CN117893779A - Method and system for realizing abnormality identification under building construction based on machine vision - Google Patents
Method and system for realizing abnormality identification under building construction based on machine vision Download PDFInfo
- Publication number
- CN117893779A CN117893779A CN202410082553.XA CN202410082553A CN117893779A CN 117893779 A CN117893779 A CN 117893779A CN 202410082553 A CN202410082553 A CN 202410082553A CN 117893779 A CN117893779 A CN 117893779A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- image data
- anomaly
- environment
- 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
- 238000009435 building construction Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000005856 abnormality Effects 0.000 title claims abstract description 43
- 238000010276 construction Methods 0.000 claims abstract description 47
- 230000002159 abnormal effect Effects 0.000 claims abstract description 44
- 238000012549 training Methods 0.000 claims abstract description 42
- 239000013598 vector Substances 0.000 claims abstract description 39
- 238000003709 image segmentation Methods 0.000 claims abstract description 15
- 238000002372 labelling Methods 0.000 claims abstract description 15
- 230000007613 environmental effect Effects 0.000 claims description 71
- 238000003860 storage Methods 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 11
- 238000011161 development Methods 0.000 claims description 8
- 230000018109 developmental process Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 13
- 230000015654 memory Effects 0.000 description 17
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000009430 construction management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000011496 digital image analysis Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the field of building construction, and provides a method and a system for identifying abnormality under building construction based on machine vision, wherein the method comprises the following steps: acquiring a site image set of a construction site, identifying image data and pre-labeling to obtain image marking data, denoising the marking data to obtain denoising image data, performing image enhancement processing to obtain enhanced image data, performing image segmentation on the enhanced image data to obtain segmented image data, dividing the segmented image data into a data training set, extracting image features, identifying feature vectors and calculating feature similarity, thereby constructing an anomaly identification model, performing environment parameter anomaly identification by using the trained model, extracting anomaly factors and calculating anomaly indexes, and generating an early warning signal to realize anomaly identification of the construction site. The invention can improve the abnormal recognition efficiency in the building construction.
Description
Technical Field
The invention relates to the field of building construction, in particular to a method and a system for identifying abnormality under building construction based on machine vision.
Background
Machine vision refers to the ability of a computer system to automatically analyze, identify, and understand objects, scenes, actions, etc. in an image or video by capturing the image or video data through a camera or other sensor and analyzing and understanding the data using techniques such as image processing, pattern recognition, etc.
At present, an anomaly identification method for realizing building construction is commonly used, which combines an image identification technology with a monitoring system of a building construction site to monitor various activities and objects in the construction process in real time, and the monitoring system can automatically analyze the image data and perform anomaly identification by using a deep learning algorithm, but in the building construction site, various types of anomaly conditions exist, such as: dangerous behavior, equipment faults and the like of field worker safety equipment are easy to reduce the recognition efficiency in a building construction field due to complex background interference or illumination change, so that a method and a system for realizing abnormal recognition under building construction based on machine vision are needed to improve the abnormal recognition efficiency in the building construction.
Disclosure of Invention
The invention provides a method and a system for realizing abnormality identification under building construction based on machine vision, and mainly aims to improve the abnormality identification efficiency in the building construction.
In order to achieve the above object, the machine vision-based method for identifying anomalies under construction comprises the following steps:
acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and pre-marking the image data to obtain image marking data;
image denoising is carried out on the image marking data to obtain denoised image data, image enhancement is carried out on the denoised image data to obtain enhanced image data, and image segmentation is carried out on the enhanced image data to obtain segmented image data;
dividing the segmented image data into a data training set, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity;
performing data training on the abnormal recognition model by using the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environmental parameters;
Performing anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
Optionally, the acquiring a field image set in a building construction site, and identifying image data corresponding to the field image set includes:
determining shooting equipment corresponding to the building construction site;
acquiring a site image set in a building construction site by using the shooting equipment;
storing the field image set into a preset cloud storage space;
performing data preprocessing on the data stored in the cloud storage space to obtain preprocessed data;
and identifying corresponding image data in the preprocessing data.
Optionally, the pre-labeling the image data to obtain image marking data includes:
performing data adjustment on the image data to obtain adjusted image data;
defining the annotation category corresponding to the adjusted image data;
based on the labeling category, performing data pre-labeling on the adjusted image data to obtain initial labeling image data;
And performing annotation correction on the initial image data to obtain image marking data.
