CN114821960A - Active safety protection system for building site personnel based on narrowband Internet of things technology - Google Patents

Active safety protection system for building site personnel based on narrowband Internet of things technology Download PDF

Info

Publication number
CN114821960A
CN114821960A CN202210732596.9A CN202210732596A CN114821960A CN 114821960 A CN114821960 A CN 114821960A CN 202210732596 A CN202210732596 A CN 202210732596A CN 114821960 A CN114821960 A CN 114821960A
Authority
CN
China
Prior art keywords
personnel
information
identification
image
safety protection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210732596.9A
Other languages
Chinese (zh)
Other versions
CN114821960B (en
Inventor
姚盛清
肖智中
张艳芳
金树楼
孙梓尧
项龙康
倪娇娇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Construction Industrial and Energy Engineering Group Co Ltd
Original Assignee
China Construction Industrial and Energy Engineering Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Construction Industrial and Energy Engineering Group Co Ltd filed Critical China Construction Industrial and Energy Engineering Group Co Ltd
Priority to CN202210732596.9A priority Critical patent/CN114821960B/en
Publication of CN114821960A publication Critical patent/CN114821960A/en
Application granted granted Critical
Publication of CN114821960B publication Critical patent/CN114821960B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/44—Event detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines

Abstract

The invention provides a construction site personnel active safety protection system based on a narrow-band Internet of things technology, which is used for identifying unsafe states (such as no safety helmet, no protection equipment and the like), unsafe behaviors (such as a condition that a worker approaches the edge of a deep foundation pit with a high falling risk and a dangerous area that the worker is in the work of a large tower crane) and dangerous conditions of a construction site (such as a condition that a fire disaster occurs in the construction site and the like) of construction personnel through analyzing a construction site field monitoring video picture, realizing accurate screening of corresponding personnel in the states through a multi-technology fusion means, and actively alarming and reminding through a narrow-band Internet of things technology and an autonomously developed intelligent wearable device penetrating through the corresponding construction personnel. The invention utilizes the machine vision technology, the narrow-band Internet of things technology and the RFID technology, provides active all-dimensional supervision and safety protection for constructors on construction sites, and effectively ensures the construction safety.

