KR102096175B1 - Ceiling rail type IoT based surveillance robot device - Google Patents

Abstract

The present invention relates to a ceiling rail-type IoT-based surveillance robot, and more specifically, a real-time facility through IoT technology and image analysis using a robot moving along a rail installed on the ceiling in a restricted or narrow environment of manpower. It is about the infrastructure configuration and operational technology that can be monitored.
To this end, the present invention is provided with a sensor node attached to each section of the facility, a ceiling rail on the ceiling of the facility and a mobile robot device moving accordingly, and a camera for photographing a real image, a thermal image, and an infrared image installed on the mobile robot device. Includes an acquisition unit that acquires information, a communication unit that transmits information from the acquisition unit, an analysis unit that analyzes the transmitted information, a processing unit that displays a result value according to the analysis result, controls the mobile robot apparatus, and sends an alarm alarm. Is done by
According to the present invention, intelligent real-time analysis to analyze the location and pattern of objects and accurately recognize objects according to predefined rules by digitizing the image information of various sensors and surveillance cameras. It can perform actions such as alert notifications to replace / replenish vulnerabilities caused by human management.

Description

Ceiling rail type IoT based surveillance robot device {Ceiling rail type IoT based surveillance robot device}

The present invention relates to a ceiling rail-type IoT-based surveillance robot, and more specifically, a real-time facility through IoT technology and image analysis using a robot moving along a rail installed on the ceiling in a restricted or narrow environment of manpower. It is about the infrastructure configuration and operational technology that can be monitored.

The Internet of Things can be viewed as a network infrastructure in which people, things, and space are all connected to each other through the Internet to interact and exchange data and information. The IoT is divided into three major categories: device (terminal sensor) area, network (wired wireless) area, and service interface (platform application) area. The device area transmits data collected and extracted from a specific object to another object by using a communication function embedded in the object. The network area is a wired / wireless path that transmits and receives data transmitted between users and objects and objects. The service interface area processes data to generate information, and controls and manages various devices.

  Intelligent video analysis technology is a technology that automatically analyzes video information to detect anomalies, objects, and sends alerts to managers. It can prevent accidents in advance and respond to them quickly to reduce damage. Since an alert is generated and notified to a monitor when a predefined event occurs through video analysis, all videos are not monitored 24 hours a day, 365 days a week. You can do it. Therefore, using intelligent video analysis technology, one person can monitor multiple CCTVs, and prevents accidents in advance and, if an accident occurs, recognizes and responds quickly to reduce damage.

Republic of Korea Patent Application No. 10-2011-0065365

The object of the present invention is to provide a method for establishing a facility management system by real-time temperature checking, real-time diagnosis, automatic detection and advance failure prediction, and anomaly diagnosis database in conjunction with ceiling rail-type moving object, IoT, and image analysis technology.

The present invention comprises the steps of measuring temperature, humidity, vibration, and acoustic data values at a sensor node attached to each section of a facility; And manipulating the movement of the moving object moving along the rail installed on the ceiling. And photographing an image on a camera mounted on the moving object. And collecting sensor node and image information. And analyzing the collected information; And it characterized in that it consists of a step of managing the facility by the analyzed information.

  According to an embodiment of the present invention, the monitoring robot device may be configured based on the Light Weight Machine to Machine (LWM2M) standard, which is an international standard for lightweight IoT. LWM2M utilizes CoAP's RESTful interface and defines Bootstrap, Registration, Object / Resource Access, and Reporting interfaces in detail. With LWM2M, functions such as device setting, software and firmware management, remote control, diagnosis and monitoring can be performed.

  According to one aspect, the surveillance robot device may include a short-range communication module such as Wi-Fi, LTE, LTE-M, NB-IoT, Zigbee, BLE.

