KR102620115B1 - Wireless AI Object Recognition Remote Monitoring System And Oject Recognition Method by the Same - Google Patents

Abstract

The present invention is intended to solve the above problems, and recognizes people approaching the mobile vehicle using a wireless ultrasonic module and a wireless camera module installed on the front and rear of a mobile vehicle such as a forklift, and monitors installed in the cockpit of the mobile vehicle. The purpose is to provide a wireless artificial intelligence object recognition remote monitoring system that can check this in real time and an object recognition method using the same. In particular, the present invention analyzes the results by fusing wireless ultrasound data measured by a plurality of wireless ultrasound modules and image data measured by a plurality of wireless camera modules, while the wireless ultrasound module detects both people and objects. The purpose is to analyze the image data measured by the wireless camera module using artificial intelligence, merge the data measured by the wireless ultrasound module and the wireless camera module, and transmit the final detection information over a short distance.

Description

Wireless AI Object Recognition Remote Monitoring System And Object Recognition Method by the Same}

The present invention relates to a wireless artificial intelligence object recognition remote monitoring system, and more specifically, to recognize people approaching a mobile vehicle using a wireless ultrasonic module and a wireless camera module installed on the front and rear of a mobile vehicle such as a forklift, thereby This relates to a wireless artificial intelligence object recognition remote monitoring system that can be checked in real time through a monitor installed inside the vehicle and an object recognition method using the same.

Artificial intelligence object recognition is a technology that processes objects present in images input from a camera in real time using artificial intelligence, and is used in fields such as security surveillance systems and medical image analysis. Such real-time object recognition must ensure both accurate recognition rate and fast recognition speed.

This artificial intelligence object recognition technology is widely used in industrial fields such as forklifts and mobile vehicles. By using real-time object recognition technology, cameras can be installed at the rear or front of forklifts, mobile vehicles, etc. to detect people among objects approaching the rear or front of forklifts or mobile vehicles, thereby preventing collisions between vehicles and people. .

The most widely used artificial intelligence object recognition system with current technology is a wired human body detection system such as CCTV, where the main controller and camera device are connected by wire. In the case of cameras actually installed in the field, they had the disadvantage of having to be installed by workers using a wired extension cable up to 15 to 20 meters long, and that installation time took a lot of time. In addition, more research is needed to increase the human body detection rate of cameras.

Republic of Korea Patent Publication No. 10-1418872 Republic of Korea Patent Publication No. 10-1854461 Republic of Korea Patent Publication No. 10-2390813 Republic of Korea Patent Publication No. 10-2021-0066207

The present invention is intended to solve the above problems, and recognizes people approaching the mobile vehicle using a wireless ultrasonic module and a wireless camera module installed on the front and rear of a mobile vehicle such as a forklift, and monitors installed in the cockpit of the mobile vehicle. The purpose is to provide a wireless artificial intelligence object recognition remote monitoring system that can check this in real time and an object recognition method using the same.

In particular, the present invention analyzes the results by fusing wireless ultrasound data measured by a plurality of wireless ultrasound modules and image data measured by a plurality of wireless camera modules, while the wireless ultrasound module detects both people and objects. The purpose is to analyze the image data measured by the wireless camera module using artificial intelligence, merge the data measured by the wireless ultrasound module and the wireless camera module, and transmit the final detection information over a short distance.

When using remote video transmission, which mostly uses LTE, LTE incurs costs and it is difficult to detect people in real time due to delay time (stuttering over time due to traffic problems between network operators).

In order to achieve the above object, the wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention is installed on the front and rear of a mobile vehicle requiring human recognition and detects people in real time using an ultrasonic sensor. A plurality of wireless ultrasonic modules transmitting detection signal data through wireless communication; A plurality of wireless camera modules installed where the plurality of wireless ultrasound modules are installed to capture images in real time and transmit the captured image data through wireless communication; It is installed at a location spaced apart from the mobile vehicle, receives, processes, and transmits the detection signal data transmitted from the wireless ultrasonic module, receives the image data transmitted from the wireless camera module, and analyzes the image data by artificial intelligence. A server module that analyzes, detects and transmits people; and a mobile vehicle module installed inside the mobile vehicle to receive and display the detection signal data processed by the server module and the image data analyzed by the server module.

The wireless ultrasonic module includes an ultrasonic sensor unit that emits ultrasonic waves to detect a person approaching the mobile vehicle, an ultrasonic data generator that generates detection signal data when a person is detected by the ultrasonic sensor unit, and the ultrasonic data generator. It includes an ultrasonic communication unit that transmits the generated detection signal data to the server module through wireless communication.

