CN116645530A - Construction detection method, device, equipment and storage medium based on image comparison - Google Patents
Construction detection method, device, equipment and storage medium based on image comparison Download PDFInfo
- Publication number
- CN116645530A CN116645530A CN202310446246.0A CN202310446246A CN116645530A CN 116645530 A CN116645530 A CN 116645530A CN 202310446246 A CN202310446246 A CN 202310446246A CN 116645530 A CN116645530 A CN 116645530A
- Authority
- CN
- China
- Prior art keywords
- scene
- construction
- image
- acquiring
- data
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 239
- 238000001514 detection method Methods 0.000 title claims abstract description 132
- 230000002159 abnormal effect Effects 0.000 claims abstract description 93
- 238000000034 method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 238000007689 inspection Methods 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 5
- 238000009435 building construction Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of construction monitoring, in particular to a construction detection method, a device, equipment and a storage medium based on image comparison, wherein the construction detection method based on the image comparison comprises the following steps: acquiring a construction detection image, and acquiring corresponding construction scene data from the construction detection image; acquiring a scene type record according to the construction scene data, and acquiring a corresponding abnormal recognition model according to the scene type record; acquiring a reference image to be compared from the abnormal recognition model, and inputting the construction detection image into the abnormal recognition model; and triggering a corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared. The application has the effect of improving the accuracy of the image recognition detection of the construction site.
Description
Technical Field
The application relates to the technical field of construction monitoring, in particular to a construction detection method, device and equipment based on image comparison and a storage medium.
Background
Currently, in the process of construction projects, in order to ensure the quality and progress of construction, relevant departments or units perform corresponding monitoring and management in the process of construction.
Along with the continuous development of informatization, in the existing construction detection process, related informatization technology is also used for monitoring the construction site, including safety monitoring, quality monitoring, progress monitoring and the like, so as to improve the monitoring efficiency and accuracy.
The prior art solutions described above have the following drawbacks:
in the above-mentioned monitoring of a construction site by using informatization, a technique using image recognition is included, and the condition of the construction site is judged based on the photographed image of the construction site, however, in the recognition process in some abnormal scenes, erroneous recognition is easily caused, and the accuracy of detection is affected, so there is room for improvement.
Disclosure of Invention
In order to improve accuracy in construction site image identification detection, the application provides a construction detection method, device, equipment and storage medium based on image comparison.
The first object of the present application is achieved by the following technical solutions:
the construction detection method based on image comparison comprises the following steps:
acquiring a construction detection image, and acquiring corresponding construction scene data from the construction detection image;
acquiring a scene type record according to the construction scene data, and acquiring a corresponding abnormal recognition model according to the scene type record;
acquiring a reference image to be compared from the abnormal recognition model, and inputting the construction detection image into the abnormal recognition model;
and triggering a corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared.
By adopting the technical scheme, when the construction site is detected through the image recognition technology, the construction scene data is positioned first, and then the scene type record in the current construction scene is judged according to the construction scene data, so that the corresponding abnormal recognition model can be screened out, the construction site can be detected by utilizing the abnormal recognition model obtained by screening, the comparison result of the reference image to be compared with the construction detection image is more consistent with the actual condition of the construction site, the accuracy of the construction detection result triggered according to the comparison result is improved, and the problem of false recognition caused during detection in the abnormal scene is greatly solved.
The present application may be further configured in a preferred example to: the construction detection image acquisition step comprises the steps of acquiring corresponding construction scene data from the construction detection image, and specifically comprises the following steps:
acquiring a shooting equipment identifier according to the construction detection image, and acquiring equipment rotation time sequence data when the construction detection image is shot according to the shooting equipment identifier;
acquiring an associated equipment identifier associated with the shooting equipment identifier according to the equipment rotation time sequence data;
and acquiring the construction scene data according to the association relation between the shooting equipment identifier and the association equipment identifier.
