A digital supervision management method and system applied to engineering projects

Abstract

The present application relates to the technical field of project supervision, and in particular to a digital supervision management method and system applied to engineering projects. The method comprises: processing construction site images to obtain processed construction site images, classifying the processed construction site images into categories to obtain a historical site image set and a current site image set, performing key abnormality analysis on the historical site image set to obtain key monitoring locations and an abnormality processing image set, screening the current site image set based on the key monitoring locations to obtain a first priority image, determining whether the first priority image has an image abnormality, and if so, performing similarity processing on the first priority image according to the abnormality processing image set to obtain construction information, determining whether the construction information contains a preset construction abnormality, and if so, generating an alarm instruction and controlling the alarm device to output an alarm. The present application improves the efficiency of supervision of the construction site.

Description

Technical Field

[0001] The present application relates to the technical field of project supervision, and in particular to a digital supervision management method and system applied to engineering projects. Background Art

[0002] During the implementation of power grid projects, safety and quality supervision is often required. Currently, the safety and quality supervision system in my country's engineering construction industry can be divided from different perspectives. For example, based on management levels, it can be divided into government safety and quality supervision, enterprise safety and quality management, and project safety and quality control.

[0003] Currently, power grid supervision and management, centered around the project lifecycle, can be broken down into several key phases. These include safety education and training oversight, construction site supervision, material quality oversight, quality acceptance and assessment oversight, and construction records and archives management oversight. These supervisory measures collectively constitute the safety and quality oversight system for power grid projects during their construction phase, providing a strong foundation for their smooth implementation and operation.

[0004] Among the key steps in power grid supervision and management, construction site supervision is one of the longest and most challenging aspects to implement. Common methods for construction site supervision involve capturing footage of the construction site through cameras. These cameras then perform image detection to determine if any abnormal construction activity or operating facilities are present. If so, electronic equipment generates alarm signals, triggering an alarm device to sound an alarm, alerting staff to promptly address the anomaly.

[0005] Regarding the common technologies mentioned above, the inventors believe that due to the influence of various factors, such as occlusion, viewing angle, etc., when construction supervision is carried out through image detection technology, abnormal construction image targets will be mistakenly identified as normal construction image targets, or normal construction image targets will be mistakenly identified as abnormal construction image targets, resulting in missed reports or false reports, which reduces the efficiency of supervision of the construction site. Summary of the Invention

[0006] In order to solve at least one of the above technical problems, the present application provides a digital supervision management method and system for engineering projects.

[0007] In the first aspect, the present application provides a digital supervision management method for engineering projects, which adopts the following technical solutions:

[0008] A digital supervision management method applied to engineering projects, comprising:

[0009] Acquire construction site images, where the construction site images are site images corresponding to different time nodes within a preset construction site area;

[0010] Performing fine processing on the construction site image to obtain a processed construction site image;

[0011] Classify the processed construction site images into categories according to time nodes to obtain a historical site image set and a current site image set;

[0012] Performing a key anomaly analysis on the historical on-site image set to obtain key monitoring locations of the construction site and a set of anomaly processing images corresponding to the key monitoring locations;

[0013] Filtering the current scene image set based on the key monitoring location to obtain a first priority image containing the key monitoring location;

[0014] determining whether the first-priority image has an image anomaly, and if so, performing similarity processing on the first-priority image according to the anomaly processing image set to obtain construction information of the first-priority image;

[0015] Determine whether there is a preset construction anomaly in the construction information. If so, generate an alarm instruction and control the alarm device to output an alarm.

[0016] By adopting the above technical solution, construction site images are obtained, and the on-site conditions at different time nodes within the preset construction site area are covered. This ensures comprehensive monitoring of the construction site and provides a rich data foundation for subsequent analysis. After fine-tuning the image processing, on-site details can be identified more clearly, providing high-quality image data for subsequent analysis. The processed construction site images are classified according to time nodes to obtain a historical site image set and a current site image set, thereby achieving effective management of construction site images. By performing key anomaly analysis on historical images, it is possible to accurately locate the key monitoring locations of the construction site and the anomaly processing image set, providing strong support for subsequent rapid response to anomalies. The current image is filtered based on the key monitoring location to obtain the first-priority image, thereby improving the efficiency of anomaly monitoring. By performing anomaly judgment on the first-priority image, it is determined whether there are anomalies such as occlusion that affect image monitoring. If so, the first-priority image is processed for similarity based on the anomaly processing image set to quickly obtain construction information corresponding to the occlusion anomaly in the first-priority image, and accurately determine whether there are preset anomalies in the construction. Once an abnormality is detected, an alarm instruction is immediately generated to control the output of the alarm equipment, realizing real-time monitoring and timely early warning of the construction site, improving the effective and safe management level of the construction site, and thus improving the supervision efficiency of the construction site.

