Infrastructure construction site safety monitoring method and system based on semantic segmentation model

Abstract

The invention discloses an infrastructure construction site safety monitoring method and system based on a semantic segmentation model. The method comprises the following steps: acquiring scene information in an infrastructure construction site; processing the scene information to obtain preprocessed data; analyzing the preprocessed data based on a semantic segmentation model to obtain positioning information of a plurality of target objects; and making a decision according to the positioning information of the plurality of target objects to obtain feedback information, and synchronizing the feedback information to a cloud for storage. According to the invention, safe and efficient automatic monitoring and management of the construction site are realized, and the monitoring accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of construction management, and in particular to a method and system for infrastructure construction site safety monitoring based on a semantic segmentation model. Background Art

[0002] Infrastructure construction site monitoring is crucial to ensure project safety, improve work efficiency and reduce potential risks. Currently, personnel safety monitoring, equipment and machinery safety monitoring, material stacking safety monitoring, and construction area safety monitoring are mostly carried out by management personnel, which is time-consuming and labor-intensive and cannot avoid human errors.

[0003] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0004] The main purpose of this application is to provide a construction site safety monitoring method and system based on a semantic segmentation model, aiming to solve the problem of poor monitoring accuracy caused by manual construction site monitoring in the prior art.

[0005] A first aspect of an embodiment of the present application provides a construction site safety monitoring method based on a semantic segmentation model, and the construction site safety monitoring method based on the semantic segmentation model includes the following steps: acquiring scene information within the construction site; processing the scene information to obtain preprocessed data; analyzing the preprocessed data based on the semantic segmentation model to obtain positioning information of multiple target objects; making decisions based on the positioning information of the multiple target objects to obtain feedback information, and synchronizing the feedback information to the cloud for storage.

[0006] Optionally, in one embodiment of the present application, the scene information includes environment data and image data, and the pre-processed data includes environment pre-processed data and image pre-processed data; the processing of the scene information to obtain the pre-processed data specifically includes: performing signal denoising processing on the environment data and the image data, respectively, to obtain environment denoising data and image denoising data; performing data conversion on the environment denoising data and the image denoising data, respectively, and performing time synchronization on the converted environment denoising data and the image denoising data, to obtain environment pre-processing data and image pre-processing data.

[0007] Optionally, in one embodiment of the present application, the semantic segmentation model includes a convolution layer, and the multiple target objects include equipment and personnel; the pre-processed data is analyzed based on the semantic segmentation model to obtain the positioning information of the multiple target objects, specifically including: extracting image features in the image pre-processing data through the convolution layer; and determining the positioning information of the equipment and personnel based on the image features.

[0008] Optionally, in one embodiment of the present application, the positioning information includes a moving path and a behavior pattern; the identifying each pixel in the image feature to determine the positioning information of the device and the personnel specifically includes: classifying each pixel in the image feature to determine the devices and personnel in the image; generating a bounding box corresponding to each of the devices and the personnel; tracking the bounding box corresponding to each of the devices and the personnel to obtain the moving path and behavior pattern corresponding to each of the devices and the personnel.

[0009] Optionally, in one embodiment of the present application, making a decision based on the positioning information of the multiple target objects to obtain feedback information specifically includes: performing analysis based on the positioning information of the equipment and the personnel to obtain an analysis result; if the analysis result is that there is an abnormal situation in the infrastructure construction site, triggering an alarm and generating feedback information.

[0010] Optionally, in one embodiment of the present application, synchronizing the feedback information to the cloud for storage specifically includes: temporarily storing the feedback information to generate storage information; sending the storage information to the cloud for storage, and receiving control instructions generated by the cloud based on the storage information.

[0011] Optionally, in one embodiment of the present application, the feedback information is synchronized to the cloud for storage, and then further includes: predicting the safety situation existing in the infrastructure construction site based on the feedback information to obtain prediction information to notify relevant personnel to implement preventive measures according to the prediction information.