By adopting the technical scheme, because the imaging equipment installed on the construction site can periodically rotate according to the preset program, and then the image of the construction site is continuously acquired in the rotation range of the imaging device, the position of the camera corresponding to the shooting equipment identifier, which is shot at the moment, can be acquired according to the equipment rotation time sequence data, and the corresponding construction scene data can be positioned by combining pictures obtained by shooting other associated equipment which are shot at the position at the same time, so that the construction scene data can be obtained rapidly and accurately, and the detection accuracy is improved.
The present application may be further configured in a preferred example to: the method for training the anomaly identification model comprises the following steps:
acquiring reference scene data, and acquiring scene types and scene type data corresponding to each scene type according to the reference scene data;
and acquiring a historical abnormal image corresponding to each scene type data, and training the historical abnormal image to obtain the abnormal recognition model corresponding to each scene type data in each reference scene.
Through adopting above-mentioned technical scheme, through obtaining corresponding benchmark scene data in advance based on this building construction project to the split obtains the scene type that every benchmark scene data corresponds, and the scene type data that every scene type corresponds, thereby can be convenient for carry out classification effectively to history abnormal image, and then richened the type of the unusual recognition model that obtains, further promoted the degree of accuracy of detection.
The present application may be further configured in a preferred example to: the method for acquiring the scene type record according to the construction scene data and acquiring the corresponding abnormal recognition model according to the scene type record specifically comprises the following steps:
acquiring scene initial information, and comparing the construction scene data with the scene initial information to obtain a comparison result;
and acquiring a difference distance value according to the comparison result, if the difference distance value is larger than a preset value, generating an abnormal matching message, and acquiring the scene type record according to the abnormal matching message.
Through adopting above-mentioned technical scheme, obtain the difference distance value through the calculation, can in time change corresponding matching standard when the scene of same construction position changes to promote the accuracy of obtaining the scene kind record.
The present application may be further configured in a preferred example to: the step of obtaining a difference distance value according to the comparison result, if the difference distance value is greater than a preset value, generating an abnormal matching message, and obtaining the scene type record according to the abnormal matching message, wherein the method specifically comprises the following steps:
matching corresponding reference scene data according to the construction scene data to serve as scene data to be compared, and acquiring scene characteristics to be compared corresponding to each scene type data according to the scene data to be compared;
and acquiring scene field characteristics of the construction scene data, and generating abnormal matching data according to the scene field characteristics and the scene characteristics to be compared.
By adopting the technical scheme, the construction scene data is utilized to match the corresponding reference scene data, so that the corresponding scene characteristics to be compared can be accurately matched, and the abnormal matching data can be accurately generated.
The second object of the present application is achieved by the following technical solutions:
a construction detection device based on image comparison, the construction detection device based on image comparison comprising:
the scene acquisition module is used for acquiring a construction detection image and acquiring corresponding construction scene data from the construction detection image;
the model acquisition module is used for acquiring a scene type record according to the construction scene data and acquiring a corresponding abnormal recognition model according to the scene type record;
the model identification module is used for acquiring a reference image to be compared from the abnormal identification model and inputting the construction detection image into the abnormal identification model;
and the detection comparison module is used for triggering a corresponding construction detection result according to the construction detection image and the comparison result of the reference image to be compared.
By adopting the technical scheme, when the construction site is detected through the image recognition technology, the construction scene data is positioned first, and then the scene type record in the current construction scene is judged according to the construction scene data, so that the corresponding abnormal recognition model can be screened out, the construction site can be detected by utilizing the abnormal recognition model obtained by screening, the comparison result of the reference image to be compared with the construction detection image is more consistent with the actual condition of the construction site, the accuracy of the construction detection result triggered according to the comparison result is improved, and the problem of false recognition caused during detection in the abnormal scene is greatly solved.
The third object of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above-described image alignment-based construction detection method when the computer program is executed.
