CN113655750A - Building construction supervision system and method based on AI object detection algorithm - Google Patents

Building construction supervision system and method based on AI object detection algorithm Download PDF

Info

Publication number
CN113655750A
CN113655750A CN202111050669.8A CN202111050669A CN113655750A CN 113655750 A CN113655750 A CN 113655750A CN 202111050669 A CN202111050669 A CN 202111050669A CN 113655750 A CN113655750 A CN 113655750A
Authority
CN
China
Prior art keywords
object detection
assembly
mcu
microprocessor
power supply
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
CN202111050669.8A
Other languages
Chinese (zh)
Other versions
CN113655750B (en
Inventor
李晓亮
周慧文
罗巍
魏昕
周云英
孙贺
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.)
North China Institute of Aerospace Engineering
Original Assignee
North China Institute of Aerospace Engineering
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 North China Institute of Aerospace Engineering filed Critical North China Institute of Aerospace Engineering
Priority to CN202111050669.8A priority Critical patent/CN113655750B/en
Publication of CN113655750A publication Critical patent/CN113655750A/en
Application granted granted Critical
Publication of CN113655750B publication Critical patent/CN113655750B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G05B19/0423—Input/output
    • G—PHYSICS
    • G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
    • G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
    • G03B15/00—Special procedures for taking photographs; Apparatus therefor
    • G03B15/02—Illuminating scene
    • G03B15/03—Combinations of cameras with lighting apparatus; Flash units
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
    • G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/74—Circuitry for compensating brightness variation in the scene by influencing the scene brightness using illuminating means
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
    • H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
    • H05B45/10—Controlling the intensity of the light
    • H05B45/12—Controlling the intensity of the light using optical feedback
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/25—Pc structure of the system
    • G05B2219/25257—Microcontroller
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Automation & Control Theory (AREA)
  • Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Emergency Management (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention provides a building construction supervision system and a method based on an AI object detection algorithm, wherein the system comprises: the device comprises a shell, an MCU, a microprocessor, an image acquisition assembly, an object detection calculation assembly and a power supply assembly, wherein the image acquisition assembly is fixedly arranged at the lower end of the shell, the microprocessor, the MCU, the object detection calculation assembly and the power supply assembly are arranged in the shell, the power supply assembly is connected with the MCU, the microprocessor, the object detection calculation assembly and the image acquisition assembly and used for supplying power, and the microprocessor is electrically connected with the MCU, the image acquisition assembly and the object detection calculation assembly. The building construction supervision system and method based on the AI object detection algorithm can realize building construction supervision under the unmanned condition, improve the precision of supervision work, strengthen a real-time feedback mechanism in supervision work and improve the technological level of the building industry.