[0012] The second aspect of the embodiment of the present application further provides a construction site safety monitoring device based on a semantic segmentation model, wherein the construction site safety monitoring device based on a semantic segmentation model includes:

[0013] Information acquisition module, used to obtain scene information in the infrastructure construction site;

[0014] A data processing module, used to process the scene information to obtain pre-processed data;

[0015] A data analysis module, used to analyze the preprocessed data based on a semantic segmentation model to obtain positioning information of multiple target objects;

[0016] The decision generation module is used to make a decision based on the positioning information of the multiple target objects, obtain feedback information, and synchronize the feedback information to the cloud for storage.

[0017] The third aspect of an embodiment of the present application also provides an edge computing device, wherein the edge computing device includes: a memory, a processor, and a construction site safety monitoring program based on a semantic segmentation model stored in the memory and executable on the processor, wherein the construction site safety monitoring program based on a semantic segmentation model implements the steps of the construction site safety monitoring method based on a semantic segmentation model as described above when executed by the processor.

[0018] The fourth aspect of the embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a construction site safety monitoring program based on a semantic segmentation model, and when the construction site safety monitoring program based on a semantic segmentation model is executed by a processor, the steps of the construction site safety monitoring method based on a semantic segmentation model as described above are implemented.

[0019] Beneficial effects: The present application provides a method and system for infrastructure construction site safety monitoring based on a semantic segmentation model. The method monitors the construction site status in real time and makes decisions immediately when an abnormality is found, thereby achieving safe and efficient automated monitoring and management of the construction site and improving monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flow chart of a preferred embodiment of the infrastructure construction site safety monitoring method based on the semantic segmentation model of the present application;

[0022] Figure 2 It is a structural schematic diagram of a preferred embodiment of the infrastructure construction site safety monitoring system based on the semantic segmentation model of the present application;

[0023] Figure 3 It is a structural schematic diagram of a preferred embodiment of the infrastructure construction site safety monitoring device based on the semantic segmentation model of the present application;

[0024] Figure 4 This is a schematic diagram of the structure of a preferred embodiment of the edge computing device of the present application.

[0025] Description of reference numerals:

[0026] 10. A construction site safety monitoring device based on a semantic segmentation model; 100. An information acquisition module; 200. A data processing module; 300. A data analysis module; 400. A decision making module.

[0027] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical scheme and effect of the present application clearer and more specific, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. The described embodiments are only possible technical implementations of the present application, not all possible implementations. Based on the embodiments in the present application, those skilled in the art can completely combine the embodiments of the present application to obtain other embodiments without creative work, and these embodiments are also within the scope of protection of the present application.

[0029] In related technologies, manual monitoring is time-consuming and labor-intensive, and 24-hour monitoring cannot be achieved; human factors may lead to monitoring errors, such as fatigue and lack of concentration; it is impossible to accurately identify and segment different objects in the image in real time; and it is impossible to predict security issues that may occur in the future.

[0030] The following describes the infrastructure construction site safety monitoring method and system based on the semantic segmentation model of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the above-mentioned related technologies use manual monitoring of infrastructure construction sites, resulting in poor monitoring accuracy, the present application provides a infrastructure construction site safety monitoring method based on a semantic segmentation model. In this method, by real-time monitoring of the site status, decisions are made immediately when abnormalities are found, thereby achieving efficient and automated monitoring and management of site safety and improving monitoring accuracy. As a result, the technical problem that the related technologies use manual monitoring of infrastructure construction sites, resulting in poor monitoring accuracy, is solved.

[0031] It should be noted that the semantic segmentation model can classify each pixel in the image, thereby providing dense pixel-level prediction capabilities, which can separate different objects in the image and provide precise positioning information for each object. It is especially suitable for places with complex environments and personnel such as infrastructure construction sites.

[0032] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0033] The infrastructure construction site safety monitoring method based on the semantic segmentation model described in the preferred embodiment of the present application is as follows: Figure 1 As shown, the infrastructure construction site safety monitoring method based on the semantic segmentation model includes the following steps:

[0034] In step S101, scene information in the infrastructure construction site is obtained.

[0035] In a possible implementation, the scene information includes environment data and image data. The environment data collected by the sensor and the image data collected by the camera are received.

[0036] Specifically, sensor network deployment: temperature, gas and other sensors are deployed to collect real-time environmental data. These sensors continuously monitor the environmental conditions of the construction site to ensure safety and timely detect potential environmental risks. Camera installation: Cameras are installed at key locations on the construction site to monitor building structures, equipment status and personnel activities. The cameras provide visual image data for further analysis and monitoring. Edge computing devices deployed on the construction site perform data preprocessing and real-time analysis, so that they can respond quickly and process sensor and camera data.