Optionally, the image denoising the image marking data to obtain denoised image data includes:
importing the image marking data, and identifying a noise type corresponding to the image marking data;
based on the noise type, carrying out noise statistics on the image marking data to obtain noise statistics data;
and carrying out frequency domain denoising on the noise statistical data to obtain denoised image data.
Optionally, the dividing the segmented image data into a data training set, and extracting features of the segmented image data to obtain image features includes:
proportional division is carried out on the segmented image data to obtain a data training set corresponding to the segmented image data;
normalizing the data training set to obtain normalized data;
determining the feature type corresponding to the segmented image data;
and carrying out feature extraction on the segmented image data based on the feature type to obtain image features.
Optionally, the calculating, based on the feature vector, feature similarity corresponding to the segmented image data includes: dividing the feature vector into a first feature vector and a second feature vector;
Calculating the feature similarity corresponding to the image feature by using the following formula:
wherein CS represents feature similarity corresponding to the image feature, the value range is between [ -1,1], the closer the value is to 1, the more similar the value is, the closer the value is to-1, the more dissimilar the value is to-1, ai represents the corresponding ith element in the first feature vector, and Bi represents the corresponding ith element in the second feature vector.
Optionally, the deploying the tested anomaly identification model into an environment corresponding to the building construction site to obtain an environmental parameter includes:
determining a development environment corresponding to the building construction site;
based on the development environment, deploying a model service corresponding to the tested abnormal recognition model;
and carrying out environment recognition on the building construction site based on the model service to obtain environment parameters.
Optionally, the performing anomaly identification on the environmental parameter to obtain an environmental anomaly parameter includes:
identifying an environment parameter list corresponding to the environment parameters; determining a real-time value in the environment parameter list;
setting a threshold range corresponding to the real-time value;
and carrying out anomaly identification on the environmental parameters based on the threshold range to obtain environmental anomaly parameters.
Optionally, the calculating the environmental anomaly index corresponding to the environmental anomaly factor includes:
calculating an environmental anomaly index corresponding to the environmental anomaly factor by using the following formula:
wherein Z represents an environmental abnormality index corresponding to the environmental abnormality factor, fi represents an ith environmental abnormality factor, fj represents a jth environmental abnormality factor, n represents the number of environmental abnormality factors, and m represents the total number of environmental abnormality factors.
In order to solve the above problems, the present invention also provides a machine vision-based anomaly identification system for implementing building construction, the system comprising:
the image marking module is used for acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and performing data pre-marking on the image data to obtain image marking data;
the image segmentation module is used for carrying out image denoising on the image marking data to obtain denoised image data, carrying out image enhancement on the denoised image data to obtain enhanced image data, and carrying out image segmentation on the enhanced image data to obtain segmented image data;
the model construction module is used for dividing the segmented image data into a data training set, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity;
The environment parameter module is used for carrying out data training on the abnormal recognition model by utilizing the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environment parameters;
the index calculation module is used for carrying out anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
The invention can identify the progress situation of a construction site by acquiring the site image set in the construction site, identify the image data corresponding to the site image set, monitor and control the progress situation of the construction site in real time, improve the quality, ensure the safety, improve the efficiency and accumulate experience, and improve the construction quality and the efficiency. Therefore, the method and the system for identifying the abnormality under the construction based on the machine vision provided by the invention are used for improving the abnormality identification efficiency in the construction.
Drawings
Fig. 1 is a schematic flow chart of a method for identifying anomalies under building construction based on machine vision according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of an anomaly identification system under construction based on machine vision according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device for implementing an anomaly identification method under building construction based on machine vision according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a method for identifying abnormality under building construction based on machine vision. The execution subject of the machine vision-based method for identifying anomalies under construction includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the machine vision based abnormality identification method under construction may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a method for identifying anomalies under building construction based on machine vision according to an embodiment of the present invention is shown. In this embodiment, the method for identifying anomalies under building construction based on machine vision includes:
s1, acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and performing data pre-marking on the image data to obtain image marking data.
According to the invention, the on-site image set in the building construction site is acquired, the image data corresponding to the on-site image set is identified, the progress condition of the construction site can be monitored in real time, the real-time monitoring, the quality improvement, the safety guarantee, the efficiency improvement and the experience accumulation are facilitated, and the construction quality and the efficiency can be improved.