Description

Active safety protection system for building site personnel based on narrowband Internet of things technology
Technical Field
The invention belongs to the technical field of building construction safety protection, and particularly relates to a construction site personnel active safety protection system based on a narrow-band Internet of things technology.
Background
The intelligent building is a product of the information era, is an integration of high-tech and modern buildings, and is an important development direction of modern buildings in future. The building site environment is complicated, special, often has various potential safety hazards, and intelligent safety protection system is paid attention to the society because it relates to building construction safety problem, has more and more important status. At present, an intelligent all-dimensional safety protection system for construction site personnel is rare, traditional construction site personnel safety protection measures are mostly for installing a camera, wearing a safety helmet, face recognition access control and the like, supervision on construction personnel is not comprehensive enough, whether the construction personnel are in a dangerous area or not and unsafe behaviors exist or not can not be automatically recognized, and active alarm reminding can not be carried out. Therefore, the invention provides a construction site personnel active safety protection system based on the narrow-band Internet of things technology, which realizes omnibearing active safety protection supervision on constructors and ensures construction safety.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a construction site personnel active safety protection system based on a narrow-band Internet of things technology, which can efficiently and accurately identify whether a constructor is in an unsafe state, whether unsafe behaviors exist, whether the constructor is in a dangerous area and whether dangerous conditions exist in a construction site, realize the accurate screening of corresponding personnel in the states by a multi-technology fusion means, and actively alarm and remind by a narrow-band Internet of things technology and independently developed intelligent wearable equipment penetrating through the corresponding constructor, so that the construction safety is ensured.
The present invention achieves the above-described object by the following technical means.
A construction site personnel active safety protection system based on a narrow-band Internet of things technology comprises a cloud platform, a visual sensing device, other sensing devices and Internet of things devices, wherein the other sensing devices comprise an infrared sensing device for monitoring infrared data of constructors, a structured light depth sensor for acquiring posture information of the constructors and an active RFID device for monitoring positions of the constructors, and the Internet of things devices comprise a narrow-band Internet of things sending device, a narrow-band Internet of things receiving device and an intelligent wearable device which are sequentially in signal connection; the visual sensing equipment, other sensing equipment and the Internet of things equipment are in signal connection with the cloud platform, and the cloud platform is used for achieving the functions of providing site real-time monitoring pictures and background alarming.
Further, the active safety protection system for the staff on the construction site comprises five functions: personnel information identification, dangerous scene identification, personnel unsafe behavior identification, personnel unsafe state identification and personnel wearing equipment alarm.
Further, the personnel information identification process is as follows:
the cloud platform extracts a frame of image in data transmitted by the visual sensing equipment, identifies all people in the frame of image, compares the identified people with a first person characteristic behavior database, identifies the name of a person, and records the position, the frame time and the name information of the person after successful identification; if the identification is unsuccessful, extracting a timestamp of the frame of image, extracting the RFID information, the depth sensing information and the infrared sensing information of the monitored area under the timestamp, comparing the extracted information with the data in the second character characteristic behavior database, and identifying the name of the constructor again;
discarding the frame of image after the secondary identification is unsuccessful, firstly recording the position, the image frame time and the name information of the person after the secondary identification is successful, then extracting all the characteristic data corresponding to the person in the timestamp, dividing the characteristic data into image data and other data, putting the image data into a first person characteristic behavior database, and putting the other data into a second person characteristic behavior database for the next identification;
the first person characteristic behavior database comprises face information, gait characteristic information and behavior characteristic information of each person in the construction site, and the second person characteristic behavior database comprises RFID information, depth sensing information and infrared sensing information of each person in the construction site.
Further, in the personnel information identification process, when identification is carried out based on a first personnel characteristic behavior database, when the coincidence rate of the human face identification reaches 90%, the human face identification is successful, otherwise, gait identification is carried out based on a fusion image and the personnel gait database, when the coincidence rate of the gait identification reaches 60%, the gait identification is finished, secondary confirmation is carried out by combining with RFID information, otherwise, the behavior characteristic identification is carried out based on the first personnel behavior database, when the coincidence rate of the behavior characteristic identification reaches 40%, the behavior characteristic identification is finished, the secondary confirmation is carried out by combining with the RFID information, and otherwise, a frame image for identification is discarded;
the fusion map used in gait recognition is obtained by the following method: extracting frame images in video data acquired by visual sensing equipment, comparing figure outline features, and then extracting figure outline information; extracting monitoring data of infrared sensing equipment, comparing human body temperature infrared characteristics, and then extracting personnel infrared information; extracting monitoring data of the structured light depth sensor, performing three-dimensional processing on figure outline information, and extracting figure skeleton joint information; and finally, fusing the layers corresponding to the extracted three kinds of information to obtain a fused graph.