[0037] In step S102, the scene information is processed to obtain pre-processed data.

[0038] In a possible implementation, the preprocessed data includes environment preprocessed data and image preprocessed data. The environment data and the image data are respectively subjected to signal denoising to obtain environment denoised data and image denoised data; the environment denoised data and the image denoised data are respectively subjected to data conversion, and the converted environment denoised data and the image denoised data are time-synchronized to obtain environment preprocessed data and image preprocessed data.

[0039] It is understood that the received data is pre-processed, including data cleaning, formatting and preliminary analysis. For example, for image data, it may include resizing the image, applying filters to reduce noise, etc.

[0040] Specifically, data preprocessing, which performs signal amplification and filtering on the data from the sensor to clarify the signal and remove noise; converting the data into a unified format to ensure the consistency and compatibility of subsequent processing; ensuring that data from different sources are synchronized in time is crucial for subsequent analysis. Instant analysis, running lightweight algorithms to detect abnormal patterns in the data, such as temperature rise, increased concentration of harmful gases, etc.; for camera image data, edge devices may perform preliminary image processing operations such as compression, cropping, and adjusting resolution. Feature extraction, combining data from different sensors and cameras to extract useful information; identifying key features in the data to prepare for further in-depth analysis.

[0041] In step S103, the preprocessed data is analyzed based on a semantic segmentation model to obtain positioning information of multiple target objects.

[0042] In a possible implementation, the semantic segmentation model includes a convolution layer, and the multiple target objects include equipment and personnel; image features in the image preprocessing data are extracted through the convolution layer; and positioning information of the equipment and personnel is determined based on the image features.

[0043] Specifically, a lightweight semantic segmentation model or other machine learning algorithm is run to analyze the preprocessed data in real time. At this stage, the device will identify and segment different objects in the image, such as people, equipment, and material stacks.

[0044] In a possible implementation, the positioning information includes a moving path and a behavior pattern. Each pixel in the image feature is classified to determine the device and person in the image; a bounding box corresponding to each of the device and the person is generated; and the bounding box corresponding to each of the device and the person is tracked to obtain a moving path and a behavior pattern corresponding to each of the device and the person.

[0045] Specifically, the pre-trained semantic segmentation model is loaded on the edge computing device. The model extracts image features through the convolution layer, classifies each pixel in the image, determines which category it belongs to (such as personnel, equipment, materials, etc.), and further distinguishes different instances in the same category if necessary. Target detection and recognition generates positioning information for each identified target, such as a bounding box or pixel-level mask; the detected target is tracked to monitor its movement path and behavior pattern.

[0046] In step S104, a decision is made based on the positioning information of the plurality of target objects to obtain feedback information, and the feedback information is synchronized to the cloud for storage.

[0047] In a possible implementation, analysis is performed based on the positioning information of the equipment and the personnel to obtain an analysis result; if the analysis result indicates that an abnormal situation exists in the infrastructure construction site, an alarm is triggered and feedback information is generated.

[0048] Specifically, based on the results of real-time analysis, edge devices can make local decisions. For example, if a fire is detected (through gas sensors and temperature sensors), the edge device can immediately trigger an alarm and activate the fire extinguishing system, while notifying the central server.

[0049] In the embodiments of the present application, the results of semantic segmentation can be used to better understand the scene, such as identifying dangerous areas, calculating personnel density, monitoring equipment operating status, etc.; abnormal situations can be detected based on the segmentation results, such as unauthorized entry, equipment moving to an unsafe location, improper stacking of materials, etc.

[0050] In a possible implementation, the feedback information is temporarily stored to generate storage information; the storage information is sent to the cloud for storage, and a control instruction generated by the cloud according to the storage information is received.

[0051] Specifically, since edge devices have already processed and analyzed most of the data, only summary information or data that requires further in-depth analysis is sent to the cloud or central server. This greatly reduces the amount of data transmission and reduces the load on the central server. Edge devices usually have local storage capabilities, which can temporarily store data when the network is unstable or disconnected, and then synchronize to the cloud after the network is restored.

