KR20230015580A - Biometric information monitoring radar and method around construction equipment - Google Patents

Abstract

The present invention relates to a radar and method for monitoring biometric information around construction equipment, wherein cross-detection of two radars and artificial intelligence techniques are used to increase detection accuracy, temporal/spatial differences are used to improve detection accuracy of human bio-signals, movement of obstacles or biometric information is detected to determine a person when construction equipment is stopped, and movement of obstacles or biometric information is detected to determine a person even when the construction equipment is moving or rotating. The radar for monitoring biometric information around construction equipment of the present invention comprises: a first radar which detects a person by transmitting and receiving RF to the person; a second radar which detects a person by transmitting and receiving RF to and from the person; and an artificial intelligence processor which analyzes detailed information about a person from the received signal of the first radar and the received signal of the second radar.

Description

Biometric information monitoring radar and method around construction equipment}

The present invention relates to a radar and method for monitoring biometric information around construction equipment, and more particularly, to monitoring biometric information around construction equipment using radar. That is, the present invention relates to a radar and method for monitoring biometric information around construction equipment capable of distinguishing between a person and an obstacle and delivering a warning to a driver.

Accidents, large and small, still occur at construction sites, and due to the nature of construction equipment, when a human accident occurs, most of them lead to fatal accidents. Efforts have been made to reduce accidents that occur at construction sites, but existing solutions have technical problems.

Cameras, which are the most frequently used safety equipment for construction equipment, have a problem that the driver must directly grasp the situation behind. If the driver is concentrating on a task and does not recognize an approaching person, the effectiveness of the camera is reduced.

Ultrasonic sensors, radar, LiDAR, etc. are used as means to detect objects approaching construction equipment, but ultrasonic sensors are vulnerable to vibration, so there is a problem in applying them to construction equipment with severe vibration of the equipment. . In the case of LIDAR, since it uses light, there is a problem that it is not suitable for construction sites with severe dust, and research to overcome this problem has been continued.

For example, Korean Patent Laid-open Publication No. 10-2016-0017485 detects people located nearby while driving heavy equipment or large vehicles, alerts the driver of the presence of people, and alerts people nearby that the vehicle is in operation. Disclosed is a human body detection alarm system for safe operation of heavy equipment or large vehicles.

However, even in this case, there is a disadvantage in that there are many measurement errors of infrared sensors, heat detection sensors, and motion detection sensors in dusty workplaces for human body detection. is needed

Republic of Korea Patent Publication No. 10-2016-0017485 (2016.02.16)

An object of the present invention is to increase the accuracy of detection using two radar cross-detection and artificial intelligence techniques, and to improve the detection accuracy of human biological signals using temporal / spatial differences. A radar for monitoring biometric information around construction equipment, and is to provide a way

The present invention determines a person by detecting the movement of an obstacle or biometric information when the construction equipment is stationary, and determines a person by detecting the motion of an obstacle or biometric information even when the construction equipment is moving or rotating. Another object is to provide a surveillance radar and method.

A radar for monitoring biometric information around construction equipment according to the present invention includes a first radar that detects a person by transmitting and receiving RF to and from a person, a second radar that detects a person by transmitting and receiving RF to and from a person, and reception of the first radar. It may include an artificial intelligence processor that analyzes detailed information of a person from the signal and the received signal of the second radar.

Here, RF may be characterized in that it is a modulated signal of any one of a frequency modulated continuous wave (FMCW) method and an ultra wide-band (UWB) method.

Also, the detailed information may include at least one of a person's heart rate or respiratory rate.

Here, the first radar and the second radar may perform transmission and reception at different measurement positions.

In addition, the first radar and the second radar may synchronize with each other and perform transmission and reception at different times.

Here, the artificial intelligence processor may learn using artificial intelligence techniques.

In addition, artificial intelligence techniques can utilize unsupervised learning for data in various environments.

Here, the artificial intelligence technique can utilize Federated Learning, which collects models learned from construction equipment into a central server without directly collecting data from the central server.