  According to another aspect, an image of a real image, a thermal image, and an infrared camera is transformed into a transformed image through a filter by a convolution neural network, which is one of the machine learning techniques (Convolution), and filtered. By repeating the process of multiplying the data of images with low resolution by reducing the resolution of the image (Max Pooling) according to a certain rule, it is possible to obtain a characteristic that can represent the entire image, and comparing the images to normal and abnormal states Can be classified for.

According to the present invention, an intelligent real-time analysis operation that analyzes the location and pattern of a facility and accurately recognizes an object according to a predefined rule by digitizing the image information of various sensors and surveillance cameras is performed. Actions such as alert notifications can be replaced / supplemented by vulnerabilities caused by human management. It can be applied to major social infrastructure facilities such as electric power, gas, and water, factories, security facilities, and houses.

  Although the present invention has been described with reference to the accompanying drawings and preferred embodiments, it is apparent to those skilled in the art that many various obvious modifications are possible without departing from the scope of the present invention. Therefore, it should be interpreted by the claims described to include many of these variations.

1 is a flow diagram schematically showing the flow of operation according to the configuration of the present invention in one embodiment of the present invention.
2 is a schematic diagram schematically showing a mobile robot apparatus according to the present invention in one embodiment of the present invention.
3 is a schematic operation flow chart of the present invention in one embodiment of the present invention.
4 is a schematic diagram schematically showing that the analysis unit of the present invention analyzes an object in an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains can easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

  Throughout the specification, when a part is “connected” to another part, this includes not only “directly connected” but also “electrically connected” with another element in between. In addition, when a part is said to “include” a certain component, it means that the component may further include other components, not to exclude other components, unless specifically stated to the contrary. The terms “.. part” and “module” described refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.

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

  1 is a block diagram of a ceiling-rail IoT-based surveillance robot device according to an embodiment of the present invention. The surveillance robot device may be configured to include a sensor 100, a camera 200, a mobile robot device 300, a gateway 400, an artificial intelligence server 500, an IoT platform 600, and a control system 700. You can.

  According to an embodiment of the present invention, the IoT platform is operated by the Light Weight Machine to Machine (LWM2M) standard, which is a lightweight international standard.

  2 is a flowchart of a monitoring robot device according to an embodiment of the present invention.

  Referring to FIG. 2, the monitoring robot apparatus includes an acquiring unit 1000 that acquires data values of environmental information, image information of a camera, and operation information of a mobile robot from a sensor node; And a communication unit 2000 in charge of communication between the sensing device and the server. And an analysis unit 3000 for analyzing environmental information, image information, and moving object operation information. And a processing unit 4000 that instructs information display and control based on the analyzed result.

  The acquisition unit 1000 receives temperature, humidity, vibration, and acoustic (S110) sensor information and real image, thermal, infrared (S210) image information, and mobile robot position (S370) information from the camera mounted on the mobile robot. To acquire.

  The communication unit 2000 may include a gateway 400, and the gateway 400 may include Wi-Fi, LTE, LTE-M, NB-IoT, Zigbee, and BLE communication modules.

  The analysis unit 3000 may be composed of an artificial intelligence server 500 and an Internet of Things platform 600, and the artificial intelligence server 500 provides a three-dimensional arrangement of each real image, thermal image, and infrared (S210) camera image. It is analyzed by object recognition by a convolutional neural network (CNN) that has two (normal, abnormal) outputs using (Width × Height × Color (Depth)) as a pixel image. In order to identify damage, overheating, fire, etc., among the images, a partial region of the input image and an object region matching the case image of the detection target are detected based on the feature amount of the similar image search to determine whether a problem has occurred.

  The IoT platform 600 analyzes temperature, humidity, vibration, and acoustic (S110) sensor information and the location of the mobile robot (S370). A threshold value is set for each sensor value, and a problem occurs when the threshold value is exceeded. The real-time position of the robot estimates the current position using the position recognition device provided in the mobile robot device, and the position recognition device uses the number of revolutions of the wheel and the inertial sensor to guess, and uses communication such as GPS, Wi-Fi and Bluetooth. It analyzes the image of the communication positioning method and the camera, and combines the image analysis positioning method, etc. to locate the exact location.