Description

Building construction supervision system and method based on AI object detection algorithm
Technical Field
The invention relates to the technical field of building supervision, in particular to a building construction supervision system and method based on an AI object detection algorithm.
Background
The fabricated building changes the defects of the traditional on-site manual construction technology through a building mode of industrialized module processing and on-site assembly construction, and the building product and the building industry develop towards the direction of low carbon, energy conservation, greenness, high efficiency and stability. However, in the construction link, the quality and even safety problems caused by the wrong assembly sequence exist, so that the marginal effect of the advantageous construction change is reduced. At present, often adopt the mode of professional on-the-spot inspection to carry out the building supervision, waste time and energy, the effect is relatively poor, has the building supervision professional talent deficient moreover, and supervision work precision is poor, and the real-time feedback mechanism is weak, and during the supervision personnel expose in dangerous construction environment, potential safety hazard scheduling problem appears easily, is unfavorable for constructor to engineering quality, progress, expense, safety in production and environmental protection's management and control. Therefore, it is necessary to design a building construction supervision system and method of AI object detection algorithm.
Disclosure of Invention
The invention aims to provide a building construction supervision system and method based on an AI object detection algorithm, which can realize building construction supervision under an unmanned condition, improve the supervision work precision, strengthen a real-time feedback mechanism in the supervision work and improve the technology level of the building industry.
In order to achieve the purpose, the invention provides the following scheme:
a building construction supervision system based on an AI object detection algorithm comprises: the device comprises a shell, an MCU, a microprocessor, an image acquisition component, an object detection calculation component and a power supply component, wherein the image acquisition component is fixedly arranged at the lower end of the shell, the microprocessor, the MCU, the object detection calculation component and the power supply component are arranged in the shell, the power supply component is connected with the MCU, the microprocessor, the object detection calculation component and the image acquisition component and used for supplying power, and the microprocessor is electrically connected with the MCU, the image acquisition component and the object detection calculation component;
the shell is provided with a power supply interface, the power supply assembly is connected with an external power supply through the power supply interface, and the top of the shell is provided with a loading platform for installing the system to a construction site;
the microprocessor comprises a first mainboard, and a CPU, an RAM, a network Bluetooth module, a USB interface, a Micro HDMI video interface, an extended GPIO, a power supply interface, a camera interface and a gigabit Ethernet interface which are arranged on the first mainboard, wherein the first mainboard is connected with a cloud server through the network Bluetooth module or the gigabit Ethernet interface, and is connected with a power supply assembly through the power supply interface;
the MCU comprises a second main board, a GPS module and a buzzing module, the GPS module and the buzzing module are connected with the second main board, the second main board is connected with the first main board through the USB interface, the GPS module is used for acquiring the physical coordinates of the system, and the buzzing module is used for alarming;
the image acquisition assembly comprises a rotating tripod head, a camera, an LED illuminating lamp and a light sensing probe, the rotating tripod head is arranged at the bottom of the shell, the camera, the LED illuminating lamp and the light sensing probe are all fixedly arranged at the bottom of the rotating tripod head, the camera is connected with the first main board through the camera interface, and the rotating tripod head, the LED illuminating lamp and the light sensing probe are all electrically connected with the MCU;
the object detection and calculation component is a nerve calculation rod, and the nerve calculation rod is connected with the first main board through the USB interface.
Optionally, an IO interface is further arranged on the second main board, and the rotary holder is connected to the second main board through the IO interface.
Optionally, the power supply assembly is a storage battery.
Optionally, the image acquisition assembly further comprises a camera protection cover, and the camera protection cover covers the lower end of the rotating holder and is used for protecting the image acquisition assembly.
Optionally, the casing is further fixedly provided with an LCD mini display screen, and the LCD mini display screen is electrically connected with the microprocessor.
The invention also provides a building construction supervision method based on the AI object detection algorithm, which is applied to the building construction supervision system based on the AI object detection algorithm and comprises the following steps:
step 1: building a BIM model according to the assembly type construction project, performing deep learning on all building components in the assembly type construction project by using Tensorflow and yolov algorithms, when the accuracy rate reaches more than 90%, determining that the learning is finished, arranging the algorithms into a first main board and a neural computing rod, and installing the arranged system on a construction site;
step 2: starting a system power supply, carrying out self-checking on the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly, and displaying state information on the LCD mini display screen;
and step 3: determining the position of the space where the system is located according to the physical coordinates acquired by the GPS module, matching the position with the corresponding position of the virtual environment in the BIM model, and displaying the matching completion on an LCD mini display screen after the matching is completed;
and 4, step 4: according to the design time node and the assembly type construction progress of the assembly type construction process of the BIM model, the original image of the space where the image acquisition assembly is located is periodically acquired through the microprocessor and the MCU, the image acquisition assembly is subjected to feature matching with the virtual environment image in the BIM model, and whether the space where the system is located is matched with the virtual environment or not is judged.