[0052] In a possible implementation, the safety situation existing at the infrastructure construction site is predicted based on the feedback information to obtain prediction information, so as to notify relevant personnel to implement preventive measures according to the prediction information.

[0053] In an embodiment of the present application, the results of semantic segmentation and feedback from on-site are collected to continuously optimize the accuracy and performance of the model; the semantic segmentation model is regularly updated to adapt to changes in the construction site environment and new working conditions.

[0054] In the embodiments of the present application, the method can improve the safety monitoring efficiency of infrastructure construction sites and reduce human errors; achieve 24-hour all-weather monitoring to ensure project safety; accurately identify and segment different objects in the image and provide fine positioning information for each object; predict possible safety issues in the future and take preventive measures in advance.

[0055] Figure 2 It is a block diagram of a construction site safety monitoring system based on a semantic segmentation model according to an embodiment of the present application.

[0056] The monitoring system uses distributed equipment to monitor unsafe behaviors of people, unsafe factors in the environment, and unsafe conditions of objects, and integrates collected data to achieve efficient monitoring and management. At the same time, the semantic segmentation model is used to accurately segment and identify each target in the collected image data, including construction personnel, equipment and machinery status, material stacking, construction area, etc.

[0057] The basic design includes providing real-time environmental data through a network of temperature, gas and other sensors deployed on the construction site, setting up cameras at key locations to monitor building structure, equipment status, personnel activities, etc., and processing sensor data through edge computing devices deployed on the construction site, accurately segmenting and identifying various targets on the construction site based on semantic segmentation models, or uploading data to the cloud for in-depth storage, processing, analysis and management. When an abnormal situation occurs, an alarm can be sent and remote control can be performed. At the same time, machine learning models can be used to predict possible safety issues in the future for the collected data.

[0058] This solution specifically requires the development of the cloud, edge and device sides. The device side can complete basic command operations, collect data through built-in sensors and return the information to the edge side through networking. The edge side performs real-time data processing and ensures local decision-making and control when there is no network. The cloud side needs to store and analyze the collected data and provide global decision-making and coordination.

[0059] Specifically, the cloud: integrates and analyzes data to provide site status monitoring; sends alarms and remotely controls when abnormal situations occur; and makes predictions based on collected data and its learning.

[0060] Edge computing devices: process sensor data; use speech segmentation models to identify, track, and segment targets; and execute instructions sent from the cloud.

[0061] Dust sensors, gas sensors, temperature sensors, etc. collect environmental data; collect real-time image data by monitoring construction areas, land subsidence, and personnel behavior; collect information on personnel and vehicle entry and exit.

[0062] Next, a construction site safety monitoring device based on a semantic segmentation model proposed in an embodiment of the present application is described with reference to the accompanying drawings.

[0063] Figure 3 It is a block diagram of a construction site safety monitoring device based on a semantic segmentation model according to an embodiment of the present application.

[0064] like Figure 3 As shown, the infrastructure construction site safety monitoring device 10 based on the semantic segmentation model includes: an information acquisition module 100, a data processing module 200, a data analysis module 300 and a decision generation module 400.

[0065] Specifically, the information acquisition module 100 is used to acquire scene information in the infrastructure construction site;

[0066] The data processing module 200 is used to process the scene information to obtain pre-processed data;

[0067] A data analysis module 300 is used to analyze the preprocessed data based on a semantic segmentation model to obtain positioning information of multiple target objects;

[0068] The decision generation module 400 is used to make a decision based on the positioning information of the multiple target objects, obtain feedback information, and synchronize the feedback information to the cloud for storage.

[0069] Figure 4 A schematic diagram of the structure of an edge computing device provided in an embodiment of the present application. The edge computing device may include:

[0070] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0071] When the processor 502 executes the program, the infrastructure construction site safety monitoring method based on the semantic segmentation model provided in the above embodiment is implemented.

[0072] Furthermore, the edge computing device also includes:

[0073] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0074] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0075] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0076] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EIS) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0077] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0078] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0079] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned infrastructure construction site safety monitoring method based on the semantic segmentation model is implemented.

