KR101203787B1 - Contents production method and system using interface based image cognition - Google Patents

Abstract

The present invention relates to a content production method and system using an image recognition-based interface. Content production method using the image recognition-based interface according to the present invention, the step of recognizing the artificial marker and the auxiliary marker disposed on the interface unit, displaying the object corresponding to the artificial marker on the screen, and corresponding to the auxiliary marker And changing the shape or operation of the object to display on the screen.
Thus, according to the present invention, since the content is produced by the interface using the image recognition technology, it is possible to create and modify the content scene easily and quickly, and to use the meaning-based markers to intuitively create the object. have. In addition, intuitive commands using a combination of markers and movements enable various settings of content, providing convenience for general users to easily create content regardless of age.

Description

CONTENT PRODUCTION METHOD AND SYSTEM USING INTERFACE BASED IMAGE COGNITION}

The present invention relates to a method and system for producing a content using an image recognition-based interface, and more specifically, to an interaction animation using an intuitive image recognition-based interface that receives a pattern and movement of an artificial marker placed on a command board by a camera. Or a method for producing a content scene of a game.

Generally, a content creation program creates an animation or scene of game content using an interface such as a keyboard input or a mouse click. The content creation method of this interface uses a method of dragging & dropping or double-clicking an object's icon or object's name in the production program to load and move an object on the content creation screen to compose a scene. In addition, it is difficult to grasp the positional correlation between the objects constituting the scene because objects are composed on the basis of other objects while the objects are loaded on the screen and the camera views are rotated.

Content production method using the conventional image recognition technology is to create augmented reality content by connecting video, audio, images to a background picture or document with a fixed marker, or initialize the menu in the production program using a simple pattern marker, object Use as controls to perform simple commands such as select, zoom in & zoom out, and delete. Or a controller, such as a mouse, is augmented in the production environment using a predetermined marker to create content using the controller.

In other words, in the production method of a content production program according to the prior art, a content is produced by arranging a scene by setting an object and setting an object on the screen using direct input or drag & drop using a keyboard and a mouse.

However, such a simple command function or augmented controller to call and write one by one requires considerable effort and time, and the process of creating a content scene is complicated. In addition, the usage of the production interface is not intuitive, so the user must be familiar with the interface.

Therefore, in the production of content scenes, the user can grasp the elements of the scene at a glance and reflect them in the production.In the use of the production tools, the user can easily and quickly produce the content by using an intuitive interface method. We need a way to do it.

The problem to be solved by the present invention is to provide a content production method and system using an image recognition-based interface that allows the user to easily and quickly produce content.

According to an aspect of the present invention, there is provided a content production method using an image recognition-based interface, including: recognizing an artificial marker and an auxiliary marker disposed on an interface unit, and displaying an object corresponding to the artificial marker. And displaying on the screen by changing the shape or operation of the object in response to the auxiliary marker.

Recognizing the artificial marker and the auxiliary marker, imaging the artificial marker and the auxiliary marker disposed on the interface unit, generating imaging information for the artificial marker and the auxiliary marker, and using the imaging information Recognizing an artificial marker and an auxiliary marker may be included.

The auxiliary marker may include an environment setting marker for setting a situation or a background of the object.

The auxiliary marker may include an operation marker for indicating an operation of the object.

In the displaying of the object corresponding to the artificial marker on the screen, the object may be displayed at the same relative coordinates corresponding to the artificial marker.

One artificial marker may be matched with one object, or two or more artificial markers may be combined and stored with one object.

Contents production system using an image recognition-based interface according to an embodiment of the present invention, the storage unit is the artificial marker and the object is matched and stored, the interface unit is disposed the artificial marker and the auxiliary marker, the interface unit is disposed An image pickup unit which picks up an artificial marker and an auxiliary marker, generates imaging information for the artificial marker and the auxiliary marker, and recognizes the artificial marker and the auxiliary marker from the imaging information, and displays the object matching the artificial marker. And a controller configured to display on the display unit and to change and display the shape or operation of the object in response to the auxiliary marker.