Further, the dangerous scene identification process is as follows:
the cloud platform extracts a frame of image in data transmitted by the visual sensing equipment, identifies whether a fire disaster occurs, and discards the frame of image if the fire disaster does not occur; after a fire disaster is identified, extracting the timestamp of the frame of image, calling monitoring data of the infrared sensing equipment at the same time and the same position, and performing secondary identification on the fire disaster; after a fire disaster is identified secondarily, whether personnel move within a range of 10m around the fire source is judged, if no personnel move is judged, the cloud platform directly gives an alarm, if personnel move is judged, personnel name information is recorded, and meanwhile, the cloud platform gives an alarm;
and after no fire occurs in the secondary identification, recording the coordinates of the fire source, judging whether the coordinates are recorded before, discarding the frame of image and the coordinate information simultaneously if the coordinates are recorded before, extracting the infrared sensing information and the image information of other timestamps at the positions in 1S before and after the frame of image and the coordinate information if the coordinates are not recorded before, and identifying the fire again.
Further, the process of identifying unsafe behaviors of people is as follows:
the cloud platform extracts the name and the position information of the personnel, compares the position information of the personnel with the coordinate data in the database of the dangerous area, judges whether the personnel move in the dangerous area, discards the frame of image if judging that no personnel move, records the name information of the personnel if judging that the personnel move, and simultaneously alarms at the cloud platform end; the dangerous area database comprises the coordinate set information of the dangerous area which is defined in advance.
Further, the process for identifying the unsafe condition of the people comprises the following steps:
the cloud platform extracts the name information of the personnel, simultaneously extracts a frame of image in the data transmitted by the visual sensing equipment, compares the frame of image with a safety protection article database, identifies whether all the protection articles of the personnel in the image are normally worn, discards the frame of image data if the protection articles are normally worn, records the name information of the personnel if the protection articles are not normally worn, and simultaneously alarms at the cloud platform end; the safety protection article database comprises a safety protection article image template.
Further, the personnel wearing equipment alarm process is as follows: the cloud platform extracts unique identification information of wearable equipment of corresponding personnel according to personnel name information recorded in personnel information identification, dangerous scene identification, personnel unsafe behavior identification and personnel unsafe state identification processes, then based on narrow-band Internet of things sending equipment, the wearable equipment corresponding to the corresponding identification information is awakened through the narrow-band Internet of things, and after awakening, the wearable equipment is used for alarming and reminding the famous personnel by using a loudspeaker of the wearable equipment.
Furthermore, the narrow-band internet of things sending device is an LORA transmitter located at a system end, the narrow-band internet of things receiving device is an LORA receiver installed on the intelligent wearable device, an RFID receiver in the RFID device is also installed on the intelligent wearable device, the RFID transmitter is located at the system end, and the system end is in signal connection with the cloud platform, transmits data and receives instructions; the intelligent wearing equipment is a safety helmet which is transformed through intelligent design, a loudspeaker and a power supply are further installed in the safety helmet, and the power supply consists of a miniature solar panel and a battery.
Furthermore, when the active safety protection system for the construction personnel is used for positioning and identifying the construction personnel, firstly, an LORA transmitter is used for sending starting information to LORA receivers on all intelligent wearable devices in the current device coverage range through a narrow-band Internet of things, after receiving the information, the LORA receivers inform a power supply to supply power to active RFID receivers at the intelligent wearable device ends, and after the RFID receivers are electrified, the communication is established with the RFID transmitter at the system end, so that the personnel positioning is realized; after positioning is completed, the LORA transmitter sends closing information to LORA receivers on all intelligent wearable devices in the coverage area of the current device, after the LORA receivers receive the information, the LORA receivers inform a power supply in the intelligent wearable devices to stop supplying power to the active RFID receivers, and then the active RFID receivers are in a dormant state again;
when the active safety protection system of the building site personnel gives an alarm to a person side, the LORA transmitter of the system side sends information to the LORA receiver of a certain specified intelligent wearable device in a point-to-point mode, and the LORA receiver receives the information and then opens a loudspeaker of the intelligent wearable device side to give an alarm.
The invention has the following beneficial effects:
the invention provides a construction site personnel safety active protection system based on a machine vision technology, a narrow-band Internet of things technology and an RFID technology, which provides active all-dimensional supervision and safety protection for constructors in a construction site and effectively guarantees construction safety. According to the invention, the unsafe state of constructors (such as no safety helmet, no protective equipment and the like), unsafe behaviors (such as the condition that workers are close to the edge of a deep foundation pit with a high falling risk and the dangerous area of the workers working in a large tower crane) and dangerous conditions of a construction site (such as fire disaster on the construction site) can be identified through analyzing the site monitoring video picture, accurate screening of corresponding personnel in the states is realized through a multi-technology fusion means, and active alarm reminding is carried out through a narrow-band Internet of things technology and independently developed intelligent wearable equipment penetrating through corresponding constructors.
