KR101979246B1 - Method and apparatus for for calibrating sensor coordinate system with game zone - Google Patents

Abstract

Embodiments include a sensor for obtaining a sensing image including at least one of a movable component movable in three-dimensional space and a surface supporting the movable component; A calibration unit for calibrating a sensor coordinate system on the one surface based on the sensing image; A game zone setting unit for determining four points on the three-dimensional space and setting a game zone; And a game progress unit for recognizing the moving component in the game zone and playing the game, wherein the coordinates of the four points are coordinates on the calibrated coordinate system; And communicating with the device; And a moving component configured to move in accordance with the move command when receiving a move command from the device.

Description

METHOD AND APPARATUS FOR FOR CALIBRATING SENSOR COORDINATE SYSTEM WITH GAME ZONE BACKGROUND OF THE INVENTION [0001]

Embodiments of the present invention relate to calibrating a sensor coordinate system in a game zone, more specifically, after calibrating a sensor coordinate system on one side supporting an object, setting a game zone and recognizing an object located on the game zone It's about playing the game

Recently, a technology for recognizing the movement of an object and an object using the 3D sensor and providing information thereon has been actively studied. Particularly, a game interaction technique for recognizing an object (for example, a part of a person's body or a robot, etc.) through a 3D sensor and playing a variety of games corresponding thereto is actively being developed.

Such a game interaction technology can input various input signals to a game device as compared with an existing game device that can only be played through an existing input device (e.g., a mouse, a keyboard, etc.) Can be input as various input signals, which is advantageous in terms of user convenience.

However, there is a possibility that the user's intended result will not be performed if the position of the user's body and / or movement is not applied accurately to the game. Therefore, there is a need for a technique of calibrating the position of the user's body and movement recognized by the 3D sensor so as to be more accurately applied to the game.

Patent Publication No. 10-2014-0141174

According to an embodiment of the present invention, there is provided a method and apparatus for performing a game by recognizing an object located on a game zone by setting a game zone after calibrating the sensor coordinate system on one side supporting the object.

Further, there is provided a system capable of playing a game according to object recognition, including a moving component capable of communicating with the apparatus and the apparatus.

According to one aspect of the present invention, a game progression method according to object recognition is performed by a device for calibrating a sensor coordinate system in a game zone, the method comprising: moving a mobile component and a moving component on one side of a three- Acquiring a first sensing image including at least one of the first and second sensing images; Calibrating a sensor coordinate system on the one surface based on the first sensing image; Determining at least four points on the three-dimensional space and setting a game zone; And recognizing the moving component in the game zone to proceed with the game. Here, the coordinates of the four points are the coordinates on the calibrated coordinate system.

In one embodiment, the calibrating step comprises: determining whether the first sensing image comprises the one side; Calculating a normal vector of the one surface; And calibrating one axis of the sensor coordinate system in parallel with the normal vector of the one surface.

In one embodiment, the step of determining whether the first sensing image includes the one side comprises: generating a point cloud for the first sensing image; Matching a point cloud for the first sensed image with a previously stored point cloud for one or more candidates for the one surface; And determining through the matching point by the matching whether the sensing image includes the one side.

In one embodiment, the step of calibrating comprises calculating the normal vector of the one side based on the position of the moving component included in the first sensing image, if the first sensing image does not include the one side As shown in FIG.

In one embodiment, the step of calibrating comprises the steps of: transmitting a move command to the moving component causing the moving component to change the direction of movement at least once; Tracking movement trajectories of the moving component through the sensor to determine at least three points included in the position trajectory of the moving component; And calculating a plane equation of one surface supporting the moving component based on the at least three points, and calculating a normal vector of the one surface.

In one embodiment, determining four points on the three-dimensional space and setting a game zone may further comprise determining based on the at least three points.

In one embodiment, the step of recognizing the moving component and proceeding with the game comprises the steps of acquiring, through the sensor, a second sensing image including a moving component in the game zone; Filtering the second sensing image; And recognizing the moving component based on the filtered second sensing image.