Optionally, in step 2, the system power is turned on, the MCU, the microprocessor, the image acquisition module and the object detection and calculation module are self-checked, and the status information is displayed on the LCD mini display screen, which specifically includes:
the system is accessed to an external power supply through a power interface, a system power supply is started, self-checking is carried out on the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly, after the self-checking is completed, information of each part is displayed on the LCD mini display screen, if an error occurs, the MCU controls the buzzer module to give an alarm, and the error information is displayed on the LCD mini display screen for a worker to handle.
Optionally, in step 4, according to the fabricated construction process design time node and the fabricated construction progress of the BIM model, periodically controlling the original image of the space where the image acquisition assembly acquisition system is located through the microprocessor and the MCU, performing feature matching on the original image and the virtual environment image in the BIM model, and judging whether the space where the system is located is matched with the virtual environment, specifically:
designing time nodes and an assembly construction progress according to an assembly construction process of a BIM model, periodically driving a rotating tripod head to rotate for 360 degrees through an MCU (microprogrammed control Unit), and further controlling a camera to acquire an original image of a space where a system is located through the microprocessor, wherein when a light sensing probe detects that ambient light influences image acquisition resolution, the MCU controls an LED illuminating lamp to be turned on to fill light into a microenvironment, image features of the original image are extracted in a neural computing bar through a yolov algorithm and are matched with the image features in a virtual environment to obtain a matching probability, if the matching probability is more than 90%, the space of the system is judged to be matched with the virtual environment, if the matching probability is less than 80%, the MCU controls a buzzer module to alarm and displays alarm information on an LCD (liquid crystal display) mini display screen, and the microprocessor uploads the alarm information and the matching information to a cloud server, and the cloud server distributes the information to a responsible person for processing.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the building construction supervision system and method based on AI object detection algorithm provided by the invention adopts a microprocessor, an MCU, an image acquisition component and a neural computing bar, can acquire images, transmits the acquired images to the microprocessor, performs object detection in the neural computing bar, and matches the acquired images with a virtual environment in an established BIM model, if a virtual environment design scheme conflicts, the MCU can also control a buzzer module to alarm, the microprocessor uploads matching information and alarm information to a cloud server, and the cloud server can distribute the matching information and the alarm information to a responsible person so as to perform processing; the system is provided with a rotating tripod head, the MCU can control the rotating tripod head to rotate for 360 degrees and can shoot all images at the position of the system, the system is also provided with a loading platform, the system can be fixed at a specified position through the loading platform, an image acquisition assembly of the system is also provided with a light sensing probe and an LED illuminating lamp, when the light sensing probe detects that ambient light influences image acquisition resolution, the MCU controls the LED illuminating lamp to be turned on to supplement light for a microenvironment, and the system is provided with a shell and a camera protective cover for protecting each assembly; the method comprises the steps of establishing a BIM model according to an assembly type construction project, carrying out deep learning on all building components in the assembly type construction project by using Tensorflow and yolov algorithms, when the accuracy rate reaches more than 90%, determining that the learning is finished, arranging the algorithms into a first main board and a neural computing rod, installing the arranged system on a construction site, starting a system power supply, carrying out self-inspection on an MCU, a microprocessor, an image acquisition component and an object detection and calculation component, displaying state information on an LCD mini display screen, determining the position of a space where the system is located according to physical coordinates acquired by a GPS module, matching the position with the corresponding position of a virtual environment in the BIM model, displaying the matching completion on the LCD mini display screen, designing time nodes and assembly type construction according to the assembly type construction process of the BIM model, periodically controlling an original image of the space where the image acquisition component is located by the microprocessor and the MCU, and carrying out feature matching on the image of the virtual environment in the BIM model, and judging whether the space where the system is located is matched with the virtual environment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic structural diagram of a building construction supervision system based on an AI object detection algorithm according to an embodiment of the invention;
FIG. 2 is a front view of the housing;
FIG. 3 is a rear view of the housing;
FIG. 4 is a schematic view of a first motherboard structure;
fig. 5 is a schematic flow chart of a building construction supervision method based on an AI object detection algorithm according to an embodiment of the present invention.