The server module receives image data transmitted from the wireless camera module and detection signal data transmitted from the wireless ultrasonic module, and transmits the processed detection signal data and analyzed image data to the mobile vehicle module; An ultrasonic data processing unit that processes the detection signal data received from the server communication unit, identifies the wireless ultrasonic module that transmitted the detection signal data, and generates a warning sound control signal, and the detection signal data received from the server communication unit matches the image data. A data determination unit that only processes cases, an artificial intelligence analysis unit that detects people by analyzing the image data transmitted from the data determination unit by artificial intelligence, and a server that displays images in which people are detected by the artificial intelligence analysis unit. Includes a display unit.

The artificial intelligence analysis unit is an artificial intelligence learning unit that learns data so that artificial intelligence can recognize people, and an artificial intelligence A person detection unit that detects a person, and a color control signal generator that generates a color control signal for the mobile vehicle module to display the person in a specific color on the mobile vehicle module when the person detection unit detects a person in the image data. Includes.

The mobile vehicle module includes a mobile vehicle communication unit that receives image data analyzed by the server module and detection signal data processed by the server module transmitted from the server module, and detection by detection signal data received from the mobile vehicle communication unit. A first display unit that displays the wireless ultrasonic module that transmitted signal data, image data received from the mobile vehicle communication unit is displayed, and when a person is detected by the artificial intelligence control unit, the person is displayed in a specific color. A second display unit, a first alarm unit that receives the warning sound control signal generated by the ultrasonic data processing unit and warns with a warning sound inside the mobile vehicle, and a first alarm unit that receives the warning sound control signal generated by the ultrasonic data processing unit and warns the outside of the mobile vehicle It includes a second alarm unit that warns with a warning sound.

The wireless camera module is provided with a camera communication unit that transmits captured image data to the server module through wireless communication, and a connection between the camera communication unit, ultrasonic communication unit, server communication unit, and mobile vehicle communication unit is performed using R/F (Radio Frequency) or LTE (LTE). It is characterized by wireless communication using the Long-Term Evolution (Long-Term Evolution) method.

In addition, an object recognition method using a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention to achieve the above object includes a wireless ultrasonic module, a wireless camera module, and a mobile vehicle module installed in a mobile vehicle. first step; A second step in which a person is detected by the wireless ultrasonic module, detection signal data is generated and transmitted to the server module, and image data captured by the wireless camera module is transmitted to the server module; A third step in which the detection signal data and image data are processed by the server module and transmitted to the mobile vehicle module; It includes a fourth step in which a warning sound sounds in the mobile vehicle, the location of the wireless ultrasonic module is displayed on the first display, and the person recognized by artificial intelligence is displayed in a specific color on the second display.

As described above, the present invention has the advantage of preventing collisions by increasing the object detection rate because it detects people using artificial intelligence in the image data captured by the wireless camera module only when the person is detected by the wireless ultrasonic module. There is.

Figure 1 is a conceptual diagram of a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention.
Figure 2 is a conceptual diagram of a wireless ultrasonic module according to an embodiment of the present invention.
Figure 3 is a configuration diagram of a wireless ultrasonic module according to an embodiment of the present invention.
Figure 4 is a configuration diagram of a server module according to an embodiment of the present invention.
Figure 5 is a configuration diagram of an artificial intelligence analysis unit according to an embodiment of the present invention.
Figure 6 is a configuration diagram of a mobile vehicle module according to an embodiment of the present invention.
Figure 7 shows a conceptual diagram of performing a warning broadcast based on the direction of a person for a mobile vehicle according to an embodiment of the present invention.
Figure 8 is a flow chart of an object recognition method using a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention.

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. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

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

For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term “and/or” includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

Hereinafter, a wireless object recognition remote monitoring system according to an embodiment of the present invention will be described with reference to the drawings. Figure 1 is a conceptual diagram of a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention. Referring to FIG. 1, the wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention includes a wireless ultrasonic module 100, a wireless camera module 200, a server module 300, and a mobile vehicle module 400. It may be configured to include. Here, mobile vehicles refer to vehicles used in industrial sites, such as forklifts and trucks.