In one embodiment, filtering the one surface may further comprise filtering a point below a predetermined height from the position of the sensor.

In one embodiment, filtering the one side comprises determining at least three points on the game zone and determining a plane comprising at least three points on the game zone; And filtering points within the predetermined range from the plane.

In one embodiment, the step of recognizing the moving component may further comprise the step of recognizing the moving component based on the plurality of points of interest when the number of filtered points is equal to or greater than the threshold.

A computer-readable recording medium according to another aspect of the present invention is a computer-readable storage medium capable of storing program instructions operable by the computer. Here, the program instructions may be executed by a processor of the computer to perform a method of calibrating a sensor coordinate system according to the above embodiments to a game zone.

An apparatus for calibrating a sensor coordinate system in a game zone according to another aspect of the present invention includes a sensor for obtaining a sensing image including at least one of a movable component movable in the three-dimensional space and a surface supporting the movable component; A calibration unit for calibrating a sensor coordinate system on the one surface based on the sensing image; A game zone setting unit for determining four points on the three-dimensional space and setting a game zone; And a game progress unit for recognizing the moving component in the game zone to proceed with the game. Here, the coordinates of the four points are the coordinates on the calibrated coordinate system.

According to another aspect of the present invention, there is provided a system for playing a game according to object recognition, comprising: a sensor for acquiring a sensing image including at least one of a movable component movable in the three-dimensional space and a surface supporting the movable component; A calibration unit for calibrating a sensor coordinate system on the one surface based on the sensing image; A game zone setting unit for determining four points on the three-dimensional space and setting a game zone; And a game progress unit for recognizing the moving component in the game zone and playing the game, wherein the coordinates of the four points are coordinates on the calibrated coordinate system; And communicating with the device; And a moving component configured to move in accordance with the move command when receiving a move command from the device.

According to the embodiment of the present invention, the position of the object recognized by the sensor can be calculated more precisely by preliminarily calibrating the sensor coordinate system on one surface supporting the object, and applied to the progress of the game.

Furthermore, even if there is no separate input device, various inputs to the game can be performed through the intuitive movement of the user, which is advantageous in terms of user convenience.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description of the claims.

1 is a diagram showing a planar conceptual diagram of an apparatus 100 for calibrating a sensor coordinate system to a game zone according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a system 1000 for recognizing an object on a game zone and proceeding with a game according to an embodiment of the present invention.
3 is a flowchart illustrating a method of calibrating a sensor coordinate system in a game zone according to an embodiment of the present invention.
4 is a view illustrating a process of calibrating a sensor coordinate system according to an embodiment of the present invention with respect to a side where a game zone is to be set.
FIG. 5 is a diagram illustrating a process of calculating one side on which a game zone is set when one side is not included in the sensing image according to the embodiments of the present invention.
FIG. 6 is a diagram illustrating a process of setting a game coordinate system according to an embodiment of the present invention.

Embodiments will now be described with reference to the accompanying drawings, however, the principles disclosed herein may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In the description of the invention, a detailed description of well-known features and techniques may be omitted to avoid unnecessarily obscuring the features of the embodiments.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As appropriate, the terms used in the singular include also plural, and vice versa. Means that a particular feature, region, integer, step, operation, element and / or component is specified and that the presence or absence of other features, regions, integers, steps, operations, elements, and / It does not exclude addition. Use " one " means " more than one " unless the use of the term " one or more " The use of the term " or " means " and / or " unless otherwise stated.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

1 is a schematic plan view of an apparatus 100 for calibrating a sensor coordinate system in a game zone according to an embodiment of the present invention. FIG. 2 is a conceptual diagram of a system for recognizing an object on a zone and proceeding with a game.

The system includes an apparatus 100 for calibrating a sensor coordinate system into a game zone and a mobile component 200 configured to communicate with the apparatus 100. [ The apparatus 100 is an apparatus for performing an interface function according to object recognition, and includes a sensor 10 and a processing unit 30.