The fourth object of the present application is achieved by the following technical solutions:
a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above-described image alignment-based construction detection method.
In summary, the present application includes at least one of the following beneficial technical effects:
1. when the construction site is detected by the image recognition technology, the construction scene data is positioned first, and then the scene type record in the current construction scene is judged according to the construction scene data, so that a corresponding abnormal recognition model can be screened out, the construction site can be detected by using the screened abnormal recognition model, the comparison result of the reference image to be compared with the construction detection image is more consistent with the actual condition of the construction site, the accuracy of the construction detection result triggered according to the comparison result is improved, and the problem of false recognition caused by detection in the abnormal scene is greatly solved;
2. because the camera equipment installed on the construction site can periodically rotate according to a preset program, and further the image of the construction site is continuously acquired within the rotation range of the camera equipment, the position of the camera corresponding to the camera equipment identification, which is shot at the moment, can be acquired according to the equipment rotation time sequence data, and the corresponding construction scene data can be positioned by combining pictures shot by other related equipment which are shot at the same time at the position, so that the construction scene data can be quickly and accurately acquired, and the detection accuracy is improved;
3. the corresponding reference scene data are obtained in advance based on the building construction project, the scene types corresponding to each reference scene data and the scene type data corresponding to each scene type are obtained in a splitting mode, so that historical abnormal images can be conveniently and effectively classified, the types of the obtained abnormal recognition models are enriched, and the detection accuracy is further improved.
Drawings
FIG. 1 is a flow chart of construction inspection based on image alignment in an embodiment of the application;
FIG. 2 is a flowchart showing the implementation of step S10 in the construction inspection based on image comparison according to an embodiment of the present application;
FIG. 3 is a flow chart of another implementation in image alignment based construction inspection in an embodiment of the present application;
FIG. 4 is a flowchart showing the implementation of step S30 in the construction inspection based on image comparison according to an embodiment of the present application;
FIG. 5 is a flowchart showing the implementation of step S32 in the construction inspection based on image comparison according to an embodiment of the present application;
FIG. 6 is a schematic block diagram of an image alignment-based construction inspection apparatus according to an embodiment of the present application;
fig. 7 is a schematic diagram of an apparatus in an embodiment of the application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
In an embodiment, as shown in fig. 1, the application discloses a construction detection method based on image comparison, which specifically comprises the following steps:
s10: and acquiring a construction detection image, and acquiring corresponding construction scene data from the construction detection image.
In the present embodiment, the construction detection image refers to an image of a construction site captured by being mounted to a construction site monitoring and photographing apparatus. The construction scene data is data of actual conditions of the construction site position corresponding to the construction detection image.
Specifically, when the construction of the building is started, each monitoring shooting device is installed on the construction site, and shooting and monitoring are carried out on the construction site in real time, so that a construction detection image is obtained.
Further, construction scene data is generated according to the actual situation of the position corresponding to the construction detection image.
S20: and acquiring a scene type record according to the construction scene data, and acquiring a corresponding abnormal recognition model according to the scene type record.
In the present embodiment, the scene type record refers to data of different types of situations in the current construction site. The abnormality recognition model is a model for recognizing whether an abnormal event occurs at a construction site based on the current actual situation.
Specifically, when construction scene data is acquired, a specific condition at the position of the construction site is judged according to the construction scene data, and an abnormality recognition model for recognizing whether an abnormality occurs in the specific condition of the site is acquired according to the specific condition. For example, for an access control system of a construction site, in a conventional use process, the access control system is used for identifying the face condition of a constructor who has registered and records, if other personnel go to visit and pass through the access control system, it is judged that a visitor visits through construction scene data, that is, the scene type is recorded as the visitor visits, the abnormality identification model can be used for judging whether the visitor has clothing or the like for wearing a protection device according to specifications and identifying the visitor, or whether abnormality occurs to a visited route; or when judging whether the construction condition is constructed according to the corresponding process through image recognition, if abnormal weather occurs, namely the scene type is recorded as the abnormal weather, judging whether constructors have corresponding reinforcing and protecting measures and the like for the construction site or the ongoing construction structure aiming at the abnormal weather through an abnormal recognition model.
