CN-115240140-B - Method and system for monitoring equipment installation progress based on image recognition

CN115240140BCN 115240140 BCN115240140 BCN 115240140BCN-115240140-B

Abstract

The invention provides an equipment installation progress monitoring method and system based on image recognition, wherein the method comprises the steps of respectively constructing a BIM structure model and a BIM equipment model, adding the BIM equipment model to a required position in the BIM structure model to obtain the BIM model, scanning a construction environment to obtain a construction environment image, superposing the BIM model in the construction environment image to obtain a virtual-real combined scene image, respectively acquiring the scene image and the construction environment image according to a set speed, recognizing the position relationship between the BIM equipment model in the scene image and real equipment in the construction environment image, and automatically counting the equipment installation condition. According to the invention, real-time data acquisition is carried out on the engineering project without depending on specific equipment, the counted equipment installation progress process can be automatically completed by the system, the working efficiency is improved, the visualization and information interaction of the engineering construction progress are realized, and further, the real-time monitoring of the engineering field equipment installation progress is realized.

Inventors

QIN KUANGYU
ZHONG BIN
SHI JIANYONG
ZENG YUANFAN
LV ZHENGYU
ZHOU LIANG

Assignees

国网上海市电力公司
上海交通大学

Dates

Publication Date: 20260512
Application Date: 20220714

Claims (8)

