CN115205780A - Construction site violation monitoring method, system, medium and electronic equipment - Google Patents
Construction site violation monitoring method, system, medium and electronic equipment Download PDFInfo
- Publication number
- CN115205780A CN115205780A CN202210706719.1A CN202210706719A CN115205780A CN 115205780 A CN115205780 A CN 115205780A CN 202210706719 A CN202210706719 A CN 202210706719A CN 115205780 A CN115205780 A CN 115205780A
- Authority
- CN
- China
- Prior art keywords
- violation
- construction site
- image
- monitoring
- features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a monitoring method, a monitoring system, a monitoring medium and electronic equipment for construction site violation, wherein a construction site image is identified according to a pre-established identification model to obtain an identification result; when the identification result comprises the violation features, determining the violation type of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types; violation monitoring is performed on the worksite based on the worksite image containing the violation features, the violation type, and the acquisition time of the worksite image containing the violation features. The identification result is obtained by collecting the construction site image and identifying the construction site image. And when the identification result contains the violation features, determining the violation types of the violation features, and automatically monitoring the construction site based on the construction site images of the violation features, the violation types and the acquisition time of the construction site images containing the violation features, so that the monitoring efficiency is improved, and the personnel investment is reduced.
Description
Technical Field
The invention belongs to the technical field of monitoring, and particularly relates to a method, a system, a medium and electronic equipment for monitoring construction site violation.
Background
The existing construction site has many safety risks and environmental pollution factors. For example, the safety helmet is not worn by construction personnel in a construction site, the personal safety of an individual is seriously threatened, and the safety production of the society is influenced. The bare land of building site is not covered effectively in time, resulting in the raise dust phenomenon, the polluted environment.
Along with the development of social economy and the improvement of the quality of life of people, the phenomena need to be monitored so as to be found in time and rectified in time. However, manual monitoring is generally adopted in the prior art, the monitoring efficiency is low, and the personnel investment is large.
Disclosure of Invention
The invention provides a method, a system, a medium and electronic equipment for monitoring construction site violation, which aim to solve the technical problems of low monitoring efficiency and large personnel investment in manual construction site monitoring in the prior art.
The invention provides a monitoring method for construction site violation, which comprises the following steps:
acquiring a construction site image of a target construction site and acquiring time of the construction site image;
identifying the construction site image according to a pre-established identification model to obtain an identification result;
when the identification result comprises the violation features, determining the violation type of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types;
violation monitoring is performed on the worksite based on the worksite image containing the violation features, the violation type, and the acquisition time of the worksite image containing the violation features.
In one embodiment of the present invention, the acquiring of the worksite image and the acquiring time of the worksite image include:
setting interval time according to the type of the target construction site;
and acquiring the construction site image at regular time according to the interval time, and recording the acquisition time of the construction site image.
In an embodiment of the present invention, recognizing the worksite image according to a pre-established recognition model to obtain a recognition result includes:
zooming the construction site image according to a preset size, and performing normalization processing on the zoomed construction site image to obtain a preprocessed image;
acquiring the length, width, image channel and batch size dimensions of the preprocessed image;
constructing a four-dimensional tensor according to the length, the width, the image channel and the size dimension of the batch, and inputting the four-dimensional tensor into a pre-established identification model for identification to obtain an initial result;
and labeling the initial result, and performing non-maximum suppression on the labeled initial result to obtain the identification result.
In an embodiment of the present invention, the establishing process of the recognition model includes:
acquiring a training data set containing a positive sample and a negative sample, wherein the positive sample is a construction site image including violation features, and the negative sample is a construction site image not including the violation features;
and configuring the pre-acquired artificial neural network, and training the artificial neural network according to the training data set pair to obtain the recognition model.
In an embodiment of the present invention, the artificial neural network is a yolov5 network, the yolov5 network includes a trunk network, a neck network, and a head network, which are sequentially connected, and the trunk network includes a cross-stage local network; configuring an artificial neural network, comprising:
acquiring a set type convolution network and an deconvolution layer;
and replacing the cross-stage local network according to the intensive convolutional network, and adding the deconvolution layer to the bottom layer of the neck network, so that the neck network is connected with the head network through the deconvolution layer, and the configuration of the artificial neural network is completed.