The field image set refers to a set containing images actually shot on the field; the image data refers to digitized information contained in an image, such as: pixel value, color value, brightness value, contrast, etc.
As one embodiment of the present invention, the acquiring a field image set in a construction site, and identifying image data corresponding to the field image set includes: determining shooting equipment corresponding to the building construction site; acquiring a site image set in a building construction site by using the shooting equipment; storing the field image set into a preset cloud storage space; performing data preprocessing on the data stored in the cloud storage space to obtain preprocessed data; and identifying corresponding image data in the preprocessing data.
Wherein, shooting equipment is used for shooting building construction site image, like: unmanned aerial vehicle, intelligent camera, intelligent monitoring camera, etc.; the preset cloud storage space refers to a cloud storage space which is set in advance and used for storing images of a construction site, for example: yun Pan, cloud servers, cloud storage services, etc.; the preprocessing data refers to processing the image data stored in the cloud storage space so as to improve the accuracy and usability of the subsequent image data.
Further, the photographing apparatus may be obtained through a machine learning algorithm implementation, such as: algorithms such as decision tree algorithm, random forest algorithm, neural network algorithm and the like; the preset cloud storage space may be obtained through a distributed storage system, for example: hadoop, ceph and other systems; the pre-processing data may be obtained by a data cleaning tool, such as: openfiner, trifacta Wrangler, pandas, etc.
The method and the device for marking the image data in the invention are used for pre-marking the image data to obtain the image marking data, can greatly simplify and accelerate the marking process, improve the consistency and the accuracy of marking, and provide better marking samples for the subsequent model training, thereby improving the efficiency and the quality of the whole data processing flow.
The image marking data refers to data obtained by marking or annotating the image data.
As an embodiment of the present invention, the pre-labeling the image data to obtain image marking data includes: performing data adjustment on the image data to obtain adjusted image data; defining the annotation category corresponding to the adjusted image data; based on the labeling category, performing data pre-labeling on the adjusted image data to obtain initial labeling image data; and performing annotation correction on the initial image data to obtain image marking data.
Wherein, the adjustment of the image data refers to a series of processing and operation on the original image so as to make the original image more suitable for marking and analysis; the marking category refers to dividing the adjusted image data into different categories or labels; the primary labeling of the image data refers to the primary labeling of the adjusted image data using an automated method or algorithm.
Further, the adjusted image data may be obtained by an image processing tool, such as: openCV, PIL, imageJ, etc.; the annotation class can be obtained by an annotation tool implementation, such as: labelImg, labelbox, rectLabel, etc.; the primary image data may be obtained by a target detection model implementation, such as: faster R-CNN.
S2, carrying out image denoising on the image marking data to obtain denoised image data, carrying out image enhancement on the denoised image data to obtain enhanced image data, and carrying out image segmentation on the enhanced image data to obtain segmented image data.
According to the image denoising method and device, the image marking data are subjected to image denoising to obtain denoised image data, so that the image quality can be improved, the image analysis and processing results are improved, the privacy of image information is protected, the data storage and transmission cost is reduced, and the image application effect and efficiency are improved.
The denoising image data refers to clear image data obtained by removing noise in an image.
As one embodiment of the present invention, the image denoising the image marking data to obtain denoised image data includes: importing the image marking data, and identifying a noise type corresponding to the image marking data; based on the noise type, carrying out noise statistics on the image marking data to obtain noise statistics data; and carrying out frequency domain denoising on the noise statistical data to obtain denoised image data.
The noise type refers to a noise type corresponding to the image marking data, for example: gaussian noise, salt and pepper noise, brightness noise, etc.; the noise statistics data refers to data obtained by performing noise statistics analysis on the image marking data, such as: noise standard deviation, noise distribution pattern, and the like.
Further, the noise type may be obtained by a digital image analysis tool implementation, such as: imageJ, MATLAB, etc.; the noise statistics may be obtained by a statistical distribution model implementation, such as: gaussian distribution model, poisson distribution model, etc.
The invention obtains the enhanced image data by carrying out image enhancement on the de-noised image data, can improve the image quality, enhance the visual effect and the enhancement characteristic, provide a better data base for the subsequent processing and facilitate the extraction and analysis of information.
Wherein, the enhanced image data refers to image data with enhanced image quality and specific characteristics, and optionally, the enhanced image data can be obtained through an image restoration algorithm, such as: least square method, total variation regularization, non-local mean value and the like.