The apparatus 100 and system 1000 according to embodiments may be entirely hardware, or may be partially hardware, and partially software. For example, hardware and related software may be collectively referred to as processing and / or transmitting / receiving data in a specific format and contents. A "unit," "module," "device," or "system" or the like in this specification refers to a computer-related entity such as a hardware, a combination of hardware and software, or software. A processor, an object, an executable, a thread of execution, a program, and / or a computer, for example, a computer, but is not limited to, a computer. For example, both an application running on a computer and a computer may correspond to a part, module, device or system of the present specification.

The sensor 10 is one means of recognizing the movement of the object and the object, and can sense and recognize the object in the sensor recognizable area (hereinafter, " recognizable area "). As a result, the game according to the object recognition can proceed.

In addition, the sensor 10 may recognize one side supporting the object. This allows the device 100 to calibrate the surface supporting the object and the sensor coordinate system. This will be described in more detail below with reference to Fig.

In one embodiment, the sensor 10 may be a 3D depth sensor that recognizes objects and colors. The three-dimensional RGB-D sensor may obtain color data (e.g., a color image) and depth data (e.g., a depth map of the color image) in a recognizable area. For example, a 3D RGB-D sensor acquires data composed of m * n * (x, y, z), where m, n are resolution, and x, y and z represent coordinates of a point. In some embodiments, the 3D RGB-D sensor may include a depth sensor and an RGB sensor. In some other embodiments, the RGB sensor may include a color camera.

In one embodiment, the depth sensor may comprise an infrared laser projector coupled to a CMOS sensor, which can shoot a myriad of infrared beams from a single camera and sense three dimensions in any brightness condition through reflected infrared light have. In addition, you can detect both the horizontal and vertical as well as the distance and proximity of the sensor to see where the object is and how it behaves.

Time-of-flight method is generally used to acquire depth information through a depth-of-field infrared (IR) laser projector, but it is also possible to project the structured light onto an object and calculate the depth through stereo matching. In another embodiment, it is possible to detect an object with respect to a dynamic object where a distance step occurs by using a blob labeling technique in a stream sequence, estimate the spatial position, and assign an id to each dynamic object.

In one embodiment, the RGB sensor collects color information of a subject, i.e., an object and a content screen, using three colors of red, green, and blue. The apparatus 100 may distinguish objects from each other through RGB sensors, and may distinguish environments around objects such as the floor, the content screen, and the like.

The three-dimensional RGB-D sensor described above and the depth sensor and the RGB sensor constituting the three-dimensional RGB-D sensor are merely examples, and various sensors capable of recognizing an object, an object motion, and a content screen can be used.

In another embodiment, the device 100 may further include a moveable connection for adjusting the sensing angle of the sensor 10. [ As a result, the recognizable area of the sensor 10 can be flexibly set.

The processing unit 30 calibrates the sensor coordinate system in the game zone based on the 3D depth data and the color data of the object and the surrounding environment acquired by the sensor 10, And may be implemented as a kind of application processor (AP) such as an MCU (Micro Control Unit) and a CPU (Central Processing Unit). In one embodiment, the processing section 30 may include a calibration section 31, a game zone setting section 33, and a game progress section 35. The operation of the processing unit 30 will be described in more detail below with reference to Fig.

In one embodiment, the apparatus 100 may further include a storage unit 40. The storage unit 40 is a means for storing program instructions for implementing the present embodiment and includes a random access memory (RAM) such as dynamic RAM (dynamic RAM) or static RAM but are not limited to, memory, erasable programmable read-only memory (ERPROM), electrically erasable programmable read-only memory (EEPROM), and non-volatile random access memory (NVRAM). The above memory types are merely exemplary and do not limit the type of storage 40 that may be used for storage of computer programs.