Reference numerals: 1. a housing; 2. a power interface; 3. a camera protective cover; 4. a loading table; 5. an LCD mini display screen; 6. a storage battery; 7. a first main board; 8. a CPU; 9. a RAM; 10. a network Bluetooth module; 11. a USB interface; 12. a Micro HDMI video interface; 13. expanding GPIO; 14. a power supply interface; 15. a camera interface; 16. gigabit ethernet interfaces; 17. a second main board; 18. a light sensing probe; 19. a neural computing rod; 20. rotating the holder; 21. a camera; 22. LED lighting lamp.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a building construction supervision system and method based on an AI object detection algorithm, which can realize building construction supervision under an unmanned condition, improve the supervision work precision, strengthen a real-time feedback mechanism in the supervision work, improve the technology level of the building industry and reduce the risk of damage caused by dust contamination of an optical fiber connector.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1 to 4, a building construction supervision system based on an AI object detection algorithm according to an embodiment of the present invention includes: the device comprises a shell 1, an MCU, a microprocessor, an image acquisition component, an object detection calculation component and a power supply component, wherein the image acquisition component is arranged at the lower end of the shell 1, the microprocessor, the MCU, the object detection calculation component and the power supply component are arranged in the shell 1, the power supply component is connected with the MCU, the microprocessor, the object detection calculation component and the image acquisition component and used for supplying power, and the microprocessor is electrically connected with the MCU, the image acquisition component and the object detection calculation component;
the power supply assembly is characterized in that a power supply interface 2 is arranged on the shell 1, the power supply assembly is connected with an external power supply through the power supply interface 2, and a loading platform 4 is arranged at the top of the shell 1 and used for installing the system to a construction site;
the microprocessor comprises a first mainboard 7, and a CPU8, an RAM9, a network Bluetooth module 10, a USB interface 11, a Micro HDMI video interface 12, an extended GPIO13, a power supply interface 14, a camera interface 15 and a gigabit Ethernet interface 16 which are arranged on the first mainboard 7, wherein the first mainboard 7 is connected with a cloud server through the network Bluetooth module 10 or the gigabit Ethernet interface 16, and the first mainboard 7 is connected with a power supply component through the power supply interface 14;
the MCU comprises a second main board 17, a GPS module and a buzzing module, the GPS module and the buzzing module are connected with the second main board 17, the second main board 17 is connected with the first main board 7 through the USB interface 11, the GPS module is used for acquiring the physical coordinates of the system, and the buzzing module is used for alarming;
the image acquisition assembly comprises a rotating tripod head 20, a camera 21, an LED illuminating lamp 22 and a light sensing probe 18, the rotating tripod head 20 is arranged at the bottom of the shell 1, the camera 21, the LED illuminating lamp 22 and the light sensing probe 18 are all fixedly arranged at the bottom of the rotating tripod head 20, the camera 21 is connected with the first main board 7 through the camera interface 15, and the rotating tripod head 20, the LED illuminating lamp 22 and the light sensing probe 18 are all electrically connected with the MCU;
the object detection calculation component is a nerve calculation stick 19, and the nerve calculation stick 19 is connected with the first main board 7 through the USB interface 11.
Still be provided with the IO interface on the second mainboard 17, rotatory cloud platform 20 passes through IO interface connection second mainboard 17, second mainboard 17 also can be through other outside delivery equipment of IO interface connection, for example unmanned vehicle or unmanned aerial vehicle etc..
The power supply assembly is a storage battery 6, an external power supply charges the storage battery 6 through the power interface 2, and the storage battery supplies power to all parts.
The image acquisition assembly further comprises a camera protection cover 3, wherein the camera protection cover 3 covers the lower end of the rotating holder 20 and is used for protecting the image acquisition assembly.
Still fixed LCD mini display screen 5 that is provided with on the shell 1, LCD mini display screen 5 electric connection microprocessor.
The building construction supervision system based on the AI object detection algorithm can be fixedly installed and can also be matched with unmanned carrying equipment such as an unmanned aerial vehicle or a robot for use.
As shown in fig. 5, the present invention further provides a building construction supervision method based on the AI object detection algorithm, which is applied to the building construction supervision system based on the AI object detection algorithm, and comprises the following steps:
step 1: building a BIM model according to the assembly type construction project, performing deep learning on all building components in the assembly type construction project by using Tensorflow and yolov algorithms, when the accuracy rate reaches more than 90%, determining that the learning is finished, arranging the algorithms into a first main board and a neural computing rod, and installing the arranged system on a construction site;
step 2: starting a system power supply, carrying out self-checking on the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly, and displaying state information on the LCD mini display screen;
and step 3: determining the position of the space where the system is located according to the physical coordinates acquired by the GPS module, matching the position with the corresponding position of the virtual environment in the BIM model, and displaying the matching completion on an LCD mini display screen after the matching is completed;
and 4, step 4: according to the design time node and the assembly type construction progress of the assembly type construction process of the BIM model, the original image of the space where the image acquisition assembly is located is periodically acquired through the microprocessor and the MCU, the image acquisition assembly is subjected to feature matching with the virtual environment image in the BIM model, and whether the space where the system is located is matched with the virtual environment or not is judged.
In step 2, a system power supply is started, the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly are subjected to self-checking, and state information is displayed on the LCD mini display screen, and the method specifically comprises the following steps:
the system is accessed to an external power supply through a power interface, a system power supply is started, self-checking is carried out on the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly, after the self-checking is completed, information of each part is displayed on the LCD mini display screen, if an error occurs, the MCU controls the buzzer module to give an alarm, and the error information is displayed on the LCD mini display screen for a worker to handle.
In step 4, designing time nodes and an assembly construction progress according to an assembly construction process of the BIM, periodically controlling an original image of a space where the image acquisition assembly acquisition system is located through the microprocessor and the MCU, performing feature matching on the original image and a virtual environment image in the BIM, and judging whether the space where the system is located is matched with the virtual environment, wherein the steps are as follows:
in order to save energy and reduce hardware loss, the invention does not need to monitor all the time, and designs time nodes and the assembly construction progress according to the assembly construction process of the BIM model, periodically drives the rotating cradle head to rotate for 360 degrees through the MCU, and then controls the camera to collect the original image of the space where the system is located through the microprocessor, wherein when the light sensing probe detects that the ambient light influences the image collection resolution, the MCU controls the LED illuminating lamp to be turned on to carry out microenvironment light filling, the image characteristics of the original image are extracted through the yolov algorithm in the neural calculation rod and are matched with the image characteristics in the virtual environment to obtain the matching probability, if the matching probability is more than 90 percent, the space of the system is judged to be matched with the virtual environment, if the matching probability is less than 80 percent, the MCU controls the buzzer module to alarm and displays the alarm information on the LCD mini display screen, the microprocessor uploads the alarm information and the matching information to the cloud server, and the cloud server distributes the information to a responsible person for processing.
The Microprocessor (Microprocessor) used in the invention is a programmable special integrated circuit, is a main component of the card computer, can be used for completely running operating systems of specific versions such as linux, Windows and the like on the card computer, is onboard with input and output equipment interfaces such as USB, Ethernet, HDMI and the like, and can be externally connected with keyboard display equipment and the like.
The Microcontroller (MCU) used in the invention is a low-cost, single-chip independent computer system. The microcontrollers are hidden in numerous daily products and are embedded in built-in computers of products such as wearable equipment, unmanned planes, 3D printers, toys, electric cookers, intelligent sockets, electric scooters, washing machines and the like, and due to the characteristics of small volume, low power consumption, strong expansibility and the like, the microcontrollers gradually replace the functions of the PLCs in the industrial and living fields, and the ability of finely controlling GPIO is a good supplement to the microprocessors.
The Neural Computing Stick (NCS) used in the invention is a deep Neural network hardware accelerator, is a hardware device for developing, finely adjusting and deploying a convolutional Neural network on a low-power consumption application for real-time reasoning, can complete edge deep learning on the hardware device, can be perfectly combined with a microprocessor, and improves the computing power of the microprocessor on the Neural network, so that the image recognition speed and the deduction speed are obviously improved. It is also a trend in the development of the internet of things to connect these devices to each other.
The object detection algorithm yolov3 in Tensorflow is arranged in a microprocessor and a neural computing bar, image acquisition time is set according to construction progress of a building project, the MCU and the microprocessor are used for periodically carrying out on-site image acquisition on the construction progress and transmitting images to the microprocessor, object detection is carried out in the neural computing bar, the object detection is matched with a constructed image in a BIM (building information model), if the object detection is in conflict with a BIM design scheme, the system gives an alarm in time, and a comparison result is transmitted to a responsible person through a network and corrected in time.
The building construction supervision system and method based on AI object detection algorithm provided by the invention adopts a microprocessor, an MCU, an image acquisition component and a neural computing bar, can acquire images, transmits the acquired images to the microprocessor, performs object detection in the neural computing bar, and matches the acquired images with a virtual environment in an established BIM model, if a virtual environment design scheme conflicts, the MCU can also control a buzzer module to alarm, the microprocessor uploads matching information and alarm information to a cloud server, and the cloud server can distribute the matching information and the alarm information to a responsible person so as to perform processing; the system is provided with a rotating tripod head, the MCU can control the rotating tripod head to rotate for 360 degrees and can shoot all images at the position of the system, the system is also provided with a loading platform, the system can be fixed at a specified position through the loading platform, an image acquisition assembly of the system is also provided with a light sensing probe and an LED illuminating lamp, when the light sensing probe detects that ambient light influences image acquisition resolution, the MCU controls the LED illuminating lamp to be turned on to supplement light for a microenvironment, and the system is provided with a shell and a camera protective cover for protecting each assembly; the method comprises the steps of establishing a BIM model according to an assembly type construction project, carrying out deep learning on all building components in the assembly type construction project by using Tensorflow and yolov algorithms, when the accuracy rate reaches more than 90%, determining that the learning is finished, arranging the algorithms into a first main board and a neural computing rod, installing the arranged system on a construction site, starting a system power supply, carrying out self-inspection on an MCU, a microprocessor, an image acquisition component and an object detection and calculation component, displaying state information on an LCD mini display screen, determining the position of a space where the system is located according to physical coordinates acquired by a GPS module, matching the position with the corresponding position of a virtual environment in the BIM model, displaying the matching completion on the LCD mini display screen, designing time nodes and assembly type construction according to the assembly type construction process of the BIM model, periodically controlling an original image of the space where the image acquisition component is located by the microprocessor and the MCU, and carrying out feature matching on the image of the virtual environment in the BIM model, and judging whether the space where the system is located is matched with the virtual environment.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (8)