In addition, the radar sensor module is based on the Doppler frequency plane according to the azimuth representing the Doppler frequency generated when the construction equipment rotates for each azimuth with respect to the turning angle of the construction equipment, based on the Doppler frequency plane according to the azimuth. can be detected by motion.

A method for monitoring biometric information around construction equipment according to another embodiment of the present invention includes an obstacle recognition step for recognizing an obstacle, a construction equipment stop determination step for determining whether the construction equipment is in a stopped state, and an obstacle when it is determined that the construction equipment is in a stopped state. Motion detection determination step for determining whether movement of the obstacle is detected, biometric information detection step for detecting biometric information of an obstacle, biometric information confirmation step for confirming whether biometric information is detected, and motion detection or biometric information confirmation in the motion detection determination step. It may include a human determination step of determining that the biometric information is detected in the step, and a stationary obstacle determination step of determining the stationary obstacle when the biometric information is not detected in the biometric information presence check step.

In addition, the method for monitoring biometric information around construction equipment includes an obstacle recognition step for recognizing an obstacle, a construction equipment stop determination step for determining whether the construction equipment is in a stopped state, and whether the motion of the obstacle is detected if the construction equipment is not determined to be in a stopped state. Motion detection judgment step to check, biometric information detection step to detect biometric information of an obstacle, biometric information presence confirmation step to check whether biometric information has been detected, motion detected in the motion detection judgment step, or biometric information detected in the biometric information presence confirmation step It may include a human determination step of determining that the obstacle is a person when detected, and a stationary obstacle determination step of determining a stationary obstacle when biometric information is not detected in the biometric information presence/absence check step.

Here, in the motion detection and determination step, based on the Doppler frequency plane according to the azimuth representing the Doppler frequency generated when the construction equipment rotates for each azimuth with respect to the turning angle of the construction equipment, the specific azimuth representing the Doppler characteristic deviating from the Doppler frequency plane according to the azimuth angle. Obstacles can be detected by movement.

Biometric information monitoring radar and method around construction equipment according to the present invention increases the accuracy of detection using two radar cross detection and artificial intelligence techniques, and improves the detection accuracy of human biosignals using temporal / spatial differences There are advantages.

In addition, the radar and method for monitoring biometric information around construction equipment according to the present invention detects movement or biometric information of an obstacle while the construction equipment is stationary to determine a person, and even when the construction equipment is moving or rotating, the motion or biometric information of the obstacle is detected. It has the advantage of being able to judge a person by detecting information.

1 is a configuration diagram showing a radar for monitoring biometric information around construction equipment according to an embodiment of the present invention.
FIG. 2 is a view showing that a person is located around construction equipment to which the radar sensor module of FIG. 1 is mounted.
3 is a view showing an example in which the radar sensor module of FIG. 1 is mounted on construction equipment and a detection area of the radar sensor module.
FIG. 4 is a diagram showing positions where the first radar and the second radar of FIG. 1 detect human biometric information.
FIG. 5 is a detailed view showing antenna structures of the first radar and the second radar of FIG. 1 .
6 is a timing diagram illustrating transmission and reception timings in the first radar and the second radar of FIG. 1 .
7 is a diagram illustrating an example in which the radar sensor module of FIG. 1 measures a person's heart rate.
8 is a diagram illustrating an example in which the radar sensor module of FIG. 1 measures a person's respiratory rate.
9 is a graph showing Doppler characteristics when the first radar of FIG. 1 does not stop.
10 is a flowchart illustrating a method for monitoring biometric information around construction equipment according to an embodiment of the present invention.

Specific embodiments for carrying out the present invention will be described with reference to the accompanying drawings.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. This is not intended to limit the present invention to specific embodiments, and it can be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Hereinafter, a radar and method for monitoring biometric information around construction equipment according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a configuration diagram showing a radar for monitoring biometric information around construction equipment according to an embodiment of the present invention, and FIGS. 2 to 9 are detailed drawings, timing diagrams, and graphs for explaining FIG. 1 in detail.

Hereinafter, a radar for monitoring biometric information around construction equipment according to an embodiment of the present invention will be described with reference to FIGS. 1 to 9 .

