KR20190048635A - Indication Objects Augmenting Apparatus using Base Point of 3D Object Recognition of Facilities and Buildings with Relative Coordinates of Indication Objects and Method thereof, and Computer readable storage medium - Google Patents

Abstract

The present invention relates to augmented reality technology and, more specifically, to a device to augment the position of a signal on a real-time image, capable of forming an augmented reality service displaying the positions of various signals installed on a facility or machine by matching the positions with real-time images, and a method thereof. The device includes: an image obtaining part obtaining an image containing an object; an object recognizing part recognizing the object in the image; and a three-dimensional image processing part three-dimensionally processing the image.

Description

TECHNICAL FIELD [0001] The present invention relates to a device for enhancing a position of a marker on a real-time image using three-dimensional recognition of objects in a video and relative coordinate information between the reference point of the object and the marker, and a computer readable storage medium storing the method. Object Recognition of Facilities and Buildings with Relative Coordinates of Indication Objects and Method thereof, and Computer Readable Storage Medium}

Field of the Invention [0002] The present invention relates to augmented reality technology, and more particularly, to an apparatus and method for enhancing a marker position in real time image realizing an augmented reality service that displays positions of various displays installed in a facility or a facility in real time .

The present invention also relates to an apparatus and method for enhancing the position of a marker on a real-time image that can accurately show a position and a measurement data of a sensor in a real-time image on a scene with a power facility.

In the past, it has been proposed to use a GPS (Global Positioning System) to provide the coordinates of the markers, to match the position of the markers to the real time image of the space, or to inform the markers that the markings are present, A method of overlaying real-time images has been used.

이상으로 커서 실시간 영상에 있는 설비 또는 시설에 설치되어 있는 다수의 표지물을 차별되게 위치에 정합하여 보여주는 것은 매우 어려운 실정이다. 이를 보여주는 도면이 도 1에 도시된다. 도 1을 참조하면, 좌표상의 전류센서1과 실제 위치간에 증강오차가 발생하곤 한다. 또는 좌표상의 전주01과 실제 위치간에 증강오차가 발생한다.The method of using the spatial coordinates by the GPS is as follows:

It is very difficult to display a plurality of markings installed in a facility or a facility in a real-time image differently from the position. A diagram showing this is shown in Fig. Referring to FIG. 1, an augmentation error between the current sensor 1 on the coordinate and the actual position is often generated. Or an incremental error occurs between the pole 01 on the coordinate and the actual position.

In addition, electric power facilities installed and operated on the spot are monitored by monitoring signs such as temperature, vibration, wind speed, and various sensors. It is a patented technology designed through "Research on smart facility wearable technology of electric power facility" and "Preliminary study of development of safety disaster management fool proof system".

In existing augmented reality technology, the position and number of the sensor are displayed on the photograph using the GPS coordinates or the equipment to indicate the position where the measured values are on the sensor attached to the facility, and the measurement data And adopts a method of expressing in a tabular form. Therefore, it was difficult to construct the data and it was inconvenient to check the measurement data in the field.

In addition, showing the related information about the sign in the form of a text has a disadvantage that the position of the sign is difficult to be grasped and the reality is poor.

1. Korean Patent Publication No. 10-2017-0088501 2. Korean Registered Patent No. 10-1755248 (Registration Date: Jul. 07, 2013) 3. Korean Registered Patent No. 10-1356644 (Registration date: 2014.01.22)

The present invention has been proposed in order to solve the problem according to the above background art, and it is an object of the present invention to provide an apparatus and method for enhancing a marker position in a real-time image realizing an augmented reality service that shows the positions of various displays installed in a facility or a facility, The purpose is to provide.

It is another object of the present invention to provide an apparatus and method for enhancing the position of a marker on a real-time image that can precisely match a position and a measurement data of a sensor with a power facility in a real-time image on the spot.

In order to achieve the above object, the present invention provides an apparatus for enhancing a marker position in a real-time image realizing an augmented reality service that displays the positions of various displays installed in a facility or a facility in real time.

The marker position enhancing apparatus includes:

An image acquiring unit acquiring an image containing an object;

An object recognition unit for recognizing an object in the image;

An image 3D processing unit for processing a 3D image through an object recognition;

A cover information inquiry unit for inquiring cover information having relative coordinates from a reference point of the object;

A real-time coordinate matching unit for matching the coordinates (positions) of the 3D image and the markers; And

And an augmented reality display unit for enhancing and displaying the coordinates (positions) of the 3D image and the beacon.

At this time, when a reference point of an object is recognized by recognizing an object in the image, a reference point of the object can be determined by designating a range of the object.