S30: and acquiring a reference image to be compared from the abnormal recognition model, and inputting the construction detection image into the abnormal recognition model.
Specifically, a standard image corresponding to the scene type record is obtained from the anomaly identification model and is used as a reference image to be compared, for example, a visitor visits, the reference image to be compared can be a judgment that a person correctly wears a protection device, clothes for identifying the visitor, and the like, and the construction detection image is input into the anomaly identification model to carry out construction detection.
S40: and triggering a corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared.
Specifically, image comparison and identification are carried out through the construction detection image and the reference image to be compared, if the comparison result is abnormal, for example, a visitor does not wear clothes for identifying the visitor according to the specification or carries out corresponding measures for abnormal weather according to the specification, the construction detection result is triggered, and intervention is timely carried out.
In this embodiment, when the construction site is detected by the image recognition technology, the construction scene data is located first, and then the scene type record in the current construction scene is judged according to the construction scene data, so that the corresponding abnormal recognition model can be screened out, the construction site can be detected by using the abnormal recognition model obtained by screening, the comparison result of the reference image to be compared with the construction detection image can be more identical with the actual condition of the construction site, the accuracy of the construction detection result triggered according to the comparison result is improved, and the problem of false recognition caused during detection in the abnormal scene is greatly improved.
In this embodiment, as shown in fig. 2, in step S10, a construction detection image is acquired, and corresponding construction scene data is acquired from the construction detection image, which specifically includes:
s11: and acquiring a shooting equipment identifier according to the construction detection image, and acquiring equipment rotation time sequence data when the construction detection image is shot according to the shooting equipment identifier.
In the present embodiment, the photographing apparatus identification refers to a unique identification of the image capturing apparatus that captured the construction detection image.
Specifically, after each image capturing apparatus is installed on a construction site, a corresponding unique identifier is set for each image capturing apparatus, and a period of horizontal rotation, for example, one of the image capturing apparatuses is set for each image capturing apparatus, which can horizontally rotate by 130 ° to capture an image, and 20 seconds are required to complete one period, every 20 seconds is set as one period. Further, when the construction detection image is acquired, the image capturing apparatus that captured the construction detection image is acquired and expressed as a capturing apparatus identification, and at the same time, when the construction detection image is acquired, apparatus rotation time series data of the image capturing apparatus, that is, a position within the image capturing apparatus rotation period, is acquired.
S12: and acquiring an associated equipment identifier associated with the shooting equipment identifier according to the equipment rotation time sequence data.
Specifically, since each image capturing apparatus may be circularly captured by horizontal rotation at the time of capturing, different image capturing apparatuses may capture the construction position corresponding to different construction detection images, and therefore, according to the apparatus rotation time sequence data at this time of capturing the apparatus identification, the image capturing apparatus capable of capturing the construction site corresponding to the picture in the construction detection image with the apparatus rotation time sequence data is acquired, and the identification thereof is used as the associated apparatus identification.
S13: and acquiring construction scene data according to the association relation between the shooting equipment identifier and the association equipment identifier.
Specifically, corresponding construction scene data is identified according to the photographed equipment identifier and the pictures photographed by the associated equipment identifier under the equipment rotation time sequence.
In one embodiment, as shown in FIG. 3, a method of training an anomaly identification model includes:
s201: acquiring reference scene data, and acquiring scene types and scene type data corresponding to each scene type according to the reference scene data.
In the present embodiment, the reference scene data is data of each position to be detected in the site of the building construction.
Specifically, when the construction project of the building construction begins, the corresponding scene to be detected is split according to the engineering design construction scheme of the project and is used as reference scene data.
