KR102135883B1 - System and method for analyzing cargo of crane - Google Patents

Abstract

The crane lifting product analysis system provides information regarding the size and position of the hook and the lifting object based on the hook of the crane and the image sensor unit recognizing the lifting object lifted on the hook, and the image data measured by the image sensor unit. A central control unit for generating calculation data, a first wireless communication unit for wirelessly transmitting the calculation data, an upper control unit including a first display unit for displaying the calculation data, and a second wireless communication unit for wirelessly receiving the calculation data And a terrestrial control unit including a second display unit for displaying the calculation data, and a third wireless communication unit for wirelessly receiving the calculation data and transmitting the control data generated by calculating the calculation data and the calculation data. It includes a control unit including a third display unit.

Description

SYSTEM AND METHOD FOR ANALYZING CARGO OF CRANE

The present invention relates to a system and method for analyzing a lifting product of a crane, and more particularly, to a lifting system and method for lifting a crane that can prevent collision by analyzing the size and position of the lifting object.

The crane is a device for transporting heavy lifting objects, and is installed in a vehicle such as a vehicle and used in a construction site.

In general, a crane lifts and moves a heavy object. Since the lifting object is connected to the hook of the crane using a rope, it can be shaken when moving from side to side after lifting, and collision may occur in an adjacent crane or other structure in this process.

In order to prevent the crane's lifted objects from colliding with other objects during movement, a method of placing the number of signals on the ground to inform the crane driver of the collision is often used, but the crane driver sometimes sees the signal of the signal number incorrectly. There is also a case where it is not possible to accurately grasp the state of the antelope, and thus there is a problem of preventing an accident due to a collision of the antelope.

Korean Patent Publication No. 10-2018-0111123 (2018.10.11)

Accordingly, the technical problem of the present invention has been devised in this regard, and an object of the present invention is to provide a system for analyzing a lifting object of a crane capable of preventing collision by analyzing the size and position of the lifting object.

Another object of the present invention is to provide a method for analyzing the lift of the crane that can prevent the collision by analyzing the size and position of the lift.

The lifting system of a crane according to an embodiment for realizing the object of the present invention includes an image sensor unit for recognizing a hook of a crane and a lifting object lifted on the hook, and image data measured by the image sensor unit. A central operation unit for generating calculation data including information on the size and position of the hook and the lifting object, a first wireless communication unit for wirelessly transmitting the calculation data, and a first display unit for displaying the calculation data Control data generated by wirelessly receiving the operation data and calculating the operation data, including an upper control unit, a second wireless communication unit which wirelessly receives the operation data, and a second display unit that displays the operation data, and wirelessly receiving the operation data It includes a third wireless communication unit for wirelessly transmitting and a control unit including a third display unit for displaying the calculation data.

In one embodiment of the present invention, the image sensor unit may recognize the hook and the salvage using an object recognition algorithm to which a machine learning based Fast R-CNN is applied.

In one embodiment of the present invention, the image sensor unit may recognize the hook and the lifting object at a speed of 30 fps or more.

In one embodiment of the present invention, the central operation unit may calculate the relative size of the hook based on the image data in terms of the number of pixels occupied by the hook image relative to the number of full screen pixels.

In one embodiment of the present invention, the central operation unit calculates an actual distance between the image sensor unit and the hook based on the image data, and the actual distance between the image sensor unit and the hook is expressed by the following equation. Can be defined by

는 상기 영상 센서부의 화각의 1/2, B는 후크의 실제 면적, a는 영상 데이터 내의 전체 화면 픽셀 수, b는 영상 데이터 내에서 후크가 차지하는 픽셀 수를 나타낸다.Here, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, B is the actual area of the hook, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the hook in the image data.

In one embodiment of the present invention, the central operation unit generates enlarged image data that enlarges an image around the hook based on the image data, and lifts an object maintaining a constant distance from the hook in the enlarged image data. Recognized as water, the size of the lift can be calculated using a change in size of an image in the enlarged image data according to an actual distance between the image sensor unit and the hook.

In one embodiment of the present invention, the size of the lifting object calculated by the central operation unit may be defined by the following equation.

는 상기 영상 센서부의 화각의 1/2, a는 영상 데이터 내의 전체 화면 픽셀 수, b는 영상 데이터 내에서 인양물이 차지하는 픽셀 수를 나타낸다.Here, B is the actual area of the lift, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the salvage in the image data.

