KR102411052B1 - Apparatus and method for detecting movement of workers based on safety cap - Google Patents

Abstract

In the method for detecting the motion of a worker based on a helmet, performed by the worker motion detection system according to an embodiment of the present invention, (a) a motion sensor capable of detecting the motion of the worker mounted on the hard hat, collecting data; (b) the motion detection sensor extracts characteristic information from the behavior data, compares the characteristic information with a pre-stored operation state pattern, and transmits the motion information of the worker corresponding to the matching operation state pattern to the server; and (c) after the server receives the motion information, transmitting the motion information to the manager terminal; but, the pre-stored motion status patterns are classified into patterns that can indicate the status of the worker wearing a hard hat and whether or not there is danger.

Description

Apparatus and method for detecting movement of workers based on hard hats {APPARATUS AND METHOD FOR DETECTING MOVEMENT OF WORKERS BASED ON SAFETY CAP}

The present invention relates to a system for calculating the state of a worker through a helmet equipped with a sensor. In detail, it relates to a system that calculates the worker's current state through machine learning and informs the manager's terminal when the sensor calculates the worker's behavior data.

With the recent development of technology, various smart devices are being developed. For example, the wearable device may be used to detect a wearer's location or state.

According to this trend, smart devices are being introduced even in places that perform dangerous tasks such as construction sites. Referring to Korea Patent Registration No. 10-2061561 smart helmet and safety management system including the same, a sensor unit is provided in the fixing part of the helmet to detect the wearer's movement. However, since the sensed signal is limited to whether the helmet is worn and the angle signal processing through the fixing unit, the algorithm accuracy and reproducibility for various situations experienced by workers due to the characteristics of signal processing are limited.

Prior Document 1: Korean Patent No. 10-2061561 (application date 2019.08.29.)

In order to solve the above problems, the present invention calculates behavioral data based on the behavior of the worker through a hard hat equipped with a motion detection sensor that detects the motion of the worker, and determines the safety status of the worker at the job site through machine learning intended to calculate.

In addition, the purpose of this is to create an environment in which supervisors can easily check the safety status of workers working at the job site.

According to an embodiment of the present invention for achieving the above technical task, in the method for detecting the motion of a worker based on a hard hat, performed by the worker motion detection system, (a) detecting the motion of the worker mounted on the hard hat A motion detection sensor capable of collecting behavior data; (b) the motion detection sensor extracts characteristic information from the behavior data, compares the characteristic information with a pre-stored operation state pattern, and transmits the motion information of the worker corresponding to the matching operation state pattern to the server; and (c) after the server receives the motion information, transmitting it to the manager terminal; but, the pre-stored motion status pattern can be classified into patterns that can indicate the worker's wearing a helmet and the status of danger. have.

In addition, the motion detection sensor is a sensor capable of detecting a tilt of three or more axes, and may include at least one of an acceleration sensor and a gyro sensor.

In addition, the motion detection sensor may be a detection sensor capable of detecting the inclination of 6 axes.

In addition, step (b) compares at least one of the type of information constituting the characteristic information, the value and order indicated by the corresponding information, and at least one of the type constituting the pre-stored operation state pattern, and the value and order indicated by the information. Thus, the operation information can be determined.

In addition, step (b) can deliver any one of digital information about the state of the worker wearing a hard hat and digital information about whether the worker is at risk to the server.

In addition, the characteristic information includes information on the rate of change of the motion detection sensor data over time, the size information of the data calculated by the motion detection sensor, statistical characteristic information of the data calculated by the motion detection sensor, and energy included in the data calculated by the motion detection sensor. It may include at least one of information and correlation information between different inertia axis data in the data calculated by the motion detection sensor.

In addition, the motion state pattern is generated in advance by a motion pattern recognition algorithm, and behavior data for a plurality of workers is collected by the motion pattern recognition algorithm, and the size, frequency, and noise of each behavior data and between the noise and the plurality of behavior data Characteristic information corresponding to each behavioral data is extracted by correlation analysis, and by performing learning on classifying characteristic information based on a machine learning algorithm, each behavioral data is classified, and the It can be created by judging the operating state.