1. An equipment installation progress monitoring method based on image recognition is characterized by comprising the following steps: respectively constructing a BIM structure model and a BIM equipment model, and adding the BIM equipment model to a required position in the BIM structure model to obtain a BIM model; scanning a construction environment to obtain a construction environment image, and overlapping the BIM model into the construction environment image to obtain a virtual-real combined scene image; Respectively acquiring the scene image and the construction environment image according to a set rate, and correspondingly enabling the scene image and the construction environment image to be one-to-one according to a timestamp, and identifying a BIM equipment model in the scene image and real equipment in the construction environment image; Setting the BIM structure model as semitransparent materials, setting the BIM device model as different monochromatic materials according to three dimensions of device type, device model and device name, acquiring all non-semitransparent materials in a current picture, acquiring two-dimensional coordinates of the BIM device model in the current picture according to the corresponding relation between preset monochromatic materials and the BIM device model, simultaneously, identifying real devices in the current picture, acquiring two-dimensional coordinates of the real devices, and judging whether the BIM device model is overlapped with the real devices according to the two sets of coordinates; If the two types of equipment are overlapped, further judging whether the BIM equipment model and the real equipment are of the same equipment type, equipment model and equipment name, if so, marking the real equipment as installed equipment, if not, acquiring the long and wide pixel values of the BIM structure model from the scene image, and drawing a circle by taking x times of the long or wide pixel values as a diameter or drawing a rectangle by taking x times of the long and wide pixel values as new long and wide pixel values to obtain a specified pixel point range, wherein x is an adjustable parameter; otherwise, marking the real equipment as uninstalled equipment; and finishing automatic statistics of the installation condition of the equipment.
2. The method for monitoring the installation progress of equipment based on image recognition according to claim 1, wherein the building a BIM structure model and a BIM equipment model respectively, and adding the BIM equipment model to a required position in the BIM structure model to obtain a BIM model, comprises: According to a CAD drawing, respectively creating a BIM structure model and a BIM equipment model according to the ratio of the model to a construction site of 1:1, and adding the BIM equipment model into the BIM structure model according to the placed real position to obtain a preliminary BIM model; converting the preliminary BIM model into a three-dimensional model file, and respectively configuring materials of the BIM structure model and the BIM equipment model to obtain a final BIM model, wherein: the material of BIM structural model is fixed material, BIM equipment model's material is according to equipment type, equipment model and three dimension of equipment name and is set up differently.
3. The method for monitoring the installation progress of equipment based on image recognition according to claim 1, wherein the scanning a construction environment to obtain a construction environment image, and superimposing the BIM model to the construction environment image to obtain a virtual-real combined scene image, comprises: Scanning a construction site to obtain a construction environment image; creating punctuation on the BIM model, obtaining virtual space coordinates, and obtaining points corresponding to the punctuation in the construction environment image to obtain construction environment space coordinates; Registering the virtual space coordinates and the construction environment coordinates, so that the BIM model and the construction environment image are overlapped, and a virtual-real combined scene image is obtained.
4. An image recognition-based equipment installation progress monitoring system, comprising: The BIM model processing module is used for respectively constructing a BIM structure model and a BIM equipment model, setting the BIM structure model to be a semitransparent material, setting the BIM equipment model to be different monochromatic materials according to three dimensions of equipment type, equipment model and equipment name, and adding the BIM equipment model to a required position in the BIM structure model to obtain the BIM model; The positioning module is used for scanning a construction environment to obtain a construction environment image, and overlapping the BIM model into the construction environment image to obtain a virtual-real combined scene image; the image processing module is used for respectively acquiring the scene image and the construction environment image according to a set speed, corresponding the scene image to the construction environment image one by one according to a time stamp, identifying a BIM equipment model in the scene image and real equipment in the construction environment image, and correlating the BIM equipment model with the real equipment; The progress recognition module is used for judging the position relation between the BIM equipment model in the scene image and the real equipment in the construction environment image, carrying out installation progress recognition and realizing automatic statistics on the equipment installation condition, and comprises the following steps: An image recognition unit for recognizing the type and position of the BIM device model appearing and the type and position of the real device appearing in each frame of image; The image matching unit is used for judging whether the BIM equipment model is overlapped with the real equipment, if so, further judging whether the BIM equipment model and the real equipment are of the same equipment type, equipment model and equipment name, if so, marking the real equipment as installed equipment, if not, acquiring long and wide pixel values of the BIM structure model from the scene image, and drawing a circle by taking x times of the long or wide pixel values as a diameter or drawing a rectangle by taking x times of the long and wide pixel values as new long and wide pixel values to obtain a specified pixel point range, wherein x is an adjustable parameter, and if the real equipment of the same equipment type, equipment model and equipment name as the BIM equipment model exists in the specified pixel point range, judging that the real equipment is installed, otherwise, marking the real equipment as uninstalled equipment; and the network module is used for being responsible for communication among the modules.
5. The image recognition-based device installation progress monitoring system of claim 4, further comprising any one or more of: -the BIM model processing module comprising: the model construction unit is used for respectively creating a BIM structure model and a BIM equipment model according to a CAD drawing and the 1:1 ratio of the model to the construction site, and adding the BIM equipment model into the BIM structure model according to the placed real position to obtain a preliminary BIM model; A format conversion unit for converting the preliminary BIM model into a three-dimensional model file; the attribute deriving unit is used for deriving model attributes from the preliminary BIM model according to the components into a text document for setting the subsequent material of the preliminary BIM model; The material unit is used for endowing the preliminary BIM model with different materials according to three dimensions of equipment type, equipment model and equipment name to obtain a final BIM model; -the positioning module comprising: the visual inertia SLAM unit is used for creating punctuation on the BIM model, obtaining virtual space coordinates, and obtaining points corresponding to the punctuation in the construction environment image to obtain construction environment space coordinates; The coordinate input unit is used for outputting initial coordinates and providing initial pose for coordinate matching of the virtual space and the real space; -the image processing module comprising: A scene recording unit for respectively acquiring the scene picture and the construction site image according to a set rate; a sensor data recording unit for recording the scene picture and the construction site image of each frame acquired; And the data processing unit is used for corresponding the scene pictures and the construction site images one by one according to the time stamps, and associating BIM equipment models in the scene images with real equipment in the construction environment images.
6. The image recognition-based device installation progress monitoring system of claim 4 or 5, further comprising any one or more of the following: -a logging module for storing data generated during operation of the system; -a progress model viewing module for showing device installation progress.
7. The device is characterized by comprising a computer and a field scanning device connected with the computer, wherein: The on-site scanning device comprises a camera and an inertial sensor, wherein the camera and the inertial sensor are used for scanning a construction environment, acquiring a construction environment image and sending the construction environment image to the computer; the computer comprising a display, a memory, a processor and a computer program stored on the memory and executable on the processor, the processor being operable to perform the method of any of claims 1-3 or to run the system of any of claims 4-6 when the program is executed.
8. A computer readable storage medium having stored thereon a computer program, which when executed by a processor is operable to perform the method of any of claims 1-3 or to run the system of any of claims 4-6.