The wireless ultrasonic module 100 is installed on the front and rear of a mobile vehicle that requires human recognition, detects people in real time using an ultrasonic sensor, and transmits detection signal data through wireless communication. A plurality of wireless ultrasonic modules 100 are installed at the front and rear of a mobile vehicle on which the wireless camera module 200 is installed. In one embodiment of the present invention, a first wireless ultrasonic module is provided on the front left side of the mobile vehicle, a second wireless ultrasonic module is provided on the front right side of the mobile vehicle, and a second wireless ultrasonic module is provided on the rear left side of the mobile vehicle. It may be equipped with three wireless ultrasonic modules, and a fourth wireless ultrasonic module provided on the rear right side based on the mobile vehicle. FIG. 2 is a conceptual diagram of a wireless ultrasonic module 100 according to an embodiment of the present invention, and FIG. 3 is a configuration diagram of a wireless ultrasonic module 100 according to an embodiment of the present invention. 2 and 3, the wireless ultrasonic module 100 according to an embodiment of the present invention may be configured to include an ultrasonic sensor unit 110, an ultrasonic data generator 120, and an ultrasonic communication unit 130. there is.

The ultrasonic sensor unit 110 detects a person approaching the mobile vehicle by emitting ultrasonic waves. The ultrasonic sensor unit 110 includes an ultrasonic transmitter that emits ultrasonic waves and an ultrasonic receiver that receives the reflected ultrasonic waves returned. The ultrasonic transmitter emits short bursts of high-frequency sound waves containing frequencies between 23 and 40 kHz, and when these sound pulses hit an object, some of the sound waves are reflected back to the ultrasonic receiver. The distance is measured by measuring the time from when ultrasonic waves are emitted to when they are received. If a person comes between the ultrasonic sensor unit and the wall or road, the measured distance changes and the person is recognized. The ultrasonic sensor unit 110 may be equipped with a regulator for stable power supply.

The ultrasonic data generation unit 120 generates detection signal data when an object is detected by the ultrasonic sensor unit 110. When a person is detected by the ultrasonic sensor unit 110, the ultrasonic data generator 120 digitizes the detected person and generates detection signal data. The detection signal data includes the location of the specific wireless ultrasonic module 100 that detected the person. In addition, the ultrasonic data generator 120 generates detection signal data and then transmits the detection signal data to the wireless camera module 200 located at the same location to notify the camera operation to cause the wireless camera module 200 to operate. It is characterized by having wealth. The camera of the wireless camera module 200 is normally kept in an off state, and then receives detection signal data transmitted from the camera operation notification unit and turns the camera on to capture images. Using the camera operation notification unit, if a person is not detected, the wireless camera module 200 remains in the off state and turns on only when the wireless ultrasonic module 100 detects a person, thereby reducing the power of the wireless camera module 200. There is an advantage in that the wireless camera module 200 can increase the detection rate of detecting people.

The ultrasonic communication unit 130 transmits the detection signal data generated by the ultrasonic data generation unit 120 to the server communication unit 310 of the server module 300 through wireless communication. The ultrasonic communication unit 130 and the server communication unit 310 of the present invention can use the R/F method or the LTE method for wireless communication. R/F communication is communication that operates at radio frequency, and the communication frequency band is generally 300 kHz to 300 GHz. RF communication can transmit signals farther than infrared communication, and communication is possible even if there are obstacles between the ultrasonic communication unit 130 and the server communication unit 310. Additionally, R/F communication uses a specific frequency band, so there is no interference. It has the advantage of having a low impact. The ultrasonic communication unit 130, camera communication unit, server communication unit 310, and mobile vehicle communication unit 410 of the present invention have an R/F module therein, and the R/F module is used to transmit and receive wireless signals between two devices. It is a small electronic device used. Several carrier frequencies are commonly used in commercial RF modules, including frequencies in the ISM radio band for industrial, scientific, and medical purposes, such as 433.92 MHz, 915 MHz, and 2,400 MHz. These frequencies are used based on national and international regulations regarding the use of radios for communications. Near-field devices may also use license-exempt frequencies such as 315 MHz and 868 MHz. In the present invention, the frequency band of the ultrasonic communication unit 130, camera communication unit, server communication unit 310, and mobile vehicle communication unit 410 may be 1 to 4 GHz, and in order to stably transmit and receive, 2.5 GHz, which is a stable frequency use band, is used. It is desirable to use Additionally, in the present invention, the LTE (Long-Term Evolution) method can be used as a wireless communication method for the ultrasonic communication unit 130, camera communication unit, server communication unit 310, and mobile vehicle communication unit 410.

The wireless camera module 200 is installed where a plurality of wireless ultrasound modules 100 are installed, captures images in real time, and transmits the captured image data through wireless communication. In one embodiment of the present invention, two wireless camera modules 200 are installed on both sides of the front and two on both sides of the rear of the mobile vehicle, but according to various embodiments, five, six, seven, eight, Nine, ten, etc. wireless camera modules 200 may be installed in a mobile vehicle. The wireless camera module 200 includes a camera and a camera communication unit. Each camera of the wireless camera module 200 can secure an angle of view of 120 degrees, and when installing 2 front channels and 2 rear channels, the cameras are arranged to secure a 320 to 360 degree view of the surrounding area.

