CN111860202A - Beam yard pedestal state identification method and system combining image identification and intelligent equipment - Google Patents
Beam yard pedestal state identification method and system combining image identification and intelligent equipment Download PDFInfo
- Publication number
- CN111860202A CN111860202A CN202010600293.2A CN202010600293A CN111860202A CN 111860202 A CN111860202 A CN 111860202A CN 202010600293 A CN202010600293 A CN 202010600293A CN 111860202 A CN111860202 A CN 111860202A
- Authority
- CN
- China
- Prior art keywords
- state
- pedestal
- beam field
- yard
- current
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Hardware Design (AREA)
- Civil Engineering (AREA)
- Architecture (AREA)
- Multimedia (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for recognizing the state of a beam yard pedestal by combining image recognition and intelligent equipment, which relate to the technical field of beam yard production management, and the method comprises the steps of acquiring video monitoring data of the existing beam yard pedestal; training a beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data; periodically judging whether the beam yard intelligent equipment returns operation information, if so, outputting the current use state of the beam yard pedestal, and if not, identifying the beam yard pedestal by using a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal; the current use state of the beam field pedestal is transmitted into a BIM beam field pedestal management model, and the BIM beam field pedestal management model displays the use state of each pedestal of the current beam field in real time. The invention can monitor the service state of the beam yard pedestal in real time, efficiently and intelligently, reduce the workload of beam yard operators and improve the intelligent level of the beam yard.
Description
Technical Field
The invention relates to the technical field of beam yard production management, in particular to a method and a system for recognizing the state of a beam yard pedestal by combining image recognition and intelligent equipment.
Background
With the rapid development of the infrastructure of China, the prefabrication of the components of expressways and bridges is more and more common, the production scale of prefabricated components is increased, large-scale and ultra-large-scale prefabricated beam fields are developed continuously, and the key for realizing the efficient turnover of resource equipment of the whole beam field and the efficient production of beams is how to realize the management of beam-making pedestals and the real-time monitoring of the service states of the pedestals.
The traditional precast beam construction adopts a 'construction area fixing and construction process circulating' prefabricating mode on a fixed pedestal, namely a series of processes such as reinforcement binding, formwork erection, concrete pouring, formwork removal, spraying maintenance, prestress tensioning, grouting and the like are carried out in the same construction area (on the fixed pedestal). The use state of the pedestal is recorded by a manual method, and the recording method has low efficiency, poor timeliness and is not intuitive.
The Chinese patent with publication number CN109523182A and name of beam yard production management method, platform, computer equipment and storage medium provides a method for recording the use state of the pedestal by mobile terminal information input and real-time display of a background server, but the information input can be carried out after the use state of the pedestal is judged manually, the real-time performance is greatly influenced by operators, and the intelligentization level is not high.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method and a system for identifying the state of a beam yard pedestal by combining image identification and intelligent equipment, which can monitor the use state of the beam yard pedestal in real time, efficiently and intelligently, reduce the workload of beam yard operators and improve the intelligent level of the beam yard.
In order to achieve the above object, the present invention provides a method for recognizing a beam field pedestal state by combining image recognition and intelligent equipment, comprising the following steps:
acquiring video monitoring data of an existing beam field pedestal;
training a beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data;
periodically judging whether the beam yard intelligent equipment returns operation information, if so, outputting the current use state of the beam yard pedestal, and if not, identifying the beam yard pedestal by using a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal;
the current use state of the beam field pedestal is transmitted into a BIM beam field pedestal management model, and the BIM beam field pedestal management model displays the use state of each pedestal of the current beam field in real time.
On the basis of the technical scheme, the using state comprises an idle state, a beam manufacturing state and a maintenance state.
On the basis of the technical scheme, the beam field pedestal is identified by the beam field pedestal state classifier to obtain the current use state of the beam field pedestal, and the method comprises the following specific steps of:
s301: recognizing the beam field pedestal by adopting a beam field pedestal state classifier to obtain the use state of the beam field pedestal;
s302: and (3) checking the current use state of the obtained beam field pedestal:
if the service state obtained last time is identified as an idle state, judging whether the service state obtained last time is an idle state or a maintenance state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state;
if the service state obtained by recognition is the beam making state, judging whether the last obtained state is the beam making state or the idle state, if so, checking to pass, outputting the service state of the beam field pedestal obtained this time as the current service state of the beam field pedestal, and if not, judging that the current state of the beam field pedestal is the last obtained state;
if the service state obtained last time is identified as the maintenance state, judging whether the service state obtained last time is the maintenance state or the beam manufacturing state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state.