According to the invention, the image segmentation is carried out on the enhanced image data to obtain segmented image data, and different objects or areas in the image can be separated, so that the identification and positioning of the objects are realized, the understanding of the content in the image can be facilitated, the scene understanding is further carried out, and the virtual reality experience and the effect of the augmented reality application are improved.
The segmented image data refers to result data obtained after image segmentation operation is performed on the enhanced image data, and optionally, the segmented image data may be obtained through a segmentation algorithm, for example: threshold segmentation, edge detection, region growing, and the like.
S3, dividing the segmented image data into data training sets, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity.
According to the invention, the segmented image data is divided into the data training sets, and the feature extraction is carried out on the segmented image data to obtain the image features, so that the performance and generalization capability of the model can be improved, the performance of the model can be effectively evaluated, and the useful image features can be obtained for subsequent image analysis and application.
Wherein the data training set refers to a subset of training models divided from the entire segmented image data; the image features refer to important information extracted from the segmented image data and describing the content and structure of the image.
As one embodiment of the present invention, the dividing the segmented image data into data training sets, and extracting features of the segmented image data to obtain image features includes: proportional division is carried out on the segmented image data to obtain a data training set corresponding to the segmented image data; normalizing the data training set to obtain normalized data; determining the feature type corresponding to the segmented image data; and carrying out feature extraction on the segmented image data based on the feature type to obtain image features.
The normalization data refers to a process of scaling data and converting the data into a uniform numerical range; the feature type refers to the feature type which needs to be focused and extracted in the image according to task requirements.
Further, the normalized data may be obtained by a normalization algorithm implementation, such as: min-Max Scaling, Z-score normalization, etc.; the feature type can be obtained by a feature extraction method, such as: GLCM, LBP, etc.
According to the invention, the feature vectors corresponding to the image features are identified, so that the optimization can be performed according to specific problems, the calculation efficiency is improved, unnecessary calculation steps can be removed, and the waste of time and resources is reduced, thereby better understanding the relationship between the image features and the target.
Wherein the feature vector refers to a set of numerical representations extracted from the image by a feature extraction algorithm, and optionally, the feature vector may be obtained by a vector recognition tool, such as: openCV, tensorFlow, etc.
As one embodiment of the present invention, the calculating, based on the feature vector, feature similarity corresponding to the segmented image data includes: dividing the feature vector into a first feature vector and a second feature vector;
calculating the feature similarity corresponding to the image feature by using the following formula:
wherein CS represents feature similarity corresponding to the image feature, the value range is between [ -1,1], the closer the value is to 1, the more similar the value is, the closer the value is to-1, the more dissimilar the value is to-1, ai represents the corresponding ith element in the first feature vector, and Bi represents the corresponding ith element in the second feature vector.
Based on the feature similarity, the invention constructs an abnormality recognition model corresponding to the field image set, and causes and features of the abnormality can be understood through visual analysis. This facilitates further analysis of the anomaly samples and corresponding measures to handle, thereby enhancing anomaly detection and monitoring tasks for the field image set.
Wherein the anomaly recognition model is a recognition model for automatically recognizing an anomaly sample in the field image set, and optionally, the anomaly recognition model can be obtained through Python programming language implementation, such as: scikit-learn, tensorFlow, pyTorch, etc.
In detail, the content is combined with image data analysis, a brand new method is provided for construction progress monitoring, construction progress conditions can be evaluated more objectively through feature extraction and similarity calculation, an abnormal recognition model is built, potential problems are early-warned in advance, subjectivity of human judgment is effectively reduced, accuracy and efficiency of monitoring are improved, and therefore better construction management and progress control are facilitated.
S4, carrying out data training on the abnormal recognition model by utilizing the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environmental parameters.
According to the invention, the data training set is utilized to perform data training on the abnormal recognition model, so that a trained abnormal recognition model is obtained, the model can be better understood to perform abnormal detection decision, the output, the feature importance and the like of the model can be analyzed, and the method is used for explaining the operation process and the abnormal judgment basis of the model.
The trained abnormal recognition model refers to a model with higher accuracy and generalization capability obtained through optimization and adjustment, and optionally, the trained abnormal recognition model can be obtained by performing data training on the abnormal recognition model by using the data training set.