In an embodiment of the present invention, training the configured artificial neural network according to the training data set includes:
zooming the positive sample in the training data set according to a preset size, and performing data enhancement on the zoomed positive sample;
carrying out affine transformation on the positive sample after the data enhancement according to the affine matrix, wherein the affine transformation comprises rotation, scaling, random cutting and translation operation;
and training the configured artificial neural network based on the positive sample after the affine transformation.
In an embodiment of the present invention, the monitoring of the violation of the construction site based on the construction site image including the violation feature, the violation type, and the acquisition time of the construction site image including the violation feature includes:
pushing the construction site image, the violation type and the acquisition time of the construction site image containing the violation characteristic to an upper-layer platform, and monitoring based on the upper-layer platform;
or configuring a message queue based on the construction site image, the violation type and the acquisition time of the construction site image containing the violation characteristics, pushing the message queue to an upper platform, and monitoring based on the upper platform.
The invention also provides a monitoring system for construction site violation, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a construction site image of a target construction site and acquisition time of the construction site image;
the recognition module is used for recognizing the construction site image according to a pre-established recognition model to obtain a recognition result;
the mapping module is used for determining the violation type of the violation feature in the recognition result according to the preset mapping relation between the violation feature and the violation type when the recognition result comprises the violation feature;
and the storage module is used for monitoring the violation of the construction site based on the construction site image containing the violation features, the violation type and the acquisition time of the construction site image containing the violation features.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of monitoring a worksite violation, as described above.
The present invention also provides an electronic device comprising: a processor and a memory;
the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory to cause the terminal to perform a method for monitoring a worksite violation as described above.
The monitoring method, the monitoring system, the monitoring medium and the electronic equipment for the construction site violation have the following beneficial effects that: identifying the construction site image according to a pre-established identification model to obtain an identification result; when the identification result comprises the violation features, determining the violation type of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types; violation monitoring is performed on the worksite based on the worksite image containing the violation features, the violation type, and the acquisition time of the worksite image containing the violation features. The identification result is obtained by collecting the construction site image and identifying the construction site image. And when the identification result contains the violation features, determining the violation types of the violation features, and automatically monitoring the construction site based on the construction site images of the violation features, the violation types and the acquisition time of the construction site images containing the violation features, so that the monitoring efficiency is improved, and the personnel investment is reduced.
Drawings
FIG. 1 is a schematic diagram of an exemplary implementation scenario of the present invention;
FIG. 2 is a flow diagram of a method for monitoring a worksite violation, according to one embodiment of the present disclosure;
FIG. 3 is a flow chart of an implementation of a method for monitoring a worksite violation, according to an embodiment of the present disclosure;
FIG. 4 is a diagram illustrating the effect of the helmet feature detection on a worksite, according to an embodiment of the present disclosure;
FIG. 5 is a diagram illustrating the effect of detecting the bare earth features of a worksite according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a worksite violation monitoring system in accordance with an embodiment of the present disclosure;
FIG. 7 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present application, and the drawings only show the components related to the present application and are not drawn according to the number, shape and size of the components in actual implementation, the type, quantity and proportion of each component in actual implementation may be changed freely, and the layout of the components may be more complicated.
In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present application, however, it will be apparent to one skilled in the art that embodiments of the present application may be practiced without these specific details.
Firstly, it should be noted that computer vision is a science for studying how to make a machine "see", and further, it means that a camera and a computer are used to replace human eyes to perform machine vision such as identification, tracking and measurement on a target, and further, graphics processing is performed, so that the computer processing becomes an image more suitable for human eyes to observe or transmitted to an instrument to detect.
The method and the system utilize computer vision to automatically monitor the construction site, and related objects mainly comprise judging whether workers without safety helmets exist or not, identifying bare land blocks of the construction site and the like; firstly, acquiring an image and then identifying the image;
as shown in fig. 1, in the monitoring of the violation of the construction site, a camera is used for acquiring an image, and then the image is identified through edge equipment; and the edge equipment uploads the identification result, the image and the related information to a server, so that the monitoring of the construction site is realized. The edge device in this embodiment decodes and AI analyzes the video based on a domestic cambrian chip.