[0080] One embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the present application Figure 1 A construction site safety monitoring method based on a semantic segmentation model is provided in any of the corresponding embodiments.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0082] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0083] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0084] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary, and then storing it in a computer memory.

[0085] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0086] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0087] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0088] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0089] It should be understood that the application of the present application is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to this application.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A construction site safety monitoring method based on a semantic segmentation model, characterized in that: The infrastructure construction site safety monitoring method based on the semantic segmentation model includes: Obtain scene information within the infrastructure construction site; Processing the scene information to obtain preprocessed data; Analyzing the preprocessed data based on a semantic segmentation model to obtain positioning information of multiple target objects; A decision is made based on the positioning information of the plurality of target objects to obtain feedback information, and the feedback information is synchronized to the cloud for storage.

2. The construction site safety monitoring method based on the semantic segmentation model according to claim 1 is characterized in that: The scene information includes environment data and image data, and the preprocessing data includes environment preprocessing data and image preprocessing data; The processing of the scene information to obtain preprocessed data specifically includes: Performing signal denoising processing on the environment data and the image data respectively to obtain environment denoising data and image denoising data; The environment denoising data and the image denoising data are respectively converted, and the converted environment denoising data and the image denoising data are time-synchronized to obtain environment preprocessing data and image preprocessing data.

3. The construction site safety monitoring method based on the semantic segmentation model according to claim 2 is characterized in that: The semantic segmentation model includes a convolutional layer, and the plurality of target objects include equipment and personnel; The analyzing the pre-processed data based on the semantic segmentation model to obtain the positioning information of multiple target objects specifically includes: Extracting image features in the image preprocessing data through the convolution layer; The positioning information of the equipment and personnel is determined according to the image features.

4. The construction site safety monitoring method based on the semantic segmentation model according to claim 3 is characterized in that: The positioning information includes movement path and behavior pattern; The identifying each pixel in the image feature to determine the location information of the device and the person specifically includes: Classifying each pixel in the image feature to determine devices and people in the image; Generate a bounding box corresponding to each of the devices and the person; The boundary boxes corresponding to each of the devices and the personnel are tracked to obtain the movement paths and behavior patterns corresponding to each of the devices and the personnel.

5. The construction site safety monitoring method based on semantic segmentation model according to claim 3 is characterized in that: The making a decision based on the positioning information of the plurality of target objects to obtain feedback information specifically includes: Performing analysis based on the location information of the device and the person to obtain an analysis result; If the analysis result indicates that an abnormal situation exists in the infrastructure construction site, an alarm is triggered and feedback information is generated.

6. The construction site safety monitoring method based on semantic segmentation model according to claim 1 is characterized in that: The step of synchronizing the feedback information to the cloud for storage specifically includes: Temporarily storing the feedback information to generate storage information; The stored information is sent to the cloud for storage, and a control instruction generated by the cloud according to the stored information is received.

7. The construction site safety monitoring method based on semantic segmentation model according to claim 1 is characterized in that: The step of synchronizing the feedback information to the cloud for storage further includes: Based on the feedback information, the safety situation existing in the infrastructure construction site is predicted to obtain prediction information to notify relevant personnel to implement preventive measures according to the prediction information.

8. A construction site safety monitoring device based on a semantic segmentation model, characterized in that: The infrastructure construction site safety monitoring device based on the semantic segmentation model includes: Information acquisition module, used to obtain scene information in the infrastructure construction site; A data processing module, used to process the scene information to obtain pre-processed data; A data analysis module, used to analyze the preprocessed data based on a semantic segmentation model to obtain positioning information of multiple target objects; The decision generation module is used to make a decision based on the positioning information of the multiple target objects, obtain feedback information, and synchronize the feedback information to the cloud for storage.

9. An edge computing device, characterized in that: The edge computing device includes: a memory, a processor, and a construction site safety monitoring program based on a semantic segmentation model stored in the memory and executable on the processor. When the construction site safety monitoring program based on a semantic segmentation model is executed by the processor, the steps of the construction site safety monitoring method based on a semantic segmentation model as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a construction site safety monitoring program based on a semantic segmentation model. When the construction site safety monitoring program based on a semantic segmentation model is executed by a processor, the steps of the construction site safety monitoring method based on a semantic segmentation model as described in any one of claims 1 to 7 are implemented.

Images