On the basis of the technical scheme, based on the acquired beam field pedestal video monitoring data, the beam field pedestal state classifier is trained, and the concrete steps comprise:
obtaining partial images of the beam field pedestal video monitoring data, wherein the obtained images comprise each using state of the beam field pedestal;
manually marking the use state of the beam field pedestal in each image;
creating a data set, and storing each image after being labeled as a subset into the data set;
and training the beam yard pedestal state classifier by using the data set so that the beam yard pedestal state classifier is provided with the capability of identifying the using state of the beam yard pedestal.
On the basis of the technical scheme, the beam field pedestal state classifier is based on a convolutional neural network model.
The invention provides a beam field pedestal state recognition system combining image recognition and intelligent equipment, which comprises:
the acquisition module is used for acquiring the video monitoring data of the existing beam field pedestal;
the training module is used for training the beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data;
the judging module is used for periodically judging whether the beam yard intelligent equipment transmits back operation information, if so, outputting the current use state of the beam yard pedestal, and if not, identifying the beam yard pedestal by using a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal;
And the transmission module is used for transmitting the current use state of the beam field pedestal into a BIM beam field pedestal management model, and the BIM beam field pedestal management model displays the use state of each pedestal of the current beam field in real time.
On the basis of the technical scheme, the using state comprises an idle state, a beam manufacturing state and a maintenance state.
On the basis of the technical scheme, adopt roof beam field pedestal state classifier to discern the roof beam field pedestal, obtain the current user state of roof beam field pedestal, concrete process includes:
recognizing the beam field pedestal by adopting a beam field pedestal state classifier to obtain the use state of the beam field pedestal;
and (3) checking the current use state of the obtained beam field pedestal:
if the service state obtained last time is identified as an idle state, judging whether the service state obtained last time is an idle state or a maintenance state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state;
if the service state obtained by recognition is the beam making state, judging whether the last obtained state is the beam making state or the idle state, if so, checking to pass, outputting the service state of the beam field pedestal obtained this time as the current service state of the beam field pedestal, and if not, judging that the current state of the beam field pedestal is the last obtained state;
If the service state obtained last time is identified as the maintenance state, judging whether the service state obtained last time is the maintenance state or the beam manufacturing state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state.
On the basis of the technical scheme, based on the acquired beam field pedestal video monitoring data, the beam field pedestal state classifier is trained, and the specific process comprises the following steps:
obtaining partial images of the beam field pedestal video monitoring data, wherein the obtained images comprise each using state of the beam field pedestal;
manually marking the use state of the beam field pedestal in each image;
creating a data set, and storing each image after being labeled as a subset into the data set;
and training the beam yard pedestal state classifier by using the data set so that the beam yard pedestal state classifier is provided with the capability of identifying the using state of the beam yard pedestal.
On the basis of the technical scheme, the beam field pedestal state classifier is based on a convolutional neural network model.
Compared with the prior art, the invention has the advantages that: adopt the mode that image recognition and smart machine combined together, if the operation information that passes back through smart machine can discern the state of roof beam field pedestal, then the current user state of direct output roof beam field pedestal, otherwise, then discern the roof beam field pedestal user state through the roof beam field pedestal state classifier that the training was accomplished, obtain the current user state of roof beam field pedestal, then according to the current user state of roof beam field pedestal, accomplish the automatic of roof beam field pedestal user state and type, and the user state of each pedestal of current roof beam field is shown in BIM roof beam field pedestal management model real-time, thereby in real time, high efficiency, intelligent control roof beam field pedestal user state, reduce roof beam field operation personnel work load, promote the intelligent level in roof beam field.
Drawings
Fig. 1 is a flowchart of a method for recognizing a state of a beam field pedestal by combining image recognition and an intelligent device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method for recognizing the state of a beam yard pedestal by combining image recognition and intelligent equipment, which is characterized in that when the state of the beam yard pedestal cannot be recognized through operation information returned by the intelligent equipment, the using state of the beam yard pedestal is recognized through a trained beam yard pedestal state classifier, and the automatic recording of the using state is completed, so that the using state of the beam yard pedestal is monitored in real time, efficiently and intelligently. The embodiment of the invention correspondingly provides a beam field pedestal state identification system combining image identification and intelligent equipment.
