the video displayed on the display unit of the additional information server by using the touch pad, thereby extracting the object. The method according to claim 6 or 7, wherein the polygon approximation unit, Contour representation server system of the moving object, characterized in that the object contour portion is configured to automatically convert to the vertex of the polygon close to the outer contour of the extracted object. The method of claim 6 or 7, wherein the feature tracking unit, Contour representation server system of the moving object, characterized in that consisting of tracking and expressing the vertices of the polygon converted by the polygon approximation unit by the movement vector value of the vector graphics and the movement of the point. delete A method for operating a contour representation apparatus for a moving object, which tracks the contour of a specified object from a frame-by-frame screen by an additional information server. A) manually inputting selected object outline information of the designated screen; B) converting and extracting from the manually inputted object contour information into a polygon by a plurality of vertices in proximity to a selected contour; C) tracking the positional transformation of each vertex as a vector graphic by comparing the extracted contours of the plurality of vertices with a frame of a next order; D) recording the information of the vector graphic by the contour of the tracked object; Contour representation device operating method of the moving object comprising a. The method of claim 13, wherein the step C, And comparing each of the extracted vertices with corresponding vertices of a next order frame to track the extracted vertices with a magnitude of a vector value. The method of claim 13 or 14, wherein the step D, And recording the tracked vector value in units of frames. An additional information server for tracking a specified object outline of a frame-by-frame screen including a display unit, a touch pad unit, and a storage unit. An object contour unit for inputting an outline of a specific object manually selected from the frame unit screen; A polygon approximation unit extracting an outline of the input object as a polygon with a plurality of vertices connected thereto; A feature tracking unit tracking each vertex position of the polygon extracted by the polygon approximation unit by comparing with a next frame image; Contour representation device of a moving object configured to include. The method of claim 16, wherein the feature tracking unit, And the position information of each vertex of the extracted polygon and a movement state of each vertex of the next frame in a sequence as a vector value. 18. The apparatus of claim 16 or 17, wherein each frame is represented by time.

Images