The mobile component 200 is an external component that is configured to be capable of communicating with the device 100 and that includes a mobile unit that is capable of moving upon receipt of an instruction associated with movement from the device 100. [ In some embodiments, the moving component 200 may receive a move command or a move command according to a game scenario that causes at least three of the sides supporting the moving component to point.

In one embodiment, the moving component 200 may be a robot-like component as shown in FIG. However, it is to be understood that this is merely exemplary and that the device 100 may be of various forms capable of communicating with and being mobile.

It will be apparent to those skilled in the art that the apparatus 100 and the system 1000 may include other components. For example, an input device for data entry, an output device for printing or other data display, and other hardware elements necessary for the operations described herein. In some embodiments, the system may further include a network, a network interface, and a protocol for connecting between an external device (e.g., smart phone, mobile component 200) for the device 100 and the like.

3 is a flowchart illustrating a method of calibrating a sensor coordinate system in a game zone according to an embodiment of the present invention. The method includes obtaining (S110) a first sensing image including at least one of a movable component movable in the three-dimensional space and a surface supporting the moving component, a sensor coordinate system based on the first sensing image (S131), determining four points on the three-dimensional space and setting a game zone (S133); And recognizing (S135) the moving component in the game zone to proceed with the game.

In one embodiment, the apparatus 100 acquires a sensing image including at least one of an object in the three-dimensional space and a surface supporting the object through the sensor (S110). Here, the object may be part or all of the mobile component 200 that is communicable with the device 100 and is configured to be mobile, and / or some or all of the body of the person.

Then, the calibration unit 31 calibrates the sensor coordinate system on the one side based on the sensing image including at least one of the object and one surface supporting the object (S131).

4 is a view illustrating a process of calibrating a sensor coordinate system according to an embodiment of the present invention with respect to a side where a game zone is to be set.

In one embodiment, the calibration unit 31 determines whether the sensing information obtained by the sensor includes one side on which the game zone is to be set. One side on which the game zone is to be set is a surface with little or no bending, and may include a floor, a desk, and the like. However, it should be understood that this is merely exemplary and that various aspects may be used to support objects such as people, animals, moving components 200, and the like. Hereinafter, for the sake of clarity of explanation, one side will be represented on the bottom.

In one embodiment, the calibration unit 31 calculates a point for the sensing information obtained by the sensor, and determines whether the sensing information includes a floor on which the game zone is to be set.

In one example, the calibration unit 31 receives a sensing image including an object from the sensor 10 and generates a point cloud for the sensed image (this process may be referred to as a scanning process) . Dimensional point cloud for the sensed image based on image information about the environment of the device 100 obtained by the sensor 10 and 3D depth information. At this time, a feature point of the point cloud for the sensing image can be selected. For example, it is possible to set as a feature point a point that is effective in comparing shapes such as a point where the color changes or a point where the outer surface is bent or abruptly deformed in the point cloud with respect to the sensing image. A selection algorithm can be used.

Then, based on feature point matching, a point cloud for the image and a point cloud for a candidate candidate model, which are stored in advance, are matched (this process can be referred to as a matching process). In one example, a point cloud for a model includes a point cloud (e.g., a pointer cloud to a floor surface, a pointer cloud to a desk surface, etc.) for one side can do. Here, the point cloud for the model is generated by photographing a model of a shape corresponding to the object, which is a previously stored comparison object for detecting an object from the image. In some embodiments, the device 100 may obtain a point cloud for a pre-generated model from an external database.

The calibration unit 31 matches the point cloud for the sensed image with the point cloud for the previously stored model based on the feature point matching and determines whether the image includes the corresponding object through the matching points by the feature point matching do.

Also, in some instances, the matching process further includes filtering, such as segmenting and sampling the point cloud for the point cloud for the model and / or for the point cloud for the model after selecting the feature point for the model It is possible.

In one embodiment, the calibration unit 31 may perform a step of determining whether the sensing image includes a bottom by generating a point cloud through a point cloud library and selecting a feature point.