Further, according to the reference scene data, scene types corresponding to the same or similar scenes as the reference scene data, and image data in each scene type, that is, scene type data, are acquired from a preset history database.
S202: and acquiring a historical abnormal image corresponding to each scene type data, and training the historical abnormal image to obtain an abnormal recognition model corresponding to each scene type data in each reference scene.
Specifically, in each scene type data, image data marked as abnormal is acquired as a history abnormal image, and class-by-class training is performed according to the history abnormal images of different scene types in different reference scenes, so as to obtain a corresponding abnormal dead class model.
In this embodiment, as shown in fig. 4, in step S30, that is, a scene type record is obtained according to construction scene data, and a corresponding anomaly identification model is obtained according to the scene type record, which specifically includes:
s31: and acquiring scene initial information, and comparing the construction scene data with the scene initial information to obtain a comparison result.
Specifically, the information of the current default construction scene at the construction site position corresponding to the construction scene data is obtained and used as scene initial information, further, after the scene initial information is obtained, the scene feature vector of the construction scene data and the initial scene feature vector of the scene initial information are extracted, and the scene feature vector and the initial scene feature vector are compared to obtain a corresponding comparison result.
S32: and acquiring a difference distance value according to the comparison result, if the difference distance value is larger than a preset value, generating an abnormal matching message, and acquiring a scene type record according to the abnormal matching message.
Specifically, the vector distance between the scene feature vector and the initial scene feature vector is calculated and used as a difference distance value, if the difference distance value is larger than a preset value, the current scene is changed, so that an abnormal matching message is generated, and a scene type record is acquired according to the abnormal matching message.
In one embodiment, as shown in fig. 5, in step S32, a difference distance value is obtained according to the comparison result, if the difference distance value is greater than a preset value, an abnormal matching message is generated, and a scene type record is obtained according to the abnormal matching message, which specifically includes:
s321: and matching corresponding reference scene data according to the construction scene data to serve as scene data to be compared, and acquiring the scene characteristics to be compared corresponding to each scene type data according to the scene data to be compared.
Specifically, according to the features extracted from the construction scene data, corresponding reference scene data is matched to serve as the scene data to be compared, and further, the features of each scene type data corresponding to the scene data to be compared are obtained to serve as the scene features to be compared.
S322: scene field characteristics of construction scene data are obtained, and abnormal matching data are generated according to the scene field characteristics and the scene characteristics to be compared.
Specifically, according to scene field features of the acquired construction scene data, abnormal matching data are generated according to the scene field features and the scene features to be compared.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
In an embodiment, a construction detection device based on image comparison is provided, and the construction detection device based on image comparison corresponds to the construction detection method based on image comparison in the embodiment one by one. As shown in fig. 6, the construction detection device based on image comparison includes a scene acquisition module, a model identification module, and a detection comparison module. The functional modules are described in detail as follows:
the scene acquisition module is used for acquiring a construction detection image and acquiring corresponding construction scene data from the construction detection image;
the model acquisition module is used for acquiring a scene type record according to the construction scene data and acquiring a corresponding abnormal recognition model according to the scene type record;
the model identification module is used for acquiring a reference image to be compared from the abnormal identification model and inputting a construction detection image into the abnormal identification model;
and the detection comparison module is used for triggering the corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared.
Optionally, the scene acquisition module includes:
the equipment positioning sub-module is used for acquiring a shooting equipment identifier according to the construction detection image and acquiring equipment rotation time sequence data when the construction detection image is shot according to the shooting equipment identifier;
the associated equipment acquisition sub-module is used for acquiring an associated equipment identifier associated with the shooting equipment identifier according to the equipment rotation time sequence data;
and the scene acquisition sub-module is used for acquiring construction scene data according to the association relation between the shooting equipment identifier and the association equipment identifier.