In one embodiment of the present invention, the information displayed on the first to third display units may be visual or auditory information.

The method for analyzing the lift of the crane according to an embodiment for realizing the object of the present invention includes the steps of generating an image data by recognizing the hook of the crane and the lifted object lifted on the hook by the image sensor, and the central operator Generating calculation data including information on the size and position of the hook and the lifting object based on the image data, transmitting the calculation data to the second wireless communication unit and the third wireless communication unit by a first wireless communication unit, and And a step in which the first display unit, the second display unit, and the third display unit display the calculation data.

In one embodiment of the present invention, the image sensor unit may recognize the hook and the salvage using an object recognition algorithm to which a machine learning based Fast R-CNN is applied.

In one embodiment of the present invention, the image sensor unit may recognize the hook and the lifting object at a speed of 30 fps or more.

In one embodiment of the present invention, the generating of the operation data includes calculating the relative size of the hook based on the image data and the number of pixels occupied by the image of the hook based on the total number of screen pixels, and the relative size of the hook. Comparing the size and the size of the actual hook to calculate the actual distance between the image sensor unit and the hook, generating an enlarged image data that enlarges the image around the hook based on the image data, the enlarged image Recognizing an object that maintains a certain distance from the hook as data as a salvage, and calculating the size of the salvage using a change in the size of the image in the magnified image data according to the actual distance between the image sensor unit and the hook It may include the steps.

In one embodiment of the present invention, the actual distance between the image sensor unit and the hook calculated in the step of calculating the actual distance between the image sensor unit and the hook may be defined by the following equation.

는 상기 영상 센서부의 화각의 1/2, B는 후크의 실제 면적, a는 영상 데이터 내의 전체 화면 픽셀 수, b는 영상 데이터 내에서 후크가 차지하는 픽셀 수를 나타낸다.Here, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, B is the actual area of the hook, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the hook in the image data.

In one embodiment of the present invention, the size of the lifting object calculated in the step of calculating the size of the lifting object may be defined by the following equation.

는 상기 영상 센서부의 화각의 1/2, a는 영상 데이터 내의 전체 화면 픽셀 수, b는 영상 데이터 내에서 인양물이 차지하는 픽셀 수를 나타낸다.Here, B is the actual area of the lift, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the salvage in the image data.

In one embodiment of the invention,

In one embodiment of the invention,

According to the present invention, the crane lift analysis system can accurately measure information about the size and location of the lift, and can inform the crane operator, manager, and signal number to easily recognize the position and size of the lift. Accordingly, it is possible to prevent a collision accident that may occur during movement of the lift.

In addition, the image sensor unit of the lifting product analysis system of the crane recognizes the hook and the lifting object using an object recognition algorithm to which a machine learning-based Fast R-CNN is applied, and recognizes the hook and the lifting object at a speed of 30 fps or more. can do. Therefore, the position of the hook and the lifting object can be tracked without delay in the real-time image, thereby enabling precise measurement of the lifting object.

In addition, the wireless communication units form a network in the form of a mesh that exchanges data with each other. Therefore, data transmission can be stably performed.

1 is a block diagram showing a system for analyzing a lift of a crane according to an embodiment of the present invention.
Figure 2 is a block diagram showing the upper control unit of the lifting system of the crane according to an embodiment of the present invention.
Figure 3 is a block diagram showing the ground control of the lifting product analysis system of the crane according to an embodiment of the present invention.
Figure 4 is a block diagram showing the control unit of the lifting system of the crane lift according to an embodiment of the present invention.
5 is a view for explaining the Fast R-CNN of the lift analysis system of the crane according to an embodiment of the present invention.
6 is a flow chart showing a method for analyzing the lift of the crane according to an embodiment of the present invention.
7 is a flowchart illustrating a step of generating calculation data of a method for analyzing a lift of a crane according to an embodiment of the present invention.
8 is a view for explaining a method for calculating the distance between the hook and the image sensor unit of the lifting system of the crane according to an embodiment of the present invention.