First, referring to FIG. 1, the radar for monitoring biometric information around construction equipment according to an embodiment of the present invention includes a first radar 110 that detects a person 200 by transmitting and receiving RF to and from a person 200, a person The second radar 120 detects the person 200 by transmitting and receiving RF to and from the person 200, and the person 200 from the received signal of the first radar 110 and the received signal of the second radar 120. It consists of an artificial intelligence processor 130 that analyzes detailed information.

Here, RF may be characterized in that it is a modulated signal of any one of a frequency modulated continuous wave (FMCW) method and an ultra wide-band (UWB) method.

In addition, the detailed information includes at least one of the heart rate and respiratory rate of the person 200 .

Here, the artificial intelligence processor 130 learns using artificial intelligence techniques.

In addition, artificial intelligence techniques utilize unsupervised learning for data in various environments.

Here, the artificial intelligence technique uses Federated Learning, which collects models learned from construction equipment into a central server, rather than directly collecting data from the central server.

Radar is the best means for detecting obstacles around construction equipment, but radar has limitations in distinguishing whether an obstacle is a person or a general stationary object. If the radar can distinguish whether an approaching object is a person or a general object, it is possible to detect the presence of a person when a person enters the danger radius and provide an effective warning.

Meanwhile, technologies and products that measure and display human heart rate and respiration in a non-contact manner have already been commercialized and sold, and many studies have been conducted. This is a two-dimensional technique in which the radar transmits radio waves to the person in front and receives the reflected waves to measure the person's heart rate and respiration.

In addition, the reason why the existing radar measures the heart rate and respiration of a person in this way is to accurately measure the biosignal. In a state where the person is stationary and the radar is also stopped, if the radar transmits and receives radio waves to the person in front, the precision of the biosignal itself increases.

Radar methods include a frequency modulated continuous wave (FMCW) method and an ultra wide band (UWB) method. The FMCW method is the most widely used radar method. It transmits FM-modulated radio waves, receives reflected waves, and compares the difference between the transmitted and received waves to determine the distance characteristics. It's easy. In particular, if two or more FMCW radars are used, it has the advantage of being able to determine the location of an object. On the other hand, FMCW radar has limitations in measuring the exact location or distance of an object.

UWB (Ultra Wide Band) radar is a method of spreading radio waves in a frequency band of 500 MHz or higher, and is a method using a wide frequency band ranging from 3.1 to 10.6 GHz. Since UWB radar has low power/high precision characteristics, it is used as a healthcare radar that measures human vital signals in a non-contact manner.

The radar for monitoring biometric information around construction equipment of the present invention transmits and receives to and from a person 200 through the first radar 110 and the second radar 120 using either FMCW or UWB, and transmits and receives it through the artificial intelligence processor 130 ) to determine the presence or absence of the person 200 by measuring the heart rate and respiratory rate of the person 200.

In addition, the artificial intelligence processor 130 can improve the accuracy of judgment by using artificial intelligence techniques. You can use Federated Learning, which collects models learned from construction equipment into a central server.

Therefore, the radar for monitoring biometric information around construction equipment according to the present invention has the advantage of increasing the accuracy of detection and improving the detection accuracy of human biosignals by using intersection detection of two radars and artificial intelligence techniques.

FIG. 2 is a view showing that a person 200 is located around construction equipment on which the radar sensor module 100 of FIG. 1 is mounted. As can be seen in FIG. 2, the concept of detecting and analyzing the heart rate and breathing rate of a person 200 located around the construction equipment by mounting the radar sensor module 100 on the construction equipment is shown.

That is, the person 200 may move around the construction equipment, but may also be in a stationary state, so it is necessary to detect the person 200 both in a moving state and in a stationary state.

3 shows the location and detection area where the radar sensor module 100 is mounted on construction equipment for the detection of a person 200 as an example, and in FIGS. 4 to 9, the biometric information monitoring radar around construction equipment according to the present invention The operating principle is explained in detail.

3 is a view showing an example in which the radar sensor module 100 of FIG. 1 is mounted on construction equipment and a detection area of the radar sensor module 100. As can be seen in FIG. 3, the radar sensor module 100 can be mounted around construction equipment, and each detection area exists. At this time, since the driver of the construction equipment is looking at the front, it is possible to recognize the front of the person 200, but it is difficult to recognize the side and rear of the construction equipment. 200) can be mounted on the side or rear where it is difficult to recognize.