In addition, any one of K-NN, RBF, and Neural Network may be used as the machine learning algorithm, but the technical scope of the present invention is not necessarily limited to these examples.

In addition, operation information includes status information on whether or not a hard hat is being worn, status information on whether the worker has received an external shock or collapses, and status information on whether vibration or movement has occurred in the space where the worker works. may include

In addition, it is possible to search for a motion state pattern having more than a preset similarity value with the characteristic information of the behavior data, and to classify the worker's motion information mapped with the status pattern as a result of the search.

In addition, the motion pattern recognition algorithm can be updated based on the motion status information received by the server and the motion status information of the actual worker.

Also, in step (c), the server transmits the information about the worker's identification information, the worker's activity level, the worker's affiliation, the worker's job, the worker's location, the worker's motion status information, and the battery level of the motion sensor to the manager's terminal. And, the manager terminal may display the received information on one screen.

In addition, when the worker recognition sensor installed in the hazardous area recognizes that the motion detection sensor of the hard hat is adjacent within the preset range based on the short-distance network, it detects the identification information of the worker wearing the hard hat and sends an access request to the server, When the server approves the access request, access to the dangerous area can be permitted.

In addition, when two or more different workers are recognized as wearing hard hats, the server may approve the work in the hazardous area.

In addition, when the server receives operational state information indicating that two or more different workers are wearing hard hats from the worker recognition sensor installed in the hazardous area, the server compares the previous operational state information before a predetermined time and, if they do not match, selects two workers. By recognizing more than one person, the server can approve work in the hazardous area.

In addition, in the safety helmet-based worker's motion detection system, the motion detection sensor is provided in the hard hat to detect the motion of the worker to generate behavior data, and to calculate the motion information of the worker based on the behavior data; a server that receives the motion information from the motion sensor and transmits it to the manager terminal; A manager terminal displaying the motion information received from the server; including, a motion sensor capable of detecting the motion of the wearer mounted on the hard hat collects behavior data, and the motion sensor extracts characteristic information from the behavior data and compares the characteristic information with the pre-stored motion status pattern, transmits the worker's motion information corresponding to the matching motion status pattern to the server, and after the server receives the motion information, transmits it to the manager terminal, but the pre-stored motion The state pattern can be classified into patterns that can indicate the state of the worker wearing a hard hat and the state of danger.

Calculating behavior data based on the behavior of the worker through a hard hat equipped with a motion detection sensor for detecting the motion of the worker according to an embodiment of the present invention, and calculating the safety status of the worker at the job site through machine learning do.

It is said that the biggest cause of accidents occurring at various workplaces in recent years is not wearing a helmet. Therefore, through the present invention, it is possible to prevent accidents in advance by monitoring the wearing of hard hats by workers in real time, and to quickly inform the headquarters when a dangerous accident such as a fall or collapse occurs, so that the accident can be quickly dealt with.

1 is a diagram showing the configuration of a worker motion detection system according to an embodiment of the present invention.
Figure 2a is a view showing the configuration of the helmet 100, according to an embodiment of the present invention.
2B is a diagram showing the configuration of the motion detection sensor 120 according to an embodiment of the present invention.
3 is an operation flowchart illustrating a method for detecting the motion of a worker based on a hard hat, performed by the worker motion detection system, according to an embodiment of the present invention.
4 is an operation flowchart illustrating a process in which the motion detection sensor 120 calculates motion information according to an embodiment of the present invention.
5 is a view showing examples of different inertia axis data according to the situation of the worker.
6 is an operation flowchart for generating a motion pattern recognition algorithm according to an embodiment of the present invention.
7 is an exemplary view of the state information of the worker displayed on the manager terminal (300).
8A and 8B are diagrams related to an embodiment for utilizing the safety helmet of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The following examples are detailed descriptions to help the understanding of the present invention, and do not limit the scope of the present invention. Accordingly, an invention of the same scope performing the same function as the present invention will also fall within the scope of the present invention.

1 is a diagram showing the configuration of a worker motion detection system according to an embodiment of the present invention.

Referring to FIG. 1 , the worker motion detection system 10 may include a hard hat 100 , a server 200 , and a manager terminal 300 . In addition, although not shown in the drawing, the respective devices may be connected to each other through a communication network by wire or wireless.