Optionally, the construction detection device based on image comparison includes:
the reference acquisition module is used for acquiring reference scene data, and acquiring scene types and scene type data corresponding to each scene type according to the reference scene data;
the model training module is used for acquiring a historical abnormal image corresponding to each scene type data, and training the historical abnormal image to obtain an abnormal recognition model corresponding to each scene type data in each reference scene.
Optionally, the model identification module includes:
the reference acquisition sub-module is used for acquiring scene initial information, and comparing construction scene data with the scene initial information to obtain a comparison result;
the record matching sub-module is used for acquiring a difference distance value according to the comparison result, generating an abnormal matching message if the difference distance value is larger than a preset value, and acquiring a scene type record according to the abnormal matching message.
Optionally, the record matching submodule includes:
the feature acquisition unit is used for matching corresponding reference scene data according to the construction scene data to serve as scene data to be compared, and acquiring scene features to be compared corresponding to each scene type data according to the scene data to be compared;
the abnormal matching unit is used for acquiring scene field characteristics of the construction scene data and generating abnormal matching data according to the scene field characteristics and the scene characteristics to be compared.
The specific limitation of the construction detection device based on image comparison can be referred to as limitation of the construction detection method based on image comparison hereinabove, and will not be described herein. The above-mentioned various modules in the construction detection device based on image comparison may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a construction detection method based on image comparison.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring a construction detection image, and acquiring corresponding construction scene data from the construction detection image;
acquiring a scene type record according to construction scene data, and acquiring a corresponding abnormal recognition model according to the scene type record;
acquiring a reference image to be compared from the abnormal recognition model, and inputting a construction detection image into the abnormal recognition model;
and triggering a corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a construction detection image, and acquiring corresponding construction scene data from the construction detection image;
acquiring a scene type record according to construction scene data, and acquiring a corresponding abnormal recognition model according to the scene type record;
acquiring a reference image to be compared from the abnormal recognition model, and inputting a construction detection image into the abnormal recognition model;
and triggering a corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. The construction detection method based on image comparison is characterized by comprising the following steps of:
acquiring a construction detection image, and acquiring corresponding construction scene data from the construction detection image;
acquiring a scene type record according to the construction scene data, and acquiring a corresponding abnormal recognition model according to the scene type record;
acquiring a reference image to be compared from the abnormal recognition model, and inputting the construction detection image into the abnormal recognition model;
and triggering a corresponding construction detection result according to the comparison result of the construction detection image and the reference image to be compared.
2. The construction detection method based on image comparison according to claim 1, wherein the acquiring a construction detection image, acquiring corresponding construction scene data from the construction detection image, specifically comprises:
acquiring a shooting equipment identifier according to the construction detection image, and acquiring equipment rotation time sequence data when the construction detection image is shot according to the shooting equipment identifier;
acquiring an associated equipment identifier associated with the shooting equipment identifier according to the equipment rotation time sequence data;
and acquiring the construction scene data according to the association relation between the shooting equipment identifier and the association equipment identifier.
3. The image alignment-based construction detection method according to claim 1, wherein the method of training the anomaly identification model comprises:
acquiring reference scene data, and acquiring scene types and scene type data corresponding to each scene type according to the reference scene data;
and acquiring a historical abnormal image corresponding to each scene type data, and training the historical abnormal image to obtain the abnormal recognition model corresponding to each scene type data in each reference scene.
4. The construction detection method based on image comparison according to claim 3, wherein the obtaining a scene type record according to the construction scene data, and obtaining a corresponding anomaly identification model according to the scene type record, specifically comprises:
acquiring scene initial information, and comparing the construction scene data with the scene initial information to obtain a comparison result;
and acquiring a difference distance value according to the comparison result, if the difference distance value is larger than a preset value, generating an abnormal matching message, and acquiring the scene type record according to the abnormal matching message.