FIG. 4 is a diagram showing positions where the first radar 110 and the second radar 120 of FIG. 1 detect biometric information of the person 200 .

As can be seen in FIG. 4 , the first radar 110 and the second radar 120 perform transmission and reception at different measurement positions.

As shown in the following figure, the first radar 110 and the second radar 120 transmit radio waves according to the time difference at regular spatial intervals to start detecting the biosignal of the person 200. . At this time, since the process of the person 200's heart beating or lungs breathing is a three-dimensional model, the probability that the first radar 110 and the second radar 120 can detect the heart rate or breathing rate is a two-dimensional model. higher than that of the model.

At this time, since the first radar 110 and the second radar 120 may interfere with each other, the first radar 110 and the second radar 120 may operate at timings that cross each other in time.

FIG. 5 is a detailed diagram illustrating antenna structures of the first radar 110 and the second radar 120 of FIG. 1 . As can be seen in FIG. 5, the first radar 110 includes a first transmission antenna 111 for transmitting an RF signal and a first reception antenna 112 for receiving an RF signal reflected from a person 200. Similarly, the second radar 120 includes a second transmitting antenna 121 for transmitting an RF signal and a second receiving antenna 122 for receiving an RF signal reflected from the person 200. Consists of.

The first radar 110 and the second radar 120 may transmit and receive at spatially different locations, or may transmit and receive at different angles through beamforming at the same location.

Meanwhile, since the first transmission antenna 111, the first reception antenna 112, the second transmission antenna 121, and the second reception antenna 122 are synchronized with each other, they may transmit and receive differently at desired timings. .

6 is a timing diagram illustrating transmission and reception timings in the first radar 110 and the second radar 120 of FIG. 1 .

As can be seen in FIG. 6, the first radar 110 and the second radar 120 synchronize with each other and perform transmission and reception at different times.

That is, the first transmission antenna 111 and the second transmission antenna 121 transmit the RF signal to the person 200 differently, and the first reception antenna 112 transmits the RF signal from the first transmission antenna 111, and the person 200 ), and the second reception antenna 122 transmits from the second transmission antenna 121 and receives the signal reflected from the person 200.

Meanwhile, the first radar 110 and the second radar 120 may use either FMCW or UWB. The first radar 110 and the second radar 120 may use the same method, or may use different methods. A modulation scheme may also be used.

In addition, when the first radar 110 and the second radar 120 use the same modulation method, since the first radar 110 and the second radar 120 are synchronized with each other, the first transmission antenna 111 or The RF signal transmitted by the second transmission antenna 121 and the signal reflected by the person 200 are simultaneously received by the first reception antenna 112 and the second reception antenna 122 to produce a spatial diversity effect. , The first transmission antenna 111 and the second transmission antenna 121 transmit MIMO signals at the same time and the first reception antenna 112 and the second reception antenna 122 simultaneously receive MIMO signals, thereby increasing reception performance. may be

Therefore, the radar for monitoring biometric information around construction equipment according to the present invention has the advantage of improving the detection accuracy of human biometric signals by using the temporal/spatial difference through cross detection of the two radars.

FIG. 7 is a diagram illustrating an example of measuring the heart rate of a person 200 by the radar sensor module 100 of FIG. 1 . As can be seen from FIG. 7, heart rate is the movement of the heart, and since the heart has a three-dimensional shape, there is a difference in the shape of the reflected signal according to the direction in which radio waves are received.

The radar for monitoring biometric information around construction equipment according to the present invention has the effect of greatly improving the detection probability of heartbeat signals because the signals transmitted by the two spatially separated radars at times that do not overlap each other are reflected to the heart and received. there is.

FIG. 8 is a diagram illustrating an example in which the radar sensor module 100 of FIG. 1 measures the respiratory rate of a person 200 . As can be seen in FIG. 8, the respiratory rate is the movement of the lungs, and since the human lungs have a three-dimensional shape, there is a difference in the shape of the reflected signal according to the direction in which the radio waves are received.