In addition, the 3D image processing may be any one of object recognition, singularity recognition, and edge recognition.

Also, the enhancement may be characterized by being able to enhance data information of the mark.

The object recognizing unit may further include: a object shape recognizing unit for recognizing an object in the image; And a object reference point processing unit for determining a reference point of the object in the image in the image.

Also, the image 3D processing unit may include a object-camera distance calculation unit for calculating a distance between the object and the camera using the feature point of the recognized object and the angle formed by the camera; A camera posture (angle) calculation unit for calculating a posture (angle) of gazing an object using the position confirmation means; And an image 3D coordinate calculator for converting an object-camera distance calculation result and a camera posture (angle) value into a measurement theory to convert the image into a 3D image.

Also, the cover information inquiry unit may include a object-cover DB unit for constructing information related to the enhancement object and the cover in a DB form. At this time, the cover information inquiry unit searches for facilities and facilities (objects) located nearby using the position of the reference point acquired by the object reference point processing unit of the object recognizing unit, and inquires about the cover information connected thereto.

Also, the object-marker DB unit may be used in connection with an external DB.

The real-time coordinate matching unit may determine whether to re-calculate coordinates of information to be augmented when the attitude (angle) of the camera changes when information is augmented on the screen, and calculate the coordinates of the image 3D coordinate and the mark according to the determination result And the matching is performed.

On the other hand, another embodiment of the present invention includes: (a) acquiring an image containing an object by an image acquiring unit; (b) recognizing an object in the image by the object recognizing unit; (c) performing 3D image processing on the image through object recognition by the image 3D processing unit; (d) a marker information inquiry unit inquiring marker information having relative coordinates from a reference point of the object; (e) matching the coordinates (positions) of the 3D image with the markers of the real time coordinate matching unit; And (f) augmenting and displaying the 3D image and the coordinates of the marker on the augmented reality display unit.

In the step (b), the object shape recognizing unit recognizes an object in the image; And

And determining a reference point of the object in the object by the object reference point processing unit.

The step (c) may include calculating the distance between the object and the camera using the object-camera distance calculation unit and the angle between the camera and the feature point of the recognized object. Calculating a posture (angle) of gazing at an object using the camera posture (angle) calculating position checking means; And a step of 3Dizing the image using the object-camera distance calculation result and the camera posture (angle) value in the measurement theory, and the image 3D coordinate calculation unit.

The step (d) may include constructing information related to objects and markers to be enhanced by the object-and-markers DB in the form of a database (DB).

The step (e) includes the steps of: determining whether coordinates of information to be augmented should be recalculated when the posture (angle) of the camera changes when the real-time coordinate-matching unit information is augmented on the screen; And matching coordinates of the image 3D coordinate and the coordinates of the image by calculation according to the determination result.

On the other hand, another embodiment of the present invention can provide a computer-readable storage medium storing the program code for executing the method for enhancing the position of a marker on the real-time image described above.

 According to the present invention, an augmented reality technology that can precisely match the position and measurement data of a sensor with a power facility in a real-time image on the spot can be implemented.

Further, another advantage of the present invention is that the management efficiency can be dramatically improved and the work efficiency can be improved by increasing the reality.

FIG. 1 is an example of an error of marker enhancement by general GPS.
2 is an example of a screen for defining object recognition and reference points.
FIG. 3 is a conceptual diagram showing a marker position increase (error reduction) according to an embodiment of the present invention.
4 is a block diagram of an apparatus 100 for enhancing a marker position in a real-time image according to an embodiment of the present invention.
5 is a conceptual diagram of a pole edge detection test according to another embodiment of the present invention.
FIG. 6 is a conceptual diagram showing object recognition as a result of the detection test in FIG.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

Like reference numerals are used for similar elements in describing each drawing.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. The term " and / or " includes any combination of a plurality of related listed items or any of a plurality of related listed items.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Should not.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an apparatus and method for enhancing a marker position in a real-time image according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

2 is an example of a screen for defining object recognition and reference points. Referring to FIG. 2, a real-time image is space-recognized by recognizing the type of facility or facility (real or imaginary) of a real-time image, and defines a certain position of the facility or facility as a reference point . The reference point refers to the end, middle point, intersection point, etc. of an object recognized through object recognition.

FIG. 3 is a conceptual diagram showing a marker position increase (error reduction) according to an embodiment of the present invention. Referring to FIG. 3, the location of a marker to be displayed in real time is assigned relative coordinates in each direction from a certain position, recognizes the type of facility or facility shown in the real-time image, The position of the marker is defined as a reference point and the position of the marker is matched to the real-time image which is spatialized through the relative coordinates of the marker from the reference point. In FIG. 3, the relative coordinates are represented by the X, Y, and Z axes, and particularly, the Z axis direction is the coarsened direction.