The camera captures images in real time at the location where the wireless camera module 200 is installed, and captures images of objects or people approaching the mobile vehicle. In general, cameras are classified according to the sensor used in the camera, and there are two types: CCD sensor type and CMOS sensor type. Both CCD sensors and CMOS sensors transmit light brightness signals (charge) to the processor, but depending on the design of the image sensor, there is a method that transmits the charge directly (CCD) or a method that transmits the charge of each pixel as a digital signal (CMOS). It can be divided into Charge loss may occur during conversion to digital signals, so CCD is relatively superior in terms of image quality, but CMOS is becoming more integrated based on semiconductor technology, and for this reason, it has a small size and excellent power efficiency. there is. In the present invention, either a CCD sensor type or a CMOS sensor type can be selected and used, but it is preferable to use a CMOS sensor type camera that consumes less power and enables high-speed processing.

The camera communication unit transmits image data captured by the camera to the server communication unit 310 of the server module 300 through wireless communication. The camera communication unit and server communication unit 310 of the present invention can use the R/F method or the LTE method for wireless communication. Additionally, in the present invention, Long-Term Evolution (LTE) can be used as a wireless communication method for the camera communication unit and the server communication unit 310 in order to efficiently transmit images captured by a camera in a short time.

The server module 300 is installed at a distance from the mobile vehicle, receives and processes detection signal data transmitted from the wireless ultrasonic module 100, and transmits it to the mobile vehicle module 400, and transmits it from the wireless camera module 200. Receives video data, analyzes the video data using artificial intelligence, detects people, and transmits it to the mobile vehicle module 400. Figure 4 is a configuration diagram of the server module 300 according to an embodiment of the present invention. Referring to FIG. 4, the server module 300 according to an embodiment of the present invention includes a server communication unit 310, an ultrasonic data processing unit 320, a data determination unit 330, an artificial intelligence analysis unit 340, and a server display. It may be configured to include a unit 350. The server module 300 according to an embodiment of the present invention may use an embedded Linux system, and the artificial intelligence may be a program written in Python. Additionally, the result of detecting a person can be displayed through the server display unit 350 connected to the GPIO port of the embedded system. The output value of the GPIO port is transmitted to another MCU module, which has the advantage of improving response speed by activating the interrupt function.

The server communication unit 310 receives detection signal data transmitted from the wireless ultrasonic module 100 and image data transmitted from the wireless camera module 200, and sends the processed detection signal data and analyzed image data to the mobile vehicle module 400. ) and send it to The server communication unit 310, the wireless ultrasonic module 100, the wireless camera module 200, and the mobile vehicle module 400 are connected by wireless communication, and the wireless communication is R/F (Radio Frequency) or LTE (Long-Frequency). You can communicate using the Term Evolution method.

The ultrasonic data processing unit 320 processes the detection signal data received from the server communication unit 310, identifies the wireless ultrasonic module 100 that transmitted the detection signal data, and generates a warning sound control signal. The ultrasonic data processing unit 320 identifies the wireless ultrasonic module 100 that transmitted it from the detection signal data transmitted from the wireless ultrasonic module 100, generates an identification signal, and transmits it to the mobile vehicle module 400 through the server communication unit 310. send to The wireless ultrasonic module 100 that transmitted the detection signal data is displayed on the second display unit 430, which has received the identification signal, so that the driver of the mobile vehicle can check it. In addition, when the wireless ultrasonic module 100 detects a person, the ultrasonic data processing unit 320 generates a warning sound control signal and transmits it to the mobile vehicle module 400 to activate the first warning unit 440 and the second warning unit 450. ) to make a warning sound.

The data determination unit 330 processes only cases where the detection signal data and image data received from the server communication unit 310 match. That is, in the present invention, image data transmitted from the wireless camera module 200 is processed only when the wireless ultrasound module 100 detects a person. The wireless ultrasonic module 100 detects people using ultrasonic waves and has a higher detection rate than other sensors. When the wireless camera module 200 is linked with the wireless ultrasonic module 100 to detect people, the wireless ultrasonic module 100 detects people. In this case, video data transmitted from the wireless camera module 200 is analyzed by artificial intelligence to detect people. To this end, the data determination unit 330 processes only the image data of the wireless camera module 200 that is received while the detection signal data is received from the wireless ultrasonic module 100.