Thus, according to the present invention, since the content is produced by the interface using the image recognition technology, it is possible to create and modify the content scene easily and quickly, and to use the meaning-based markers to intuitively create the object. have. In addition, intuitive commands using a combination of markers and movements enable various settings of content, providing convenience for general users to easily create content regardless of age.

1 is a view showing a content production system using an image recognition-based interface according to an embodiment of the present invention.
2 is a view showing a content production method using an image recognition-based interface according to an embodiment of the present invention.
3 is a simplified diagram illustrating a process of producing content using an image recognition-based interface according to an embodiment of the present invention.
4 is a diagram of a magic board used as an image recognition-based interface according to an embodiment of the present invention.
5A to 5C are diagrams illustrating an artificial marker and object correlation according to an embodiment of the present invention.
6 is a diagram illustrating a process of configuring a screen using an image recognition-based interface according to an embodiment of the present invention.
7 is a diagram illustrating a relationship between an artificial marker and an object on a screen according to an exemplary embodiment of the present invention.
8A and 8B illustrate a background screen generation using an environment setting marker according to an embodiment of the present invention.
9A to 9C are diagrams for describing a method for setting an operation of an object according to an exemplary embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention.

1 is a view showing a content production system using an image recognition-based interface according to an embodiment of the present invention.

The content production system shown in FIG. 1 includes a storage unit 10, an imaging unit 20, a control unit 30, an interface unit 40, and a screen display unit 50. The storage unit 10, the control unit 30, the interface tab 40, and the screen display unit 50 are implemented on a magic board, and the imaging unit 20 captures a magic board on which a marker is disposed.

In the storage unit 10, an artificial marker and an object are matched and stored, and various situations, backgrounds, or motions corresponding to the auxiliary marker are matched and stored. The artificial marker and the auxiliary marker may be displayed on a planar material such as paper, and may be formed while being attached to one side of a cube-shaped cube.

In addition, the artificial marker is a marker corresponding to the object, and includes a marker based artificial marker that can directly feel the object from the marker and an image marker that can not directly feel the object from the marker. In addition, the auxiliary marker includes an environment setting marker for setting a situation or a background of the object and an action marker for indicating an operation of the object.

The imaging unit 20 photographs the artificial marker and the auxiliary marker disposed on the magic board from the front, and generates imaging information on the disposed marker. The imaging unit 20 may be implemented in the form of a multi-camera, and generates imaging information about an artificial marker and an auxiliary marker in real time.

The control unit 30 receives the imaging information from the imaging unit 20, recognizes the marker disposed on the magic board from the imaging information, and displays an object matching the artificial marker on the screen display unit 50, and displays the auxiliary marker. Correspondingly, the form or operation of the object is displayed on the screen display unit 50.

The interface unit 40 is an area in which the artificial marker and the auxiliary marker are disposed, and receives a command from the user to change the shape or operation of the object. That is, the interface unit 40 receives a command through an artificial marker that matches the object or an auxiliary marker that can set the situation of the object and perform an operation.

2 is a view showing a content production method using an image recognition-based interface according to an embodiment of the present invention.

First, the controller 30 recognizes an artificial marker and an auxiliary marker disposed on the interface unit 40 (S210). Herein, the controller 30 recognizes the artificial marker and the auxiliary marker by using the imaging information on the markers captured by the imaging unit 20.

The controller 30 displays an object corresponding to the artificial marker on the screen display unit 50 (S220). Here, the object corresponding to the artificial marker is pre-stored in the storage unit 10.

Next, the controller 30 sets the shape or operation of the object in response to the auxiliary marker and displays it on the screen display unit 50 (S230).

Hereinafter, a method for producing content using an image recognition based interface according to an embodiment of the present invention will be described in more detail with reference to FIGS. 3 to 9C.

3 is a simplified diagram illustrating a process of producing content using an image recognition-based interface according to an embodiment of the present invention.

The image recognition-based interface unit 40 according to an embodiment of the present invention obtains information on the meaning-based artificial markers or auxiliary markers located on the magic board using a multi-camera in real time, and utilizes the information as an interface.