The present invention will be described in further detail with reference to the accompanying drawings and examples. As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computers, usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Referring to fig. 1, a method for recognizing a state of a beam field pedestal by combining image recognition and an intelligent device according to an embodiment of the present invention includes the following steps:
s1: and acquiring the video monitoring data of the existing beam field pedestal. At current beam yard job site, for making things convenient for daily management, all can install the camera and monitor the beam yard pedestal, so the video monitoring data of beam yard pedestal can carry out the record to the user state of beam yard pedestal.
S2: and training the beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data. The beam field pedestal state classifier in the embodiment of the invention is based on a convolutional neural network model, and is trained by using the video monitoring data of the beam field pedestal, so that the beam field pedestal state classifier has the capability of identifying the using state of the beam field pedestal.
In the embodiment of the invention, based on the acquired video monitoring data of the beam field pedestal, the state classifier of the beam field pedestal is trained, and the method specifically comprises the following steps:
s201: acquiring a video monitoring data partial image of the beam field pedestal, wherein the acquired image comprises each use state of the beam field pedestal;
s202: and manually marking the use state of the beam field pedestal in each image. The beam field pedestal video monitoring data is video data, each picture of the video data contains a beam field pedestal, and the marking of the using state of the beam field pedestal in each image is carried out in a manual marking mode.
S203: and creating a data set, and storing each image after being labeled as a subset into the data set.
S204: and training the beam yard pedestal state classifier by using the data set so that the beam yard pedestal state classifier is provided with the capability of identifying the using state of the beam yard pedestal.
In the embodiment of the invention, the using state comprises an idle state, a beam manufacturing state and a maintenance state. The idle state means that nothing is placed on the system beam pedestal. The beam-making state means that a template is placed on a beam-making pedestal, and the beam-making technological process comprises template engineering, reinforcing steel bar engineering, concrete engineering and the like. The maintenance state refers to the subsequent processes of the beam, such as spraying maintenance, pre-primary tensioning and the like, after the template on the beam manufacturing pedestal is removed.
S3: and periodically judging whether the beam field intelligent equipment transmits back operation information, if so, outputting the current use state of the beam field pedestal, and if not, identifying the beam field pedestal by adopting a beam field pedestal state classifier to obtain the current use state of the beam field pedestal.
At present, intelligent equipment is adopted for construction in part of processes of beam manufacturing sites, the current construction stage can be determined according to operation information returned by the intelligent equipment, and then the use state corresponding to the pedestal is judged. So when the operation information that can pass back through smart machine discerns the beam yard user state, then directly export the current user state of beam yard pedestal, otherwise, adopt beam yard pedestal state classifier to discern the beam yard pedestal to obtain the current user state of beam yard pedestal, guarantee can learn the user state of beam yard pedestal in real time, make things convenient for beam yard managers to formulate the production plan. The beam manufacturing needs a plurality of processes, the intelligent equipment in the embodiment of the invention can be mechanical equipment used in a certain process, the traditional mechanical equipment does not send information outwards, and the existing intelligent equipment needs to transmit the operating beam, the set operation parameters and the like back to the information platform during operation, so that the process can be determined by means of the information, and the current use state of the beam yard pedestal can be determined by the process.
Because the precast beam is manufactured in a strict manufacturing sequence, the using state of the beam field pedestal only circulates among the idle state, the beam manufacturing state and the maintenance state in sequence, and on the basis, the recognition result of the beam field pedestal state classifier can be verified. Specifically, in the embodiment of the present invention, a beam field pedestal state classifier is adopted to identify the beam field pedestal to obtain the current use state of the beam field pedestal, and the specific steps include:
s301: recognizing the beam field pedestal by adopting a beam field pedestal state classifier to obtain the use state of the beam field pedestal;
s302: and (3) checking the current use state of the obtained beam field pedestal:
if the service state obtained last time is identified as an idle state, judging whether the service state obtained last time is an idle state or a maintenance state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state;
if the service state obtained by recognition is the beam making state, judging whether the last obtained state is the beam making state or the idle state, if so, checking to pass, outputting the service state of the beam field pedestal obtained this time as the current service state of the beam field pedestal, and if not, judging that the current state of the beam field pedestal is the last obtained state;
If the service state obtained last time is identified as the maintenance state, judging whether the service state obtained last time is the maintenance state or the beam manufacturing state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state.