According to an embodiment of the present invention, in the worker motion detection system 10, the motion sensor capable of detecting the motion of the worker mounted on the hard hat 100 collects behavior data, and the motion sensor features the behavior data from the behavior data. After extracting the information, the worker's motion information corresponding to the matching motion status pattern is transmitted to the server 200 by comparing it with the previously stored motion status pattern.

Thereafter, the server 200 transmits the received operation information to the manager terminal 300 to determine the state of the worker.

At this time, the behavior data refers to the motion detection sensor provided in the hard hat 100 corresponding to the 6-axis change data or raw data corresponding to the behavior of the worker. It means data, and it can be inertia or acceleration data with different axes. For example, the motion sensor may correspond to 6-axis change data corresponding to the movement of the worker.

In addition, the feature information is a value extracted from the behavior data, and may be a value calculated by analyzing the size, frequency, and noise of the behavior data and a correlation between a plurality of behavior data.

In addition, the pre-stored operation state pattern means a value classified into a pattern that can indicate the state of the worker wearing the hard hat 100 and whether there is a danger. Through this, the hard hat 100 is to determine the actual state of the worker based on the behavior data measured from the worker.

According to an embodiment of the present invention, the hard hat 100 is a hat for a worker to wear for work to protect his/her head, and in the present invention, a motion sensor for detecting the motion of the worker is provided.

The motion sensor collects behavior data based on the behavior of the worker, calculates the motion information of the current worker, and transmits it to the server 200 .

A detailed description of the hard hat 100 will be further performed through FIGS. 2A and 2B to be described later.

According to an embodiment of the present invention, the server 200 receives the operation information of the worker from at least one or more hard hats 100 , and transmits it to the manager terminal 300 .

According to an embodiment of the present invention, the manager terminal 300 is a terminal of a manager who manages workers, and receives and displays the worker's motion information from the server 200 .

In this case, the manager terminal 300 refers to a communication terminal capable of using a terminal application in a wired/wireless communication environment. Although the manager terminal 300 is illustrated as a smart phone, which is a type of portable terminal in FIG. 1 , the inventive concept is not limited thereto, and as described above, there is no limitation on a terminal capable of mounting a terminal application can be borrowed

In more detail, the manager terminal 300 may include a handheld computing device (eg, a PDA, an email client, etc.), any type of mobile phone, or any other type of computing or communication platform. However, the present invention is not limited thereto.

In addition, the application for using the worker motion detection system 10 used by the manager terminal 300 may be an application built into the manager terminal 300, or an application downloaded from an application distribution server and installed in the manager terminal 300. have.

Meanwhile, the communication network serves to connect the hard hat 100 , the server 200 , and the manager terminal 300 . That is, the communication network means a communication network that provides an access path so that the hard hat 100 and the manager terminal 300 can transmit and receive data after accessing the server 200 . The communication network is, for example, wired networks such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), ISDNs (Integrated Service Digital Networks), and wireless networks such as wireless LANs, CDMA, Bluetooth, and satellite communication. may be covered, but the scope of the present invention is not limited thereto.

As a further embodiment, the server 200 and the manager terminal 300 may be combined into one and used. That is, the manager terminal 300 may concurrently serve as the server 200 .

Figure 2a is a view showing the configuration of the helmet 100, according to an embodiment of the present invention.

Referring to FIG. 2A , the hard hat 100 may include a main body 110 and a motion detection sensor 120 .

According to an embodiment of the present invention, the main body 110 has an optimal shape for protecting the head of the worker.

Therefore, in the present invention, if the helmet 100 is provided with a motion detection sensor 120 to effectively collect behavior data, the shape of the main body 110 does not limit the scope of the present invention.

According to an embodiment of the present invention, the motion sensor 120 detects the motion of the worker, collects behavior data, calculates the motion information of the worker based on the collected behavior data, and transmits it to the server 200 .

At this time, the motion detection sensor 120 is a sensor capable of detecting a tilt of three or more axes in a selective embodiment, and includes at least one of an acceleration sensor and a gyro sensor, or can detect a tilt of six axes in another optional embodiment It may be configured as a detection sensor.

2B is a diagram showing the configuration of the motion detection sensor 120 according to an embodiment of the present invention.