Drawings
FIG. 1 is a schematic diagram of a process for identifying information of persons according to the present invention;
FIG. 2 is a schematic diagram of a dangerous scene recognition process according to the present invention;
FIG. 3 is a schematic diagram illustrating an unsafe behavior identification process according to the present invention;
FIG. 4 is a schematic diagram illustrating an unsafe condition identification process of a person according to the present invention;
FIG. 5 is a schematic diagram of an alarm process for a personal wearable device of the present invention;
FIG. 6 is a schematic diagram of the operation of the intelligent wearable device according to the invention;
FIG. 7 is a schematic diagram of the identification process of the triple-recognition mechanism according to the present invention;
FIG. 8 is a schematic view of a fused image according to the present invention.
Detailed Description
The invention will be further described with reference to the following figures and specific examples, but the scope of the invention is not limited thereto.
The active safety protection system for the building site personnel based on the narrow-band Internet of things technology comprises a cloud platform, a visual sensing device, other sensing devices and Internet of things devices, wherein the Internet of things devices comprise narrow-band Internet of things sending devices, narrow-band Internet of things receiving devices and intelligent wearable devices which are in signal connection in sequence. The cloud platform is used for realizing the functions of providing site real-time monitoring pictures and background alarming, and the visual sensing equipment, other sensing equipment and the Internet of things equipment are in signal connection with the cloud platform.
The visual sensing equipment is used for carrying out real-time video monitoring on the construction site condition and transmitting the monitored video data to the cloud platform; the other sensing devices comprise infrared sensing devices used for monitoring infrared data of constructors, structured light depth sensors used for collecting posture information of the constructors and active RFID devices used for monitoring positions of the constructors, and data detected by the other sensing devices are synchronously uploaded to the cloud platform. The vision sensing equipment is in a continuous operation state, other sensing equipment is in a low-power consumption operation state, and the vision sensing equipment is awakened only when the vision sensing equipment is needed to be used, so that the low-power consumption operation of the whole set of active safety protection system is facilitated, and the energy is saved.
The active safety protection system comprises five functions: personnel information identification, dangerous scene identification, personnel unsafe behavior identification, personnel unsafe state identification and personnel wearing equipment alarm.
When personnel information identification is carried out:
as shown in fig. 1, the cloud platform extracts one frame of image in the data transmitted by the visual sensing device, identifies all people in the frame of image, compares the identified people with data in a first person characteristic behavior database (the first person characteristic behavior database contains face information, gait characteristic information and behavior characteristic information of each person on the construction site), identifies the name of a specific constructor, and records the position, the image frame time and the name information (namely name information) of the constructor after successful identification;
if the identification is unsuccessful, extracting a timestamp of the frame of image, extracting the RFID information, the depth sensing information and the infrared sensing information of the monitored area under the timestamp, then comparing the extracted information with data in a second person characteristic behavior database (the second person characteristic behavior database contains the RFID information, the depth sensing information and the infrared sensing information of each person in the construction site), and identifying the name of the constructor again;
discarding the frame image after the second recognition is unsuccessful, firstly recording the position, the frame time and the name information of the worker after the second recognition is successful, then extracting all the characteristic data (including the image information corresponding to the worker in the frame image, the information read by the RFID equipment, the information read by the depth sensing equipment and the information detected by the infrared sensing equipment) corresponding to the constructor in the time stamp, dividing the characteristic data into image data and other data, putting the image data into a first person characteristic behavior database, and putting the other data into a second person characteristic behavior database for the next recognition.
When dangerous scene recognition is carried out:
as shown in fig. 2, after extracting a frame of image from data transmitted by the visual sensing device, the cloud platform identifies whether a fire occurs, and discards the frame of image if no fire occurs; after a fire disaster is identified (namely a fire source is identified), extracting the timestamp of the frame of image, calling monitoring data of infrared sensing equipment at the same time and the same position, and carrying out secondary identification on the fire disaster; after a fire disaster occurs in secondary recognition, judging whether personnel move within a range of 10m around the fire source or not by combining the position, the picture frame time and the name information of constructors recorded in the personnel information recognition process, if no personnel move, directly carrying out alarm prompt by the cloud platform, if personnel move, recording the name information of the personnel, and simultaneously giving an alarm by the cloud platform end;
and after no fire occurs in the secondary identification, recording the coordinates of the fire source, judging whether the coordinates are recorded before, discarding the frame of image and the coordinate information simultaneously if the coordinates are recorded before, extracting the infrared sensing information and the image information of other timestamps at the positions in 1S before and after the frame of image and the coordinate information if the coordinates are not recorded before, and identifying the fire again.
When the unsafe behaviors of the personnel are identified:
as shown in fig. 3, the cloud platform extracts the names and the position information of the staff according to the position, the frame time and the name information of the constructors recorded in the process of identifying the staff information, compares the staff position information with coordinate data in a danger area database (the danger area database contains information of a preset danger area coordinate set, for example, X30-60, Y20-40 areas are deep foundation pits, X180-200, and Y420-900 are tower crane working areas, wherein X represents a horizontal coordinate, Y represents a vertical coordinate, and numbers represent coordinate values) to judge whether the staff moves in the danger area, discards the frame image if the staff does not move, records the staff name information if the staff moves, and alarms at the cloud platform end.
When the unsafe state of the personnel is identified:
as shown in fig. 4, the cloud platform extracts the name information of the worker according to the position, the picture frame time and the name information of the constructor recorded in the process of identifying the worker information, and simultaneously extracts a frame of image in the data transmitted by the visual sensing equipment, compares the frame of image with the image data in the safety protection article database (the safety protection article database contains the image template of the safety protection article), identifies whether all the protection articles of the worker in the image are normally worn, discards the frame of image data if the protection articles are normally worn, records the name information of the worker if the protection articles are not normally worn, and gives an alarm at the cloud platform end.
Personnel wearing equipment alarms:
as shown in fig. 5, the cloud platform extracts the unique identification information of the wearable device corresponding to the name information of the person recorded in each identification process, wakes up the wearable device corresponding to the identification information through the narrowband internet of things based on the narrowband internet of things sending device, and alerts the constructor by using the speaker of the wearable device after waking up, thereby realizing active protection of the field constructor.
As shown in fig. 6, the intelligent wearable device is a low-power consumption intelligent wearable device based on a narrow-band internet of things and an RFID technology, the narrow-band internet of things sending device is an LORA transmitter located at a system end, the narrow-band internet of things receiving device is an LORA receiver installed on the intelligent wearable device, an RFID receiver in the RFID device is also installed on the intelligent wearable device, the RFID transmitter is located at the system end, and the system end is in signal connection with a cloud platform to transmit data and receive instructions. In this embodiment, intelligence wearing equipment is the safety helmet through intelligent design transformation, still installs speaker, power in the safety helmet, and the power comprises miniature solar panel and battery.
As shown in fig. 6, in practical application, when positioning and identification are required to be performed on constructors, firstly, the system-side LORA transmitter is used for sending starting information to LORA receivers on all intelligent wearable devices in the current device coverage area through a narrow-band internet of things, after the LORA receivers receive the information, the LORA receivers inform a power supply to supply power to active RFID receivers on the intelligent wearable devices, and after the RFID receivers are powered on, the LORA receivers establish communication with the system-side RFID transmitter, so that personnel positioning is realized. After the positioning is completed, the LORA transmitter of the system end sends closing information to the LORA receivers on all the intelligent wearable devices in the coverage range of the current device, after the LORA receivers receive the information, the LORA receivers inform the power supply in the intelligent wearable devices of stopping supplying power to the active RFID receivers, and then the active RFID receivers are in a dormant state again. When the human body side alarm function needs to be achieved, the LORA transmitter of the system side sends information to the LORA receiver of a certain specified intelligent wearable device in a point-to-point mode, and the LORA receiver receives the information and then turns on a loudspeaker of the intelligent wearable device side to alarm.
In whole operation process, LORA equipment is the state of opening all the time, and active RFID equipment then opens when needing, is in the off-state when not needing, has reduced intelligent wearing equipment's power consumption greatly.
As shown in FIG. 7, in the process of identifying the personnel information, the invention utilizes the multi-layer fusion technology, adds gait identification and behavior feature identification on the basis of face identification to form a triple identification mechanism, and greatly increases the accuracy of personnel identification. When the human face recognition coincidence rate reaches 90%, the recognition is successful, otherwise, the gait recognition is carried out based on the fusion image and the human gait database, when the gait recognition coincidence rate reaches 60%, the recognition is completed, the secondary confirmation is carried out by combining the RFID information, otherwise, the behavior characteristic recognition is carried out based on the human behavior database, when the behavior characteristic recognition coincidence rate reaches 40%, the recognition is completed, the secondary confirmation is carried out by combining the RFID information, and otherwise, the frame image used for recognition is discarded.
As shown in fig. 8, the fusion map used in gait recognition is obtained by the following method: extracting frame images in video data acquired by visual sensing equipment, comparing figure outline features, and then extracting figure outline information; extracting monitoring data of infrared sensing equipment, comparing human body temperature infrared characteristics, and then extracting personnel infrared information; extracting monitoring data of the structured light depth sensor, performing three-dimensional processing on figure outline information, and extracting figure skeleton joint information; and finally, fusing the layers corresponding to the extracted three kinds of information to obtain a fused graph.
The present invention is not limited to the above-described embodiments, and any obvious improvements, substitutions or modifications can be made by those skilled in the art without departing from the spirit of the present invention.