S4: the current using state of the beam field pedestal is transmitted into a Building Information Model (BIM) beam field pedestal management model, and the BIM beam field pedestal management model displays the using state of each pedestal of the current beam field in real time, so that the production state of the beam field is visually displayed, and a decision basis is provided for production management of the beam field.
The method for recognizing the state of the beam yard pedestal by combining the image recognition and the intelligent equipment adopts a mode of combining the image recognition and the intelligent equipment, directly outputs the current use state of the beam yard pedestal if the state of the beam yard pedestal can be recognized through operation information returned by the intelligent equipment, otherwise recognizes the use state of the beam yard pedestal through a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal, then completes the automatic input of the use state of the beam yard pedestal according to the current use state of the beam yard pedestal, and displays the current use state of each pedestal of the beam yard in real time in a BIM beam yard pedestal management model, so that the use state of the beam yard pedestal is monitored efficiently and intelligently in real time, the workload of beam yard operators is reduced, and the intelligent level of the beam yard is improved.
The beam yard pedestal state recognition system combining image recognition and intelligent equipment comprises an acquisition module, a training module, a judgment module and a transmission module. The acquisition module is used for acquiring the video monitoring data of the existing beam field pedestal; the training module is used for training the beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data; the judging module is used for periodically judging whether the beam yard intelligent equipment transmits back operation information, if so, outputting the current use state of the beam yard pedestal, and if not, identifying the beam yard pedestal by using a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal; the transmission module is used for transmitting the current use state of the beam field pedestal into a BIM beam field pedestal management model, and the BIM beam field pedestal management model displays the use state of each pedestal of the current beam field in real time.
In the embodiment of the invention, the using state comprises an idle state, a beam manufacturing state and a maintenance state. In the embodiment of the invention, a beam field pedestal state classifier is adopted to identify the beam field pedestal to obtain the current use state of the beam field pedestal, and the specific process comprises the following steps:
recognizing the beam field pedestal by adopting a beam field pedestal state classifier to obtain the use state of the beam field pedestal;
And (3) checking the current use state of the obtained beam field pedestal:
if the service state obtained last time is identified as an idle state, judging whether the service state obtained last time is an idle state or a maintenance state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state; (ii) a
If the service state obtained by recognition is the beam making state, judging whether the last obtained state is the beam making state or the idle state, if so, checking to pass, outputting the service state of the beam field pedestal obtained this time as the current service state of the beam field pedestal, and if not, judging that the current state of the beam field pedestal is the last obtained state; (ii) a
If the service state obtained is identified as the maintenance state, judging whether the last obtained state is the maintenance state or the beam manufacturing state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state; .
In the embodiment of the invention, based on the acquired video monitoring data of the beam field pedestal, the state classifier of the beam field pedestal is trained, and the specific process comprises the following steps:
Obtaining partial images of the beam field pedestal video monitoring data, wherein the obtained images comprise each using state of the beam field pedestal;
manually marking the use state of the beam field pedestal in each image;
creating a data set, and storing each image after being labeled as a subset into the data set;
and training the beam yard pedestal state classifier by using the data set so that the beam yard pedestal state classifier is provided with the capability of identifying the using state of the beam yard pedestal. The beam field pedestal state classifier is based on a convolutional neural network model.
The beam yard pedestal state recognition system combining image recognition and intelligent equipment adopts a mode of combining image recognition and intelligent equipment, if the state of a beam yard pedestal can be recognized through operation information returned by the intelligent equipment, the current use state of the beam yard pedestal is directly output, otherwise, the use state of the beam yard pedestal is recognized through a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal, then automatic input of the use state of the beam yard pedestal is completed according to the current use state of the beam yard pedestal, and the use state of each pedestal of the current beam yard is displayed in a BIM beam yard pedestal management model in real time, so that the use state of the beam yard pedestal is monitored efficiently and intelligently in real time, the workload of beam yard operators is reduced, and the intelligent level of a beam yard is improved.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (10)
1. A method for recognizing the state of a beam field pedestal by combining image recognition and intelligent equipment is characterized by comprising the following steps of:
acquiring video monitoring data of an existing beam field pedestal;
training a beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data;
periodically judging whether the beam yard intelligent equipment returns operation information, if so, outputting the current use state of the beam yard pedestal, and if not, identifying the beam yard pedestal by using a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal;
The current use state of the beam field pedestal is transmitted into a BIM beam field pedestal management model, and the BIM beam field pedestal management model displays the use state of each pedestal of the current beam field in real time.