The edge device 110 shown in fig. 1 may be any device supporting computer vision operation, such as a smart phone, a vehicle-mounted computer, a tablet computer, a notebook computer, or a wearable device, but is not limited thereto. The navigation server 120 shown in fig. 1 is a cloud computing server, and may be, for example, an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, a cloud storage, a web service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), and a big data and artificial intelligence platform, which is not limited herein. The edge device 110 may communicate with the navigation server 120 through a wireless network such as 3G (third generation mobile information technology), 4G (fourth generation mobile information technology), 5G (fifth generation mobile information technology), etc., which is not limited herein.
As shown in fig. 2, the present application provides a method for monitoring a construction site violation, including the steps of:
s210, acquiring a construction site image of a target construction site and acquiring time of the construction site image;
the device for acquiring the building site image is a camera, and the camera can record the acquisition time of the building site image while acquiring the building site image;
s220, identifying the construction site image according to a pre-established identification model to obtain an identification result;
after the camera acquires the construction site image, the construction site image is sent to the edge equipment, the identification model is arranged in the edge equipment, the construction site image is identified by means of computing power of the edge equipment, and an identification result is obtained.
S230, when the identification result comprises the violation features, determining the violation types of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types;
identifying the construction site image by means of the computing power of the edge equipment, and after obtaining an identification result, determining the violation type according to a preset mapping relation when the identification result contains violation features, for example, a worker who does not wear a safety helmet corresponds to a safety violation, and a large bare land corresponds to an environmental protection violation; when a worker who does not wear a safety helmet appears in the construction site image, determining that the violation type is a safety violation; when a large bare land block appears in the construction site image, determining that the violation type is an environmental protection violation;
the violation features in this embodiment mainly include: workers who do not wear the safety helmet and large bare land masses occur, the workers who do not wear the safety helmet do not meet the safety standards, and the large bare land masses are easy to generate dust to pollute the environment;
and S240, monitoring the violation of the construction site based on the construction site image containing the violation features, the violation type and the acquisition time of the construction site image containing the violation features.
The violation features in this embodiment mainly include: workers who do not wear the safety helmet and large exposed land blocks appear, the workers who do not wear the safety helmet do not conform to safety standards, and the large exposed land blocks are easy to generate dust to pollute the environment, so the target construction site mainly aims at the two types of construction sites, wherein the construction site is constructed, a large number of construction sites of workers exist, and the construction site is not constructed for a long time and has exposed land blocks but carries out shielding construction sites. Once the recognition result generated by the recognition model comprises that a worker does not wear a safety helmet or the land is directly exposed; uploading the corresponding images, violation types (mainly including unworn safety helmets and bare plots) and image acquisition time to an upper-layer platform for monitoring; the upper platform may be a server.
In some embodiments, the process of acquiring a worksite image, the time of acquisition of the worksite image, may include steps S310 through S320, as detailed below:
s310, setting interval time according to the type of the target construction site;
due to different construction site types, if the construction site is monitored, images need to be acquired and identified in real time, and the wearing condition of the safety helmet needs to be discovered in time; if the bare land is monitored, the bare land does not need to be monitored in real time; therefore, generally, the time interval required for monitoring the construction site is shorter, and the time interval required for monitoring the exposed land is longer;
and S320, acquiring the building site images according to the interval time at regular time, and recording the acquisition time of the building site images.
The interval time required for monitoring the construction site is short, the interval time required for monitoring the bare land is long, different interval times are set and images are extracted from the video stream of the camera according to different construction site types, and real-time monitoring in the embodiment means that the time interval for extracting the images is short, and each frame of image in the video stream can be identified.
In some embodiments, the process of identifying the image of the worksite according to the pre-established identification model and obtaining the identification result may include steps S410 to S440, which are described in detail as follows:
s410, zooming the construction site image according to a preset size, and performing normalization processing on the zoomed construction site image to obtain a preprocessed image;
in step S410, specifically, the scaled worksite image is fixed to 640 × 640 pixels, and the image pixel values are normalized by normaize (a normalization function) to obtain a preprocessed image;
s420, acquiring the length, the width, the image channel and the batch size dimension (Batchsize) of the preprocessed image;
in step S420, the length and width are the size attributes of the preprocessed image, and the picture channels refer to red, green, and blue portions in the RGB color mode. That is, a complete image is composed of three channels, red, green, and blue. The batch size (Batchsize) refers only to the size of each batch of data.