  The processing unit 4000 displays an analysis result from the analysis unit 3000 and gives a command to perform regular monitoring. When an abnormality is detected, an alarm can be generated on the control screen to inform the monitor of the abnormality. Normally, the mobile robot is automatically controlled by a certain cycle, but it can be changed to remote driving by selecting a monitor and moved to a desired position.

 Specifically, when the mobile robot device reciprocates the section where the rail is installed and maintains a constant monitoring state, when the analytical unit detects an abnormal condition, heat, etc., it moves to the point of occurrence of the problem by the command of the processing unit to observe it in more detail. can do.

In particular, the movement of the mobile robot can be freely moved for each section using a plurality of movement path divergence points in the section, and in driving, manual driving by a monitor or autonomous driving by the analysis unit may be selectively performed.

Moreover, autonomous driving is performed by analyzing the measurement information of the sensor node, image information of the camera, and location information of the mobile robot device and selecting an organic autonomous driving mode by the analysis unit. Specifically, the autonomous driving mode is the shortest movement mode that recognizes an occurrence of an abnormality and moves to the abnormally occurring facility in the shortest time, a risk avoidance mode that reduces or limits movement to the section of the facility where the abnormality occurs to prevent damage to the mobile robot device, By analyzing the frequency of anomalies, it is possible to configure the efficiency movement mode to set and prioritize facility monitoring. In particular, the AI server can be equipped with an AI learning system to collect information on facilities in the monitoring section, analyze it, and learn for itself to gradually improve the efficiency of autonomous driving.

Furthermore, when a plurality of mobile robot devices are provided, the analysis unit generally monitors facilities by zone allocation, and when an abnormality occurs, configures a centralized monitoring mode using a plurality of mobile robot devices. In the high zone, the movement paths of a plurality of mobile robot devices are overlapped, and thus, an important monitoring mode can be configured to increase the efficiency of facility monitoring.

In addition, in the case of a camera, a plurality of lenses are provided to take a facility in an omni-directional direction and construct a 360-degree camera to create an omnidirectional image.

Moreover, the mobile robot device is equipped with a movement sensor that measures the state of the facility in proximity to the facility on one side, and the movement sensor is a sensor that measures more precise sensors or information that the sensor node does not measure than the measurement sensor on the sensor node. It may include a sensor that is not provided in the node.

In addition, the mobile robot device may include a situation response device that responds first and foremost to emergencies, such as theft, intrusion, fire, and damage to facilities on one side. Specifically, it may include a warning device or lighting device to cope with theft or intrusion, a fire extinguishing device or a cooling device to cope with a fire or overheating problem.

  As described above, the sensor information 110, the image information 210, and the robot position information 370 acquired by the acquisition unit 1000 are sent to the gateway 400 of the communication unit 2000, and the gateway 400 transmits the information. It is collected and transferred to the analysis unit 3000. The analysis unit 3000 determines whether the image is normal or abnormal by using the artificial neural network (CNN) of the virtual image, the thermal image, and the infrared 210 image information by the artificial intelligence server 500, and the IoT platform 600 Analyzes temperature, humidity, vibration, and acoustic (S110) sensor information, and if any one of the artificial intelligence server 500 or the IoT platform 600 is monitored, an alarm is immediately alerted to the control system 700 of the processing unit 4000 ( S610) Send a signal. Alarm The control system 700 that has received the alarm (S610) floats an alarm on the screen to inform the watcher and sends a command to send the monitoring robot to the problem area.

  As described above, according to the embodiments of the present invention, the ceiling-rail IoT-based surveillance robot device provides real-time diagnosis, automatic detection and advance failure prediction, database for diagnosis of anomalies, and real-time temperature check in environments where access is limited or narrow. As a result, it provides a method for establishing a facility management system capable of promptly responding to damages, fires, and abnormalities of facilities.