2. The method for recognizing the state of the beam field pedestal by combining the image recognition with the intelligent equipment as claimed in claim 1, wherein the method comprises the following steps: the using state comprises an idle state, a beam manufacturing state and a maintenance state.
3. The method for recognizing the state of the beam field pedestal by combining the image recognition with the intelligent equipment as claimed in claim 2, wherein the step of recognizing the beam field pedestal by using the beam field pedestal state classifier to obtain the current use state of the beam field pedestal comprises the following specific steps:
s301: recognizing the beam field pedestal by adopting a beam field pedestal state classifier to obtain the use state of the beam field pedestal;
s302: and (3) checking the current use state of the obtained beam field pedestal:
if the service state obtained last time is identified as an idle state, judging whether the service state obtained last time is an idle state or a maintenance state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state;
If the service state obtained by recognition is the beam making state, judging whether the last obtained state is the beam making state or the idle state, if so, checking to pass, outputting the service state of the beam field pedestal obtained this time as the current service state of the beam field pedestal, and if not, judging that the current state of the beam field pedestal is the last obtained state;
if the service state obtained last time is identified as the maintenance state, judging whether the service state obtained last time is the maintenance state or the beam manufacturing state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state.
4. The method for recognizing the state of the beam field pedestal by combining image recognition and intelligent equipment according to claim 1, wherein the training of the beam field pedestal state classifier is performed based on the acquired video monitoring data of the beam field pedestal, and the method comprises the following specific steps:
obtaining partial images of the beam field pedestal video monitoring data, wherein the obtained images comprise each using state of the beam field pedestal;
manually marking the use state of the beam field pedestal in each image;
Creating a data set, and storing each image after being labeled as a subset into the data set;
and training the beam yard pedestal state classifier by using the data set so that the beam yard pedestal state classifier is provided with the capability of identifying the using state of the beam yard pedestal.
5. The method for recognizing the state of the beam field pedestal by combining the image recognition with the intelligent equipment as claimed in claim 4, wherein the method comprises the following steps: the beam field pedestal state classifier is based on a convolutional neural network model.
6. The utility model provides a beam field pedestal state identification system that image recognition and smart machine combined which characterized in that includes:
the acquisition module is used for acquiring the video monitoring data of the existing beam field pedestal;
the training module is used for training the beam field pedestal state classifier based on the acquired beam field pedestal video monitoring data;
the judging module is used for periodically judging whether the beam yard intelligent equipment transmits back operation information, if so, outputting the current use state of the beam yard pedestal, and if not, identifying the beam yard pedestal by using a trained beam yard pedestal state classifier to obtain the current use state of the beam yard pedestal;
and the transmission module is used for transmitting the current use state of the beam field pedestal into a BIM beam field pedestal management model, and the BIM beam field pedestal management model displays the use state of each pedestal of the current beam field in real time.
7. The system for recognizing the state of the beam field pedestal by combining the image recognition with the intelligent device as claimed in claim 6, wherein: the using state comprises an idle state, a beam manufacturing state and a maintenance state.
8. The system for recognizing the state of the beam field pedestal by combining image recognition and intelligent equipment according to claim 7, wherein the beam field pedestal is recognized by a beam field pedestal state classifier to obtain the current use state of the beam field pedestal, and the specific process comprises the following steps:
recognizing the beam field pedestal by adopting a beam field pedestal state classifier to obtain the use state of the beam field pedestal;
and (3) checking the current use state of the obtained beam field pedestal:
if the service state obtained last time is identified as an idle state, judging whether the service state obtained last time is an idle state or a maintenance state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state;
if the service state obtained by recognition is the beam making state, judging whether the last obtained state is the beam making state or the idle state, if so, checking to pass, outputting the service state of the beam field pedestal obtained this time as the current service state of the beam field pedestal, and if not, judging that the current state of the beam field pedestal is the last obtained state;
If the service state obtained last time is identified as the maintenance state, judging whether the service state obtained last time is the maintenance state or the beam manufacturing state, if so, checking to pass, outputting the service state of the beam yard pedestal obtained this time as the current service state of the beam yard pedestal, and if not, judging that the current state of the beam yard pedestal is the last obtained state.