Referring to FIG. 2B , the motion sensor 120 may include a communication module 121 , a memory 122 , a processor 123 , a sensor unit 124 , and a power supply unit 125 .

In detail, the communication module 121 provides a communication interface necessary to provide a transmission/reception signal between the hard hat 100 and the server 200 in the form of packet data in conjunction with a communication network. Furthermore, the communication module 121 may receive a data request from the server 200 and transmit data in response thereto.

Here, the communication module 121 may be a device including hardware and software necessary for transmitting and receiving signals such as control signals or data signals through wired/wireless connection with other network devices.

In the memory 122, a program for detecting the motion of the worker based on the hard hat 100 is recorded. In addition, the processor 123 performs a function of temporarily or permanently storing the processed data. Here, the memory 122 may include magnetic storage media or flash storage media, but the scope of the present invention is not limited thereto.

In addition, the memory 122 may serve as a database in an optional embodiment, and information of workers, behavioral data, characteristic information, operation state patterns, and the like may be stored.

The processor 123 is a kind of central processing unit and controls the entire process of detecting the motion of the hard hat-based worker. Each step performed by the processor 123 will be described later with reference to FIG. 3 .

Here, the processor 123 may include all kinds of devices capable of processing data, such as a processor. Here, the 'processor' may refer to, for example, a data processing device embedded in hardware having a physically structured circuit to perform a function expressed as a code or command included in a program. As an example of the data processing apparatus embedded in the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated (ASIC) circuit) and a processing device such as a field programmable gate array (FPGA), but the scope of the present invention is not limited thereto.

The sensor unit 124 is a sensor capable of detecting a tilt of three or more axes, and any one of an acceleration sensor and a gyro sensor may be applied.

In a further embodiment, the sensor unit 124 may include a global positioning system (GPS) capable of detecting a location to measure the location information of the worker. Based on the measured location information, it is possible to determine where the worker is working or whether the worker is approaching the danger zone. You can check if the job is being done.

The power supply unit 125 provides power to the motion detection sensor 120 provided in the hard hat 100 . At this time, the power supply unit 125 is provided with a battery to operate.

In this case, the motion detection sensor 120 reduces battery consumption and data packet consumption by providing minimal motion information when communicating with the server 200 in an optional embodiment. For example, if the hard hat 100 transmits the worker's status as coordinates and data to the server 200, the worker's status can be accurately identified, but battery and data packet consumption increases, but simply "danger", "falling" If only brief information such as "and "not wearing a hard hat" is transmitted to the server 200, data packet consumption is reduced during communication and battery efficiency is also increased.

3 is an operation flowchart illustrating a method for detecting the motion of a worker based on a helmet, performed by the worker motion detection system, according to an embodiment of the present invention.

Referring to FIG. 3 , the motion sensor 120 collects worker's behavior data ( S310 ).

In a further embodiment, the motion sensor 120 checks whether the worker wears the hard hat 100 , but when the worker wears the hard hat 100 , the motion detecting sensor 120 operates to operate the battery of the hard hat 100 . can save

The motion sensor 120 calculates motion information through the behavior data, and transmits the motion information to the server 200 (S320).

In this case, the process of the motion detection sensor 120 calculating the motion information will be described with reference to FIG. 4 to be described later.

At this time, the motion information transmitted by the motion sensor 120 to the server 200 may correspond to any one of digital information about the state in which the worker wears the hard hat 100 and digital information about whether the worker is at risk. have. The reason why the motion sensor 120 converts the worker's motion information into simple digital information and transmits it to the server 200 is the reason for using small data packets and saving the battery as described above. In addition, as an additional embodiment, the motion detection sensor 120 may reduce battery consumption by calculating the motion information at a preset period rather than always calculating the motion information.

The server 200 transmits the received operation information to the manager terminal 300 (S330).

In step S330, the server 200 receives information about the worker's identification information, the worker's activity level, the worker's affiliation, the worker's job, the worker's location, the worker's motion state information, and the remaining battery power of the motion sensor 120. It is transmitted to the manager terminal 300 .

Thereafter, the manager terminal 300 displays the received information on one screen, thereby notifying the manager of the current situation of the worker.