S430, constructing a four-dimensional tensor by using the length, width, image channel and batch size dimensions, and inputting the four-dimensional tensor into a pre-established identification model for identification to obtain an initial result;
in step S430, combining the length, the width, the image channel, and the batch size to generate a four-dimensional tensor (NCHW), and inputting the four-dimensional tensor into a pre-established recognition model for recognition to obtain an initial result, where the four-dimensional tensor (NCHW) is widely applied in a Convolutional Neural Network (CNN) and is generally used for storing Feature map (Feature maps) data, and in this embodiment, the four-dimensional tensor (NCHW) includes: a batch size N of the worksite images; length (or height) H of the worksite image; width W of the worksite image; the number of channels C;
and S440, marking the initial result, and performing non-maximum suppression on the marked initial result to obtain an identification result.
In the step S440, the Anchor frames (anchors) in the yolov5 network are set in advance, before training, the labels are clustered in the safety helmet or bare land data set by adopting a K-means algorithm, 9 self-adaptive Anchor frames (anchors) with different sizes are output, and the initial results are labeled by using the Anchor frames (anchors); the accuracy of the position prediction of the target is improved. And meanwhile, processing the initial result by adopting a Non-maximum suppression (NMS) algorithm to obtain a recognition result.
In some embodiments, the process of establishing the recognition model may include steps S510 to S520, which are described in detail as follows:
s510, acquiring a training data set containing a positive sample and a negative sample, wherein the positive sample is an image including violation features, and the negative sample is an image not including the violation features;
in step S510, the occurrence of false detection is reduced by adding a negative sample scene;
s520, configuring the artificial neural network, and training the configured artificial neural network according to the training data set to obtain a recognition model.
In step S520, the recognition of the recognition model is more accurate based on the training data set including the positive samples and the negative samples.
In some embodiments, the artificial neural network is yolov5 network, the yolov5 network comprises a trunk network, a neck network and a head network which are sequentially connected, and the trunk network comprises a cross-stage local network; the process of configuring the artificial neural network may include steps S610 to S620:
s610, acquiring a set type convolution network (DenseNet) and a deconvolution layer I-FPN (BI-directional feature pyramid network, BI-FPN);
s620, replacing a Cross-Stage local Network CSPNet (CSPNet) according to a dense convolutional Network (DenseNet), adding a BI-directional feature convolutional Network (BI-FPN) to a bottom layer of a neck Network (namely, to the back of a convolutional layer of the bottom layer of the neck Network) so that the neck Network is connected with a head Network head through the deconvolution layer, and completing the configuration of the artificial neural Network
In this embodiment, a base Network based on intensive (DenseNet) prediction is constructed to replace an original Cross-Stage local Network CSPNet (CSPNet), and is used to extract features of a target from an input image, including edge features, texture features, color features, and deep semantic features. In the latch part of yolov5, in order to further improve the accuracy of feature fusion, an deconvolution layer BI-FPN (BI-directional feature fusion) is added on the original basis for feature fusion, so that the accuracy of target identification is improved. And the original architecture is reserved in the Head prediction part.
In some embodiments, the training of the configured artificial neural network according to the training data set may include steps S710 to S730, which are described in detail as follows:
s710, zooming the positive sample in the training data set according to a preset size, and performing data enhancement on the zoomed positive sample;
in step S710, the positive sample is a target image containing the violation feature, and the scaled positive sample has a size of 640 pixels by 640 pixels;
s720, carrying out affine transformation on the positive sample after the data enhancement according to the affine matrix, wherein the affine transformation comprises rotation, scaling, random cutting and translation operation;
in step S720, the affine matrix is used to perform affine transformation on the positive sample, where the affine transformation is linear transformation plus translation, and is commonly used to perform rotational translation on an image in image processing; randomly shearing the positive sample by utilizing a shearing coefficient in the affine matrix; carrying out translation operation on the positive sample by utilizing a translation coefficient in the affine matrix;
and S730, training the configured artificial neural network based on the positive sample after affine transformation.
In this embodiment, step S610 performs data enhancement on the scaled positive sample by using a Mosaic data enhancement method in yolov5 network; after the rotation, scaling, random clipping and translation operations in step S620, the number of target labels during training is increased, which is more favorable for improving the generalization capability of the model.