[0017] In a preferred example, the present application may be further configured as follows: performing fine processing on the construction site image to obtain a processed construction site image includes:

[0018] Performing edge filtering on the construction site image to obtain standard contour layers of different construction workers and construction equipment at the construction site and key contour layers of behavioral details of the construction workers and operating status details of the construction equipment at the construction site;

[0019] Dividing the standard contour layer into a plurality of sub-regions, and collecting a regional histogram corresponding to each sub-region and an overall histogram corresponding to the standard contour layer, as well as a regional flatness corresponding to each sub-region and an overall flatness corresponding to the standard contour layer;

[0020] Determining an overall contrast curve and an overall brightness curve corresponding to the standard contour layer according to the overall histogram and the overall flatness;

[0021] Determining a regional contrast curve corresponding to each sub-region according to the sub-region histogram, and fusing the regional contrast curve with the overall contrast curve to obtain a fused contrast curve;

[0022] determining a brightness curve adjustment weight corresponding to each sub-region according to the flatness of the sub-region, and fusing the overall brightness curve with the fused contrast curve based on the brightness curve adjustment weight to obtain a parameter adjustment curve;

[0023] Adjusting each sub-region of the standard contour layer according to the parameter adjustment curve to obtain an adjusted standard contour layer;

[0024] The adjusted standard contour layer is fused with the key contour layer to obtain a processed construction site image.

[0025] In a preferred example, the present application may be further configured as follows: performing key abnormality analysis on the historical on-site image set to obtain key monitoring locations of the construction site and a set of abnormality-processed images corresponding to the key monitoring locations, including:

[0026] Performing an anomaly analysis on each image in the historical scene image set to obtain a shooting area corresponding to each image and an image anomaly type;

[0027] Summarize the abnormal marking points according to the shooting area to obtain a first marking point set corresponding to each shooting area at different time nodes;

[0028] Statistically dividing the abnormal marker point set according to the same image position coordinates to obtain a second marker point set corresponding to different position coordinates of each shooting area;

[0029] Determine whether the number of abnormal marking points corresponding to the second marking point set exceeds a preset abnormal number. If so, mark the position of the shooting area corresponding to the number of abnormal marking points to obtain the key monitoring position of the construction site;

[0030] Exception handling information corresponding to the key monitoring location is collected, and the exception handling information, the shooting area, and the image exception type are respectively bound to corresponding historical on-site images to obtain an exception handling image set corresponding to the key monitoring location.

[0031] In a preferred example, the present application may be further configured as follows: performing similarity processing on the first priority image according to the exception processing image set to obtain construction information of the first priority image includes:

[0032] Determine, based on the current scene image set, a common view scene image that is adjacent to the time position node of the first priority image and has the key monitoring position;

[0033] Performing three-dimensional simulation processing based on the first priority image and the common viewing scene image to obtain an abnormal three-dimensional image containing the image abnormality;

[0034] Determining abnormal coordinate information in the abnormal three-dimensional image and abnormal descriptor information corresponding to the abnormal coordinate information;

[0035] Performing a multi-dimensional spatial data search on the abnormal images in the abnormal processing image set based on the image feature points of the key monitoring positions in the abnormal three-dimensional image to obtain a matching image set;

[0036] performing similarity analysis on the first priority image and each abnormal image in the matching image set according to the abnormal coordinate information and the abnormal descriptor information to obtain similarity information;

[0037] Based on the similarity information, a similarity mean is determined, and it is judged whether the similarity mean satisfies a preset similarity range. If so, the target processing information, target area, and target abnormality type corresponding to the similarity mean in the abnormality processing image set are determined, and the target processing information, the target area, and the target abnormality type are respectively bound to the first priority image to obtain the construction information of the first priority image.