The present invention can be applied to various changes and can have various forms, and the embodiments will be described in detail in the text. However, this is not intended to limit the present invention to specific disclosure forms, and it should be understood that all modifications, equivalents, and substitutes included in the spirit and scope of the present invention are included. In describing each drawing, similar reference numerals are used for similar components. Terms such as first and second 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 other components. The terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise.

In this application, terms such as “comprises” or “consisting of” are intended to indicate the presence of features, numbers, steps, operations, components, parts or combinations thereof described in the specification, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, actions, components, parts or combinations thereof are not excluded in advance.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the present invention pertains. Terms, such as those defined in a commonly used dictionary, should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

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

1 is a block diagram showing a system for analyzing a lift of a crane according to an embodiment of the present invention. Figure 2 is a block diagram showing the upper control unit of the lifting system of the crane according to an embodiment of the present invention. Figure 3 is a block diagram showing the ground control of the lifting product analysis system of the crane according to an embodiment of the present invention. Figure 4 is a block diagram showing the control unit of the lifting system of the crane lift according to an embodiment of the present invention. 5 is a view for explaining the Fast R-CNN of the lift analysis system of the crane according to an embodiment of the present invention.

1 to 5, the side pulling prevention system 10 of the crane according to an embodiment of the present invention includes an upper control unit 100, a ground control unit 200, and a control unit 300.

The upper control unit 100 may include an image sensor unit 110, a central operation unit 120, a first display unit 130, and a first wireless communication unit 140.

The image sensor unit 110 may generate image data by recognizing the hook of the crane and the lifting object lifted on the hook. The image sensor unit 110 may recognize the hook and the lifting object using an object recognition algorithm to which a machine learning-based Fast R-CNN is applied.

The Fast R-CNN is a technology developed to compensate for the problem that the speed of the R-CNN is slow. The basic structure of R-CNN is as follows. Using the Region Proposal generation algorithm called Selective Search from the input image, Region Proposals estimated to exist are extracted. After that, each Region Proposal is in the form of an image in a rectangular bounding box. After making the same size for all Region Proposals, it is classified through CNN. In this process, one more model that predicts the exact location and size of the bounding box is used because it is impossible to determine the exact location of the object when performing image classification using Region Proposal. Therefore, one more regression model is implemented to perform the task of allowing each Bounding Box to pinpoint the exact position and size of the objects contained therein.

However, these R-CNNs must run one CNN for every Region Proposal, so it must be slow, and the model for extracting image features, the model for classification, and the model for holding the Bounding Box must be trained at the same time. It is bound to take a lot.

The technology developed to solve this problem is a model called Fast R-CNN, and the Fast R-CNN model does not extract a feature from an input image, as shown in FIG. 5, but instead uses Spatial Pyramid Pooling on a Feature Map through CNN. The feature is to extract features using RoI Pooling, a special form of. Through this, the structure of the network that has been slowed down by rotating one CNN per Region Proposal can be dramatically improved and speed can be increased.

In addition, the image sensor unit 110 according to an embodiment of the present invention may recognize the hook and the lifting object at a speed of 30 fps or more. Therefore, it is possible to track the position of the hook and the lifting object without delay in the real-time image.

The central operation unit 120 may generate operation data including information on the size and position of the hook and the lifting object based on the image data measured by the image sensor unit. The method of generating the operation data by the central operation unit 120 will be described in detail with reference to FIGS. 6 to 8.

The first display unit 130 may display calculation data generated by the central calculation unit 120. The information displayed on the first display unit 130 may be visual or auditory information. For example, the first display unit 130 may be configured as a display device, and the position and size of the hook and lifting object may be displayed as an image, and information on the hook and lift may be guided by voice. Based on the information displayed on the first display unit 130, the operator of the crane can recognize the position and size of the lifting object. Therefore, it is possible to prevent a collision accident that may occur during the movement of the lift.

The first wireless communication unit 140 transmits the calculation data to the second wireless communication unit 220 and the third wireless communication unit 340, and the second wireless communication unit 220 and the third wireless communication unit 340 Various data to be transmitted can be received.

The ground control unit 200 may include a second display unit 210 and a second wireless communication unit 220.

The second display unit 210 may display the calculation data. The information displayed on the second display unit 210 may be visual or auditory information. For example, the second display unit 210 may be configured as a display device, and the position and size of the hook and lifting object may be displayed as an image, and information on the hook and lift may be guided by voice. Based on the information displayed on the second display unit 210, the number of signals disposed on the ground can recognize the position and size of the lift. Therefore, the signal number can inform the crane driver of the risk of collision of the lifting object, and accordingly, it is possible to prevent a collision accident that may occur during movement of the lifting object.

The second wireless communication unit 220 may wirelessly receive calculation data transmitted by the first wireless communication unit 140, and the first wireless communication unit 140 may receive various data generated by the ground control unit 200. And a third wireless communication unit 340.

The control unit 300 can remotely manage the operating state of the crane. The control unit 300 may include a third display unit 310, a remote control unit 320, a data storage unit 330, and a third wireless communication unit 340. The control unit 300 may be configured as a PC program, WEB or mobile program.

The third display unit 310 may display calculation data transmitted by the first wireless communication unit 140. The information displayed on the third display unit 310 may be visual or auditory information. For example, the third display unit 310 may be configured as a display device, and the position and size of the hook and lifting object may be displayed as an image, and information on this may be guided by voice. Based on the information displayed on the third display unit 310, the manager disposed in the control unit can recognize the location and size of the lift. Accordingly, the manager can inform the crane operator of the risk of collision of the lift, and if necessary, remotely stop the operation of the crane or move the position of the crane. Accordingly, it is possible to prevent a collision accident that may occur during movement of the lift.

The remote control unit 320 may remotely control the operation of the crane based on the image data and the calculation data. For example, when the sensor data or the calculation data shows that there is a possibility of collision of lifting objects, the operation of the crane can be stopped remotely or the position of the crane can be moved remotely.

The data storage unit 330 may store data including the image data, the calculation data, and information remotely controlled by the remote control unit 320. The data stored in the data storage unit 330 may be used as data for calculation in the process of the central calculation unit 220 calculating the position and size of the lift.

The third wireless communication unit 340 receives data transmitted by the first wireless communication unit 140 and the second wireless communication unit 220, and the first wireless communication unit 140 and the second wireless communication unit 220 ) Can transmit various data.

The first wireless communication unit 140, the second wireless communication unit 230, and the third wireless communication unit 340 form a network in the form of a mesh that exchanges data with each other. Therefore, data transmission can be stably performed.

6 is a flow chart showing a method for analyzing the lift of the crane according to an embodiment of the present invention. 7 is a flowchart illustrating a step of generating calculation data of a method for analyzing a lift of a crane according to an embodiment of the present invention. 8 is a view for explaining a method for calculating the distance between the hook and the image sensor unit of the lifting system of the crane according to an embodiment of the present invention.

Referring to FIGS. 6 to 8, a method for analyzing a lift object of a crane according to an embodiment of the present invention includes generating an image data by recognizing a hook of the crane and a lift object lifted on the hook (S100) , Generating a calculation data including information on the size and position of the hook and the lifting object based on the image data (S200), wherein the first wireless communication unit generates the calculation data using the second wireless communication unit and the second wireless communication unit. 3 transmitting to the wireless communication unit (S300) and the first display unit, the second display unit and the third display unit (S400) for displaying the calculation data.

In the step S100 of generating the image data by recognizing the hook of the crane and the lifted object on the hook (S100), the image sensor unit recognizes the lifted object on the hook of the crane and the hook and generates image data. can do. The image sensor unit may recognize the hook and the salvage using an object recognition algorithm to which a machine learning-based Fast R-CNN is applied. In addition, the image sensor unit may recognize the hook and the lifting object at a speed of 30 fps or more.

In the step (S200) of generating the calculation data including information on the size and position of the hook and the lifting object based on the image data, the central computing unit determines the size and position of the hook and the lifting object based on the image data. It is possible to generate computational data including information about.

The step of generating the calculation data including information on the size and position of the hook and the lifting object based on the image data by the central operator (S200) is based on the image data, the image of the hook compared to the total number of screen pixels. Computing the relative size of the hook with the number of pixels occupied by (S210), Comparing the relative size of the hook and the actual size of the hook to calculate the actual distance between the image sensor unit and the hook (S220), the Generating enlarged image data by enlarging the image around the hook based on the image data (S230), Recognizing an object maintaining a certain distance from the hook as the salvage object in the enlarged image data (S240) and the It may include the step of calculating the size of the lifting object using the size change of the image in the enlarged image data according to the actual distance between the image sensor unit and the hook (S250).

In the step of calculating the relative size of the hook (S210), the relative size of the hook may be calculated from the number of pixels occupied by the hook image to the number of pixels of the entire screen of image data.

Thereafter, in step S220 of calculating the actual distance between the image sensor unit and the hook, the actual distance between the image sensor unit and the hook may be calculated by comparing the relative size of the hook with the size of the actual hook.

, 후크의 실제 면적을 B라고 하면, 전체 이미지에서의 한변의 실제 길이는

가 되고, 전체 이미지의 실제 면적은

이 된다. 이때, 영상 데이터 내의 전체 화면 픽셀 수를 a, 영상 데이터 내에서 후크가 차지하는 픽셀 수를 b하고 하면, 아래의 수학식 1과 같은 비례식이 정의될 수 있다.As shown in Figure 8, d the distance between the image sensor unit and the hook, 1/2 of the angle of view of the image sensor unit

, If the actual area of the hook is B, the actual length of one side of the entire image is

And the actual area of the entire image

It becomes. At this time, if the total number of screen pixels in the image data is a and the number of pixels occupied by the hook in the image data is b, a proportional expression as in Equation 1 below may be defined.

Equation 1

In summary, Equation 1 may be defined as Equation 2 below.

Equation 2

Summarizing Equation 2 with respect to d, which is a distance between the image sensor unit and the hook, the distance between the image sensor unit and the hook may be defined by Equation 3 below.

Equation 3

The imaging range measured by the image sensor unit is displayed in a pyramid shape when calculated in a three-dimensional form. In addition, the size of the image included in the image data may be changed according to the distance between the image sensor unit and the hook, and the size change of the image in the enlarged image data according to the actual distance between the image sensor unit and the hook may be used. The distance between the hook and the jig can be calculated. In addition, the accuracy of the measurement can be improved by correcting the measurement angle according to the position of the hook in the image included in the image data.

When the actual distance between the image sensor unit and the hook is calculated, an image may be enlarged by designating a new area around the detected hook position. In the generating of the enlarged image data (S230), the enlarged image data may be generated by enlarging an image around the hook based on the image data in order to recognize a lifted object that is lifted on the hook. Since there are many objects identical to the lifting object on the entire screen, it may be difficult to recognize the actual lifting object. The standard for recognizing an object can be a hook, and an object maintaining the same distance as the hook is recognized as an object (S240).

When an object is recognized, in step S250 of calculating the size of the object, the size of the object is calculated using a change in size of an image in the enlarged image data according to an actual distance between the image sensor unit and the hook. Can. At this time, the size of the lift can be calculated using the distance between the hook and the jig, and the size of the lift can be defined by Equation 4 below.

Equation 4

는 상기 영상 센서부의 화각의 1/2, a는 영상 데이터 내의 전체 화면 픽셀 수, b는 영상 데이터 내에서 인양물이 차지하는 픽셀 수를 나타낸다.Here, B is the actual area of the lift, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the salvage in the image data.

In the step (S300) of the first wireless communication unit transmitting the calculation data to the second wireless communication unit and the third wireless communication unit, operation data including information regarding the size and location of the lifting object may be transmitted.

After the wireless communication units receive the operation data, in operation S400 of displaying the operation data, the first display unit, the second display unit, and the third display unit may display the operation data.

Therefore, since the crane operator, the manager, and the signal number can easily recognize the position and size of the lifting object, it is possible to prevent a collision accident that may occur during the moving of the lifting object.

According to the present invention, the crane lift analysis system can accurately measure information about the size and location of the lift, and can inform the crane operator, manager, and signal number to easily recognize the position and size of the lift. Accordingly, it is possible to prevent a collision accident that may occur during movement of the lift.

In addition, the image sensor unit of the lifting product analysis system of the crane recognizes the hook and the lifting object using an object recognition algorithm to which a machine learning-based Fast R-CNN is applied, and recognizes the hook and the lifting object at a speed of 30 fps or more. can do. Therefore, the position of the hook and the lifting object can be tracked without delay in the real-time image, thereby enabling precise measurement of the lifting object.

In addition, the wireless communication units form a network in the form of a mesh that exchanges data with each other. Therefore, data transmission can be stably performed.