Description

Method and system for monitoring equipment installation progress based on image recognition Technical Field The invention relates to the technical field of engineering progress management, in particular to a device installation progress monitoring method and system based on image recognition, and provides corresponding devices and a computer-readable storage medium. Background The progress management is carried out on the foundation projects, so that the project is guaranteed to be completed as expected, and the foundation projects are important management indexes of construction units and construction units. In order to ensure the engineering progress and realize the engineering progress target, each unit tracks and manages the progress in construction. The conventional method is to take the developed cross-road diagram and network diagram plan as a base line plan. As the project progresses, progress related data is collected and the original plan is updated. And judging the speed of the engineering progress through comparison of the new plan and the baseline plan, and then adjusting the progress through a deviation correcting mode. The conventional method is used for managing the progress of engineering projects, and has a plurality of advantages. But the biggest drawback is the lack of visualization and information interaction. No description or report of similar technology is found at present, and similar data at home and abroad are not collected. Disclosure of Invention The invention aims at the defects in the prior art, provides a device installation progress monitoring method and system based on image recognition, and provides corresponding devices and a computer-readable storage medium. The invention is realized by the following technical scheme. According to one aspect of the present invention, there is provided an apparatus installation progress monitoring method based on image recognition, including: Respectively constructing a BIM structure model and a BIM equipment model, and adding the BIM equipment model to a required position in the BIM structure model to obtain a BIM model; scanning a construction environment to obtain a construction environment image, and overlapping the BIM model into the construction environment image to obtain a virtual-real combined scene image; And respectively acquiring the scene image and the construction environment image according to a set rate, identifying the position relation between the BIM equipment model in the scene image and the real equipment in the construction environment image, and automatically counting the equipment installation condition. Optionally, the building a BIM structure model and a BIM device model respectively, and adding the BIM device model to a required position in the BIM structure model to obtain a BIM model, which includes: according to a CAD drawing, respectively creating a BIM structure model and a BIM equipment model according to the ratio of the model to a construction site of 1:1, and adding the BIM equipment model into the BIM structure model according to the placed real position to obtain a preliminary BIM model; converting the preliminary BIM model into a three-dimensional model file, and respectively configuring materials of the BIM structure model and the BIM equipment model to obtain a final BIM model, wherein: the material of BIM structural model is fixed material, BIM equipment model's material is according to equipment type, equipment model and three dimension of equipment name and is set up differently. Optionally, the scanning the construction environment to obtain a construction environment image, and overlapping the BIM model into the construction environment image to obtain a virtual-real combined scene image, including: Scanning a construction site to obtain a construction environment image; creating punctuation on the BIM model, obtaining virtual space coordinates, and obtaining points corresponding to the punctuation in the construction environment image to obtain construction environment space coordinates; Registering the virtual space coordinates and the construction environment coordinates, so that the BIM model and the construction environment image are overlapped, and a virtual-real combined scene image is obtained. Optionally, the acquiring the scene image and the construction environment image according to the set speed respectively, identifying a position relationship between a BIM device model in the scene image and a real device in the construction environment image, and automatically counting device installation conditions, including: Respectively acquiring the scene picture and the construction site image according to a set rate, and correspondingly enabling the scene picture and the construction site image to be one-to-one according to a timestamp, and identifying a BIM device model in the scene picture and real devices in the construction site image; judging whether the BIM equipment model is overl