9. The system for recognizing the state of the beam field pedestal by combining image recognition and intelligent equipment according to claim 6, wherein the training of the beam field pedestal state classifier is performed based on the acquired video monitoring data of the beam field pedestal, and the specific process comprises the following steps:
obtaining partial images of the beam field pedestal video monitoring data, wherein the obtained images comprise each using state of the beam field pedestal;
manually marking the use state of the beam field pedestal in each image;
creating a data set, and storing each image after being labeled as a subset into the data set;
and training the beam yard pedestal state classifier by using the data set so that the beam yard pedestal state classifier is provided with the capability of identifying the using state of the beam yard pedestal.
10. The system for recognizing the state of the beam field pedestal by combining the image recognition with the intelligent device as claimed in claim 9, wherein: the beam field pedestal state classifier is based on a convolutional neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600293.2A CN111860202A (en) | 2020-06-28 | 2020-06-28 | Beam yard pedestal state identification method and system combining image identification and intelligent equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600293.2A CN111860202A (en) | 2020-06-28 | 2020-06-28 | Beam yard pedestal state identification method and system combining image identification and intelligent equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860202A true CN111860202A (en) | 2020-10-30 |
Family
ID=72988731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010600293.2A Pending CN111860202A (en) | 2020-06-28 | 2020-06-28 | Beam yard pedestal state identification method and system combining image identification and intelligent equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860202A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116843844A (en) * | 2023-05-30 | 2023-10-03 | 中铁八局集团第一工程有限公司 | BIM-based beam field digital management system and method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105931029A (en) * | 2016-05-17 | 2016-09-07 | 中建三局第建设工程有限责任公司 | Production management system for girder fabrication yard based on BIM |
| JP2016207039A (en) * | 2015-04-24 | 2016-12-08 | 富士通フロンテック株式会社 | Image processing system, image processing device, image processing method, and image processing program |
| CN106446869A (en) * | 2016-10-20 | 2017-02-22 | 国家电网公司 | Automatic detection method for state of isolating switch based on image intelligent recognition algorithm |
| CN107480341A (en) * | 2017-07-21 | 2017-12-15 | 河海大学 | A kind of dam safety comprehensive method based on deep learning |
| CN108596148A (en) * | 2018-05-10 | 2018-09-28 | 华南理工大学 | A kind of construction worker's labour state analysis system based on computer vision and method |
| CN109523182A (en) * | 2018-11-27 | 2019-03-26 | 华规软件(上海)有限公司 | A kind of beam field production management method, platform, computer equipment and storage medium |
| CN110363852A (en) * | 2019-07-15 | 2019-10-22 | 中铁四局集团有限公司 | A kind of 3-dimensional digital Liang Chang, construction method, computer equipment and storage medium |
| CN110598633A (en) * | 2019-09-12 | 2019-12-20 | 杭州品茗安控信息技术股份有限公司 | Tumble behavior identification method, device and system |
| CN110658790A (en) * | 2019-09-17 | 2020-01-07 | 广州市微柏软件股份有限公司 | Precast beam production management system based on three-dimensional visual process management |
| US20200098103A1 (en) * | 2018-09-21 | 2020-03-26 | Chongqing Construction Engineering Group Corporation Limited | High-precision Intelligent Detection Method For Bridge Diseases Based On Spatial Position |
| CN111272135A (en) * | 2020-02-13 | 2020-06-12 | 东南大学 | Automatic linear measurement and control method for continuous beam bridge prefabrication and assembly construction |
-
2020
- 2020-06-28 CN CN202010600293.2A patent/CN111860202A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016207039A (en) * | 2015-04-24 | 2016-12-08 | 富士通フロンテック株式会社 | Image processing system, image processing device, image processing method, and image processing program |
| CN105931029A (en) * | 2016-05-17 | 2016-09-07 | 中建三局第建设工程有限责任公司 | Production management system for girder fabrication yard based on BIM |