According to the invention, the tested abnormal recognition model is deployed in the environment corresponding to the building construction site to obtain the environment parameters, so that the real-time monitoring, early warning and guaranteeing can be realized, the working efficiency is improved, the data analysis and optimization are performed, and the automatic management is realized, thereby bringing various benefits to the building construction site.
Wherein, the environmental parameter refers to various physical quantities or characteristics related to the environment in the construction site.
As an embodiment of the present invention, the deploying the tested anomaly identification model into the environment corresponding to the building construction site to obtain the environmental parameter includes: determining a development environment corresponding to the building construction site; based on the development environment, deploying a model service corresponding to the tested abnormal recognition model; and carrying out environment recognition on the building construction site based on the model service to obtain environment parameters.
The development environment refers to software and hardware environments required by model deployment and test on a construction site; the model service refers to deploying the tested anomaly identification model into a service which can be accessed.
Further, the development environment may be obtained through a deep learning model implementation, such as: convolutional neural networks, recurrent neural networks, long-term memory networks; the model service may be obtained through a build tool implementation, such as: flash, django, etc.
S5, carrying out anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
According to the invention, the environment parameters are obtained through carrying out anomaly identification on the environment parameters, the environment anomaly parameters can be adjusted and optimized according to specific service requirements so as to adapt to anomaly identification tasks of different environments and parameters, and the model can be modified, updated and improved according to actual conditions.
Wherein, the environment anomaly parameters refer to factors that may affect the environment state or performance, such as: temperature, humidity, pressure, illumination, electromagnetic radiation, etc., optionally, the environmental anomaly parameters may be obtained by an operation and maintenance tool, such as: monitoring systems, log analysis tools, and the like.
As an embodiment of the present invention, the performing anomaly identification on the environmental parameter to obtain an environmental anomaly parameter includes: identifying an environment parameter list corresponding to the environment parameters; determining a real-time value in the environment parameter list; setting a threshold range corresponding to the real-time value; and carrying out anomaly identification on the environmental parameters based on the threshold range to obtain environmental anomaly parameters.
The environmental parameter list refers to a list corresponding to each environmental parameter to be monitored and identified, for example: list of temperature, humidity, pressure, light, etc.; the real-time value refers to the current value of the environmental parameter obtained by a sensor or other equipment; the threshold range refers to a valid range set for each environmental parameter.
Further, the list of environmental parameters may be obtained by an environmental monitoring system implementation, such as: sensors, data acquisition equipment, data processing tools and the like; the real-time value may be obtained by a sensor implementation, such as: temperature, humidity, illumination, etc.; the threshold range may be obtained by a clustering algorithm implementation.
According to the invention, the environment anomaly factors in the environment anomaly parameters are extracted, and can be customized and adjusted according to specific requirements so as to adapt to the extraction of the environment anomaly factors in a specific scene, and a proper feature extraction method and model can be flexibly selected according to different environment parameters and anomaly conditions.
The environmental anomaly factor refers to a key feature or index capable of causing anomaly in environmental parameters, and optionally, the environmental anomaly factor can be obtained through a supervised learning model, such as: decision trees, random forests, support vector machines, etc.
As one embodiment of the present invention, the calculating the environmental anomaly index corresponding to the environmental anomaly factor includes:
calculating an environmental anomaly index corresponding to the environmental anomaly factor by using the following formula:
wherein Z represents an environmental abnormality index corresponding to the environmental abnormality factor, fi represents an ith environmental abnormality factor, fj represents a jth environmental abnormality factor, n represents the number of environmental abnormality factors, and m represents the total number of environmental abnormality factors.
According to the invention, the corresponding early warning signal of the building construction site is generated based on the environment abnormality index, so that the abnormality identification in the building construction site is realized, the abnormality in the building construction site can be identified, the potential environment abnormality problem can be timely found and solved, the problem is prevented from further deteriorating, and the safety and reliability of the construction site are improved.
The early warning signal refers to early warning information about abnormal conditions in a construction site, and optionally, the early warning signal can be obtained through monitoring equipment, such as a site monitor and other tools.
The invention can identify the progress situation of a construction site by acquiring the site image set in the construction site, identify the image data corresponding to the site image set, monitor and control the progress situation of the construction site in real time, improve the quality, ensure the safety, improve the efficiency and accumulate experience, and improve the construction quality and the efficiency. Therefore, the method and the system for identifying the abnormality under the construction based on the machine vision provided by the invention are used for improving the abnormality identification efficiency in the construction.