As shown in FIG. 3, the user first places a meaning-based artificial marker or an auxiliary marker on a magic board to create and set a scene (S310). The content production system recognizes the meaning-based artificial markers or auxiliary markers from the images acquired by the multi-camera, and analyzes information such as the position, pattern, direction, and movement paths of the artificial markers or auxiliary markers and displays them on the screen. A content scene is configured by placing a corresponding object or setting an option (S320). Through this process, the final content is completed as shown in the right side of FIG. 3 (S330).

Hereinafter, the interface unit 40 according to the embodiment of the present invention will be described with reference to FIG. 4.

4 is a diagram of a magic board used as an image recognition-based interface according to an embodiment of the present invention. The interface unit included in the magic board 200 includes three spaces: a command space 210, a control space 220, and a work space 230.

The command space 210 includes a command selection button 211, a texture dial button 212 and a marker command dial 213. First, the command selection button 211 allows the user to select the functions of object registration and object size adjustment, background load, movement path setting, and motion setting of the image recognition-based interface. Among the command selection buttons 211, the red buttons indicate that the buttons are inactive.

The texture dial button 212 is a button for changing the texture of the selected object. When the user turns the direction indicated by the arrow in a dial form, the color or texture of the object is changed.

The marker command dial button 213 uses a pattern of markers, and may display objects in various and detailed modes through the marker command dial button 213.

The control space 220 includes a preference command space 221 and a marker gesture command space 222. The preference command space 221 sets a situation or a background using a method of registering or combining the preference markers 224. That is, when the environment setting marker for setting the situation or the background is arranged in the environment setting command space 221, the object may be changed according to the setting situation or the background.

The marker gesture command space 222 is a space in which the movement direction and the path of the object can be set, and the user can directly set the operation of the object by moving the operation marker 223 disposed in the marker gesture command space 222. In addition, the size of the object selected by the up, down, left, and right movement gestures of the operation marker 223 may be adjusted in the marker gesture command space 222. That is, the larger the distance between the reference marker and the motion marker, the larger the size of the selected object. On the contrary, the shorter the distance, the smaller the size of the selected object.

The work space 230 actually arranges an artificial marker so that the object is displayed on the screen display unit 50. When the artificial marker 231 is placed in the work space 230, the controller 30 analyzes the pattern and the position direction of the artificial marker to place the object corresponding to the artificial marker 231 through the screen display unit 50. As described above, according to the exemplary embodiment of the present invention, content production is performed using the command space 210, the control space 220, and the work space 230 as an image recognition-based interface.

5A to 5C are diagrams illustrating an artificial marker and object correlation according to an embodiment of the present invention.

Of the artificial markers used in the image recognition-based interface, meaning-based artificial markers can be used by assigning meanings so that the user can infer the shape of the object to be created by looking at the artificial markers, rather than a simple pattern marker for distinguishing between general markers. . Therefore, using the pattern of the object and the similar appearance generated as shown in Figure 5a to use as a meaning-based artificial marker. That is, when the meaning-based artificial marker 231 is disposed in the work space 230, an object 232 having the same shape as the pattern is generated on the content creation screen.

However, the semantic marker does not simply use the shape of the object as a pattern. As a simple example, assume that there is a pattern representing a house and a pattern representing a cross as shown in FIG. 5B. If a cross is placed on the house in combination, people may think that it is a church. In this way, a pattern having a meaning can be combined and used as a pattern representing an object.

In addition, as shown in FIG. 5C, an object may be generated using an index concept using a combination of a semantic-based artificial marker and a numeric marker. That is, a desired object may be generated on the content creation screen by using a combination of markers for the same object having various shapes. In addition, since the shape of an object recognized as a pattern may vary depending on the user, the user may change a setting of an object that is desired to be created in the semantic pattern through the content production system.

6 is a diagram illustrating a process of configuring a screen using an image recognition-based interface according to an embodiment of the present invention.

In general, in constructing a scene, a simple sketch is often used to envision a content scene. Such a sketch has an advantage that the position of the object can be identified at a glance.