Claims (10)

1. A construction site personnel active safety protection system based on a narrow-band Internet of things technology is characterized by comprising a cloud platform, a visual sensing device, other sensing devices and Internet of things devices, wherein the other sensing devices comprise an infrared sensing device for monitoring infrared data of constructors, a structured light depth sensor for acquiring posture information of the constructors and an active RFID device for monitoring positions of the constructors, and the Internet of things devices comprise a narrow-band Internet of things sending device, a narrow-band Internet of things receiving device and an intelligent wearing device which are in signal connection in sequence; the visual sensing equipment, other sensing equipment and the Internet of things equipment are in signal connection with the cloud platform, and the cloud platform is used for providing a site real-time monitoring picture and a background alarm function.
2. The active safety protection system for the building site personnel based on the narrow-band internet of things technology as claimed in claim 1, characterized in that the active safety protection system for the building site personnel comprises five functions: personnel information identification, dangerous scene identification, personnel unsafe behavior identification, personnel unsafe state identification and personnel wearing equipment alarm.
3. The active safety protection system for the workers on the construction site based on the narrowband internet of things technology of claim 2, wherein the personnel information identification process is as follows:
the cloud platform extracts a frame of image in data transmitted by the visual sensing equipment, identifies all people in the frame of image, compares the identified people with a first person characteristic behavior database, identifies the name of a person, and records the position, the frame time and the name information of the person after successful identification; if the identification is unsuccessful, extracting a timestamp of the frame of image, extracting the RFID information, the depth sensing information and the infrared sensing information of the monitored area under the timestamp, comparing the extracted information with the data in the second character characteristic behavior database, and identifying the name of the constructor again;
discarding the frame of image after the secondary identification is unsuccessful, firstly recording the position, the image frame time and the name information of the person after the secondary identification is successful, then extracting all the characteristic data corresponding to the person in the timestamp, dividing the characteristic data into image data and other data, putting the image data into a first person characteristic behavior database, and putting the other data into a second person characteristic behavior database for the next identification;
the first person characteristic behavior database comprises face information, gait characteristic information and behavior characteristic information of each person in the construction site, and the second person characteristic behavior database comprises RFID information, depth sensing information and infrared sensing information of each person in the construction site.
4. The active safety protection system of the personnel on the construction site based on the narrow-band internet of things technology as claimed in claim 3, wherein in the personnel information identification process, when the identification is carried out based on the first human characteristic behavior database, when the coincidence rate of the human face identification reaches 90%, the human face identification is successful, otherwise, the gait identification is carried out based on the fusion image and the personnel gait database, when the coincidence rate of the gait identification reaches 60%, the gait identification is completed, otherwise, the behavior characteristic identification is continuously carried out based on the first human behavior database, when the coincidence rate of the behavior characteristic identification reaches 40%, the behavior characteristic identification is completed, otherwise, the frame image for identification is discarded;
the fusion map used in gait recognition is obtained by the following method: extracting frame images in video data acquired by visual sensing equipment, comparing figure outline features, and then extracting figure outline information; extracting monitoring data of infrared sensing equipment, comparing human body temperature infrared characteristics, and then extracting personnel infrared information; extracting monitoring data of the structured light depth sensor, performing three-dimensional processing on figure outline information, and extracting figure skeleton joint information; and finally, fusing the layers corresponding to the extracted three kinds of information to obtain a fused graph.
5. The active safety protection system for worksite personnel based on narrowband internet of things technology according to claim 2, wherein the dangerous scene identification process is as follows:
the cloud platform extracts a frame of image in data transmitted by the visual sensing equipment, identifies whether a fire disaster occurs, and discards the frame of image if the fire disaster does not occur; extracting the timestamp of the frame of image after a fire disaster is identified, and calling monitoring data of infrared sensing equipment at the same time and the same position to perform secondary identification on the fire disaster; after a fire disaster is identified secondarily, whether personnel move within a range of 10m around the fire source is judged, if the personnel do not move, the cloud platform directly carries out alarm prompt, if the personnel move, the name information of the personnel is recorded, and meanwhile, the cloud platform end alarms;