  Although the embodiments have been mainly described above, these are merely examples and do not limit the present invention, and those skilled in the art to which the present invention pertains are not exemplified above, without departing from the essential characteristics of the embodiments. It will be appreciated that various modifications and applications are possible. For example, each component specifically shown in the embodiment may be modified. And differences related to these modifications and applications should be construed as being included in the scope of the invention defined in the appended claims.

100: sensor 200: camera 300: mobile robot device
400: Gateway 500: Artificial Intelligence 600: Internet of Things Platform
700: control system
310: communication antenna 320: control board 330: motor
340: real image, thermal image, infrared camera 350: wireless charging module
360: wireless charging pad
S110: Temperature, humidity, vibration, sound S210: Real image, thermal image, infrared
S370: Robot position S610: Information alarm
S710: robot movement command
1000: acquisition unit 2000: communication unit` 3000: analysis unit
4000: processing unit

Claims (4)

In the ceiling-rail IoT-based surveillance robot device;
Sensor nodes that measure temperature, humidity, vibration, and sound attached to each section of a facility, ceiling rails that serve as a path for monitoring robots on the ceiling of facilities, mobile robot devices that move along the ceiling rails, and installed on the mobile robot devices A real image, a thermal image, and an infrared image;
Acquisition unit for acquiring measurement values of the sensor node, photographed images of the camera, and movement position information of the mobile robot device, a communication unit for transmitting the information of the acquisition unit to the analysis unit, and an analysis unit for analyzing the situation of the facility based on the transmitted information , Displaying a result value according to the analysis result of the analysis unit, controlling the mobile robot device, and providing a processing unit that sends an alarm alarm to the monitor when an abnormality is detected;
The analysis unit is composed of an artificial intelligence server and an IOT platform, and the artificial intelligence server analyzes an image of a camera's real image, thermal image, and infrared image by object recognition by a convolutional neural network having an output of a three-dimensional array. The IoT platform is configured to analyze temperature, humidity, vibration, and acoustic sensor information of the sensor node and location information of the mobile robot in real time;
The ceiling rail has a plurality of movement path branch points in the section so as to increase the degree of freedom of movement of the branch point by section of the mobile robot device;
The mobile robot device is configured such that remote driving by a monitor or autonomous driving by the analysis unit is selectively performed using the branch point;
The autonomous driving is configured to select an autonomous driving mode by analyzing measurement information of a sensor node, image information of a camera, and location information of a mobile robot device;
The autonomous driving mode is a shortest movement mode that recognizes an occurrence of an abnormality and moves in the shortest time to an abnormality occurrence facility, a risk avoidance mode that limits or limits movement to a section of the facility where an abnormality occurs to prevent damage to the mobile robot device. A ceiling-rail IoT-based surveillance robot device characterized by having an efficiency transfer mode that analyzes the frequency of occurrence and prioritizes facility monitoring.
The method of claim 1;
Measuring data values for temperature, humidity, vibration, and sound at a sensor node attached to each section of the facility; And manipulating the movement of the movable body installed on the ceiling. And photographing an image on a camera mounted on the moving object. And collecting sensor node data and image information. And analyzing the collected information; And a step of managing facilities according to the analyzed information.
According to claim 1,
The camera is equipped with a plurality of lenses and equipped with a 360-degree camera to make an omnidirectional image by photographing facilities in all directions;
The mobile robot apparatus is provided with a movement sensor that measures the state of the facility in close proximity to the facility on one side;
The mobile sensor is a ceiling rail-type IoT-based surveillance robot device, characterized in that it has a sensor that is not provided in the sensor node to measure more precise sensors or information that the sensor node does not measure than the measurement sensor in the sensor node.
According to claim 1;
The mobile robot device is a ceiling rail type IoT-based surveillance robot device, characterized in that it has a situation response device that responds quickly and quickly to an emergency when an emergency occurs in a facility.

Images