1. A building construction supervision system based on an AI object detection algorithm, comprising: the device comprises a shell, an MCU, a microprocessor, an image acquisition component, an object detection calculation component and a power supply component, wherein the image acquisition component is fixedly arranged at the lower end of the shell, the microprocessor, the MCU, the object detection calculation component and the power supply component are arranged in the shell, the power supply component is connected with the MCU, the microprocessor, the object detection calculation component and the image acquisition component and used for supplying power, and the microprocessor is electrically connected with the MCU, the image acquisition component and the object detection calculation component;
the shell is provided with a power supply interface, the power supply assembly is connected with an external power supply through the power supply interface, and the top of the shell is provided with a loading platform for installing the system to a construction site;
the microprocessor comprises a first mainboard, and a CPU, an RAM, a network Bluetooth module, a USB interface, a Micro HDMI video interface, an extended GPIO, a power supply interface, a camera interface and a gigabit Ethernet interface which are arranged on the first mainboard, wherein the first mainboard is connected with a cloud server through the network Bluetooth module or the gigabit Ethernet interface, and is connected with a power supply assembly through the power supply interface;
the MCU comprises a second main board, a GPS module and a buzzing module, the GPS module and the buzzing module are connected with the second main board, the second main board is connected with the first main board through the USB interface, the GPS module is used for acquiring the physical coordinates of the system, and the buzzing module is used for alarming;
the image acquisition assembly comprises a rotating tripod head, a camera, an LED illuminating lamp and a light sensing probe, the rotating tripod head is arranged at the bottom of the shell, the camera, the LED illuminating lamp and the light sensing probe are all fixedly arranged at the bottom of the rotating tripod head, the camera is connected with the first main board through the camera interface, and the rotating tripod head, the LED illuminating lamp and the light sensing probe are all electrically connected with the MCU;
the object detection and calculation component is a nerve calculation rod, and the nerve calculation rod is connected with the first main board through the USB interface.
2. The AI object detection algorithm based building construction supervision system of claim 1, wherein the second main board is further provided with an IO interface, and the rotating pan/tilt head is connected to the second main board through the IO interface.
3. The AI object detection algorithm-based construction supervision system according to claim 1, wherein the power supply component is a battery.
4. The AI object detection algorithm-based construction supervision system according to claim 1, wherein the image capturing assembly further comprises a camera protection cover, which is covered at a lower end of the rotating pan/tilt head for protecting the image capturing assembly.
5. The AI object detection algorithm based building construction supervision system of claim 1, wherein an LCD mini-screen is further fixed on the housing and electrically connected to the microprocessor.
6. A building construction supervision method based on AI object detection algorithm, which is applied to the building construction supervision system based on AI object detection algorithm of any claim 1-5, characterized by comprising the following steps:
step 1: building a BIM model according to the assembly type construction project, performing deep learning on all building components in the assembly type construction project by using Tensorflow and yolov algorithms, when the accuracy rate reaches more than 90%, determining that the learning is finished, arranging the algorithms into a first main board and a neural computing rod, and installing the arranged system on a construction site;
step 2: starting a system power supply, carrying out self-checking on the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly, and displaying state information on the LCD mini display screen;
and step 3: determining the position of the space where the system is located according to the physical coordinates acquired by the GPS module, matching the position with the corresponding position of the virtual environment in the BIM model, and displaying the matching completion on an LCD mini display screen after the matching is completed;
and 4, step 4: according to the design time node and the assembly type construction progress of the assembly type construction process of the BIM model, the original image of the space where the image acquisition assembly is located is periodically acquired through the microprocessor and the MCU, the image acquisition assembly is subjected to feature matching with the virtual environment image in the BIM model, and whether the space where the system is located is matched with the virtual environment or not is judged.
7. The AI object detection algorithm-based building construction supervision method according to claim 6, wherein in step 2, the system power is turned on, the MCU, the microprocessor, the image acquisition module and the object detection calculation module are self-checked, and the LCD mini-display screen displays status information, specifically:
the system is accessed to an external power supply through a power interface, a system power supply is started, self-checking is carried out on the MCU, the microprocessor, the image acquisition assembly and the object detection calculation assembly, after the self-checking is completed, information of each part is displayed on the LCD mini display screen, if an error occurs, the MCU controls the buzzer module to give an alarm, and the error information is displayed on the LCD mini display screen for a worker to handle.
8. The AI object detection algorithm-based building construction supervision method according to claim 6, wherein in step 4, according to the fabricated construction process design time node and the fabricated construction progress of the BIM model, the microprocessor and the MCU are periodically used to control the image acquisition component to acquire the original image of the space where the system is located, and perform feature matching with the virtual environment image in the BIM model, and determine whether the space where the system is located matches with the virtual environment, specifically:
designing time nodes and an assembly construction progress according to an assembly construction process of a BIM model, periodically driving a rotating tripod head to rotate for 360 degrees through an MCU (microprogrammed control Unit), and further controlling a camera to acquire an original image of a space where a system is located through the microprocessor, wherein when a light sensing probe detects that ambient light influences image acquisition resolution, the MCU controls an LED illuminating lamp to be turned on to fill light into a microenvironment, image features of the original image are extracted in a neural computing bar through a yolov algorithm and are matched with the image features in a virtual environment to obtain a matching probability, if the matching probability is more than 90%, the space of the system is judged to be matched with the virtual environment, if the matching probability is less than 80%, the MCU controls a buzzer module to alarm and displays alarm information on an LCD (liquid crystal display) mini display screen, and the microprocessor uploads the alarm information and the matching information to a cloud server, and the cloud server distributes the information to a responsible person for processing.
CN202111050669.8A 2021-09-08 2021-09-08 Building construction supervision system and method based on AI object detection algorithm Active CN113655750B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111050669.8A CN113655750B (en) 2021-09-08 2021-09-08 Building construction supervision system and method based on AI object detection algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111050669.8A CN113655750B (en) 2021-09-08 2021-09-08 Building construction supervision system and method based on AI object detection algorithm