Fig. 2 is a functional block diagram of a method and a system for identifying anomalies under building construction based on machine vision according to an embodiment of the present invention.
The abnormality recognition system 200 based on machine vision for realizing building construction can be installed in electronic equipment. Depending on the functions implemented, the machine vision based anomaly identification system 200 under construction may include an image tagging module 201, an image segmentation module 202, a model construction module 203, an environmental parameters module 204, and an index calculation module 205. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the image marking module 201 is configured to obtain a field image set in a construction site, identify image data corresponding to the field image set, and perform data pre-marking on the image data to obtain image marking data;
the image segmentation module 202 is configured to perform image denoising on the image tag data to obtain denoised image data, perform image enhancement on the denoised image data to obtain enhanced image data, and perform image segmentation on the enhanced image data to obtain segmented image data;
The model construction module 203 is configured to divide the segmented image data into data training sets, perform feature extraction on the segmented image data to obtain image features, identify feature vectors corresponding to the image features, calculate feature similarities corresponding to the segmented image data based on the feature vectors, and construct an anomaly recognition model corresponding to the field image set based on the feature similarities;
the environmental parameter module 204 is configured to perform data training on the anomaly identification model by using the data training set to obtain a trained anomaly identification model, and deploy the tested anomaly identification model to an environment corresponding to the building construction site to obtain environmental parameters;
the index calculation module 205 is configured to perform anomaly identification on the environmental parameter to obtain an environmental anomaly parameter, extract an environmental anomaly factor in the environmental anomaly parameter, calculate an environmental anomaly index corresponding to the environmental anomaly factor, and generate an early warning signal corresponding to the building construction site based on the environmental anomaly index, so as to implement anomaly identification in the building construction site.
In detail, each module in the system 200 for identifying an abnormality under construction based on machine vision in the embodiment of the present invention adopts the same technical means as the method for identifying an abnormality under construction based on machine vision in the drawings, and can produce the same technical effects, which are not described herein.
Fig. 3 is a schematic structural diagram of an electronic device for implementing the method for identifying anomalies under construction based on machine vision.
The electronic device 1 may comprise a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may further comprise a computer program stored in the memory 31 and executable on the processor 30, such as an engineering safety supervisor based on artificial intelligence.
The processor 30 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and so on. The processor 30 is a Control Unit (Control Unit) of the electronic device 1, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules (e.g., an artificial intelligence-based engineering safety supervision program, etc.) stored in the memory 31, and invokes data stored in the memory 31 to perform various functions of the electronic device and process the data.
The memory 31 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 31 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 31 may also be an external storage device of the electronic device in other embodiments, for example, a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 31 may also include both an internal storage unit and an external storage device of the electronic device. The memory 31 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of a database-configured connection program, but also for temporarily storing data that has been output or is to be output.
The communication bus 32 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 31 and at least one processor 30 or the like.
The communication interface 33 is used for communication between the electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 30 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
It should be understood that the examples are for illustrative purposes only.
The database-configured connection program stored in the memory 31 in the electronic device 1 is a combination of a plurality of computer programs, which, when run in the processor 30, can implement:
acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and pre-marking the image data to obtain image marking data;
image denoising is carried out on the image marking data to obtain denoised image data, image enhancement is carried out on the denoised image data to obtain enhanced image data, and image segmentation is carried out on the enhanced image data to obtain segmented image data;
Dividing the segmented image data into a data training set, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity;
performing data training on the abnormal recognition model by using the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environmental parameters;
performing anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
In particular, the specific implementation method of the processor 30 on the computer program may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the integrated modules/units of the electronic device 1 may be stored in a non-volatile computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. The storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and pre-marking the image data to obtain image marking data;
image denoising is carried out on the image marking data to obtain denoised image data, image enhancement is carried out on the denoised image data to obtain enhanced image data, and image segmentation is carried out on the enhanced image data to obtain segmented image data;
Dividing the segmented image data into a data training set, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity;
performing data training on the abnormal recognition model by using the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environmental parameters;
performing anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The method for identifying the abnormality under the construction of the building based on the machine vision is characterized by comprising the following steps:
acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and pre-marking the image data to obtain image marking data;
image denoising is carried out on the image marking data to obtain denoised image data, image enhancement is carried out on the denoised image data to obtain enhanced image data, and image segmentation is carried out on the enhanced image data to obtain segmented image data;
dividing the segmented image data into a data training set, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity;
performing data training on the abnormal recognition model by using the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environmental parameters;
Performing anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
2. The machine vision-based anomaly identification method under construction of claim 1, wherein the acquiring a field image set in a construction site, identifying image data corresponding to the field image set, comprises:
determining shooting equipment corresponding to the building construction site;
acquiring a site image set in a building construction site by using the shooting equipment;
storing the field image set into a preset cloud storage space;
performing data preprocessing on the data stored in the cloud storage space to obtain preprocessed data;
and identifying corresponding image data in the preprocessing data.