The artificial intelligence analysis unit 340 analyzes the image data transmitted from the data determination unit 330 using artificial intelligence to detect people. Figure 5 is a configuration diagram of the artificial intelligence analysis unit 340 according to an embodiment of the present invention. Referring to Figure 5, the artificial intelligence analysis unit 340 according to an embodiment of the present invention may be configured to include an artificial intelligence learning unit 341, a person detection unit 342, and a color control signal generating unit 343. there is. The human recognition of the present invention uses an object detection model based on artificial intelligence, and the object detection model can be broadly divided into One-Stage Detector and Two-Stage Detector. One-stage detectors include YOLO, SSD, and RetinaNet, and two-stage detectors include R-CNN, Fast R-CNN, and Faster R-CNN. As the artificial intelligence algorithm of the present invention, one of YOLO, SSD, RetinaNet, R-CNN, Fast R-CNN, and Faster R-CNN can be selected and used.

The artificial intelligence learning unit 341 learns data so that artificial intelligence can recognize people. The artificial intelligence learning unit 341 of the present invention has already repeatedly learned labeled data through machine learning or deep learning.

The person detection unit 342 detects people using artificial intelligence in the image data transmitted from the data determination unit 330 based on content learned in the artificial intelligence learning unit 341. The person detection unit 342 analyzes image data transmitted from the data determination unit 330 in real time based on data learned from the artificial intelligence learning unit 341. It detects people using artificial intelligence among the image data, and detects people using artificial intelligence. A detection signal is generated and transmitted to the color control signal generator 343. The person detection unit 342 includes a worker detection unit that distinguishes between workers and non-workers working in the workplace. The worker detection unit learns the worker from the artificial intelligence learning unit 341, and determines whether the person photographed is a worker or a non-worker from the captured image data. For example, the color control signal generator 343 generates different colors for workers and non-workers classified in the worker detection unit and transmits them to the server display unit 350 and the first display unit 420 so that the driver can It can be used to recognize workers or non-workers.

The color control signal generator 343 generates a color control signal for the mobile vehicle module 400 to display the person in a specific color on the mobile vehicle module 400 when the person detection unit 342 detects a person in the image data. do. The color control signal generator 343 may receive a person detection signal from the person detection unit 342 and change the color of the recognized person or display a line on the outside of the person image so that the person can be distinguished from the image data. For example, the color control signal generator 343 generates a color control signal that displays the outline of a person detected in the image data as a red dotted line and transmits it to the server display unit 350 and the first display unit 420. , the server display unit 350 and the second display unit 430 display an image in which the outline of a person is processed with a red dotted line.

The server display unit 350 displays an image in which a person is detected by the artificial intelligence analysis unit 340. The image data captured by the wireless camera module 200 is transmitted to the server module 300, and the image data selected by the data determination unit 330 is analyzed in real time by the artificial intelligence analysis unit 340. The image data is displayed through the server display unit 350. Through the server display unit 350, the manager can check in real time whether a person is detected by the artificial intelligence analysis unit 340. The server display unit 350, first display unit 420, and second display unit 430 of the present invention can use various types of displays, for example, CRT (Cathode Ray Tube), PDP (Plasma Display Panel) ), OLED (Organic LED), LED (Light Emitting Diode), FED (Field, Emission Display), VFD (Vacuum Fluorescent Display), LCD (Liquid Crystal Display), EPD (Electrophoretic Display), ECD (Electrochromic Display) However, you are not limited to this and can use displays including those not listed here.

The mobile vehicle module 400 is installed inside the mobile vehicle and receives and displays the image data analyzed by the server module 300 and the detection signal data processed by the server module 300. Figure 6 is a configuration diagram of a mobile vehicle module 400 according to an embodiment of the present invention. Referring to FIG. 6, the mobile vehicle module 400 according to an embodiment of the present invention includes a mobile vehicle communication unit 410, a first display unit 420, a second display unit 430, and a first alarm unit 440. and a second alarm unit 450.

The mobile vehicle communication unit 410 receives the image data analyzed by the server module 300 and the detection signal data processed by the server module 300, which are transmitted from the server module 300. The server communication unit 310 and the mobile vehicle module 400 are connected through wireless communication, and may communicate wirelessly using a Radio Frequency (R/F) method or a Long-Term Evolution (LTE) method.

The first display unit 420 displays the wireless ultrasonic module 100 that transmitted the detection signal data based on the detection signal data received from the mobile vehicle communication unit 410. The first display unit 420 displays the wireless ultrasonic module 100 identified by the identification signal transmitted to the ultrasonic data processing unit 320, notifies the driver that a person has been detected by the wireless ultrasonic module 100, and informs the driver that a person has been detected by the wireless ultrasonic module 100. The detected wireless ultrasonic module 100 is displayed so that the driver can know the location where the person was detected.