5. The construction detection method based on image comparison according to claim 1, wherein the obtaining a difference distance value according to the comparison result, if the difference distance value is greater than a preset value, generating an abnormal matching message, and obtaining the scene type record according to the abnormal matching message, specifically includes:
matching corresponding reference scene data according to the construction scene data to serve as scene data to be compared, and acquiring scene characteristics to be compared corresponding to each scene type data according to the scene data to be compared;
and acquiring scene field characteristics of the construction scene data, and generating abnormal matching data according to the scene field characteristics and the scene characteristics to be compared.
6. The utility model provides a construction detection device based on image comparison which characterized in that, construction detection device based on image comparison includes:
the scene acquisition module is used for acquiring a construction detection image and acquiring corresponding construction scene data from the construction detection image;
the model acquisition module is used for acquiring a scene type record according to the construction scene data and acquiring a corresponding abnormal recognition model according to the scene type record;
the model identification module is used for acquiring a reference image to be compared from the abnormal identification model and inputting the construction detection image into the abnormal identification model;
and the detection comparison module is used for triggering a corresponding construction detection result according to the construction detection image and the comparison result of the reference image to be compared.
7. The image alignment-based construction detection device according to claim 6, wherein the scene acquisition module includes:
the equipment positioning sub-module is used for acquiring a shooting equipment identifier according to the construction detection image and acquiring equipment rotation time sequence data when the construction detection image is shot according to the shooting equipment identifier;
the associated equipment acquisition sub-module is used for acquiring an associated equipment identifier associated with the shooting equipment identifier according to the equipment rotation time sequence data;
and the scene acquisition sub-module is used for acquiring the construction scene data according to the association relation between the shooting equipment identifier and the association equipment identifier.
8. The image-alignment-based construction detection device according to claim 6, wherein the image-alignment-based construction detection device comprises:
the reference acquisition module is used for acquiring reference scene data, and acquiring scene types and scene type data corresponding to each scene type according to the reference scene data;
the model training module is used for acquiring a historical abnormal image corresponding to each scene type data, and training the historical abnormal image to obtain the abnormal recognition model corresponding to each scene type data in each reference scene.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the image alignment based construction detection method according to any one of claims 1 to 5.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the image alignment-based construction detection method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446246.0A CN116645530A (en) | 2023-04-23 | 2023-04-23 | Construction detection method, device, equipment and storage medium based on image comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446246.0A CN116645530A (en) | 2023-04-23 | 2023-04-23 | Construction detection method, device, equipment and storage medium based on image comparison |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116645530A true CN116645530A (en) | 2023-08-25 |
Family
ID=87617802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310446246.0A Pending CN116645530A (en) | 2023-04-23 | 2023-04-23 | Construction detection method, device, equipment and storage medium based on image comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116645530A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117037075A (en) * | 2023-10-08 | 2023-11-10 | 深圳市金众工程检验检测有限公司 | Engineering detection method and system based on image processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889377A (en) * | 2019-11-28 | 2020-03-17 | 深圳市丰巢科技有限公司 | Method and device for identifying abnormality of advertising object, server device and storage medium |
| CN111199346A (en) * | 2019-12-30 | 2020-05-26 | 广东海外建设咨询有限公司 | Comprehensive management gallery supervision method and device, computer equipment and storage medium |