3. The method for identifying an abnormality under construction based on machine vision according to claim 1, wherein the performing data pre-labeling on the image data to obtain image marking data comprises:
Performing data adjustment on the image data to obtain adjusted image data;
defining the annotation category corresponding to the adjusted image data;
based on the labeling category, performing data pre-labeling on the adjusted image data to obtain initial labeling image data;
and performing annotation correction on the initial image data to obtain image marking data.
4. The method for identifying anomalies under construction based on machine vision according to claim 1, wherein image denoising is performed on the image-marking data to obtain denoised image data, comprising:
importing the image marking data, and identifying a noise type corresponding to the image marking data;
based on the noise type, carrying out noise statistics on the image marking data to obtain noise statistics data;
and carrying out frequency domain denoising on the noise statistical data to obtain denoised image data.
5. The machine vision-based anomaly identification method for building construction of claim 1, wherein the dividing the segmented image data into data training sets and extracting features of the segmented image data to obtain image features comprises:
proportional division is carried out on the segmented image data to obtain a data training set corresponding to the segmented image data;
Normalizing the data training set to obtain normalized data;
determining the feature type corresponding to the segmented image data;
and carrying out feature extraction on the segmented image data based on the feature type to obtain image features.
6. The machine vision-based anomaly identification method under construction of claim 1, wherein the calculating the feature similarity corresponding to the segmented image data based on the feature vector comprises: dividing the feature vector into a first feature vector and a second feature vector;
calculating the feature similarity corresponding to the image feature by using the following formula:
wherein CS represents feature similarity corresponding to the image feature, the value range is between [ -1,1], the closer the value is to 1, the more similar the value is, the closer the value is to-1, the more dissimilar the value is to-1, ai represents the corresponding ith element in the first feature vector, and Bi represents the corresponding ith element in the second feature vector.
7. The method for identifying the abnormality under the building construction based on the machine vision according to claim 1, wherein the deploying the tested abnormality identification model into the environment corresponding to the building construction site to obtain the environmental parameter comprises:
Determining a development environment corresponding to the building construction site;
based on the development environment, deploying a model service corresponding to the tested abnormal recognition model;
and carrying out environment recognition on the building construction site based on the model service to obtain environment parameters.
8. The method for identifying anomalies under construction of a building based on machine vision according to claim 1, wherein the performing anomaly identification on the environmental parameters to obtain environmental anomaly parameters includes:
identifying an environment parameter list corresponding to the environment parameters; determining a real-time value in the environment parameter list;
setting a threshold range corresponding to the real-time value;
and carrying out anomaly identification on the environmental parameters based on the threshold range to obtain environmental anomaly parameters.
9. The machine vision-based anomaly identification method under construction of claim 1, wherein the calculating the environmental anomaly index corresponding to the environmental anomaly factor comprises:
calculating an environmental anomaly index corresponding to the environmental anomaly factor by using the following formula:
wherein Z represents an environmental abnormality index corresponding to the environmental abnormality factor, fi represents an ith environmental abnormality factor, fj represents a jth environmental abnormality factor, n represents the number of environmental abnormality factors, and m represents the total number of environmental abnormality factors.