In some embodiments, the process of violation monitoring a worksite based on the worksite image containing the violation features, the violation type, and the time of acquisition of the worksite image containing the violation features may include steps S810-S820, as detailed below:
s810, directly pushing the construction site image, the violation type and the acquisition time of the construction site image containing the violation characteristic to an upper-layer platform, and monitoring based on the upper-layer platform;
in step S810, the upper platform may be a server, a PC host, or other device, and the upper platform is used to visually display the construction site image, the violation type, and the acquisition time of the construction site image including the violation feature, so as to complete monitoring.
S820, or configuring a message queue based on the construction site image, the violation type and the acquisition time of the construction site image containing the violation characteristics, pushing the message queue to an upper-layer platform, and monitoring based on the upper-layer platform.
In step S820, if the number of site images including the violation feature is large and the pushing cannot be performed at one time, a message queue-based push is generated.
As shown in fig. 3, specifically, the embodiment of the present application is as follows:
(1) Logging in a platform;
(2) Activating the edge device;
(3) Recording camera information;
(4) Performing configuration algorithm analysis in the edge device;
(5) Analyzing the image by using an algorithm, generating an analysis log and storing the analysis log in a local disk so as to conveniently check a historical analysis result;
(6) And returning and uploading the analysis result to an upper-level platform for monitoring.
Fig. 4-5 are schematic diagrams illustrating the implementation results of the method described in the present application, and as shown in fig. 4-5, the present application can effectively identify the characteristics of the person without the helmet and the bare ground in the construction site.
According to the monitoring method for the construction site violation, a construction site image is identified according to a pre-established identification model, and an identification result is obtained; when the identification result comprises the violation features, determining the violation types of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types; violation monitoring is performed on the worksite based on the worksite image containing the violation features, the violation type, and the acquisition time of the worksite image containing the violation features. And acquiring a recognition result by acquiring a construction site image and recognizing the construction site image. And when the identification result contains the violation features, determining the violation type of the violation features, and automatically monitoring the construction site based on the construction site image of the violation features, the violation type and the acquisition time of the construction site image containing the violation features, so that the monitoring efficiency is improved, and the personnel investment is reduced.
The application also provides a monitoring system for construction site violation, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a construction site image of a target construction site and acquisition time of the construction site image;
the identification module is used for identifying the construction site image according to a pre-established identification model to obtain an identification result;
the mapping module is used for determining the violation type of the violation feature in the recognition result according to the preset mapping relation between the violation feature and the violation type when the recognition result comprises the violation feature;
and the storage module is used for monitoring the violation of the construction site based on the construction site image containing the violation features, the violation type and the acquisition time of the construction site image containing the violation features.
According to the monitoring system for the construction site violation, a construction site image is identified according to a pre-established identification model, and an identification result is obtained; when the identification result comprises the violation features, determining the violation type of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types; violation monitoring is performed on the worksite based on the worksite image containing the violation features, the violation type, and the acquisition time of the worksite image containing the violation features. The identification result is obtained by collecting the construction site image and identifying the construction site image. And when the identification result contains the violation features, determining the violation type of the violation features, and automatically monitoring the construction site based on the construction site image of the violation features, the violation type and the acquisition time of the construction site image containing the violation features, so that the monitoring efficiency is improved, and the personnel investment is reduced.
It should be noted that the monitoring system for a construction site violation provided in the foregoing embodiment and the monitoring method for a construction site violation provided in the foregoing embodiment belong to the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiment, and is not described herein again. In practical applications, the monitoring system for monitoring a construction site violation provided in the above embodiment may distribute the functions to different function modules according to needs, that is, divide the internal structure of the device into different function modules to complete all or part of the functions described above, which is not limited herein.
An embodiment of the present application further provides an electronic device, including: one or more processors; a storage device configured to store one or more programs, which when executed by the one or more processors, cause the electronic device to implement the method for monitoring a worksite violation provided in the above-described embodiments.