For example, FIG. 7 is an exemplary diagram of worker status information displayed on the manager terminal 300. Referring to FIG. 7, worker status 710, data reception time 720, and worker location information ( 730), whether or not the helmet is worn 740, and the battery state 750 may be displayed.

The worker's status 710 may display the server 200 connection status of the hard hat 100, the cumulative number of staff and the amount of activity, and the affiliation or name and rank of the worker.

The data reception time 720 may correspond to the time at which the server 200 receives operation information from the hard hat 100 .

The location information 730 of the worker indicates the location where the worker is working based on the received motion information. At this time, the position information 730 of the worker is measured based on the change time of the acceleration measured by the motion sensor 120 based on the preset position. However, if the helmet 100 is equipped with a GPS, the server 200 may directly receive the location information 730 of the worker from the GPS.

Whether or not the hard hat is worn 740 is displayed to check whether the worker wears the hard hat 100 . In an additional embodiment, the manager terminal 300 or the server 200 stores the location when the worker takes off the hard hat 100 or the communication connection is lost, and the worker wears the hard hat 100 later, or the communication is connected If it is, the location information 730 of the worker may be calculated based on the stored location.

The battery state 750 represents the battery state of the helmet 100 . The battery state 750 may be displayed in various colors depending on whether the battery is charged, and as an additional embodiment, when the charging rate is lower than a preset charge rate, a warning is provided to the manager terminal 300 or the hard hat 100 .

4 is an operation flowchart illustrating a process in which the motion detection sensor 120 calculates motion information according to an embodiment of the present invention.

Referring to FIG. 4 , the motion sensor 120 extracts feature information from the behavior data generated by the sensor unit 124 ( S321 ).

At this time, the calculated characteristic information is information on the rate of change of the data of the motion detection sensor 120 according to time, information on the size of the data calculated by the motion detection sensor 120, statistical characteristic information of the data calculated by the motion detection sensor 120, At least one of energy information included in the data calculated by the motion detection sensor 120 and correlation information between different inertial axis data in the data calculated by the motion detection sensor 120 is included.

For example, FIG. 5 is a diagram showing examples of different inertia axis data according to the situation of the worker.

Referring to FIG. 5, the sensor unit 124 of the motion sensor 120 measures the seven situations (walking, running, work, not wearing a helmet, impact, fall and noise) that workers may experience at the work site. It can be inertia axis data corresponding to the possible X, Y, and Z axes. The motion sensor 120 is to extract characteristic information corresponding to each state of the worker through each inertia axis data.

The motion detection sensor 120 compares the characteristic information with the pre-stored motion state pattern (S322).

In step S322, the motion sensor 120 searches for a motion state pattern having more than a preset similarity value with the characteristic information of the behavior data, and as a result of the search, the worker's motion information mapped to the status pattern is classified. .

At this time, the compared operation state pattern is a value generated and stored by the motion pattern recognition algorithm, and will be described again with reference to FIG. 6 to be described later.

Therefore, when the final step S323 is finished, the motion pattern recognition algorithm is updated based on the motion status information received by the server 200 and the motion status information of the actual worker. For example, when the motion status information received by the server is somewhat different from the motion status information of the actual worker, the motion pattern recognition algorithm can be updated by correcting the motion status pattern based on the motion actually performed by the worker. Through this, the motion pattern recognition algorithm can more accurately and quickly search the motion state pattern with the behavior data generated when the worker performs the same motion.

Finally, the motion sensor 120 transmits motion information corresponding to the motion state pattern calculated as a result of the comparison to the server 200 (S323).

As described above, the worker's motion information corresponding to the pre-stored motion status pattern includes status information about whether the worker is wearing or not wearing a hard hat, status information about whether the worker has received an external shock or collapses, and the Includes status information on whether vibration or movement has occurred.

6 is an operation flowchart for generating a motion pattern recognition algorithm according to an embodiment of the present invention.

Referring to FIG. 6 , the server collects worker behavior data to generate a motion pattern recognition algorithm (S410).

Then, the motion pattern recognition algorithm analyzes the collected behavior data (S420) and trains the algorithm model (S430).