The second display unit 430 displays image data received from the mobile vehicle communication unit 410, and when a person is detected by the artificial intelligence control unit, the person is displayed in a specific color. The second display unit 430 displays the image analyzed by the artificial intelligence analysis unit 340, and receives the color control signal generated by the color control signal generator 343 to display people in a specific color or with a red dotted line. This allows the driver to immediately recognize that a person has been detected. The driver can confirm that a person has approached the mobile vehicle from any direction through the first display unit 420, and can confirm the location of the person through a specifically displayed image through the second display unit 430. . The second display unit 430 has a screen divided by the number of wireless camera modules 200, and the playback screen of the wireless camera module 200 where a person is detected can be enlarged and played back compared to other screens.

The second display unit 430 of the present invention may include a screen splitter. The screen dividing unit is a first image of the wireless camera module 200 for the front left side of the mobile vehicle, a second image of the wireless camera module 200 for the front right side, and a second image of the wireless camera module 200 for the front right side, and The third image of the wireless camera module 200 for the rear left and the fourth image of the wireless camera module 200 for the rear right can be displayed in four areas divided into equal areas on one screen. You can. In addition, the screen dividing unit includes a screen size adjusting unit, and the screen size adjusting unit, when a person is observed in any one of the first to fourth images, changes the image in which the person is observed to the image in which the person is not observed. It can be displayed by enlarging it larger than the image. For example, when a person is observed in the first image, the size of the first image may be increased by 1.5 to 2 times, and the size of the second to fourth images may be reduced by 0.3 to 0.5 times. In addition, the screen dividing unit includes a screen position adjusting unit, and the screen position adjusting unit adjusts the image in which the person is observed to the center of the screen when a person is observed in any one of the first to fourth images. It can be positioned. Therefore, the driver can continue driving while observing more closely without manually enlarging the image of the dangerous area.

The first warning unit 440 receives the warning sound control signal generated by the ultrasonic data processing unit 320 and issues a warning sound inside the mobile vehicle. When the wireless ultrasonic module 100 detects a person, the first alarm unit 440 receives the warning sound control signal generated by the ultrasonic data processing unit 320 through wireless communication and warns with a warning sound. The first alarm unit 440 is located inside the cockpit of the mobile vehicle and sounds a warning sound to indicate that a person has been detected by the wireless ultrasonic module 100. The first alarm unit 440 according to an embodiment of the present invention may use a speaker built into the first display unit 420, and the warning sound may be 60 to 80 db. Additionally, the first alarm unit 440 may notify the location of a specific wireless ultrasonic module 100 in which a person is detected using a pre-recorded human voice. For example, when the wireless ultrasonic module 100 located at the right rear detects a person, the first alarm unit 440 plays a voice saying “A person has been detected at the right rear. Be careful” to alert the driver that the person is present. The specific detected location can be notified.

The second warning unit 450 receives the warning sound control signal generated by the ultrasonic data processing unit 320 and issues a warning sound from the outside of the mobile vehicle. If the first warning unit 440 warns the driver of the mobile vehicle with a warning sound, the second warning unit 450 warns people outside the mobile vehicle with a warning sound. Unlike the first alarm unit 440, the second alarm unit 450 is installed outside the mobile vehicle and can sound a warning sound to a person approaching the mobile vehicle. The warning sound of the second warning unit 450 can warn people approaching the mobile vehicle with a relatively loud sound of 130 to 150 db. Additionally, the second alarm unit 450 can notify a dangerous situation to a detected approaching person using a pre-recorded human voice. For example, when the specific wireless ultrasonic module 100 detects a person, the second alarm unit 450 plays a voice saying "There is a risk of collision with a mobile vehicle. Stay away from the mobile vehicle." You can notify people approaching of a dangerous situation. The second alarm unit 450 is provided with a plurality of alarms, and the alarms include a second alarm 450A for the front left side provided on the front left side of the mobile vehicle, and a second alarm device 450A for the front right side provided on the front right side ( 450B), a second alarm for the rear left (450C) provided on the rear left, and a second alarm for the rear right (450D) provided on the rear right, and the second alarm unit has a selection warning unit to detect a plurality of alarms among a plurality of alarms. From the image data obtained from the wireless camera module 200, a warning broadcast can be selectively sent only to alarms corresponding to the location where the person was observed.