The radar for monitoring biometric information around construction equipment according to the present invention has the effect of significantly improving the detection probability of breathing signals because the signals transmitted by the two spatially separated radars at times that do not overlap each other are reflected to the lungs and received. there is.

9 is a graph showing Doppler characteristics when the first radar 110 of FIG. 1 does not stop.

As can be seen in FIG. 9, the radar sensor module 100 is based on the Doppler frequency plane 310 according to the azimuth representing the Doppler frequency generated when the construction equipment rotates for each azimuth with respect to the turning angle of the construction equipment. Motion is detected for an obstacle in a specific orientation exhibiting Doppler characteristics that deviate from the Doppler frequency plane 310 .

When the construction equipment equipped with the radar sensor module 100 continues turning, information output from the first radar 110 to the artificial intelligence processor 130 may include a Doppler frequency. At this time, an object located at the front of the direction in which the construction equipment rotates outputs a positive Doppler frequency, whereas an object located at the rear of the direction in which the construction equipment rotates outputs a negative Doppler frequency.

At this time, when the construction equipment turns, when an object of a specific azimuth shows a plus or minus Doppler frequency than on the Doppler frequency plane 310 according to the azimuth with respect to the Doppler frequency plane 310 according to the azimuth representing the Doppler frequency for each azimuth perceived as an obstacle.

Therefore, the radar for monitoring biometric information around construction equipment according to the present invention has the advantage of being able to detect nearby obstacles based on Doppler frequency characteristics for each azimuth even when the construction equipment turns.

10 is a flowchart illustrating a method for monitoring biometric information around construction equipment according to an embodiment of the present invention.

As can be seen in FIG. 10, the method for monitoring biometric information around construction equipment includes recognizing an obstacle (S110), determining whether the construction equipment is in a stopped state (S120), and when it is determined that the construction equipment is in a stopped state. In the steps of determining whether motion of an obstacle is detected (S130), detecting biometric information of an obstacle (S140), determining whether biometric information is detected (S150), and determining motion detection (S130), motion is detected or biometric information is detected (S130). If biometric information is detected in the information presence check step (S150), the step of determining the person 200 (S160), and if the biometric information is not detected in the biometric information check step (S150), the step of determining a stationary obstacle ( S170).

In addition, the method for monitoring biometric information around construction equipment includes an obstacle recognition step for recognizing an obstacle (S110), a construction equipment stop determination step for determining whether the construction equipment is in a stopped state (S120), and when the construction equipment is not determined to be in a stopped state. In the steps of determining whether movement of an obstacle is detected (S230), detecting biometric information of an obstacle (S240), determining whether biometric information is detected (S250), and determining motion detection (S230), motion is detected or biometric information is detected (S230). If biometric information is detected in the information presence check step (S150), the step of determining the person 200 (S260), and if the biometric information is not detected in the biometric information check step (S250), the stationary obstacle is determined as a stationary obstacle. It consists of a judgment step (S170).

Here, in the motion detection determination step (S230), the Doppler frequency plane 310 according to the azimuth based on the Doppler frequency plane 310 according to the azimuth representing the Doppler frequency generated when the construction equipment rotates for each azimuth with respect to the turning angle of the construction equipment Obstacles in a specific orientation, which exhibit Doppler characteristics that deviate from the

That is, the method for monitoring biometric information around construction equipment according to the present invention determines the presence or absence of a person 200 by analyzing a signal reflected from a person 200 using the radar sensor module 100 when the construction equipment is stationary. can do.

In addition, when the construction equipment does not stop, when an object of a specific azimuth shows a plus or minus Doppler frequency than on the Doppler frequency plane 310 according to the azimuth with respect to the Doppler frequency plane 310 according to the azimuth representing the Doppler frequency for each azimuth By detecting the motion, there is an advantage in that the person 200 can be quickly identified in the rapidly moving construction equipment.

Therefore, the method for monitoring biometric information around construction equipment according to the present invention can accurately measure the heart rate and respiratory rate when the construction equipment is stationary, and even when the construction equipment is turning, based on the Doppler frequency characteristics for each azimuth, the human 200 It has the advantage of being able to detect motion more quickly.