Publications (2)

Publication Number Publication Date
CN113655750A true CN113655750A (en) 2021-11-16
CN113655750B CN113655750B (en) 2023-08-18

Family

ID=78493697

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111050669.8A Active CN113655750B (en) 2021-09-08 2021-09-08 Building construction supervision system and method based on AI object detection algorithm

Country Status (1)

Country Link
CN (1) CN113655750B (en)

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109657575A (en) * 2018-12-05 2019-04-19 国网安徽省电力有限公司检修分公司 Outdoor construction personnel's intelligent video track algorithm
CN110287519A (en) * 2019-05-14 2019-09-27 深圳大学 A kind of the building engineering construction progress monitoring method and system of integrated BIM
CN110428448A (en) * 2019-07-31 2019-11-08 腾讯科技（深圳）有限公司 Target detection tracking method, device, equipment and storage medium
CN110781964A (en) * 2019-10-28 2020-02-11 兰州交通大学 Human body target detection method and system based on video image
CN111160838A (en) * 2018-11-07 2020-05-15 苏州微缔软件股份有限公司 3D visualization building project management system and method based on BIM technology
CN111260325A (en) * 2019-07-23 2020-06-09 上海建工集团股份有限公司 Bridge construction progress management system based on BIM
CN111561915A (en) * 2020-05-27 2020-08-21 永康龙飘传感科技有限公司 Building construction state monitoring feedback device, system and method
CN111563680A (en) * 2020-05-06 2020-08-21 北方工业大学 BIM-based assembly type building construction safety protection method and device and electronic equipment
CN112613097A (en) * 2020-12-15 2021-04-06 中铁二十四局集团江苏工程有限公司 BIM rapid modeling method based on computer vision
CN112907211A (en) * 2021-03-02 2021-06-04 惠州城际工程咨询有限公司 BIM-based project progress supervision method, device, equipment and storage medium
CN112950773A (en) * 2021-04-07 2021-06-11 万翼科技有限公司 Data processing method and device based on building information model and processing server
CN113032868A (en) * 2021-03-08 2021-06-25 万翼科技有限公司 Prefabricated part management method and device, electronic equipment and storage medium