In another embodiment, the device 100 may include one or more sensors 10. In this case, the calibration unit 31 may determine whether the sensing image includes a bottom using a least square method.

In one embodiment, the calibration unit 31 generates a point cloud for the sensing image including the floor, and matches the point cloud for the previously stored candidate group with the sensing image, respectively. In some embodiments, the matching process may be performed by extracting feature points. Since the sensing image includes the floor, it will match with the point cloud for the floor model of the candidate group model. Based on this matching result, it can be determined whether the sensed image includes a bottom.

If it is determined that the sensing image includes the bottom, the calibration unit 31 then calculates the normal vector of the bottom. The calibration unit 31 calculates a normal vector of one surface based on the coordinates of the points corresponding to the bottom. In some embodiments, normal vectors may be computed after filtering points with elevation coordinates (e.g., z coordinates) above a predetermined interval for ease of computation.

Then, the calibration unit 31 calibrates one axis of the preset sensor coordinate system in parallel with the calculated normal vector of the one surface. Referring to Fig. 4, the calibration unit 31 calibrates the direction vector of the vertical axis (e.g., z axis) of the sensor coordinate system in parallel with the normal vector.

In one embodiment, the calibration unit 31 generates a world coordinate system having the normal vector of the surface on the z-axis, the direction vector in the front direction that directs the focus of the sensor from the sensor to the x-axis, and the zero point of the sensor coordinate system as a zero point You may. For this reason, a sensor coordinate system having a coordinate axis different from that of one side before calibration can be calibrated with a world coordinate system representing the environment of the apparatus 100.

In some embodiments, the calibration unit 31 may calculate a transformation matrix between the world coordinate system and the sensor coordinate system based on a normal vector and a common zero point.

FIG. 5 is a diagram illustrating a process of calculating one side on which a game zone is set when one side is not included in the sensing image according to the embodiments of the present invention.

In one embodiment, when it is determined that the sensing image does not include the bottom, the calibration unit 31 may calculate the bottom normal vector based on the position of the object included in the sensing image. In some embodiments, the calibration unit 31 may calculate the normal vector of the floor surface based on the position of the moving component 200 included in the sensed image.

The calibration unit 31 transmits a move command to the moving component 200 to cause the moving component 200 to point at least three of the bottom surfaces supporting the moving component 200. [ The at least three location points are points that can determine the supporting floor, excluding all points on a straight line. That is, the move command includes an instruction that causes the moving component 200 to change at least one direction of movement.

Here, the change in the moving direction indicates that the absolute value of the slope of the equation of the straight line based on the moving direction is different before and after the change in the moving direction. For example, when the slope before the direction change is + a and the slope after the direction change is -a, it does not correspond to at least one moving direction change.

Referring to FIG. 5A, the calibration unit 31 transmits a movement command for changing the movement direction of one movement to the movement component 200. In this case, the movement command includes data related to the horizontal movement distance (P1-P2), the vertical movement distance (P2-P3) and the direction change angle (90 deg.

Referring to FIG. 5B, the calibration unit 31 transmits a movement command to the movement component 200 to change the movement direction of the second movement. In this case, the movement command includes data related to the vertical movement distances P1-P2 and P3-P4, the horizontal movement distance P2-P3 and the direction change angle 90 °.

The calibration unit 31 continuously recognizes the moving component 200 based on the information m * n * (x, y, z) of the sensing image including the moving component 200 (I.e., a linear equation on the bottom surface) with respect to the moving locus of the moving component 200. The process of the calibration unit 31 recognizing the moving component 200 is similar to the process of recognizing the bottom surface described above, and thus a detailed description will be omitted.

Referring to Figure 5A, the initial direction (P1-P2) of the moving component is different from the latter direction (P2-P3). In this case, the calibration unit 31 may use the movement start point P1, the direction change point P2, and the movement end point P3 of the moving component 200 to calculate the bottom plane equations. Since the plane equation includes a component representing a normal vector, the calibration unit 31 can calculate the normal vector of the bottom plane through the motion component recognition.