The work space 230 of the magic board may be a whiteboard function to generate a scene sketch using the magic board as if sketching the overall concept of the content (S610). The artificial marker based on the meaning is placed in the work space 230 based on the sketched content on the magic board thus created (S620). Then, the image recognition-based interface generates a content by recognizing a pattern, a position, a direction, and the like of a semantic artificial marker and arranging an object connected to the screen of the production program (S630).

When the scene of the content is generated by arranging artificial markers using the image recognition-based interface, the production is simple and fast, and the scene can be intuitively arranged to create the scene. And since the scene is created like a sketch, it is possible to grasp the positional correlation between the arranged objects at a glance, making it easy to manufacture.

7 is a diagram illustrating a relationship between an artificial marker and an object on a screen according to an exemplary embodiment of the present invention.

The screen display unit 50 of the content creation system has relative coordinates in the same space as the work space 230 of the magic board. Therefore, the relative distance between the artificial marker 231 disposed in the work space 230 and another artificial marker is equal to the distance between the object 232 generated on the screen display unit 50 and the object generated by another artificial marker. Is expressed. In addition, the moving direction of the semantic based artificial marker disposed on the work space 230 determines the moving direction of the object created on the screen display unit 50.

As such, when an object corresponding to the meaning-based artificial marker is generated on the screen display unit 50, the user may create content regarding the operation characteristic of the object by using the environment setting marker and the operation marker.

8A and 8B illustrate a background screen generation using an environment setting marker according to an embodiment of the present invention.

When the preference marker 224 registered in the storage unit 10 of the content creation system is placed in the configuration command space 221 on the top of the control space 220 of the magic board, the content creation system generates a pattern of the preference marker. By analyzing the feature, the screen scene 50 retrieves the content scene stored as the feature of the pattern to generate a screen.

Here, the preference marker 224 uses an image such as a picture or a foreground as a pattern of an artificial marker. Thus, when the user places the preference marker 224 having a background or scene previously stored as shown in FIG. 8B in the preference setting space 221, the user may generate a corresponding background scene as shown on the right side.

9A to 9C are diagrams for describing a method for setting an operation of an object according to an exemplary embodiment of the present invention.

The method of selecting the motion of the object using the magic board is composed of two steps, a selection step using a preference marker pattern (S710) and a mode marker selection step (S720) using a marker movement path as shown in FIG. 9A.

First, the environment setting marker is a marker representing a situation or environment facing an object, and as shown in FIG. 9A, a high level environment marker 224a such as general life, combat / martial arts, sports, etc., and a low level corresponding to each high environment marker 224a. Environment marker 224b. As illustrated in FIG. 9A, the upper environment marker 224a representing sports may include a lower environment marker 224b representing gymnastics, soccer, and the like.

In FIG. 9B, the environment setting markers 224 are illustrated, and related environment markers are grouped to form a tree structure and can be selected by the user.

Therefore, in the case where it is desired to display the scene in which the object is fought, the environment marker indicating sport and the environment marker indicating fighting are sequentially arranged in the environment setting command space 221.

When the selection step S710 using the marker pattern is completed, the operation marker selection step S720 using the marker gesture is performed. The selection using the gesture is made in the marker gesture command space 222 of the control space 220, and the motion similar to the motion to be set for the object in the selected motion field is expressed as the marker gesture.

The marker gesture action consists of four directions: up, down, left, and right, and as shown in FIG. 9C, the motion of the object is created by using a combination of gestures using two marker actions among the motion markers 223 of the head, foot, hand, and body. Choose.

Therefore, the gesture using the marker uses a combination of four movements up, down, left, and right, and meaning-based markers of the head, foot, hand, and body that exist to the left and the right, so that a total of 256 motions can be set and expressed. For example, when setting a character's bow bow to greet the audience in a content scene, bow bow can be seen that the head moves from top to bottom. With this principle, you can set a motion to say hello to a selected object by moving one marker, which means head, and to move the two markers, which means head, to say hello at a large angle.