| CN113112480A (en) * | 2021-04-16 | 2021-07-13 | 北京文安智能技术股份有限公司 | Video scene change detection method, storage medium and electronic device |
| CN113642404A (en) * | 2021-07-13 | 2021-11-12 | 季华实验室 | Target identification detection association method, device, medium, and computer program product |
| CN113723184A (en) * | 2021-07-23 | 2021-11-30 | 广东电网有限责任公司广州供电局 | Scene recognition system, method and device based on intelligent gateway and intelligent gateway |
| CN115424405A (en) * | 2022-08-30 | 2022-12-02 | 广州瀚信通信科技股份有限公司 | Smoke and fire monitoring and alarming method, device, equipment and storage medium |
| CN115909219A (en) * | 2022-12-29 | 2023-04-04 | 深圳市诺龙技术股份有限公司 | Scene change detection method and system based on video analysis |
-
2023
- 2023-04-23 CN CN202310446246.0A patent/CN116645530A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889377A (en) * | 2019-11-28 | 2020-03-17 | 深圳市丰巢科技有限公司 | Method and device for identifying abnormality of advertising object, server device and storage medium |
| CN111199346A (en) * | 2019-12-30 | 2020-05-26 | 广东海外建设咨询有限公司 | Comprehensive management gallery supervision method and device, computer equipment and storage medium |
| CN113112480A (en) * | 2021-04-16 | 2021-07-13 | 北京文安智能技术股份有限公司 | Video scene change detection method, storage medium and electronic device |
| CN113642404A (en) * | 2021-07-13 | 2021-11-12 | 季华实验室 | Target identification detection association method, device, medium, and computer program product |
| CN113723184A (en) * | 2021-07-23 | 2021-11-30 | 广东电网有限责任公司广州供电局 | Scene recognition system, method and device based on intelligent gateway and intelligent gateway |
| CN115424405A (en) * | 2022-08-30 | 2022-12-02 | 广州瀚信通信科技股份有限公司 | Smoke and fire monitoring and alarming method, device, equipment and storage medium |
| CN115909219A (en) * | 2022-12-29 | 2023-04-04 | 深圳市诺龙技术股份有限公司 | Scene change detection method and system based on video analysis |
Non-Patent Citations (1)
| Title |
|---|
| 陈峰军;: "基于物联网的智慧施工视频联动管理***", 建筑施工, no. 11, pages 2009 - 2011 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117037075A (en) * | 2023-10-08 | 2023-11-10 | 深圳市金众工程检验检测有限公司 | Engineering detection method and system based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110781750A (en) | Dangerous person monitoring processing method and device, computer equipment and storage medium | |
| CN108985162A (en) | Object real-time tracking method, apparatus, computer equipment and storage medium | |
| CN109002786B (en) | Face detection method, face detection equipment and computer-readable storage medium | |
| CN111191532B (en) | Face recognition method and device based on construction area and computer equipment | |
| CN112364715B (en) | Nuclear power operation abnormity monitoring method and device, computer equipment and storage medium | |
| CN111339979B (en) | Image recognition method and image recognition device based on feature extraction | |
| CN112954315B (en) | Image focusing measurement method and system for security camera | |
| CN113095132B (en) | Neural network based gas field identification method, system, terminal and storage medium | |
| CN111259813B (en) | Face detection tracking method, device, computer equipment and storage medium | |
| CN116645530A (en) | Construction detection method, device, equipment and storage medium based on image comparison | |
| CN111325128A (en) | Illegal operation detection method and device, computer equipment and storage medium | |
| WO2020206900A1 (en) | Vehicle loss assessment method and apparatus, computer device and storage medium | |
| CN112464030B (en) | Suspicious person determination method and suspicious person determination device | |
| CN110909675A (en) | Method and device for identifying violation behaviors, computer equipment and storage medium | |
| CN111241938A (en) | Face recognition method and device based on image verification and computer equipment | |
| CN110610610A (en) | Vehicle access management method and device and storage medium | |
| CN116048124B (en) | Unmanned plane subway tunnel inspection method and device, computer equipment and storage medium | |
| CN111212280B (en) | Method and system for testing depth camera module, computer equipment and storage medium | |
| CN111353426A (en) | Abnormal behavior detection method and device | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN115187439A (en) | Comprehensive operation management method and system for intelligent park | |
| CN115346060A (en) | Picture abnormity identification method and device, electronic equipment and storage medium | |
| CN112580467A (en) | Video regression testing method and device, computer equipment and storage medium | |
| CN111582179A (en) | Monitoring video analysis method and device, computer equipment and storage medium | |
| CN109919017B (en) | Face recognition optimization method, device, computer equipment and storage medium |
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 |