5B, the initial direction (P1-P2), the middle direction (p2-P3), and the later direction (P3-P4) of the moving component are different from each other. In this case, the calibration unit 31 calculates the movement start point P1, the first direction change point P2, the second direction change point P3, and the movement end point P4 of the moving component 200, It can be used to calculate the plane equations.

In one embodiment, if it is determined that the sensed image does not include a floor or an object, the device 100 may move to extract a suitable other floor to which the content screen is to be scanned. In some embodiments, the device 100 may inform the user that there is no suitable zone for the game zone to be set.

FIG. 6 is a diagram illustrating a process of setting a game coordinate system according to an embodiment of the present invention. In some embodiments, when the direction change angle included in the movement command is 90 degrees, the calibration unit 31 may convert the coordinate axes of the game coordinate system to correspond to at least a part of the movement trajectory of the moving component 200. [

Referring to FIG. 6, since the direction change angle included in the movement command is 90 degrees, the x-axis and the y-axis of the game coordinate system can be converted to correspond to the movement trajectories (P2-P1 and P2-P3) of the moving component, respectively. Accordingly, when a game is recognized after an object is recognized at a later time, the position of the recognized object can be calculated directly as coordinates on the game coordinate system.

The game zone setting unit 33 determines at least four points on the three-dimensional space, and sets a game zone having the four points as a range. Here, the positions of at least four points are represented by a calibrated coordinate system (i.e., game coordinate system).

In one embodiment, the game zone setting unit 33 can determine at least four points at random while making the z coordinates the same.

In another embodiment, the game zone setting unit 33 can determine at least four points for setting the game zone based on at least three points used to calculate the bottom surface plane equation.

Referring to FIG. 5A, the game zone setting unit 33 determines three points (P1-P3) used for calculating the bottom plane equations to be three out of at least four points, And the coordinates of the remaining point P4 can be calculated.

Referring to FIG. 5B, the game zone setting unit 33 can immediately set a game zone using four points (P1-P4) used for calculating the plane equation of the bottom surface.

In another embodiment, the game zone setting unit 33 recognizes the moving component 200 and sets the game zone. In the above embodiment, a movement command for setting a game zone is transmitted to the moving component 200. [ The move command causes at least the moving component 200 to change direction at least two times. For example, the move command may be an instruction that causes the moving component 200 to move, as shown in FIG. 5B. In addition, the movement command may include information related to the horizontal and vertical intervals of the game zone, the position coordinates of the vertex, and the like. In some embodiments, the game zone setting unit 33 includes various data for setting a game zone based on a preset game in the movement command.

The game zone setting unit 33 tracks the movement trajectory of the moving component through the sensor to calculate at least four positions among the points included in the movement trajectory of the moving component, . The process of tracking the moving locus to calculate at least four positions is similar in operation principle to the process of determining at least three position points in order to calculate the plane equation of the floor when the sensing image does not include the floor surface. Is omitted.

In another embodiment, the game zone may be set via another object (e.g., a pointer).

The game progress unit 35 executes a game program stored in advance and recognizes an object such as a moving component 200, a person or the like located on the game zone through the sensor 10, and proceeds with a previously stored game program.

The game progress unit 35 acquires a sensing image including the moving component 200 in the game zone through the sensor 10, and filters the bottom surface when the sensing image includes a floor surface.

In one embodiment, the game progress section 35 filters points below the predetermined height in the sensor 10 to remove the bottom surface from the sensed image. For example, when the height of the sensor 10 is 150 cm, the game progress unit 35 filters the point having the height coordinate of 140 cm or less from the sensor 10, and moves the point having the height coordinate of 10 cm or more, .

In another embodiment, the game progress section 35 determines at least three points on the game zone and determines the plane containing the at least three points. Here, the height coordinate values of at least three points on the game zone are equal to each other, and the plane coordinate value is randomly determined within the game zone range.