As described above, the radar and method for monitoring biometric information around construction equipment according to the present invention increase the accuracy of detection by using the cross detection of two radars and artificial intelligence techniques, and the detection accuracy of human biosignals by using temporal / spatial differences. It has the advantage of improving, and it is possible to determine a person by detecting the movement of an obstacle or biometric information while the construction equipment is stationary, and to determine a person by detecting the motion of an obstacle or biometric information even when the construction equipment is moving or rotating. There are advantages to being

What has been described above includes examples of one or more embodiments. Of course, it is not possible to describe every possible combination of components or methods for purposes of describing the above embodiments, but those skilled in the art will recognize that many additional combinations and permutations of various embodiments are possible. Accordingly, the described embodiments are intended to cover all alternatives, modifications and adaptations falling within the spirit and scope of the appended claims.

Claims (12)

a first radar detecting a person by transmitting and receiving RF to and from a person;
a second radar detecting the person by transmitting and receiving RF to and from the person; and
An artificial intelligence processor for analyzing detailed information of the person from the received signal of the first radar and the received signal of the second radar. According to claim 1,
The RF is a modulation signal of either a frequency modulated continuous wave (FMCW) method or an ultra wide-band (UWB) method. According to claim 1,
The detailed information includes at least one of a heart rate and a respiratory rate of the person. According to claim 1,
Wherein the first radar and the second radar perform transmission and reception at different measurement positions. According to claim 1,
The first radar and the second radar are synchronized with each other and transmit and receive at different times, characterized in that biometric information monitoring radar around construction equipment. According to claim 1,
The artificial intelligence processor is a biometric information surveillance radar around construction equipment, characterized in that for learning using artificial intelligence techniques. According to claim 5,
The artificial intelligence technique utilizes unsupervised learning for data in various environments. According to claim 5,
The artificial intelligence technique utilizes federated learning that collects models learned from construction equipment to a central server without directly collecting data from the central server. According to claim 1,
The radar sensor module, based on the Doppler frequency plane according to the azimuth representing the Doppler frequency generated when the construction equipment rotates for each azimuth with respect to the turning angle of the construction equipment, a specific orientation representing Doppler characteristics deviating from the Doppler frequency plane according to the azimuth angle Biometric information surveillance radar around construction equipment, characterized in that for detecting the movement of the obstacle. An obstacle recognition step of recognizing an obstacle;
Construction equipment stop determination step of determining whether the construction equipment is stopped;
A motion detection determination step of determining whether motion of the obstacle is detected when it is determined that the construction equipment is in a stopped state;
a biometric information detection step of detecting biometric information of the obstacle;
Biometric information confirmation step of confirming whether the biometric information is detected;
a person determination step of determining that the motion is detected in the motion detection and determination step or the biometric information is detected in the biometric information check step; and
A method for monitoring biometric information around construction equipment, comprising: determining whether a stationary obstacle is a stationary obstacle when the biometric information is not detected in the biometric information check step. An obstacle recognition step of recognizing an obstacle;
Construction equipment stop determination step of determining whether the construction equipment is stopped;
A motion detection determination step of determining whether motion of the obstacle is detected when the construction equipment is not determined to be in a stopped state;
a biometric information detection step of detecting biometric information of the obstacle;
Biometric information confirmation step of confirming whether the biometric information is detected;
a person determination step of determining that the motion is detected in the motion detection and determination step or the biometric information is detected in the biometric information check step; and
A method for monitoring biometric information around construction equipment, comprising: determining whether a stationary obstacle is a stationary obstacle when the biometric information is not detected in the biometric information check step. According to claim 11,
In the motion detection and determination step, based on the Doppler frequency plane according to the azimuth indicating the Doppler frequency generated when the construction equipment rotates for each azimuth with respect to the turning angle of the construction equipment, the Doppler characteristic representing the deviation from the Doppler frequency plane according to the azimuth A method for monitoring biometric information around construction equipment, characterized in that for sensing an obstacle in a specific direction by the movement.

Images