이내로 대폭 향상시킬 수 있으며, 설비 또는 시설과 표지물을 동시에 현실감 있게 나타낼 수 있어 기존에서 표지물의 위치를 표현하기 위해서 설비 또는 시설 사진에 표지물 번호 및 위치 표시 등의 자료작성이 필요 없게 되어 관리업무 단순화 및 효율개선 등 효과가 크다Accuracy

And it is possible to display the facilities or the facilities and the signs at the same time in a realistic manner. Therefore, it is not necessary to create the data such as the marker number and the location indication in the facility or the facility photograph in order to express the position of the marker in the past, Efficiency improvement is great.

4 is a block diagram of an apparatus 400 for enhancing a marker position in a real-time image according to an embodiment of the present invention. 4, the marker position enhancing apparatus 400 includes an image acquiring unit 410, an object recognizing unit 420, an image 3D processing unit 430, a cover information inquiry unit 440, a real time coordinate aligning unit 450, Augmented reality display unit 470, and the like.

The image acquisition unit 410 is an image sensor such as a camera for acquiring an image of an object to be viewed.

The object recognizing unit 420 recognizes the shape of an object, such as an outline, a size, and a shape, of an object of the facility and / or facility acquired through the image acquiring unit 410. For this purpose, the object recognition unit 420 may include a object shape recognition unit 421 for recognizing the object shape, and a object reference point processing unit 422 for defining the reference point using the recognized object shape.

The 3D image processing unit 430 includes a object-camera distance calculation unit 431 that calculates a distance between an object and a camera using the shape size recognized by the object shape recognition unit 421, A camera posture calculation unit 432 for calculating the posture (angle) of the camera from the shape of the recognized object acquired through the image acquisition unit 410, And a real-time image 3D coordinate calculator 433 for calculating an image having 3D coordinates in accordance with the trigonometrical surveying theory using the real-time image 3D coordinate calculator 433 and the like.

The camera posture calculation unit 432 calculates the posture (angle) of the camera to look at an object by using a position check means such as a geomagnetic sensor, a compass, or the like.

In addition to the object recognition technology described above, the 3D image processing can be classified into a singularity recognition and an edge recognition technology.

The cover information inquiry unit 440 searches for nearby facilities and / or facilities (objects) by using the positions of the reference points acquired by the object reference point processing unit 422 of the object recognition unit 420, From the database 40, and generates a object-markup DB. The object-marker DB is composed of the location of facilities and facilities (objects), the name of the marker, the relative coordinates from the reference point of the marker, and the display data information.

The real-time coordinate matching unit 450 determines whether the posture of the image sensor is changed before the coordinates of the 3D image and the object-mark DB are matched and recalculates coordinates to match the 3D coordinate of the image and the relative coordinates of the mark . In other words, if the posture of the image sensor is changed before the coordinates of the image and the object-mark DB are matched, the object recognition unit 420 performs object recognition again (451). Otherwise, if there is no change of posture, the 3D coordinate-based real-time image and the marker having relative coordinate information are matched with the real-time image through object recognition (452).

The augmented reality display unit 470 performs a function of augmenting and displaying a marker on a real-time image input through the image acquisition unit 410. [ The incremental display unit 470 may include a liquid crystal display (LCD), a light emitting diode (LED) display, a plasma display panel (PDP), an organic light emitting diode (OLED) display, a touch screen, a cathode ray tube (CRT) .

5 is a conceptual diagram of a pole edge detection test according to another embodiment of the present invention. Referring to Fig. 5, the electric pole edge is detected. In other words, the left screen is the detection screen of the electric pole edge in the pole of the object, and the right screen is the pole shape stored in advance in the database.

FIG. 6 is a conceptual diagram showing object recognition as a result of the detection test in FIG. Referring to FIG. 6, the left screen and the right screen of FIG. 5 are compared with each other, and crossing points, reference points, and the like are defined through object recognition at detected pole edges.

Means a unit for processing at least one function or operation, and may be implemented by hardware, software, or a combination of hardware and software.

(DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microprocessor, and the like, which are designed to perform the above- , Other electronic units, or a combination thereof. In software implementation, it may be implemented as a module that performs the above-described functions. The software may be stored in a memory unit and executed by a processor. The memory unit or processor may employ various means well known to those skilled in the art.

The method of enhancing the position of a marker in the real-time image according to the present invention may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination.

The program code (command) recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

The medium may be a transmission medium such as an optical or metal line, a wave guide, or the like, including a carrier wave for transmitting a signal designating a program command, a data structure, or the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

400: marker position enhancer 410: image acquiring unit
420: object recognition unit 430: image 3D processing unit
440: marker information inquiry unit 450: real-time coordinate matching unit
470: Augmented Reality Display

Claims (19)

An image acquiring unit acquiring an image containing an object;
An object recognition unit for recognizing an object in the image;
An image 3D processing unit for processing a 3D image through an object recognition;
A cover information inquiry unit for inquiring cover information having relative coordinates from a reference point of the object;
A real-time coordinate matching unit for matching the coordinates (positions) of the 3D image and the markers; And
An augmented reality display unit for enhancing and displaying the coordinates (position) of the 3D image and the beacon;
And a controller for controlling the position of the marker in the real-time image.
The method according to claim 1,
Wherein when a reference point of an object is recognized by determining an object in the image, a reference point of the object can be determined by designating a range of the object.
The method according to claim 1,
Wherein the 3D image processing is any one of object recognition, singularity recognition, and edge recognition.
The method according to claim 1,
Wherein the enhancement can also enhance the data information of the markers.
The method according to claim 1,
The object recognizing unit,
An object shape recognition unit for recognizing an object in the image; And
And a object reference point processing unit for determining a reference point of the object in the image in the real time image.
The method according to claim 1,
The image 3D processing unit,
An object-camera distance calculation unit for calculating a distance between the object and the camera using the feature point of the recognized object and the angle formed by the camera;
A camera posture (angle) calculation unit for calculating a posture (angle) of gazing an object using the position confirmation means; And
And an image 3D coordinate calculation unit that uses the object-camera distance calculation result and the camera posture (angle) value as the measurement theory to make the image 3D.
The method according to claim 1,
The cover information inquiry unit,
And a object-markup DB unit for constructing information related to the object to be augmented in the form of a database (DB), wherein the location of the reference point acquired by the object reference point processing unit of the object recognizing unit And searches for the marker information connected to the marker.
8. The method of claim 7,
Wherein the object-marker DB unit is used in connection with an external DB.
The method according to claim 1,
The real-time coordinate matching unit determines whether to re-calculate the coordinates of information to be augmented when the attitude (angle) of the camera changes when the information is augmented on the screen, and calculates the coordinate of the image 3D coordinate and the mark according to the determination result And the position of the marker in the real time image is matched.
(a) acquiring an image containing an object by an image acquiring unit;
(b) the object recognition unit recognizes an object in the image;
(c) 3D image processing of the image through object recognition by the image 3D processing unit;
(d) a marker information inquiry unit inquiring marker information having relative coordinates from a reference point of the object;
(e) matching the coordinates (positions) of the 3D image with the markers of the real time coordinate matching unit; And
(f) the augmented reality display unit enhances and displays the coordinates (position) of the 3D image and the marker;
The method comprising the steps of:
11. The method of claim 10,
Wherein when a reference point of an object is recognized by recognizing an object in the image, a reference point of the object can be determined by designating a range of the object.
11. The method of claim 10,
Wherein the 3D image processing is any one of object recognition, singularity recognition, and edge recognition.
11. The method of claim 10,
Wherein the enhancement can also enhance the data information of the markers.
11. The method of claim 10,
The step (b)
Recognizing the object in the image by the object shape recognizing unit; And
And determining a reference point of the object in the object based on the object reference point processing unit. 11. The method of claim 10,
The step (c)
Calculating a distance between the object and the camera using the object-camera distance calculation unit and the angle between the camera and the feature point of the recognized object;
Calculating a posture (angle) of gazing at an object using the camera posture (angle) calculating position checking means; And
And a step of 3Dizing the image by using the image-camera distance calculation result and the camera posture (angle) value in the image 3D coordinate calculation unit to the measurement theory.
11. The method of claim 10,
The step (d)
And constructing information related to objects and markers to be augmented by the object-markup DB unit in the form of a database (DB), wherein the location of the reference points acquired by the object reference point processing unit of the object recognizing unit And searching for the marker information associated with the marker.
17. The method of claim 16,
Wherein the object-marker DB unit is used in connection with an external DB.
11. The method of claim 10,
The step (e) includes the steps of: determining whether coordinates of information to be augmented should be recalculated when a posture (angle) of the camera changes when real-time coordinate-matching-unit information is augmented on the screen; And
And matching the 3D coordinates of the image with the coordinates of the cover through computation according to the determination result.
18. A computer-readable storage medium storing program code for executing a method for enhancing a marker position in a real-time image according to any one of claims 10 to 18.

Images