and recording the coordinates of the fire source after no fire occurs in the secondary identification, judging whether the coordinates are recorded before, discarding the frame of image and the coordinate information simultaneously if the coordinates are recorded, and extracting the infrared sensing information and the image information of other timestamps at the positions in the front and back 1S to perform fire identification again if the coordinates are recorded before.
6. The active safety protection system for the workers on the construction site based on the narrowband internet of things technology of claim 3, wherein the process of identifying the unsafe behaviors of the workers is as follows:
the cloud platform extracts the name and the position information of the personnel recorded in the personnel information identification process, compares the personnel position information with the coordinate data in the dangerous area database, judges whether personnel move in the dangerous area, discards the frame of image when judging that no personnel move, otherwise records the name information of the personnel, and simultaneously alarms at the cloud platform end; the dangerous area database comprises the coordinate set information of the dangerous area which is defined in advance.
7. The active safety protection system for the workers on the construction site based on the narrowband internet of things technology of claim 3, wherein the process of identifying the unsafe state of the workers is as follows:
the cloud platform extracts the name information of the personnel recorded in the personnel information identification process, simultaneously extracts a frame of image in the data transmitted by the visual sensing equipment, compares the frame of image with the safety protection article database, identifies whether the protection articles of the personnel in the frame of image are all normally worn, discards the frame of image data if the protection articles are all normally worn, otherwise records the name information of the personnel, and simultaneously alarms at the cloud platform end; the safety protection article database comprises a safety protection article image template.
8. The active safety protection system for workers on construction site based on narrowband internet of things technology of claim 2, wherein the personnel-worn device alarm process is: the cloud platform extracts unique identification information of wearable equipment of corresponding personnel according to personnel name information recorded in personnel information identification, dangerous scene identification, personnel unsafe behavior identification and personnel unsafe state identification processes, then based on narrowband Internet of things sending equipment, the wearable equipment corresponding to the corresponding identification information is awakened through the narrowband Internet of things, and after awakening, the personnel is warned by using a speaker of the wearable equipment.
9. The active safety protection system for the building site personnel based on the narrow-band internet of things technology as claimed in claim 8, wherein the narrow-band internet of things sending device is an LORA transmitter located at a system end, the narrow-band internet of things receiving device is an LORA receiver installed on an intelligent wearable device, an RFID receiver in the RFID device is also installed on the intelligent wearable device, the RFID transmitter is located at the system end, and the system end is in signal connection with a cloud platform, and transmits data and receives instructions; the intelligent wearing equipment is a safety helmet which is transformed through intelligent design, a loudspeaker and a power supply are further installed in the safety helmet, and the power supply consists of a miniature solar panel and a battery.
10. The active safety protection system for the building site personnel based on the narrow-band internet of things technology of claim 9 is characterized in that when the active safety protection system for the building site personnel carries out positioning identification on constructors, an LORA transmitter is used for sending starting information to LORA receivers on all intelligent wearable devices in the current device coverage range through the narrow-band internet of things, after receiving the information, the LORA receivers inform a power supply to supply power to active RFID receivers on the intelligent wearable device end, and after being powered on, the RFID receivers establish communication with RFID transmitters on the system end, so that personnel positioning is realized; after positioning is completed, the LORA transmitter sends closing information to LORA receivers on all intelligent wearable devices in the coverage area of the current device, after the LORA receivers receive the information, the LORA receivers inform a power supply in the intelligent wearable devices to stop supplying power to the active RFID receivers, and then the active RFID receivers are in a dormant state again;
when the active safety protection system of the building site personnel gives an alarm to a person side, the LORA transmitter of the system side sends information to the LORA receiver of a certain specified intelligent wearable device in a point-to-point mode, and the LORA receiver receives the information and then opens a loudspeaker of the intelligent wearable device side to give an alarm.
CN202210732596.9A 2022-06-27 2022-06-27 Active safety protection system for building site personnel based on narrowband Internet of things technology Active CN114821960B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210732596.9A CN114821960B (en) 2022-06-27 2022-06-27 Active safety protection system for building site personnel based on narrowband Internet of things technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210732596.9A CN114821960B (en) 2022-06-27 2022-06-27 Active safety protection system for building site personnel based on narrowband Internet of things technology