FIG. 7 illustrates a schematic structural diagram of a computer system suitable for use to implement the electronic device of the embodiments of the subject application. It should be noted that the computer system 700 of the electronic device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can execute various appropriate actions and processes, such as executing the method in the above-mentioned embodiment, according to a program stored in a Read-Only Memory (ROM) 702 or a program loaded from a storage portion 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for system operation are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An Input/Output (I/O) interface 705 is also connected to the bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The driver 77 is also connected to the I/O interface 705 as necessary. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 77 as necessary, so that a computer program read out therefrom is installed into the storage section 708 as necessary.
In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. When the computer program is executed by a Central Processing Unit (CPU) 701, various functions defined in the system of the present application are executed.
It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may comprise a propagated data signal with a computer-readable computer program embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
Another aspect of the present application also provides a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements the foregoing method of monitoring a worksite violation. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist separately without being incorporated in the electronic device.
Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read by a processor of the computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the method for monitoring a worksite violation provided in the various embodiments described above.
The above-described embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.
Claims (10)
1. A method of monitoring a worksite violation, comprising the steps of:
acquiring a construction site image of a target construction site and acquiring time of the construction site image;
identifying the construction site image according to a pre-established identification model to obtain an identification result;
when the identification result comprises the violation features, determining the violation type of the violation features in the identification result according to a preset mapping relation between the violation features and the violation types;
violation monitoring is performed on the worksite based on the worksite image containing the violation features, the violation type, and the acquisition time of the worksite image containing the violation features.
2. A method of monitoring a worksite violation according to claim 1, wherein acquiring a worksite image, the time of acquisition of the worksite image, comprises:
setting interval time according to the type of the target construction site;
and acquiring the construction site image according to the interval time at regular time, and recording the acquisition time of the construction site image.
3. The method for monitoring the construction site violation according to claim 1, wherein the step of identifying the construction site image according to a pre-established identification model to obtain an identification result comprises the following steps:
zooming the construction site image according to a preset size, and performing normalization processing on the zoomed construction site image to obtain a preprocessed image;
acquiring the length, width, image channel and batch size dimensions of the preprocessed image;
constructing a four-dimensional tensor according to the length, the width, the image channel and the size dimension of the batch, and inputting the four-dimensional tensor into a pre-established identification model for identification to obtain an initial result;
and labeling the initial result, and performing non-maximum suppression on the labeled initial result to obtain the identification result.
4. A method according to claim 1, wherein the process of establishing the recognition model comprises:
acquiring a training data set containing a positive sample and a negative sample, wherein the positive sample is a construction site image including violation features, and the negative sample is a construction site image not including the violation features;
and configuring the pre-acquired artificial neural network, and training the artificial neural network according to the training data set pair to obtain the recognition model.
5. The method for monitoring the construction site violation according to claim 4, wherein the artificial neural network is a yolov5 network, the yolov5 network comprises a trunk network, a neck network and a head network which are sequentially connected, and the trunk network comprises a cross-stage local network; configuring an artificial neural network, comprising:
acquiring a set type convolution network and an deconvolution layer;
and replacing the cross-stage local network according to the intensive convolutional network, and adding the deconvolution layer to the bottom layer of the neck network, so that the neck network is connected with the head network through the deconvolution layer, and the configuration of the artificial neural network is completed.
6. A method for monitoring worksite violations according to claim 4, wherein training the configured artificial neural network based on the training data set includes:
zooming the positive sample in the training data set according to a preset size, and performing data enhancement on the zoomed positive sample;
carrying out affine transformation on the positive sample after the data enhancement according to the affine matrix, wherein the affine transformation comprises rotation, scaling, random cutting and translation operation;
and training the configured artificial neural network based on the positive sample after the affine transformation.
7. The method for monitoring the construction site violation according to claim 1, wherein the monitoring of the construction site violation based on the construction site image containing the violation feature, the violation type, and the acquisition time of the construction site image containing the violation feature comprises:
pushing the construction site image, the violation type and the acquisition time of the construction site image containing the violation characteristic to an upper-layer platform, and monitoring based on the upper-layer platform;
or configuring a message queue based on the construction site image, the violation type and the acquisition time of the construction site image containing the violation characteristics, pushing the message queue to an upper platform, and monitoring based on the upper platform.