[0038] In a preferred example, the present application may be further configured as follows: the step of determining whether the first priority image has an image abnormality further includes:

[0039] If there is no image anomaly in the first priority image, determining based on the current on-site image set that there is no second priority image of the key monitoring location;

[0040] determining whether there is an image anomaly in the second-priority image; if so, determining a monitoring anomaly location where the image anomaly exists in the second-priority image; generating a UAV flight instruction based on the monitoring anomaly location, and controlling the UAV to fly from an initial location to the monitoring anomaly location for monitoring;

[0041] collecting the construction monitoring image sent by the drone, and determining whether the construction monitoring image contains a preset construction anomaly; if so, determining the information to be processed and the type of processing to be processed of the construction monitoring image based on the construction anomaly standard;

[0042] The key monitoring locations of the construction site and the abnormality processing image set corresponding to the key monitoring locations are pre-updated according to the monitored abnormality locations, the information to be processed and the type to be processed to obtain updated key monitoring locations and updated abnormality processing image set.

[0043] In a preferred example, the present application may be further configured as follows: pre-updating the key monitoring locations of the construction site and the abnormality processing image set corresponding to the key monitoring locations according to the abnormality monitoring locations, the information to be processed, and the type to be processed to obtain updated key monitoring locations and updated abnormality processing image set, and then further comprising:

[0044] Acquire data reflecting that the first-priority image has an image anomaly within a preset time;

[0045] Determining the abnormal frequency occurring at the key monitoring location according to the reflected data, and determining whether the abnormal frequency exceeds a preset abnormal frequency;

[0046] When the abnormal frequency does not exceed the preset abnormal frequency, the key monitoring position and the abnormal processing image set corresponding to the key monitoring position are eliminated and updated to obtain an updated key monitoring position and abnormal processing image set.

[0047] In a preferred example, the present application may be further configured as follows: performing an abnormality analysis on each image in the historical scene image set to obtain the shooting area and image abnormality type corresponding to each image includes:

[0048] Each image in the historical scene image set is input into a preset anomaly detection model for anomaly detection analysis to obtain the shooting area and image anomaly type corresponding to each image.

[0049] In a second aspect, the present application provides a digital supervision management system for engineering projects, which adopts the following technical solutions:

[0050] A digital supervision management system applied to engineering projects, comprising:

[0051] An image acquisition module is used to acquire construction site images, wherein the construction site images are site images corresponding to different time nodes within a preset construction site area;

[0052] An image processing module is used to perform fine processing on the construction site image to obtain a processed construction site image;

[0053] An image classification module is used to classify the processed construction site images according to time nodes to obtain a historical site image set and a current site image set;

[0054] An anomaly analysis module, configured to perform a key anomaly analysis on the historical on-site image set to obtain a key monitoring location of the construction site and an anomaly processing image set corresponding to the key monitoring location;

[0055] An image screening module, configured to screen the current scene image set based on the key monitoring location to obtain a first priority image containing the key monitoring location;

[0056] a similarity processing module, configured to determine whether the first-priority image has an image anomaly, and if so, perform similarity processing on the first-priority image based on the anomaly processing image set to obtain construction information of the first-priority image;

[0057] The alarm control module determines whether there is a preset construction anomaly in the construction information. If so, it generates an alarm instruction and controls the alarm device to output an alarm.

[0058] In a possible implementation, when the image processing module performs fine processing on the construction site image to obtain the processed construction site image, it is specifically configured to:

[0059] Performing edge filtering on the construction site image to obtain standard contour layers of different construction workers and construction equipment at the construction site and key contour layers of behavioral details of the construction workers and operating status details of the construction equipment at the construction site;

[0060] Dividing the standard contour layer into a plurality of sub-regions, and collecting a regional histogram corresponding to each sub-region and an overall histogram corresponding to the standard contour layer, as well as a regional flatness corresponding to each sub-region and an overall flatness corresponding to the standard contour layer;

[0061] Determining an overall contrast curve and an overall brightness curve corresponding to the standard contour layer according to the overall histogram and the overall flatness;

[0062] Determining a regional contrast curve corresponding to each sub-region according to the sub-region histogram, and fusing the regional contrast curve with the overall contrast curve to obtain a fused contrast curve;

[0063] determining a brightness curve adjustment weight corresponding to each sub-region according to the flatness of the sub-region, and fusing the overall brightness curve with the fused contrast curve based on the brightness curve adjustment weight to obtain a parameter adjustment curve;

[0064] Adjusting each sub-region of the standard contour layer according to the parameter adjustment curve to obtain an adjusted standard contour layer;

[0065] The adjusted standard contour layer is fused with the key contour layer to obtain a processed construction site image.