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111160838A (en) * 2018-11-07 2020-05-15 苏州微缔软件股份有限公司 3D visualization building project management system and method based on BIM technology
CN109657575A (en) * 2018-12-05 2019-04-19 国网安徽省电力有限公司检修分公司 Outdoor construction personnel's intelligent video track algorithm
CN110287519A (en) * 2019-05-14 2019-09-27 深圳大学 A kind of the building engineering construction progress monitoring method and system of integrated BIM
CN111260325A (en) * 2019-07-23 2020-06-09 上海建工集团股份有限公司 Bridge construction progress management system based on BIM
CN110428448A (en) * 2019-07-31 2019-11-08 腾讯科技（深圳）有限公司 Target detection tracking method, device, equipment and storage medium
CN110781964A (en) * 2019-10-28 2020-02-11 兰州交通大学 Human body target detection method and system based on video image
CN111563680A (en) * 2020-05-06 2020-08-21 北方工业大学 BIM-based assembly type building construction safety protection method and device and electronic equipment
CN111561915A (en) * 2020-05-27 2020-08-21 永康龙飘传感科技有限公司 Building construction state monitoring feedback device, system and method
CN112613097A (en) * 2020-12-15 2021-04-06 中铁二十四局集团江苏工程有限公司 BIM rapid modeling method based on computer vision
CN112907211A (en) * 2021-03-02 2021-06-04 惠州城际工程咨询有限公司 BIM-based project progress supervision method, device, equipment and storage medium
CN113032868A (en) * 2021-03-08 2021-06-25 万翼科技有限公司 Prefabricated part management method and device, electronic equipment and storage medium
CN112950773A (en) * 2021-04-07 2021-06-11 万翼科技有限公司 Data processing method and device based on building information model and processing server

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王舒琪等: "基于BIM技术与物联网的建筑施工安全监控系统研究", 《智能建筑与智慧城市》 *

Also Published As

Publication number Publication date
CN113655750B (en) 2023-08-18

Similar Documents

Publication Publication Date Title
US9454707B1 (en) System and method for reading a tire code and obtaining tire-related information
CN102713500A (en) Display for coordinate measuring machine
Russell et al. Low-cost, rapid prototyping of IMU and pressure monitoring system using an open source hardware design
Nayyar et al. A comprehensive review of beaglebone technology: Smart board powered by ARM
CN211956466U (en) Storage mainboard based on processor soars
CN113655750A (en) Building construction supervision system and method based on AI object detection algorithm
CN111338470B (en) Method for controlling big clock through gestures
CN206863509U (en) Tiny motion control computer
Moharkar et al. Review on Different Microcontroller Boards used in IoT
CN203101077U (en) Intelligent repair system for equipment
CN108415448A (en) A kind of winged control method and system of aerial crusing robot
Lang et al. Selecting a development board for your capstone or course project
CN211180764U (en) Head-mounted style migration device
CN207148820U (en) A kind of COMe_nano core boards based on Godson 2H chip applications
CN207814815U (en) Display for computer face recognition system
CN206224383U (en) A kind of gesture identification acquisition system based on binocular vision
CN214470662U (en) Handheld scanning measuring instrument based on linear laser and measuring camera
CN114967588B (en) PLC data management and control system and method based on embedded AI computer
CN111858261B (en) Monitoring management board card of Feiteng server
CN216351265U (en) Intelligent natural field electrical method instrument
CN217955317U (en) Embedded artificial intelligence thing networking development board
CN217489623U (en) Fire water monitor inclination angle control device
CN210864620U (en) Human body gesture recognition system based on inertia technology
Chapa et al. BOGGLES: Boundary Optical GeoGraphic Lidar Environment System
CN216623313U (en) Online power plant inspection terminal

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