Although described above with reference to embodiments, those skilled in the art can variously modify and change the present invention without departing from the spirit and scope of the present invention described in the claims below. You will understand that there is.

10: lifting product analysis system
100: upper control
110: image sensor unit
120: central operation unit
130: first display unit
140: first wireless communication unit
200: ground control
210: second display unit
220: second wireless communication unit
300: control unit
310: third display unit
320: remote control
330: data storage
340: third wireless communication unit

Claims (14)

Generating calculation data including information on the size and position of the hook and the lifting object based on the image data measured by the hook and the hook of the crane and the image sensor unit that recognizes the lifting object lifted on the hook An upper control unit including a central operation unit, a first wireless communication unit for wirelessly transmitting the operation data, and a first display unit for displaying the operation data;
A ground control unit including a second wireless communication unit wirelessly receiving the calculation data and a second display unit displaying the calculation data; And
A third wireless communication unit that wirelessly receives the calculation data and transmits control data generated by calculating the calculation data, a third display unit that displays the calculation data, a remote control unit that remotely controls the upper control unit, and And a control unit including a data storage unit for storing the image data and the operation data,
The central operation unit calculates the relative size of the hook based on the image data, based on the number of pixels occupied by the image of the hook compared to the total number of screen pixels,
The central calculation unit calculates an actual distance between the image sensor unit and the hook based on the image data, and the actual distance between the image sensor unit and the hook is a crane lift analysis system defined by the following equation. .

Here, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, B is the actual area of the hook, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the hook in the image data.
The system of claim 1, wherein the image sensor unit recognizes the hook and the lifting object using an object recognition algorithm to which a machine learning-based Fast R-CNN is applied.
The lifting system of claim 1, wherein the image sensor unit recognizes the hook and the lifting object at a speed of 30 fps or more.
delete delete According to claim 1,
The central operation unit generates enlarged image data obtained by enlarging an image around the hook based on the image data, recognizes an object maintaining a constant distance from the hook as the salvage object from the enlarged image data, and the image sensor unit Crane size analysis system, characterized in that for calculating the size of the lift by using the size change of the image in the enlarged image data according to the actual distance between the and the hook.
The method of claim 6,
The lifting object analysis system of the crane, characterized in that the size of the lifting object calculated by the central operation unit is defined by the following equation.

Here, B is the actual area of the lift, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the salvage in the image data.
According to claim 1,
Crane information analysis system, characterized in that the information displayed on the first to third display portion is information by visual or hearing.
Generating an image data by recognizing the hook of the crane and the lifting object lifted on the hook;
Generating a calculation data including information on the size and position of the hook and the lifting object based on the image data by the central calculation unit;
Transmitting, by the first wireless communication unit, the calculation data to the second wireless communication unit and the third wireless communication unit; And
The first display unit, the second display unit and the third display unit includes the step of displaying the calculation data,
The step of generating the operation data,
Calculating a relative size of the hook based on the image data and the number of pixels occupied by the hook image compared to the total number of screen pixels;
Comparing the relative size of the hook and the actual size of the hook to calculate the actual distance between the image sensor unit and the hook;
Generating enlarged image data obtained by enlarging an image around the hook based on the image data;
Recognizing an object maintaining a certain distance from the hook as the salvage object from the enlarged image data; And
And calculating the size of the lifting object using a change in size of an image in the enlarged image data according to an actual distance between the image sensor unit and the hook.
The method of claim 9, wherein the image sensor unit recognizes the hook and the lifting object using an object recognition algorithm to which a machine learning-based Fast R-CNN is applied.
The method of claim 9, wherein the image sensor unit recognizes the hook and the lifting object at a speed of 30 fps or more.
delete The lifting distance of the crane according to claim 9, wherein the actual distance between the image sensor unit and the hook calculated in the step of calculating the actual distance between the image sensor unit and the hook is defined by the following equation. Water analysis method.

Here, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, B is the actual area of the hook, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the hook in the image data.
14. The method of claim 13, wherein the size of the lifting object calculated in the step of calculating the size of the lifting object is defined by the following equation.

Here, B is the actual area of the lift, d is the distance between the image sensor unit and the hook,

Is 1/2 of the angle of view of the image sensor unit, a is the total number of screen pixels in the image data, and b is the number of pixels occupied by the salvage in the image data.

Images