That is, the motion pattern recognition algorithm collects behavior data for a plurality of workers, and the characteristic information of each behavior data is extracted by analyzing the size, frequency, and correlation between the noise and the plurality of behavior data of each behavior data. do.

Thereafter, each behavioral data is classified by performing learning about classifying feature information based on a machine learning algorithm, and the behavioral data is generated by judging the matching worker's operation status for each classified behavioral data.

In this case, any one of K-NN, RBF, and Neural Network may be used as the machine learning algorithm. However, the classification model listed above is an example of a classification model that can be applied to the technology of the present invention, and a higher classification model with higher efficiency developed as technology develops may be applied. Accordingly, the type of classification model applied to the technology of the present invention does not limit the scope of the present invention.

8A and 8B are diagrams related to an embodiment for utilizing the safety helmet of the present invention.

First, referring to FIG. 8A , when the worker recognition sensor installed in the hazardous area 810 recognizes that the motion detection sensor 120 of the hard hat 100 is adjacent within a preset range based on the local network, the hard hat 100 ) to identify the worker 830 wearing the identification information and transmits the access request 840 to the server.

Thereafter, when approval of the access request 840 is confirmed from the server 200 , a function allowing access to the dangerous area 810 may be used as an embodiment.

That is, when the worker 830 approaches the door 820 of the hazardous area 810 where only the worker 830 wearing the hard hat 100 can enter, the worker recognition sensor recognizes the worker 830, and the server The door 820 is selectively opened depending on whether 200 is approved.

Referring to FIG. 8B as another embodiment, when it is recognized that two or more different workers 830 are wearing the hard hat 100, the server 200 approves the work in the hazardous area 810. can

In detail, when it is necessary to perform work in the hazardous area 810, it is common for two or more people to perform the work in one group in preparation for an accident. Accordingly, when a plurality of hard hats 100 approach the danger area 810 in a state in which they are located adjacent to each other, the server 200 approves whether the operation is performed. Conversely, when one hard hat 100 approaches the danger area 810, the server 200 determines that the worker approaches the danger area 810 alone, and refuses to perform the work.

In addition, when the server 200 receives operation information indicating that two or more different workers 830 are wearing the hard hat 100 from the worker recognition sensor installed in the hazardous area 810, the previous operation information of a predetermined time If they do not match each other by comparison, the worker 830 is recognized as two or more, and the server 200 approves the work in the hazardous area 810 . Even in this case, the server 200 approves the work because it recognizes that there are two or more workers 830 in the dangerous area 810 .

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

10: system
100: hard hat 110: body part
120: motion detection sensor
200: server 300: administrator terminal

Claims (16)