In a situation where a warning sound is sounded by the first alarm unit 440 and the second alarm unit 450 of the mobile vehicle module 400, the distance between the mobile vehicle and the person from the wireless ultrasonic module 110 is less than a certain distance. In this case, it may further include an emergency stop unit that stops the operation of the mobile vehicle. The emergency stop is a special situation in which a person approaching the mobile vehicle or the driver does not recognize the warning sound or the screen of the first display unit 420 and the second display unit 430, when the mobile vehicle and the person are close to a certain distance or less. It can stop the operation of a mobile vehicle. The emergency stop unit is connected to the electric circuit of the mobile vehicle and supplies current in an emergency situation, allowing the mobile vehicle to stop. The administrator can set the proximity distance, for example, set the mobile vehicle to stop when the distance between the mobile vehicle and the person is 1 meter. Having an emergency stop unit has the advantage of preventing a collision situation between people and a mobile vehicle.

Figure 7 shows a conceptual diagram of performing a warning broadcast based on the direction of a person for a mobile vehicle according to an embodiment of the present invention. The person detection unit 342 of the artificial intelligence analysis unit 340 includes a direction detection unit that analyzes image data and detects the direction in which the person is heading with respect to the mobile vehicle, and the second alarm unit 450 includes a mobile vehicle detected by the direction detection unit. It is provided with a direction response unit that sends out a warning broadcast corresponding to the direction in which the person is heading with respect to the vehicle. Here, the warning broadcast indicates the warning direction for the mobile vehicle according to the direction in which the person is located: there is a vehicle on the front right, there is a vehicle on the front left, there is a vehicle on the rear right, and there is a vehicle on the rear left. Broadcast a warning. For example, when there is a person on the front left side of the mobile vehicle, the second alarm for the front left broadcasts, and also when the person is facing the same direction (i) as the front of the mobile vehicle (①), “Rear A warning broadcast saying "There is a vehicle on the right" is made, and when a person is looking in the same direction (ii) as the right side of the mobile vehicle (②), a warning broadcast saying "There is a vehicle on the right ahead" is broadcast, and the person is looking in the same direction (ii) to the right of the mobile vehicle. When a person is facing the same direction as the left side (iii) of the mobile vehicle (③), a warning message is broadcast saying “there is a vehicle on the rear left”, and when a person is looking in the same direction (iv) as the rear of the mobile vehicle, a warning message is broadcast (③). At (④), a warning broadcast saying "There is a vehicle on the left ahead" is broadcast, and artificial intelligence analyzes and informs the location of the mobile vehicle according to the person's direction, allowing people to evacuate effectively.

Hereinafter, an object recognition method using a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention will be described with reference to the drawings. Figure 8 is a flow chart of an object recognition method using a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention. Referring to FIG. 8, an object recognition method using a wireless artificial intelligence object recognition remote monitoring system according to an embodiment of the present invention may be configured to include the following four steps.

First step (S10): Installing the wireless ultrasonic module 100, wireless camera module 200, and mobile vehicle module 400 in a mobile vehicle.

Second step (S20): A person is detected by the wireless ultrasonic module 100, detection signal data is generated and transmitted to the server module 300, and image data captured by the wireless camera module 200 is transmitted to the server module ( Step 300)

Third step (S30): A step in which detection signal data and image data are processed by the server module 300 and transmitted to the mobile vehicle module 400.

Fourth step (S40): A warning sound sounds in the mobile vehicle, the location of the wireless ultrasonic module 100 is displayed on the first display unit 420, and the person recognized by artificial intelligence is displayed on the second display unit 430. Steps displayed in color

The first step (S10) is a step of installing the wireless ultrasonic module 100, the wireless camera module 200, and the mobile vehicle module 400 in a mobile vehicle. A plurality of wireless ultrasonic modules 100 and wireless camera modules 200 are installed at the front and rear of the mobile vehicle. The mobile vehicle module 400 is installed inside the cockpit, and the server module 300 is installed in a safe location away from the mobile vehicle.

In the second step (S20), a person is detected by the wireless ultrasonic module 100, detection signal data is generated and transmitted to the server module 300, and image data captured by the wireless camera module 200 is sent to the server module 300. ). The wireless ultrasonic module 100 detects a person approaching the mobile vehicle. When a person is detected by the ultrasonic sensor, detection signal data is generated by the ultrasonic data generator 120 and sent to the server. It is transmitted through wireless communication to the module 300. In addition, the wireless camera module 200 captures people approaching the vicinity of the mobile vehicle in real time, and the wireless camera module 200 transmits the captured image data to the server module 300. ) is transmitted by wireless communication.