Then, the game progress unit 35 filters the points within the predetermined range from the plane, and recognizes the plurality of points as moving components when the number of filtered points is equal to or larger than the threshold value.

For example, the game progress section 35 may generate a point cloud for the sensing image including the moving component 200 on the game zone after the plane determination, and set the point cloud for the sensing image to a predetermined range from the plane Filter. For example, the game progress unit 35 selects any three points having a height coordinate value of 100 cm, and determines the corresponding plane. Then, points that are out of range to use only points within 50 cm from the plane are removed through filtering. In some embodiments, the predetermined filtering range may include a range from above the corresponding plane.

In some embodiments, the game progress unit 35 may recognize the floor surface through the point cloud library and remove it. This operation principle is similar to the above-described operation principle for determining whether the sensing image includes the bottom surface, and thus a detailed description thereof will be omitted.

Through the embodiment described above, the floor supporting the moving component 200 is filtered in the sensing image. The game progress unit 35 recognizes the point cloud as a moving component when the number of points (i.e., the filtered point cloud) for the filtered sensing image is equal to or larger than the threshold value.

If the angle of the sensor 10 is set so that the sensing image does not include the moving component and / or the floor supporting the person, the game progress unit 35 recognizes the object without filtering the one side Can be performed.

The game progress unit 35 can know where the moving component is located in the game zone based on the plane coordinates (x, y) of the corresponding plurality of points (i.e., the corresponding point cloud).

In addition, the game progress unit 35 can classify the objects based on the interval between the point clouds. For example, if the interval between point clouds is less than a predetermined distance, it is determined to be one object, while if it is more than a predetermined distance, it is determined to be a different object (e.g., moving component 200 and person).

Through the above-described object recognition process such as floor, person, and / or moving component 200, the game progress unit 35 can play various games that interact with object recognition.

In one embodiment, the game progress unit 35 moves a game in which the moving component 200 moves a grid-like map consisting of four squares horizontally and vertically, and a person moves along the movement path of the moving component 200 You can proceed.

For example, the moving component 200 exits the grating through the arrival position at a predetermined starting position on the grating. Thereafter, the user moves along the path along which the moving component 200 has moved. At this time, if the device 100 recognizes that the user deviates from the predetermined path through the sensor, it provides the user with a path deviation notification.

When the user receives the path deviation notification, the user starts the path movement from the first position again. The game progress unit 35 may notify the user that the game has been successfully completed within a predetermined time.

In some embodiments, the game progress section 35 may set the plaid pattern to be virtual on the game zone.

The steps described above with reference to FIG. 3 are exemplary only, and the order may be different, omitted, or changed depending on the setting state of the apparatus 100. [

The method of calibrating the sensor coordinate system in the game zone and the operation by the apparatus according to the embodiments described above can be implemented at least partially in a computer program. Here, the program for implementing the present embodiment is configured in the form of functional program instructions and codes that can be executed in the computing device. The above-described operations and their associated units, modules, etc., may be implemented within software, firmware, hardware, or any combination thereof. For example, a software module may be implemented with a program product comprised of a computer-readable medium including program code, which may be executed by a processor for performing any or all of the steps, operations, or procedures described herein .

Program instructions that perform a method of calibrating a sensor coordinate system to a game zone, when executed by a processor of the apparatus 100 for calibrating a sensor coordinate system to a game zone, But can be readily understood by those skilled in the art to which this embodiment belongs.

In addition, the method of calibrating the sensor coordinate system in the game zone and the operation by the apparatus can be recorded on a computer-readable recording medium. A method for calibrating a sensor coordinate system according to embodiments to a game zone and a program for implementing the operation by the apparatus are recorded and a computer readable recording medium includes any type of recording apparatus in which data readable by a computer is stored . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. The computer readable recording medium may also be distributed over a networked computer system so that computer readable code is stored and executed in a distributed manner.