Publications (2)

Publication Number Publication Date
CN114821960A true CN114821960A (en) 2022-07-29
CN114821960B CN114821960B (en) 2022-09-30

Family

ID=82522073

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210732596.9A Active CN114821960B (en) 2022-06-27 2022-06-27 Active safety protection system for building site personnel based on narrowband Internet of things technology

Country Status (1)

Country Link
CN (1) CN114821960B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111275941A (en) * 2020-01-18 2020-06-12 傲通环球环境控制（深圳）有限公司 Construction site safety management system
CN211180869U (en) * 2020-03-20 2020-08-04 广西路桥工程集团有限公司 Intelligent system for construction safety management
CN111615059A (en) * 2020-04-08 2020-09-01 中核华纬工程设计研究有限公司 Positioning equipment and system for monitoring information of building site personnel in real time
CN113158752A (en) * 2021-02-05 2021-07-23 国网河南省电力公司鹤壁供电公司 Intelligent safety management and control system for electric power staff approach operation
CN113408683A (en) * 2021-07-06 2021-09-17 山东电力工程咨询院有限公司 Construction site safety supervision method and system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111275941A (en) * 2020-01-18 2020-06-12 傲通环球环境控制（深圳）有限公司 Construction site safety management system
CN211180869U (en) * 2020-03-20 2020-08-04 广西路桥工程集团有限公司 Intelligent system for construction safety management
CN111615059A (en) * 2020-04-08 2020-09-01 中核华纬工程设计研究有限公司 Positioning equipment and system for monitoring information of building site personnel in real time
CN113158752A (en) * 2021-02-05 2021-07-23 国网河南省电力公司鹤壁供电公司 Intelligent safety management and control system for electric power staff approach operation
CN113408683A (en) * 2021-07-06 2021-09-17 山东电力工程咨询院有限公司 Construction site safety supervision method and system

Also Published As

Publication number Publication date
CN114821960B (en) 2022-09-30

Similar Documents

Publication Publication Date Title
CN109151383B (en) BIM-based tunnel safety monitoring information early warning system
CN109448155A (en) Equipment-patrolling method based on AR technology
CN109215285A (en) The intelligent fire-pretection system and method for fire behavior monitoring and rescue run based on WiFi probe
CN112308510A (en) Green and environment-friendly building construction management system and method
CN108227606A (en) A kind of ship security intelligent management system perceived based on multi-source
CN108839036A (en) Home intelligent health supervision robot
CN109139115A (en) A kind of downhole data acquisition terminal, processing system and processing method
CN106089305B (en) A kind of underground real time monitoring and personnel location system
CN208900095U (en) A kind of downhole data acquisition terminal and processing system
CN205230242U (en) Intelligent residential district security protection system
CN111432188B (en) Security monitoring system and method based on artificial intelligence
CN108540941A (en) A kind of remote monitoring safe-guard system
CN111275941A (en) Construction site safety management system
CN107886677A (en) A kind of the elderly's gait household monitoring system based on Kinect
CN111753780A (en) Transformer substation violation detection system and violation detection method
CN213457742U (en) Welding operation monitoring system
CN114866958A (en) Alarm information grading system device and alarm method based on personnel position detection
CN114821960B (en) Active safety protection system for building site personnel based on narrowband Internet of things technology
CN109741574A (en) A kind of comprehensive monitor system based on intelligent safety helmet
CN109257576A (en) Transmission line of electricity external force damage prevention monitoring system and method based on artificial intelligence technology
CN113115212A (en) Management system based on UWB mine staff
CN112543497A (en) Safety monitoring system of degree of depth perception
CN208537961U (en) Wisdom fire-fighting monitoring management system based on technology of Internet of things
WO2017071012A1 (en) Kindergarten picking-up system based on palm vein recognition technology
CN105976564A (en) Functional remote monitoring system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant