KR102085168B1 - Method and apparatus for managing safety in dangerous zone based on motion tracking - Google Patents

Abstract

The present invention discloses an apparatus for managing safety in a dangerous region, which comprises the steps of: obtaining a real image and a thermal image through a camera; detecting movement of an object using the real image and detecting a temperature distribution of the object using the thermal image; confirming the existence of a region of interest using movement information by the real image and temperature distribution information by the thermal image; and confirming the existence of a dangerous situation through analysis of the region of interest using artificial intelligence. According to the present invention, an operation amount and an error rate can be reduced by using a real image and a thermal image for a dangerous situation, and detecting an object based on movement and a temperature distribution.

Description

METHOD AND APPARATUS FOR MANAGING SAFETY IN DANGEROUS ZONE BASED ON MOTION TRACKING}

The present invention relates to a safety management method and apparatus, and more particularly, to a method and apparatus for managing safety in a dangerous area by predicting and preventing the occurrence of a safety accident in advance based on human tracking.

Due to the development of computing resources, AI research is actively being conducted in various fields. A system that enables pre-learning of large amounts of data that could not have been imagined in the past, and enables fast and accurate prediction / determination using the learned results, is easily accessible not only in the industrial field but also in daily life.

However, this seemingly versatile AI system is actually only possible with a huge amount of data computation and processing within the system, which means that the equipment that composes the system needs to be upgraded, that is, costly.

Image processing using camera images is used in various fields.

In particular, the use of industrial sites is very diverse, such as human body detection, worker counting, hazardous area monitoring, and inspection equipment only by changing the target image processing algorithm.

However, when using the classical image processing method, various exceptions occur due to external factors such as workplace environment, light, and movement of various machines.

The present invention aims to provide a quality service compared to the existing by configuring the advanced technology of artificial intelligence at a minimum cost.

According to the related art of safety management, safety is mainly managed by detecting a user's movement by using a sensor and blocking the operation of the machine in advance for a user who may be in a dangerous situation in relation to the machine. However, in the prior art, when the shape or structure of an industrial facility including a machine is changed, the safety management system using the sensor must be redesigned, and the safety management system using the sensor is only useless when the sensor is arbitrarily released. There were a lot.

According to the method and apparatus for safety zone safety management according to an embodiment of the present invention, a real image and a thermal image are used to track a user's motion and to control a device operated by the user, for example, a machine tool or a control device of a PLC. It detects and prevents dangerous situations that can be produced in advance, but infers the dangerous situation by using artificial intelligence in a limited area of the area of interest. In this regard, the method and apparatus for safe zone safety management according to an exemplary embodiment of the present invention are distinguished from the above-described prior art and are disclosed to solve the problems of the prior art.

Korea Patent Publication No. 10-1852284 (2018.04.19.)

An object of the present invention is to provide a dangerous situation safety management method and apparatus that can monitor and prevent a dangerous situation that a user operating a machine may face through an image.

Another object of the present invention is to provide a risk situation safety management method and apparatus that can reduce an error rate by detecting an object based on a motion and temperature distribution using a real image and a thermal image.

Another object of the present invention is to provide a risk situation safety management method and apparatus that can infer a risk situation through an artificial intelligence model trained through learning using an artificial intelligence algorithm.

Safety zone safety management method according to an embodiment of the present invention, the step of obtaining a real image and a thermal image through a camera; Detecting a movement of the object by using the real image and detecting a temperature distribution of the object by using the thermal image; Confirming the existence of the ROI by using the motion information of the real image and the temperature distribution information of the thermal image; And confirming the existence of a risk situation by analyzing the ROI using artificial intelligence.

The dangerous area safety management method may include correcting at least one of real image data and thermal image data using an offset value of feature point coordinates extracted from the real image and the thermal image. It further comprises a pre-processing step of matching each other.

The detecting of the motion may be performed by using a motion of pixels in which a brightness value is changed between adjacent frames of the acquired real image, but using a mean value of a plurality of data stored in the past with respect to the same object. The detection error rate is reduced by separating the object and the background operating according to.

The temperature distribution detecting step may include detecting a region satisfying the temperature distribution of the object in the thermal image based on the temperature distribution according to the temperature profile of the object.

The determining of the existence of the region of interest may include detecting a region of interest occupied by the object in the real image and the thermal image that match each other using the result data of the motion detection and the result data of the temperature distribution detection.

Here, the step of confirming the existence of the dangerous situation may include inferring a dangerous situation of an object in the ROI according to learning using an artificial intelligence algorithm for a dangerous situation about a machine and a human-manipulating object. It features.

According to an embodiment of the present disclosure, an apparatus for managing a danger zone according to an embodiment of the present disclosure may include a motion detection module detecting a motion of an object using a real image obtained through a camera, and a temperature detection detecting a temperature distribution of the object using a thermal image. module; A region of interest detector configured to confirm the presence of the region of interest by using motion information of the real image and temperature distribution information of the thermal image; And an artificial intelligence situation determination unit for confirming the existence of a dangerous situation by analyzing the region of interest using artificial intelligence.

Here, the dangerous area safety management device corrects at least one of the real image data and the thermal image data by using an offset value of the feature point coordinates extracted from the real image and the thermal image. It further comprises a data preprocessor for matching each other.

Here, the motion detection module uses motions of pixels in which a change in brightness value occurs between adjacent frames of the acquired real image, but uses an average value of a plurality of data stored in the past with respect to the same object according to a change of state. The detection error rate may be lowered by separating the moving object from the background.

Here, the temperature detection module, based on the temperature distribution according to the temperature profile of the object, characterized in that for detecting a region satisfying the temperature distribution of the object in the thermal image.

The ROI detector may detect an ROI occupied by the object in the real image and the thermal image that match each other using the result data of the motion detection and the result data of the temperature detection.

The method according to claim 7, wherein the artificial intelligence situation determination unit, infer the risk situation of the object in the region of interest according to the learning using the artificial intelligence algorithm for the dangerous situation with respect to the machine and the human subject that can manipulate the human It is characterized by.

According to the present invention, by monitoring and preventing a dangerous situation that a user who operates a machine may face through the image, it is possible to be flexible to industrial equipment changes and to prevent any release of the dangerous situation.

In addition, it is possible to reduce the amount of computation and the error rate by using real images and thermal images for risk situations and detecting objects based on movement and temperature distribution.

In addition, the risk situation can be inferred from the AI model trained through the AI algorithm.

1 is a block diagram of a risk situation safety management system according to an embodiment of the present invention.
2 is a block diagram of a risk situation safety management apparatus according to an embodiment of the present invention.
3 is a block diagram according to an exemplary embodiment of a risk situation safety management apparatus corresponding to a computing device.
4 is a flowchart illustrating a risk situation safety management method according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings will be described in detail a preferred embodiment of the risk situation safety management method and apparatus.

Like reference numerals in the drawings denote like elements. In addition, specific structural to functional descriptions of one embodiment of the present invention are only illustrated for the purpose of describing the embodiment according to the present invention, and unless otherwise defined, all terms used herein including technical or scientific terms are used. The terms have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in the commonly used dictionaries should be construed as having meanings consistent with the meanings in the context of the related art, and shall not be construed in ideal or excessively formal meanings unless expressly defined herein. It is preferable not to.

Hereinafter, a risk situation safety management system 1000 according to an embodiment of the present invention will be described.

1 is a block diagram of a risk situation safety management system according to an embodiment of the present invention.

Referring to FIG. 1, the hazardous area safety management system 1000 according to an embodiment of the present disclosure may include a dangerous area safety management device 100, a server 200, a camera 300, and a control target device 400. Network 500.

The dangerous area safety management apparatus 100 serves to infer the risk situation of the user by using the real image and the thermal image acquired through the camera 300. In step by step, the danger zone safety management apparatus 100 detects the movement of the object using the real image and detects the temperature distribution of the object using the thermal image. And the danger zone safety management device 100 confirms the existence of the ROI by using the detection result, and analyzes the ROI to confirm the existence of the risk situation.

The server 200 is a kind of data server for storing data collected by the dangerous area safety management device 100, an API for utilizing artificial intelligence, a server for creating and learning artificial intelligence models, and dangerous area safety management. Includes a control server for

The data server 200 stores raw data acquired by the camera 300 and data processed by the dangerous area safety management apparatus 100. The stored data may be used to detect an ROI performed by the danger zone safety management apparatus 100. That is, the danger zone safety management apparatus 100 may detect the movement of the object or the temperature distribution by using the accumulated data stored and stored in each corresponding area, for example, a work site equipped with various control target devices 400. have.

The server 200 for artificial intelligence provides an API regarding an artificial intelligence algorithm. In addition, the server 200 for artificial intelligence may generate an artificial intelligence model for determining a dangerous situation. The generated model is trained using the data stored by the risk situation learning module 151.

The control server 200 integrates and manages the dangerous area safety management device 100 installed in various facilities and monitors a dangerous situation. And it recognizes the occurrence of the dangerous situation by using the information received through the danger zone safety management device 100, and serves to inform the dangerous situation to other terminals, especially user terminal connected to the network.

The camera 300 includes a real image camera 310 and a thermal image camera 320 as a kind thereof. The real image camera 310 obtains a real image using light in a visible wavelength range. The thermal imaging camera 320 acquires a thermal image using light in an infrared wavelength region. Here, the real image and the thermal image obtained through the camera 300 is transmitted to the dangerous area safety management device 100 through a network or to the dangerous area safety management device 1000 through a directly connected image data transmission cable. Can be.

The camera 300 may be installed in plural in a position capable of capturing the movement of the object. For example, consider a case where a machine including cutting means for reciprocating a certain linear trajectory by a motor power is included among objects. In this case, the camera 300 may display the reciprocating motion as a horizontal motion in the image in a direction perpendicular to the linear trajectory. Also, in order to detect the state in which the cutting means and the human figure overlap each other in the direction in which the linear trajectory is displayed as a point, the camera 300 is additionally installed opposite the point in the direction in which the linear trajectory is represented by a point. May be

The location and place where the camera 300 is installed may be changed based on the statistics of the risk inference result. That is, when the ROI is detected based on the motion detection and the temperature distribution detection, and the actual danger is not detected in the process of determining the ROI as a dangerous situation, the position of the existing camera 300 is set to a new position and direction. Can be changed to

The control target device 400 refers to an electronic and mechanical device capable of producing a dangerous situation in relation to a user. For example, the control target device 400 is a kind thereof, and includes a PLC system, various machine tools, and accessories connected to the PLC. In addition, the control target device 400 includes a power source such as a motor or an engine, and features a typical trajectory movement while reciprocating, rotating, and arranging according to the power source.

The control target device 400 may be connected to the dangerous area management device 100 through a dedicated cable for transmitting a control command or may be connected through a network. The control target device 400 connected to the dangerous area management device 100 through a network includes an operating system as an embedded system and a communication device and software for driving them.

Network 500 may be a wired and wireless network, such as the Internet, intranet and extranet, cellular, such as a wireless telephone network, a local area network, a wide area network. ), A WiFi network, an ad hoc network, and a combination thereof.

Network 500 may include a connection of network elements such as hubs, bridges, routers, switches, and gateways. Network 500 may include one or more connected networks, such as a multi-network environment, including a public network such as the Internet and a private network such as a secure corporate private network. Access to the network 500 may be provided through one or more wired or wireless access networks.

2 is a block diagram of a danger zone safety management apparatus according to an embodiment of the present invention.

Referring to FIG. 2, the danger zone safety management apparatus 100 includes a camera controller 110, a data detector 120, a data preprocessor 130, an ROI detector 140, an artificial intelligence situation determination unit 150, And dangerous situation processing unit 160.

The camera controller 110 adjusts an area photographed by the real image camera and the thermal image camera through the operation control of the camera so that the same area is captured. In detail, the camera controller 110 may control the zoom-in and zoom-out operations of the camera, or control the photographing angle and focus by controlling the degree of rotation of the camera. Ultimately, the camera controller 110 may synchronize and control the camera 110 acquiring the real image and the camera 120 acquiring the thermal image. Accordingly, the synchronized real image camera 110 and the thermal image camera 120 acquire images of the same region and the same subject.

The data detector 120 includes a motion detection module 121 and a temperature detection module 122.

The motion detection module 121 detects the movement of the object by using the real image acquired through the camera.

In particular, the motion detection module 121 detects the movement of the object using a difference value of brightness data between adjacent frames of the acquired image.

In detail, the motion detection module 121 extracts feature points that form a contour of the moving object by using brightness values of pixels distributed in the real image, and detects the movement of the object by detecting the change of these feature points in adjacent frames. . The motion detection module 121 recognizes the state change by using the difference in the brightness value of the pixel, and reduces the detection error rate by separating the object and the background operating according to the state change by using the accumulated data.

Here, the object is a concept including a human and a machine. In addition, the risk situation refers to a situation in which a human being can be infringed by a machine in the relationship between the human body and the machine that constitutes the object. For example, the operating range of the machine and the human operating range are set in advance, and in each range, the situation where the machine and the human position overlap with each other at the same time or the position of each other is beyond the limit range is a dangerous situation. .

The motion detection module 121 detects motion of the machine and the human among the objects for the basis of the risk repayment determination. Among the subjects, the machine is characterized by repeatedly moving a certain range at a predetermined time interval. Therefore, the motion detection module 121 may detect the motion of the machine according to a relatively high recognition rate based on the period and the movement range. On the other hand, human movement may be out of range.

The motion detection module 121 compares adjacent frames constituting the acquired image with each other to detect a moving human. For example, by comparing the brightness between adjacent frames, human pixels are detected by identifying the pixels with different brightness values as human shapes. A pixel having a brightness value that does not change in a comparison between frames may be treated as a background.

The temperature detection module 122 detects the temperature distribution of the object by using the thermal image. Since the subject includes a machine and a human, the temperature distribution of the subject well represents the temperature distribution characteristics of the machine and the human. For example, the temperature distribution in humans is characterized by a consistent range of body temperature changes. And the temperature distribution of the machine is characterized by a change up with time according to the operating time and the temperature of the room air. In particular, there may be a part in which the temperature rises according to the consumption of fuel or power, such as an engine and a motor, and the temperature detection module may detect the temperature distribution of the target machine in consideration of the characteristics of the machine and the operation time.

The temperature detection module 122 may detect a region that satisfies the temperature distribution of the object in the thermal image based on the temperature distribution according to the temperature profile of the object.

The data preprocessor 130 selects coordinates of the feature points extracted from the real image and the thermal image, and compares the offset values of the two coordinates in each coordinate to match the real image data and the thermal image data. The data preprocessor 130 processes the real image data and the thermal image data to help the ROI detector 140 detect the ROI. In one embodiment, the data preprocessor 130 corrects a real image having a different parameter value, for example, a resolution, a size of an image, a brightness of an image by matching parameters of a real image and a thermal image, and corrects the pixels of the real image and the thermal image. Can match each other. The region of interest detector 140 may detect the region of interest based on the new image matched or based on the unmatched real image and the thermal image.

The ROI detector 140 detects an ROI by using motion information of a real image and a temperature distribution of the thermal image. That is, the region of interest refers to a region in which the movement of the object appears and a region in which the temperature distribution of the object appears by the thermal image based on the motion information of the real image in the obtained entire image. Here, the ROI detector may distinguish the human and machine regions from the object by using the motion information and the temperature distribution of the object.

In detail, the ROI detecting unit 140 detects an area corresponding to an AND condition as an ROI by filtering and extracting an area predicted as an object from the entire image using the motion detection result, and applying a motion detection result to the extracted area. do. Alternatively, the ROI detector 140 may track and extract the moving object by using the motion detection result, and detect the ROI by verifying whether the extracted region is the object area by using the temperature distribution result. In any of the above methods, it is not necessary to compare the adjacent frames with respect to the entire real image area, and the computation amount can be significantly reduced since the comparison between the frames is only performed with respect to the area expected as the object in the entire area.

The artificial intelligence situation determination unit 150 serves to confirm the existence of a dangerous situation through analysis of the ROI using artificial intelligence. As described above, the risk situation may be detected by the mutual position of the subjects.

The artificial intelligence situation determination unit 150 may include a risk situation learning module 151 and a risk situation determination module 152 as its components. In more detail, the risk learning module 151 may control a learning model generation and learning process performed by the server 200. The risk situation determination module 152 infers a risk situation that can be detected in the ROI using the learned model.

First, video data indicating a dangerous situation is prepared. Image data is provided reflecting the characteristics of the facilities for each facility of different configurations. In addition, the image data representing the danger situation may be provided by dividing the grade according to the degree of danger.

The training data depicts the position of the subject at risk, particularly the typical movement of the machine and the deviant movement of the human. The risk situation learning module 151 may learn a risk situation using learning image data for predicting a collision between objects that may occur in the future in consideration of the concept of time, and may be set to a predetermined level of risk according to the degree of risk situation. Learn about

The risk situation determination module 152 serves to infer a risk situation with respect to actual data using a model learned through the risk situation learning module. In this context, risk inference involves classifying the degree of risk.

In addition, the dangerous situation may include not only mutual collisions of the subjects, but also thermal hazards according to temperature changes of the heat generating parts of the machine among the subjects. For example, the risk of fire due to overheating of the machine may be inferred by the dangerous situation determination module 152.

The artificial intelligence situation determination unit 150 learns a dangerous situation about a machine and an object that can be produced by a human who manipulates it using an artificial intelligence algorithm, and infers a dangerous situation of an object in the region of interest according to the learning. Characterized in that.

The dangerous situation processing unit 160 controls the machine to stop the operation of the machine in order to allow the human to escape from the dangerous situation in the relationship between the human and the machine among the objects. The dangerous situation processing unit 160 transmits a control command through a cable directly connected according to a method of connecting the control target device 400 and the dangerous area management device 100 or a packet related to the control command through the network to the embedded system. Can be transmitted to the control target device (400).

The configuration of the hazardous area safety management apparatus 100 illustrated in FIG. 2 is a functionally divided configuration for convenience of description, and may be configured as a logical function handled by one processor in hardware. The present invention is not limited by the classification.

In addition, although the connection relationship between each configuration is shown as a connection line, or the connection relationship between each other is not expressed individually, communication or transmission for control or data exchange may occur even between the configurations in which the connection line is not shown, and only as shown. It does not limit the invention.

The danger zone safety management apparatus 100 according to an embodiment of the present invention may correspond to the computing device 600. Hereinafter, the danger zone safety management apparatus 100 according to an embodiment of the present invention corresponding to the computing device 600 may be described in more detail through other embodiments.

The hazardous area safety management device 100 may include a computing system including one or more central processing units (CPUs), memory, mass storage, an input interface device, and an output interface device. The elements of the computing system can communicate with each other via a bus.

The hardware platform of the computing device may be a distributed computing environment, such as a cloud based computing system, including any of a personal computer, handheld or laptop device, a multiprocessor system, a microprocessor based system, a program appliance, and any of the above systems or devices. It can be implemented in many forms, including.

3 is a block diagram according to an exemplary embodiment of a risk situation safety management apparatus corresponding to a computing device.

Referring to FIG. 3, the computing device 600 includes an input interface device 610, an output interface device 620, a memory 631, a storage device 632, a power supply 640, a processor 650, and a network interface. Device 660, wireless communication device 670, and bus 680.

The input interface device 610 inputs a character or an object according to a user's input. The input interface device 610 includes, but is not limited to, a keyboard, a touch screen, a mouse, a stylus pen, and a pen tablet.

The output interface device 620 includes a display for displaying a user interface related to an application module for dangerous area safety management, and a printer for printing out a print. In addition, the output interface device 620 includes a speaker, a head-phone, and a headset for outputting text to speech using a text to speech (TTS) engine.

The processor 650 may execute a computer instruction set included in an application for dangerous area safety management according to an embodiment of the present invention stored in the memory 631 and / or the storage device 632. The processor 650 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which the methods according to the present invention are performed. The memory 631 and the storage device 632 may be configured of a volatile storage medium and / or a nonvolatile storage medium. For example, the memory 631 may be configured as read only memory (ROM) and / or random access memory (RAM).

The wireless communication device 670 includes a device for near field communication, wireless data communication, and wireless voice communication.

Each component included in the computing device 600 is connected by a bus 680 to communicate with each other.

Hereinafter, a dangerous area safety management method according to an exemplary embodiment of the present invention executed by the dangerous area safety management device 100 described above through computation of a computer instruction set included in a hardware or an application module for dangerous area safety management. 1, 2 and 4 will be described.

The dangerous area safety management method according to an embodiment of the present invention is characterized by being performed by the dangerous area safety management device 100, and each component constituting the dangerous area safety management device 100 at each step of the method. It is characterized by performing a role.

4 is a flowchart illustrating a method for safeguarding a danger zone according to an embodiment of the present invention.

4, the dangerous area safety management method (S100) according to an embodiment of the present invention includes steps S111 to S160.

Optionally, a camera control step of adjusting an area photographed by the real image camera and the thermal imaging camera may be preceded by controlling the operation of the camera so that the same areas are captured.

First, each of the real image and the thermal image captured by the camera is obtained (S111, S112).

Next, the movement of the object is detected using the real image, and the temperature distribution of the object is detected using the thermal image (S121 and S122).

The detecting of the motion may include detecting a motion of the object using a difference value of brightness data between adjacent frames of the acquired image.

The detecting of the motion may include detecting a state change by using a difference value of the brightness data and lowering a detection error rate by separating an object and a background operating according to the state change by using cumulative data. do.

The temperature distribution detecting step may include detecting a region satisfying the temperature distribution of the object in the thermal image, based on the temperature distribution according to the temperature profile of the object.

Optionally, a preprocessing step of selecting coordinates of the feature points extracted from the real image and the thermal image, matching the real image data and the thermal image data by comparing offset values of the two coordinates at each coordinate ( S130).

Next, the presence of the ROI is confirmed using the motion information of the real image and the temperature distribution of the thermal image (S140).

The determining of the existence of the region of interest may include detecting the region of interest including the object using the result data of the motion detection and the result data of the temperature detection.

Next, the existence of a risk situation is confirmed through analysis of the ROI using artificial intelligence (S150).

Here, the step of confirming the existence of the danger situation, learning about a dangerous situation about a machine and an object that can be produced by a human manipulating the same by using an artificial intelligence algorithm, the risk of an object in the region of interest according to the learning It is characterized by inferring the situation.

Finally, the risk situation is processed based on the determination result of the risk situation (S160).

The dangerous area safety management method (S100) according to an embodiment described with reference to the drawings may be implemented in the form of a recording medium including a command set executable by a computer, such as a program module executed by a computer. have. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery media.

As such, according to an embodiment of the present invention, by monitoring and preventing a dangerous situation that a user who operates a machine may face through the image, it is possible to prevent the release of the monitoring of the dangerous situation flexibly in response to industrial equipment changes. have.

In addition, it is possible to reduce the amount of computation and the error rate by using real images and thermal images for risk situations and detecting objects based on movement and temperature distribution.

In addition, the risk situation can be inferred from the AI model trained through the AI algorithm.

The above description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in 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 exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

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

100: hazardous area safety management device
110: camera control unit
120: data detector
121: motion detection module
122: temperature detection module
130: data preprocessing unit
140: region of interest detector
150: artificial intelligence situation determination unit
151: Risk Learning Module
152: risk assessment module
160: dangerous situation processing unit

Claims (10)

Acquiring a real image and a thermal image through a camera;
Detecting a movement of an object using the real image and detecting a temperature distribution of the object using the thermal image;
Confirming the existence of the ROI by using the motion information of the real image and the temperature distribution information of the thermal image; And
Confirming the existence of a risk situation by analyzing the ROI using artificial intelligence,
At least one of real image data and thermal image data using an offset value of feature point coordinates extracted from the real image and the thermal image between detecting the temperature distribution of the object and confirming the existence of the ROI. A preprocessing step of matching the pixels of the real image and the thermal image to each other by correcting the data,
Detecting the movement,
By using the movement of the pixels that change the brightness value between adjacent frames of the acquired real image,
Using the average value of a plurality of data stored in the past with respect to the same object, it is characterized in that the detection error rate is lowered by separating the background and the object operating in accordance with the change of state, dangerous area safety management method. delete delete The method according to claim 1,
The temperature distribution detection step,
On the basis of the temperature distribution according to the temperature profile of the object, the risk area safety management method, characterized in that for detecting a region satisfying the temperature distribution of the object. The method according to claim 4,
Confirming the existence of the region of interest,
And detecting a region of interest occupied by the object in the real image and the thermal image that match each other using the result data of the motion detection and the result data of the temperature distribution detection. A motion detection module that detects the movement of the object by using the real image acquired through the camera, and a temperature detection module that detects the temperature distribution of the object by using the thermal image;
A region of interest detector configured to confirm the presence of the region of interest using motion information of the real image and temperature distribution information of the thermal image; And
Including an artificial intelligence situation determination unit for confirming the existence of a risk situation through the analysis of the region of interest using artificial intelligence,
And a data preprocessor configured to match pixels of the real image and the thermal image by correcting at least one of the real image data and the thermal image data by using an offset value of the feature point coordinates extracted from the real image and the thermal image. ,
The motion detection module,
By using the movement of the pixels that change the brightness value between adjacent frames of the acquired real image,
Using a mean value of a plurality of data stored in the past with respect to the same object, it is characterized in that the detection error rate is lowered by separating the object and the background operating in accordance with the change of state, dangerous area safety management device. delete delete The method according to claim 6,
The temperature detection module,
On the basis of the temperature distribution according to the temperature profile of the object, the danger zone safety management device, characterized in that for detecting a region satisfying the temperature distribution of the object in the thermal image. The method according to claim 9,
The region of interest detection unit,
And a region of interest occupied by the object in the real image and the thermal image matched with each other using the result data of the motion detection and the result data of the temperature detection.

Images