While the invention has been shown and described with reference to certain embodiments thereof, it will be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. However, it should be understood that such modifications are within the technical scope of the present invention. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

Claims (13)

1. A method of calibrating a sensor coordinate system performed by an apparatus for calibrating a sensor coordinate system in a game zone,
Obtaining a first sensing image including at least one of a movable component movable in one side of the three-dimensional space and a side supporting the moving component;
Calibrating a sensor coordinate system on the one surface based on the first sensing image;
Determining at least four points on the three-dimensional space and setting a game zone; And
And recognizing the moving component in the game zone to proceed with the game,
Wherein the coordinates of the four points are the coordinates on the calibrated coordinate system. The method according to claim 1,
Wherein the calibrating comprises:
Determining if the first sensing image includes the one side;
Calculating a normal vector of the one surface; And
And calibrating one axis of the sensor coordinate system parallel to the normal vector of the one surface. 3. The method of claim 2,
Wherein determining if the first sensing image includes the one side comprises:
Generating a point cloud for the first sensing image;
Matching a point cloud for the first sensed image with a previously stored point cloud for one or more candidates for the one surface; And
And determining through the matching point by the matching whether the sensing image includes the one side. 3. The method of claim 2,
Wherein the calibrating comprises:
If the first sensing image does not include the one side, calculating a normal vector of the one side based on the position of the moving component included in the first sensing image. 5. The method of claim 4,
Wherein the calibrating comprises:
Transmitting a move command to the mobile component causing the mobile component to change its direction of movement at least once;
Tracking movement trajectories of the moving component through the sensor to determine at least three points included in the position trajectory of the moving component; And
Further comprising: calculating a plane equation of one surface supporting the moving component based on the at least three points, and calculating a normal vector of the one surface. 6. The method of claim 5,
Determining four points on the three-dimensional space and setting a game zone,
And determining based on the at least three points. 3. The method of claim 2,
Wherein the step of recognizing the moving component in the game zone comprises:
Acquiring a second sensing image including the moving component of the game zone range and one side supporting the moving component through the sensor;
Filtering the one side in the second sensing image; And
And recognizing the moving component based on the filtered second sensing image. 8. The method of claim 7,
Wherein filtering the one side comprises:
Further comprising filtering a point below a predetermined height from the position of the sensor. 8. The method of claim 7,
Wherein filtering the one side comprises:
Determining at least three points on the game zone and determining a plane including at least three points on the game zone; And
Further comprising filtering points within the predetermined range from the plane. 10. The method of claim 9,
Wherein recognizing the moving component comprises:
And recognizing the moving component based on the corresponding plurality of points when the number of filtered points is equal to or greater than the threshold. A computer-readable medium having stored thereon program instructions readable by a computer and operable by the computer, the program instructions being executable by a processor of the computer, In a game zone, a sensor coordinate system corresponding to the game zone. An apparatus for playing a game according to object recognition,
A sensor for obtaining a sensing image including at least one of a movable component movable in three-dimensional space and a surface supporting the movable component;
A calibration unit for calibrating a sensor coordinate system on the one surface based on the sensing image;
A game zone setting unit for determining four points on the three-dimensional space and setting a game zone; And
And a game progress unit for recognizing the moving component in the game zone to proceed with the game,
Wherein the coordinates of the four points are the coordinates on the calibrated coordinate system. A system for playing a game according to object recognition,
A sensor for obtaining a sensing image including at least one of a movable component movable in three-dimensional space and a surface supporting the movable component; A calibration unit for calibrating a sensor coordinate system on the one surface based on the sensing image; A game zone setting unit for determining four points on the three-dimensional space and setting a game zone; And a game progress unit for recognizing the moving component in the game zone and playing the game, wherein the coordinates of the four points are coordinates on the calibrated coordinate system; And
Communicate with the device; And a moving component configured to move in accordance with the move command when receiving a move command from the device.

Images