[0066] In another possible implementation, when the anomaly analysis module performs a focused anomaly analysis on the historical site image set to obtain a key monitoring location of the construction site and an anomaly processing image set corresponding to the key monitoring location, the anomaly analysis module is specifically configured to:

[0067] Performing an anomaly analysis on each image in the historical scene image set to obtain a shooting area corresponding to each image and an image anomaly type;

[0068] Summarize the abnormal marking points according to the shooting area to obtain a first marking point set corresponding to each shooting area at different time nodes;

[0069] Statistically dividing the abnormal marker point set according to the same image position coordinates to obtain a second marker point set corresponding to different position coordinates of each shooting area;

[0070] Determine whether the number of abnormal marking points corresponding to the second marking point set exceeds a preset abnormal number. If so, mark the position of the shooting area corresponding to the number of abnormal marking points to obtain the key monitoring position of the construction site;

[0071] Exception handling information corresponding to the key monitoring location is collected, and the exception handling information, the shooting area, and the image exception type are respectively bound to corresponding historical on-site images to obtain an exception handling image set corresponding to the key monitoring location.

[0072] In another possible implementation, when the similarity processing module performs similarity processing on the first priority image according to the exception processing image set to obtain the construction information of the first priority image, it is specifically configured to:

[0073] Determine, based on the current scene image set, a common view scene image that is adjacent to the time position node of the first priority image and has the key monitoring position;

[0074] Performing three-dimensional simulation processing based on the first priority image and the common viewing scene image to obtain an abnormal three-dimensional image containing the image abnormality;

[0075] Determining abnormal coordinate information in the abnormal three-dimensional image and abnormal descriptor information corresponding to the abnormal coordinate information;

[0076] performing a multidimensional spatial data search on the abnormal images in the abnormal processing image set based on the image feature points of the key monitoring positions in the abnormal three-dimensional image to obtain a matching image set;

[0077] performing similarity analysis on the first priority image and each abnormal image in the matching image set according to the abnormal coordinate information and the abnormal descriptor information to obtain similarity information;

[0078] Based on the similarity information, a similarity mean is determined, and it is judged whether the similarity mean satisfies a preset similarity range. If so, the target processing information, target area, and target abnormality type corresponding to the similarity mean in the abnormality processing image set are determined, and the target processing information, the target area, and the target abnormality type are respectively bound to the first priority image to obtain the construction information of the first priority image.

[0079] In another possible implementation, the system further includes: an image determination module, a flight control module, a flight monitoring module, and a data update module, wherein:

[0080] The image determination module is configured to determine, based on the current on-site image set, that there is no second-priority image of the key monitoring location when there is no image anomaly in the first-priority image;

[0081] The flight control module is configured to determine whether there is an image anomaly in the second-priority image, and if so, determine a monitoring anomaly location where the image anomaly exists in the second-priority image, and generate a UAV flight instruction based on the monitoring anomaly location to control the UAV to fly from an initial location to the monitoring anomaly location for monitoring;

[0082] The flight monitoring module is configured to collect the construction monitoring images sent by the drone and determine whether the images contain a preset construction anomaly. If so, the module determines the information to be processed and the type of processing to be performed on the images based on a construction anomaly standard.

[0083] The data update module is used to pre-update the key monitoring locations of the construction site and the abnormal processing image set corresponding to the key monitoring locations according to the monitored abnormal locations, the information to be processed and the type to be processed, to obtain the updated key monitoring locations and the updated abnormal processing image set.

[0084] In another possible implementation, the system further includes: a data acquisition module, a frequency determination module, and a data elimination module, wherein:

[0085] The data acquisition module is used to acquire data reflecting that the first priority image has an image anomaly within a preset time;

[0086] The frequency determination module is used to determine the abnormal frequency occurring at the key monitoring location according to the reflected data, and determine whether the abnormal frequency exceeds a preset abnormal frequency;

[0087] The data elimination module is used to eliminate and update the key monitoring position and the abnormal processing image set corresponding to the key monitoring position when the abnormal frequency does not exceed the preset abnormal frequency, so as to obtain an updated key monitoring position and abnormal processing image set.

[0088] In another possible implementation, when the anomaly analysis module performs an anomaly analysis on each image in the historical scene image set to obtain the shooting area and image anomaly type corresponding to each image, it is specifically configured to:

[0089] Each image in the historical scene image set is input into a preset anomaly detection model for anomaly detection analysis to obtain the shooting area and image anomaly type corresponding to each image.

[0090] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0091] at least one processor;

[0092] Memory;

[0093] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned digital supervision management method applied to engineering projects.

[0094] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0095] A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute a digital supervision management method applied to an engineering project.