8. A worksite violation monitoring system, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a construction site image of a target construction site and acquisition time of the construction site image;
the recognition module is used for recognizing the construction site image according to a pre-established recognition model to obtain a recognition result;
the mapping module is used for determining the violation type of the violation feature in the identification result according to a preset mapping relation between the violation feature and the violation type when the identification result comprises the violation feature;
and the storage module is used for monitoring the violation of the construction site based on the construction site image containing the violation features, the violation type and the acquisition time of the construction site image containing the violation features.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements the method of any one of claims 1 to 7.
10. An electronic device, comprising: a processor and a memory;
the memory is configured to store a computer program and the processor is configured to execute the computer program stored by the memory to cause the terminal to perform the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706719.1A CN115205780A (en) | 2022-06-21 | 2022-06-21 | Construction site violation monitoring method, system, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706719.1A CN115205780A (en) | 2022-06-21 | 2022-06-21 | Construction site violation monitoring method, system, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115205780A true CN115205780A (en) | 2022-10-18 |
Family
ID=83575774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210706719.1A Pending CN115205780A (en) | 2022-06-21 | 2022-06-21 | Construction site violation monitoring method, system, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115205780A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601709A (en) * | 2022-11-07 | 2023-01-13 | 北京万理软件开发有限公司（Cn） | Coal mine employee violation statistical system, method and device and storage medium |
| CN117611928A (en) * | 2024-01-23 | 2024-02-27 | 青岛国实科技集团有限公司 | Illegal electric welding identification method, electronic equipment and storage medium |
-
2022
- 2022-06-21 CN CN202210706719.1A patent/CN115205780A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601709A (en) * | 2022-11-07 | 2023-01-13 | 北京万理软件开发有限公司（Cn） | Coal mine employee violation statistical system, method and device and storage medium |
| CN115601709B (en) * | 2022-11-07 | 2023-10-27 | 北京万理软件开发有限公司 | Colliery staff violation statistics system, method, device and storage medium |
| CN117611928A (en) * | 2024-01-23 | 2024-02-27 | 青岛国实科技集团有限公司 | Illegal electric welding identification method, electronic equipment and storage medium |
| CN117611928B (en) * | 2024-01-23 | 2024-04-09 | 青岛国实科技集团有限公司 | Illegal electric welding identification method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11238272B2 (en) | Method and apparatus for detecting face image | |
| CN107622240B (en) | Face detection method and device | |
| CN115205780A (en) | Construction site violation monitoring method, system, medium and electronic equipment | |
| KR102002024B1 (en) | Method for processing labeling of object and object management server | |
| TW202121233A (en) | Image processing method, processor, electronic device, and storage medium | |
| CN110659391A (en) | Video detection method and device | |
| US20240104248A1 (en) | Privacy transformations in data analytics | |
| CN111353436A (en) | Super store operation analysis method and device based on image deep learning algorithm | |
| CN116347045B (en) | Monitoring method, device, equipment and storage medium based on communication and satellite technology | |
| Balchandani et al. | A deep learning framework for smart street cleaning | |
| CN114241358A (en) | Equipment state display method, device and equipment based on digital twin transformer substation | |
| CN114550076A (en) | Method, device and equipment for monitoring area abnormal behaviors and storage medium | |
| CN112001322A (en) | Method and device for determining tag personnel gathering and storage medium | |
| CN111950457A (en) | Oil field safety production image identification method and system | |
| CN114067396A (en) | Vision learning-based digital management system and method for live-in project field test | |
| CN112528825A (en) | Station passenger recruitment service method based on image recognition | |
| CN113378790A (en) | Viewpoint positioning method, apparatus, electronic device and computer-readable storage medium | |
| CN117455762A (en) | Method and system for improving resolution of recorded picture based on panoramic automobile data recorder | |
| CN115760886B (en) | Land parcel dividing method and device based on unmanned aerial vehicle aerial view and related equipment | |
| CN109801394B (en) | Staff attendance checking method and device, electronic equipment and readable storage medium | |
| CN114743157B (en) | Pedestrian monitoring method, device, equipment and medium based on video | |
| CN114445751A (en) | Method and device for extracting video key frame image contour features | |
| CN112016503B (en) | Pavement detection method, device, computer equipment and storage medium | |
| CN112101192B (en) | Artificial intelligence-based camouflage detection method, device, equipment and medium | |
| CN113869427A (en) | Scene analysis method and device, electronic 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 |