| CN106446869A (en) * | 2016-10-20 | 2017-02-22 | 国家电网公司 | Automatic detection method for state of isolating switch based on image intelligent recognition algorithm |
| CN107480341A (en) * | 2017-07-21 | 2017-12-15 | 河海大学 | A kind of dam safety comprehensive method based on deep learning |
| CN108596148A (en) * | 2018-05-10 | 2018-09-28 | 华南理工大学 | A kind of construction worker's labour state analysis system based on computer vision and method |
| US20200098103A1 (en) * | 2018-09-21 | 2020-03-26 | Chongqing Construction Engineering Group Corporation Limited | High-precision Intelligent Detection Method For Bridge Diseases Based On Spatial Position |
| CN109523182A (en) * | 2018-11-27 | 2019-03-26 | 华规软件(上海)有限公司 | A kind of beam field production management method, platform, computer equipment and storage medium |
| CN110363852A (en) * | 2019-07-15 | 2019-10-22 | 中铁四局集团有限公司 | A kind of 3-dimensional digital Liang Chang, construction method, computer equipment and storage medium |
| CN110598633A (en) * | 2019-09-12 | 2019-12-20 | 杭州品茗安控信息技术股份有限公司 | Tumble behavior identification method, device and system |
| CN110658790A (en) * | 2019-09-17 | 2020-01-07 | 广州市微柏软件股份有限公司 | Precast beam production management system based on three-dimensional visual process management |
| CN111272135A (en) * | 2020-02-13 | 2020-06-12 | 东南大学 | Automatic linear measurement and control method for continuous beam bridge prefabrication and assembly construction |
Non-Patent Citations (4)
| Title |
|---|
| 张迎松等: "深中通道BIM技术在预制梁场的成套解决方案研究与实践", 《土木建筑工程信息技术》, vol. 12, no. 2, pages 55 - 61 * |
| 李俊男: "基于BIM的版本协同及生命周期维护研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 6, pages 038 - 113 * |
| 李俊男: "基于BIM的版本协同及生命周期维护研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》, vol. 1, no. 6, pages 038 - 113 * |
| 陈林等: "《"互联网+"智慧校园技术与工程实施》", vol. 01, 电子科技大学出版社, pages: 75 - 80 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116843844A (en) * | 2023-05-30 | 2023-10-03 | 中铁八局集团第一工程有限公司 | BIM-based beam field digital management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401765B (en) | Engineering progress supervision system based on big data | |
| CN108763550B (en) | Blast furnace big data application system | |
| CN110216789B (en) | Intelligent control system of bridge segment prefabrication field | |
| CN110216788B (en) | Intelligent control method for bridge segment prefabricating field | |
| CN103823458A (en) | Remote diagnosis device, method and system for equipment | |
| CN109299908A (en) | A kind of remote visualization assistance system | |
| CN111062504A (en) | AR technology-based intelligent power distribution station operation and maintenance system and method | |
| CN111046075A (en) | Project supervision informatization construction and management method and device | |
| CN114326625B (en) | Monitoring system and method for potential safety risk in power grid infrastructure construction | |
| CN104966140B (en) | The mobile engineer station of power grid work compound | |
| Parusheva | Digitalization and digital transformation in construction-benefits and challenges | |
| CN111369220A (en) | Teacher's cloud platform is built to wisdom | |
| CN108833827A (en) | monitoring method and device | |
| CN110717736A (en) | Construction progress intelligent tracking method and system for building | |
| CN115809785A (en) | Wisdom building site management system | |
| CN115494802A (en) | Flow operation multi-level safety digital intelligent monitoring system | |
| CN103136634A (en) | Region certified property intelligent task management system | |
| CN111125235A (en) | Production control method | |
| CN111860202A (en) | Beam yard pedestal state identification method and system combining image identification and intelligent equipment | |
| CN104023205A (en) | Intelligent security monitoring system | |
| CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
| CN110348145B (en) | Construction method for building tunnel based on BIM technology | |
| CN105321225A (en) | Management instrument for installation and maintenance of engineering machinery and application of management instrument | |
| CN112926401A (en) | Transmission line hardware corrosion detection method and system | |
| CN116843844B (en) | BIM-based beam field digital management system and method |
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 |