In the method for detecting the motion of a worker based on a hard hat, performed by the worker motion detection system,
(a) a motion sensor capable of detecting the motion of the worker mounted on the hard hat, collecting behavior data;
(b) the motion detection sensor extracts characteristic information from the behavior data, compares the characteristic information with a previously stored operation state pattern, and transmits the movement information of the worker corresponding to the matching operation state pattern to the server ; and
(c) transmitting the operation information to the manager terminal after the server receives the operation information;
including,
The pre-stored operation state pattern is classified into a pattern that can indicate the state of the worker's wearing a helmet and the state of danger,
Step (b) is
determining the operation information by comparing the type of information constituting the characteristic information, the value and order indicated by the information, the type constituting the pre-stored operation state pattern, and the value and order indicated by the information,
The characteristic information includes information on the rate of change of the data calculated by the motion sensor over time, information on the size of the data calculated by the motion sensor, statistical characteristic information of the data calculated by the motion sensor, and the motion sensor calculates Including correlation information between energy information included in one data and data of different inertia axes in the data calculated by the motion detection sensor,
The characteristic information corresponding to each of the behavior data is extracted by analyzing the correlation between the size, frequency, and noise of each behavior data and a plurality of the behavior data,
When the server receives the motion information that the two or more different workers are wearing hard hats from the worker recognition sensor installed in the hazardous area, the server compares the past motion information before a predetermined time, a hard hat-based worker How to detect motion. The method of claim 1,
The motion detection sensor is a sensor capable of detecting a tilt of three or more axes, and includes at least one of an acceleration sensor and a gyro sensor. 3. The method of claim 2,
The motion detection sensor is a detection sensor capable of detecting the inclination of the 6-axis, a safety helmet-based method of detecting a worker's motion. delete The method of claim 1,
Step (b) is
A method of detecting a motion of a worker based on a hard hat, which transmits any one of digital information about the state of the worker wearing the hard hat and digital information about whether the worker is at risk to the server. delete The method of claim 1,
The operation state pattern is generated in advance by a motion pattern recognition algorithm,
by the motion pattern recognition algorithm
the behavioral data for a plurality of workers is collected;
By performing learning on classifying the feature information based on a machine learning algorithm, each behavioral data is classified, and the operation of a hard hat-based worker is generated by judging the matching worker's operating state for each classified behavioral data. detection method. 8. The method of claim 7,
The machine learning algorithm is any one of K-NN, RBF, and Neural Network is used, a hard hat-based motion detection method of workers. The method of claim 1,
The operation information includes state information on whether the hard hat is being worn or not, state information on whether the worker has received an external shock or collapses, and a state of whether vibration or movement has occurred in the space where the worker works A method for detecting motion of a worker based on a hard hat, comprising information. 8. The method of claim 7,
Step (b) is
The operation of a worker based on a hard hat, which searches for the motion state pattern having more than a preset similarity value with the characteristic information of the behavior data, and classifies the motion information of the worker mapped with the motion state pattern as a result of the search detection method. 11. The method of claim 10,
Based on the motion status information and the actual worker motion status information received by the server, the motion pattern recognition algorithm is updated, a hard hat-based motion detection method. The method of claim 1,
Step (c) is
The server transmits information about the worker's identification information, the worker's activity level, the worker's affiliation, the worker's job, the worker's location, the worker's motion state information, and the remaining battery level of the motion sensor to the manager terminal, and the manager terminal is to display the received information on a single screen, a safety helmet-based worker motion detection method. The method of claim 1,
When the worker recognition sensor installed in the hazardous area recognizes that the motion detection sensor of the hard hat is adjacent to within a preset range based on the short-distance network, it identifies the worker identification information wearing the hard hat and delivers an access request to the server, , When approval of the access request from the server is confirmed, to allow access to the dangerous area, a hard hat-based worker motion detection method. The method of claim 1,
When it is recognized that the different two or more workers are wearing the hard hat, the server approves the work in the hazardous area, a hard hat-based worker motion detection method. 15. The method of claim 14,
By comparing the past motion information before the predetermined time and if they do not match each other, the worker is recognized as two or more people, and the server approves the work in the hazardous area. In the safety helmet-based worker's motion detection system,
a motion detection sensor provided in the hard hat to detect the motion of the worker to generate behavior data, and to calculate the motion information of the worker based on the behavior data;
a server that receives the motion information from the motion sensor and transmits it to a manager terminal;
The manager terminal for displaying the operation information received from the server;
including,
A motion sensor that can detect the motion of the wearer mounted on the helmet collects behavior data, the motion sensor extracts characteristic information from the behavior data, and compares the characteristic information with a pre-stored motion state pattern. , transmits the operation information of the worker corresponding to the matching operation state pattern to the server, and after the server receives the operation information, transmits it to the manager terminal, but the pre-stored operation state pattern is the worker's helmet wearing state and Classify into patterns that can indicate the status of risk,
In the process of transmitting the worker's motion information to the server, the type of information constituting the characteristic information, the value and order indicated by the information, and the type constituting the pre-stored motion state pattern, the value and order indicated by the information are compared. to determine the motion information, and the characteristic information includes information on a rate of change of data calculated by the motion sensor over time, information on the size of data calculated by the motion sensor, and statistical characteristics of data calculated by the motion sensor information, energy information included in the data calculated by the motion detection sensor, and correlation information between different inertia axis data in the data calculated by the motion detection sensor, and includes the size, frequency, and noise of each behavior data The characteristic information corresponding to each of the behavior data is extracted by analyzing the correlation between the behavior data,
When the server receives the motion information that the two or more different workers are wearing hard hats from the worker recognition sensor installed in the dangerous area, the server compares the past motion information before a predetermined time, a hard hat-based worker motion detection system.

Images