10. Machine vision based anomaly identification system for implementing a construction anomaly identification method according to any one of claims 1 to 9, said system comprising:
the image marking module is used for acquiring a site image set in a building construction site, identifying image data corresponding to the site image set, and performing data pre-marking on the image data to obtain image marking data;
the image segmentation module is used for carrying out image denoising on the image marking data to obtain denoised image data, carrying out image enhancement on the denoised image data to obtain enhanced image data, and carrying out image segmentation on the enhanced image data to obtain segmented image data;
the model construction module is used for dividing the segmented image data into a data training set, extracting features of the segmented image data to obtain image features, identifying feature vectors corresponding to the image features, calculating feature similarity corresponding to the segmented image data based on the feature vectors, and constructing an abnormal recognition model corresponding to the field image set based on the feature similarity;
The environment parameter module is used for carrying out data training on the abnormal recognition model by utilizing the data training set to obtain a trained abnormal recognition model, and deploying the tested abnormal recognition model into an environment corresponding to the building construction site to obtain environment parameters;
the index calculation module is used for carrying out anomaly identification on the environment parameters to obtain environment anomaly parameters, extracting environment anomaly factors in the environment anomaly parameters, calculating environment anomaly indexes corresponding to the environment anomaly factors, and generating early warning signals corresponding to the building construction sites based on the environment anomaly indexes so as to realize anomaly identification in the building construction sites.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410082553.XA CN117893779A (en) | 2024-01-19 | 2024-01-19 | Method and system for realizing abnormality identification under building construction based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410082553.XA CN117893779A (en) | 2024-01-19 | 2024-01-19 | Method and system for realizing abnormality identification under building construction based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117893779A true CN117893779A (en) | 2024-04-16 |
Family
ID=90639331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410082553.XA Pending CN117893779A (en) | 2024-01-19 | 2024-01-19 | Method and system for realizing abnormality identification under building construction based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893779A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283446A (en) * | 2021-05-27 | 2021-08-20 | 平安科技（深圳）有限公司 | Method and device for identifying target object in image, electronic equipment and storage medium |
| CN117392615A (en) * | 2023-12-12 | 2024-01-12 | 南昌理工学院 | Anomaly identification method and system based on monitoring video |
-
2024
- 2024-01-19 CN CN202410082553.XA patent/CN117893779A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283446A (en) * | 2021-05-27 | 2021-08-20 | 平安科技（深圳）有限公司 | Method and device for identifying target object in image, electronic equipment and storage medium |
| WO2022247005A1 (en) * | 2021-05-27 | 2022-12-01 | 平安科技（深圳）有限公司 | Method and apparatus for identifying target object in image, electronic device and storage medium |
| CN117392615A (en) * | 2023-12-12 | 2024-01-12 | 南昌理工学院 | Anomaly identification method and system based on monitoring video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11488294B2 (en) | Method for detecting display screen quality, apparatus, electronic device and storage medium | |
| CN107123131B (en) | Moving target detection method based on deep learning | |
| CN115294117B (en) | Defect detection method and related device for LED lamp beads | |
| CN114758249B (en) | Target object monitoring method, device, equipment and medium based on field night environment | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN115953566B (en) | Feature analysis method, system and medium for infrared thermal imager | |
| CN115690615B (en) | Video stream-oriented deep learning target recognition method and system | |
| CN113033385A (en) | Deep learning-based violation building remote sensing identification method and system | |
| CN114579791A (en) | Construction safety violation identification method and system based on operation ticket | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| Vishwanath et al. | Connected component analysis for Indian license plate infra-red and color image character segmentation | |
| US20210166028A1 (en) | Automated product recognition, analysis and management | |
| CN116824135A (en) | Atmospheric natural environment test industrial product identification and segmentation method based on machine vision | |
| CN117893779A (en) | Method and system for realizing abnormality identification under building construction based on machine vision | |
| CN112203053A (en) | Intelligent supervision method and system for subway constructor behaviors | |
| CN113723355A (en) | Target monitoring method and device, storage medium and electronic device | |
| CN115474441A (en) | Obstacle detection method, apparatus, device, and computer storage medium | |
| CN112347989A (en) | Reflective garment identification method and device, computer equipment and readable storage medium | |
| CN112131418A (en) | Target labeling method, target labeling device and computer-readable storage medium | |
| CN114359645B (en) | Image expansion method, device, equipment and storage medium based on characteristic area | |
| CN117333929B (en) | Method and system for identifying abnormal personnel under road construction based on deep learning | |
| Obu et al. | Crop Disease Detection using Yolo V5 on Raspberry Pi | |
| CN117851817B (en) | Intelligent filtering analysis method, system and storage medium for humid air | |
| CN117576719A (en) | Method for detecting illegal behaviors in operation scene | |
| CN117496507A (en) | Target detection method and device for edible fungus insect damage |
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 |