[0096] In summary, this application includes at least one of the following beneficial technical effects:

[0097] Acquire construction site images and cover the on-site conditions at different time nodes within the preset construction site area. This ensures comprehensive monitoring of the construction site and provides a rich data foundation for subsequent analysis. After fine-tuning the image processing, on-site details can be more clearly identified, providing high-quality image data for subsequent analysis. The processed construction site images are classified by time nodes to obtain a historical on-site image set and a current on-site image set, thereby achieving effective management of construction site images. Performing key anomaly analysis on historical images can accurately locate the key monitoring locations of the construction site and the anomaly processing image set, providing strong support for subsequent rapid response to anomalies. Filtering the current image based on the key monitoring location to obtain the first-priority image improves the efficiency of anomaly monitoring. By performing anomaly judgment on the first-priority image, it is determined whether there are anomalies such as occlusion that affect image monitoring. If so, the first-priority image is processed for similarity based on the anomaly processing image set to quickly obtain construction information corresponding to the occlusion anomaly in the first-priority image, and accurately determine whether there are preset anomalies in the construction. Once an abnormality is detected, an alarm instruction is immediately generated to control the output of the alarm equipment, realizing real-time monitoring and timely early warning of the construction site, improving the effective and safe management level of the construction site, and thus improving the supervision efficiency of the construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 A flowchart of a digital supervision management method for an engineering project provided in an embodiment of the present application;

[0099] Figure 2 A schematic diagram of the structure of a digital supervision management system for an engineering project provided in an embodiment of the present application;

[0100] Figure 3A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0101] The following is combined with Figure 1 To the attached Figure 3 This application is described in further detail.

[0102] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0103] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0104] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0105] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0106] The embodiment of the present application provides a digital supervision and management method for engineering projects, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected through wired or wireless communication. The embodiment of the present application does not limit this. Figure 1 As shown, the method includes:

[0107] Step S10: Acquire a construction site image.

[0108] The construction site images are site images corresponding to different time nodes within a preset construction site area.

[0109] For the embodiment of the present application, the construction site image representation is the actual picture of the construction site captured by photography or video equipment during the construction process. These images are generally used to record construction progress, check construction quality or monitor on-site safety and other situations. The preset construction site area refers to a specific building construction area determined and demarcated in advance, and this area is the target range for obtaining images. Different time nodes are used to represent different time periods or time points at the construction site, such as the initial, mid-term, and later stages of construction, or different time periods of each day (such as morning, afternoon, and evening).

[0110] In the embodiments of this application, an existing monitoring system is utilized. First, a monitoring camera is installed at the construction site, ensuring that the camera's field of view covers the entire preset area. Second, the monitoring system's recording parameters, such as recording time, resolution, and storage location, are configured. Finally, the monitoring system automatically records images of the construction site at the set time points and saves the image data to a designated storage device.

[0111] Step S11: performing fine processing on the construction site image to obtain a processed construction site image.

[0112] In the embodiment of the present application, edge filtering is performed on the construction site image to obtain standard contour layers of different construction workers and construction equipment at the construction site, as well as key contour layers of the behavioral details of the construction workers and the operating status details of the construction equipment at the construction site. The standard contour layer is divided into multiple sub-regions, and the regional histogram corresponding to each sub-region and the overall histogram corresponding to the standard contour layer, as well as the regional flatness corresponding to each sub-region and the overall flatness corresponding to the standard contour layer are collected. The overall contrast curve and the overall brightness curve corresponding to the standard contour layer are determined based on the overall histogram and the overall flatness. The regional contrast curve corresponding to each sub-region is determined based on the sub-region histogram, and the regional contrast curve is fused with the overall contrast curve to obtain a fused contrast curve. The brightness curve adjustment weight corresponding to each sub-region is determined based on the sub-region flatness, and based on the brightness curve adjustment weight, the overall brightness curve is fused with the fused contrast curve to obtain a parameter adjustment curve. The standard contour layer is adjusted for each sub-region according to the parameter adjustment curve to obtain an adjusted standard contour layer. The adjusted standard contour layer is fused with the key contour layer to obtain a processed construction site image.

[0113] Step S12: Classify the processed construction site images according to time nodes to obtain a historical site image set and a current site image set.

[0114] Specifically, the historical site image collection refers to a collection of construction site images from one or more past time points, used for reviewing and analyzing historical conditions. The current site image collection refers to a collection of construction site images from the most recent or current time point, used for real-time monitoring and current status analysis.