As such, the motion marker as shown in FIG. 9C is a marker indicating the motion of the object and indicates the motion of the head, foot, hand, and body. For example, in FIG. 9C, the head-shaped motion marker may represent an action such as greeting, heading, shaking from side to side, and the foot-shaped motion marker may represent an action of kicking, shooting, running, walking, and the like. Similarly, a hand-shaped motion marker may represent an action such as clapping, shaking hands, raising a hand, or clenching a fist, and a body-shaped motion marker may represent an action such as shaking from side to side, dancing, or lying down. Of course, the specific motion is determined according to the manner in which the user moves the motion marker.

Hereinafter, the movement of a specific object will be described using the environment setting marker and the operation marker described with reference to FIGS. 9A to 9C.

First, when a user arranges environment setting markers indicating fighting in the environment setting command space 221 and then moves an action marker indicating a right foot among the left foot and the right foot in the marker gesture command space 222 as shown in FIG. 9A. Will be described with an example. In this case, since the current fight scene is configured, the object performs the right kicking operation.

In addition, when the user places the preference markers representing soccer in the preference command space 221 and then moves the motion marker indicating the right foot upward in the marker gesture command space 222, the object moves to the right foot shot. Will be performed.

In this way, even if the same operation marker is moved in the same way, it can be seen that the operation of the object varies according to the set situation.

In this way, the motion of the object is selected using the movement of the marker similar to the selection of the motion field using the semantic marker. Therefore, various motions can be selected and produced in an intuitive manner.

Thus, it is possible to compose a scene simply and quickly with the content production interface using the image recognition technology of the marker, and provides the convenience that anyone can easily produce the content by the intuitive production method using the semantic marker and gesture.

Although the preferred embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

10: storage unit, 20: imaging unit,
30: control unit, 40: interface unit,
50: screen display, 210: command space,
220: control space 230: motion marker,
224: preference marker 230: workspace,
231: artificial marker 232: object,

Claims (11)

In the content production method using a content production system,
Recognizing artificial markers and auxiliary markers disposed on the interface unit based on image recognition;
Displaying an object corresponding to the artificial marker on a screen, and
And changing the shape or operation of the object in response to the auxiliary marker and displaying the same on the screen.
The auxiliary marker,
A configuration marker for setting a situation or a background of the object and an operation marker for indicating an operation of the object,
And an image recognition-based interface for determining an operation of the object in response to a situation set by the preference marker and an operation selected by the operation marker. The method of claim 1,
Recognizing the artificial marker and the auxiliary marker,
Imaging the artificial marker and the auxiliary marker arranged in the interface unit, generating imaging information for the artificial marker and the auxiliary marker, and
And recognizing the artificial marker and the auxiliary marker using the sensing information. delete delete The method of claim 2,
Displaying an object corresponding to the artificial marker on the screen,
And an image recognition-based interface displaying the object at the same relative coordinates corresponding to the artificial marker. The method of claim 1,
A method of producing a content using an image recognition-based interface in which one artificial marker is matched with one object or two or more artificial markers are combined and stored with one object. A storage unit in which an artificial marker and an object are matched and stored;
An interface unit based on image recognition, wherein the artificial marker and the auxiliary marker are disposed;
An imaging unit which picks up the artificial marker and the auxiliary marker arranged in the interface unit, and generates imaging information for the artificial marker and the auxiliary marker, and
And a controller configured to recognize the artificial marker and the auxiliary marker from the imaging information, to display the object matching the artificial marker on a screen display unit, and to change and display a shape or an operation of the object corresponding to the auxiliary marker. ,
The auxiliary marker,
A configuration marker for setting a situation or a background of the object and an operation marker for indicating an operation of the object,
The control unit,
And an image recognition-based interface for determining an operation of the object in response to a situation set by the preference marker and an operation selected by the operation marker. The method of claim 7, wherein
The screen display unit,
And an image recognition-based interface displaying an object matching the artificial marker at a corresponding relative coordinate. The method of claim 7, wherein
Wherein,
1. A content production system using an image recognition-based interface for matching and storing one artificial marker as one object or combining and storing two or more artificial markers as one object. delete delete

Images