The third step (S30) is a step in which the detection signal data and image data are processed by the server module 300 and transmitted to the mobile vehicle module 400. The server module 300, which has received the detection signal data transmitted from the wireless ultrasonic module 100, identifies the wireless ultrasonic module 100 that transmitted the detection signal data by the ultrasonic data processing unit 320 and generates a warning sound control signal. and transmits it to the mobile vehicle module 400 through wireless communication. Additionally, the data determination unit 330 allows image data to be analyzed by artificial intelligence only when the received detection signal data and image data match. The artificial intelligence analysis unit 340 analyzes the image data transmitted from the data determination unit 330, recognizes the person, generates a color control signal so that the detected person is displayed in a specific color, and transmits it to the mobile vehicle through wireless communication.

In the fourth step (S40), a warning sound sounds in the mobile vehicle, the location of the wireless ultrasonic module 100 is displayed on the first display unit 420, and the person recognized by artificial intelligence is specified on the second display unit 430. This is the stage where it is displayed in color. The mobile vehicle receives the warning sound control signal transmitted from the ultrasonic data processing unit 320 and sounds a warning sound through the first alarm unit 440 located inside the mobile vehicle and the second alarm unit 450 located outside the mobile vehicle. Additionally, the identification signal of the wireless ultrasound module 100 transmitted from the ultrasound data processing unit 320 is received and the location of the wireless ultrasound module 100 that has recognized the person is displayed on the first display unit 420. In addition, the mobile vehicle module 400 receives image data analyzed by the artificial intelligence analysis unit 340 and to which a color control signal is added, and displays the recognized person in a specific color on the second display unit 430.

The present invention is not limited to the above-mentioned embodiments, but can be manufactured in various different forms, and those skilled in the art may manufacture the present invention in other specific forms without changing the technical idea or essential features of the present invention. You will understand that it can be done. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

100: wireless ultrasonic module
110: ultrasonic sensor unit
120: Ultrasound data generation unit
130: Ultrasonic communication department
200 ; wireless camera module
300: server module
310: Server communication department
320: Ultrasonic data processing unit
330: data judgment unit
340: Artificial intelligence analysis department
341: Artificial Intelligence Learning Department
342: person detection unit
343: Color control signal generator
350: Server display unit
400: Mobile vehicle module
410: Mobile vehicle communication unit
420: first display unit
430: second display unit
440: 1st warning unit
450: 2nd alarm unit
500: Mobile vehicle
600: people

Claims (7)

A plurality of wireless ultrasonic modules installed on the front and rear of the mobile vehicle to detect people in real time using an ultrasonic sensor and transmit detection signal data through wireless communication;
A plurality of wireless camera modules installed on the front and rear of the mobile vehicle to capture images in real time and transmit the captured image data through wireless communication;
A server module that receives, processes, and transmits the detection signal data transmitted from the wireless ultrasonic module, receives the image data transmitted from the wireless camera module, analyzes the image data by artificial intelligence, detects a person, and transmits it. ; and
A mobile vehicle module installed inside the mobile vehicle to receive and display the detection signal data processed by the server module and the image data analyzed by the server module,
The wireless ultrasonic module,
An ultrasonic sensor unit that sends ultrasonic waves to detect people adjacent to the mobile vehicle,
An ultrasonic data generator that generates detection signal data when a person is detected by the ultrasonic sensor unit, and
It includes an ultrasonic communication unit that transmits the detection signal data generated by the ultrasonic data generation unit to the server module through wireless communication,
The server module is,
A server communication unit that receives image data transmitted from the wireless camera module and detection signal data transmitted from the wireless ultrasonic module, and transmits the processed detection signal data and analyzed image data to the mobile vehicle module;
An ultrasonic data processing unit that processes detection signal data received from the server communication unit, identifies the wireless ultrasonic module that transmitted the detection signal data, and generates a warning sound control signal;
a data determination unit that performs processing only when the detection signal data and image data received from the server communication unit match;
An artificial intelligence analysis unit that detects people by analyzing the image data transmitted from the data determination unit using artificial intelligence, and
A wireless artificial intelligence object recognition remote monitoring system including a server display unit on which an image of a person detected in the artificial intelligence analysis unit is displayed. delete delete In claim 1,
The artificial intelligence analysis unit,
An artificial intelligence learning department that learns data so that artificial intelligence can recognize people,
A person detection unit that detects a person by artificial intelligence from the image data transmitted from the data determination unit based on the content learned in the artificial intelligence learning unit, and
A wireless artificial intelligence object including a color control signal generator that generates a color control signal for the mobile vehicle module to display the person in a specific color on the mobile vehicle module when the person detection unit detects a person in the image data. Cognitive remote monitoring system. delete delete delete