[0115] In the embodiment of the present application, time information is extracted from the image using image recognition technology (such as OCR). Then, based on the preset time node rules, the image is determined to belong to the historical or current category. The image is stored in the corresponding historical scene image set and current scene image set respectively.

[0116] Step S13: performing a key anomaly analysis on the historical on-site image set to obtain key monitoring locations of the construction site and a set of anomaly processing images corresponding to the key monitoring locations.

[0117] In the embodiment of the present application, an abnormality analysis is performed on each image in the historical site image set to obtain the shooting area and image abnormality type corresponding to each image. The abnormal marking points are then aggregated according to the shooting area to obtain a first marking point set corresponding to each shooting area at different time nodes. The abnormal marking point set is statistically divided according to the same image position coordinates to obtain a second marking point set corresponding to different position coordinates of each shooting area. It is determined whether the number of abnormal marking points corresponding to the second marking point set exceeds the preset abnormal number. If it exceeds, the position of the shooting area corresponding to the number of abnormal marking points is marked to obtain the key monitoring position of the construction site, and the abnormality processing information corresponding to the key monitoring position is collected. The abnormality processing information, shooting area, and image abnormality type are respectively bound to the corresponding historical site image to obtain the abnormal processing image set corresponding to the key monitoring position.

[0118] Specifically, when performing anomaly analysis on each image in the historical scene image collection and obtaining the shooting area and image anomaly type corresponding to each image, it is specifically used to: input each image in the historical scene image collection into a preset anomaly detection model for anomaly detection analysis, and obtain the shooting area and image anomaly type corresponding to each image.

[0119] In an embodiment of the present application, each on-site image is preprocessed, including size standardization, grayscale conversion, or color space conversion, to meet the model input requirements. The preprocessed on-site image is then input into a deep learning-based anomaly detection model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), for feature extraction and anomaly identification. Finally, the model outputs anomaly detection results, including anomaly type and location information. In addition, other methods can also be used to implement anomaly detection, such as statistical-based methods or hybrid methods that combine deep learning and rules, which are not limited here.

[0120] In the embodiment of the present application, the image anomaly type refers to the category of abnormal conditions identified by the model, such as abnormal equipment operation, equipment failure, abnormal personnel behavior, etc.

[0121] Step S14: Filter the current scene image set based on the key monitoring location to obtain the first priority image where the key monitoring location exists.

[0122] Specifically, a deep learning-based approach is used. First, a deep learning model, such as a convolutional neural network (CNN), is trained to identify and locate key monitoring locations. Each image in the current on-site image set is then input into the model to obtain the confidence and location information of the key monitoring locations output by the model. Finally, based on the model output, the first-priority images with a confidence level higher than a preset threshold are screened. It is understood that other methods can also be used to implement image screening, such as rule-based methods or hybrid methods that combine deep learning and rules, which are not limited here.

[0123] Step S15: Determine whether there is an image anomaly in the first priority image. If so, perform similarity processing on the first priority image according to the anomaly processing image set to obtain construction information of the first priority image.

[0124] For an embodiment of the present application, a common view scene image adjacent to the time position node of the first priority image and having a key monitoring position is determined based on the current scene image set, three-dimensional simulation processing is performed based on the first priority image and the common view scene image to obtain an abnormal three-dimensional image with image abnormalities, abnormal coordinate information in the abnormal three-dimensional image and abnormal descriptor information corresponding to the abnormal coordinate information are determined, and a multi-dimensional spatial data search is performed on the abnormal images in the abnormal processing image set based on the image feature points of the key monitoring position in the abnormal three-dimensional image to obtain a matching image set, and a similarity analysis is performed between the first priority image and each abnormal image in the matching image set according to the abnormal coordinate information and the abnormal descriptor information to obtain similarity information, and a similarity mean is determined based on the similarity information, and it is judged whether the similarity mean satisfies a preset similarity range. If so, the target processing information, target area, and target abnormality type corresponding to the similarity mean in the abnormal processing image set are determined, and the target processing information, target area, and target abnormality type are respectively bound to the first priority image to obtain construction information of the first priority image.

[0125] Specifically, the description of image feature points at key monitoring locations in anomaly 3D images involves assigning a specific, identifiable ID to each extracted feature point. This ID is typically related to the brightness of the surrounding image, similar to assigning an ID number to each person. Feature point descriptions also typically include an intensity value, indicating the prominence of the feature. A higher intensity indicates less sensitivity to ambient lighting and greater stability, while a lower intensity indicates less reliability. Each extracted feature point can be represented as {(u, v), s, d}.

[0126] Where (u, v) represents the abnormal coordinates of the feature point, s is its intensity value, and d is the abnormal descriptor (usually a matrix of fixed size).

[0127] Specifically, the process of determining the abnormal coordinate information and abnormal descriptor information of the key monitoring position in the abnormal three-dimensional image includes: converting the abnormal three-dimensional image into an abnormal three-dimensional video according to a preset observation angle and preset action change rules, and collecting visual frames of the abnormal three-dimensional video to obtain object visual frames, analyzing and processing the object visual frames to obtain object map points, and determining the abnormal coordinate information and abnormal descriptor information corresponding to the image feature points of the key monitoring position in the abnormal three-dimensional image in different observation directions based on the object map points.

[0128] Among them, the preset observation angle includes the initial observation angle of the abnormal three-dimensional image and the final observation angle of the abnormal three-dimensional image. The preset action change rule is used to represent the change process rule of the abnormal three-dimensional image from the initial position to the final position. For example: when the abnormal three-dimensional image is tiled, its observation angle is defined as 90 degrees, that is, the observation is perpendicular to the abnormal three-dimensional image. At this time, the electronic device observes the image from left to right. The initial observation angle of the abnormal three-dimensional image is 0 degrees, and the final observation angle of the abnormal three-dimensional image is 180 degrees. The preset action change rule is based on the counterclockwise rotation of the central axis of the abnormal three-dimensional image, so that the observation angle of the abnormal three-dimensional image changes from 0 degrees to 180 degrees.

[0129] Specifically, based on the abnormal coordinate information and the abnormal descriptor information, a similarity analysis is performed between the first-priority image and each abnormal image in the matching image set to obtain similarity information. This includes: matching the abnormal coordinate information with the corresponding coordinate position of each abnormal image in the matching image set to obtain matching descriptor information, where the matching descriptor information is used to represent the descriptor information corresponding to the abnormal coordinate information for each abnormal image in the matching image set. A matrix comparison is performed between the descriptors in the abnormal descriptor information and the descriptors in the matching descriptor information to obtain similarity information.

[0130] Specifically, the descriptor matrix in the abnormal descriptor information is compared with the descriptor matrix in the matching descriptor information, and the matching degree in the two matrices is calculated to obtain similarity information. For example, if the descriptor matrix in the abnormal descriptor information and the descriptor matrix in the matching descriptor information both have three rows and three columns of data, i.e., nine groups of data, and nine of the groups of data are the same, then the average similarity of the two matrices is 100%. In this embodiment of the present application, the preset similarity range is that the average similarity is not less than 86%.

[0131] Step S16: Determine whether there is a preset construction anomaly in the construction information. If so, generate an alarm instruction and control the alarm device to output an alarm.

[0132] In an embodiment of the present application, construction site images are obtained, and the on-site conditions at different time nodes within a preset construction site area are covered. Comprehensive monitoring of the construction site is ensured, providing a rich data basis for subsequent analysis. After fine-tuning the image processing, on-site details can be more clearly identified, providing high-quality image data for subsequent analysis. The processed construction site images are classified according to time nodes to obtain a historical site image set and a current site image set, thereby achieving effective management of the construction site images. By performing key anomaly analysis on the historical images, the key monitoring positions and the anomaly processing image set of the construction site can be accurately located, providing strong support for subsequent rapid response to anomalies. The current image is filtered based on the key monitoring position to obtain a first-priority image, thereby improving the efficiency of anomaly monitoring. By performing anomaly judgment on the first-priority image, it is determined whether there is an anomaly such as occlusion that affects image monitoring. If so, the first-priority image is subjected to similarity processing based on the anomaly processing image set, and the construction information corresponding to the occlusion anomaly in the first-priority image is quickly obtained, and it is accurately judged whether there is a preset anomaly in the construction. Once an abnormality is detected, an alarm instruction is immediately generated to control the output of the alarm equipment, realizing real-time monitoring and timely early warning of the construction site, improving the effective and safe management level of the construction site, and thus improving the supervision efficiency of the construction site.

[0133] Furthermore, it is determined whether there is an image anomaly in the first priority image, and then it also includes: if there is no image anomaly in the first priority image, then based on the current on-site image set, it is determined that there is no second priority image at the key monitoring location. It is determined whether there is an image anomaly in the second priority image. If there is an image anomaly, then the monitoring anomaly location where the image anomaly exists in the second priority image is determined, and a UAV flight instruction is generated according to the monitoring anomaly location, and the UAV is controlled to fly from the initial location to the monitoring anomaly location for monitoring. The construction monitoring image sent by the UAV is collected, and it is determined whether there is a preset construction anomaly in the construction monitoring image. If so, the information to be processed and the type to be processed of the construction monitoring image are determined based on the construction anomaly standard. The key monitoring location of the construction site and the abnormal processing image set corresponding to the key monitoring location are pre-updated according to the monitoring anomaly location, the information to be processed and the type to be processed, and the updated key monitoring location and the updated abnormal processing image set are obtained.

[0134] Furthermore, the key monitoring locations of the construction site and the abnormality processing image sets corresponding to the key monitoring locations are pre-updated based on the monitored abnormality locations, the information to be processed, and the type to be processed, to obtain updated key monitoring locations and updated abnormality processing image sets. The method then includes: obtaining reflection data indicating the presence of image abnormalities in the first priority images within a preset time, determining the abnormality frequency occurring at the key monitoring locations based on the reflection data, and determining whether the abnormality frequency exceeds the preset abnormality frequency. When the abnormality frequency does not exceed the preset abnormality frequency, the key monitoring locations and the abnormality processing image sets corresponding to the key monitoring locations are eliminated and updated, to obtain updated key monitoring locations and abnormality processing image sets.

[0135] In the embodiment of the present application, the preset abnormal frequency is a frequency set by the staff according to actual needs and is not limited here.

[0136] The above embodiment introduces a digital supervision management method applied to engineering projects from the perspective of method flow. The following embodiment introduces a digital supervision management system applied to engineering projects from the perspective of virtual modules or virtual units. Please refer to the following embodiment for details.

[0137] The embodiment of the present application provides a digital supervision management system 20 applied to engineering projects, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a digital supervision management system for an engineering project provided in an embodiment of the present application. The system 20 may specifically include:

[0138] An image acquisition module 21 is used to acquire construction site images, where the construction site images are site images corresponding to different time nodes within a preset construction site area;

[0139] An image processing module 22 is used to perform fine processing on the construction site image to obtain a processed construction site image;

[0140] An image classification module 23 is used to classify the processed construction site images according to time nodes to obtain a historical site image set and a current site image set;

[0141] Anomaly analysis module 24 is used to perform key anomaly analysis on the historical site image set to obtain key monitoring locations of the construction site and anomaly processing image sets corresponding to the key monitoring locations;

[0142] An image screening module 25 is configured to screen the current on-site image set based on the key monitoring location to obtain a first priority image having the key monitoring location;

[0143] A similarity processing module 26 is configured to determine whether the first priority image has an image anomaly. If so, similarity processing is performed on the first priority image based on the anomaly processing image set to obtain construction information of the first priority image.

[0144] The alarm control module 27 determines whether there is a preset construction anomaly in the construction information. If so, it generates an alarm instruction and controls the alarm device to output an alarm.

[0145] In one possible implementation of the embodiment of the present application, the image processing module 22 performs fine processing on the construction site image to obtain the processed construction site image, specifically for:

[0146] Perform edge filtering on the construction site image to obtain standard contour layers of different construction workers and construction equipment at the construction site, as well as key contour layers that detail the behavior of construction workers and the operating status of construction equipment at the construction site.

[0147] The standard contour layer is divided into multiple sub-regions, and the regional histogram corresponding to each sub-region and the overall histogram corresponding to the standard contour layer are collected, as well as the regional flatness corresponding to each sub-region and the overall flatness corresponding to the standard contour layer;

[0148] Determine the overall contrast curve and overall brightness curve corresponding to the standard contour layer according to the overall histogram and overall flatness;

[0149] Determine the regional contrast curve corresponding to each sub-region according to the sub-region histogram, and fuse the regional contrast curve with the overall contrast curve to obtain a fused contrast curve;

[0150] Determine the brightness curve adjustment weight corresponding to each sub-region according to the flatness of the sub-region, and based on the brightness curve adjustment weight, fuse the overall brightness curve with the fusion contrast curve to obtain a parameter adjustment curve;

[0151] Adjust each sub-region of the standard contour layer according to the parameter adjustment curve to obtain an adjusted standard contour layer;

[0152] The processed construction site image is obtained by fusing the adjusted standard contour layer with the key contour layer.

[0153] In another possible implementation of the embodiment of the present application, when the anomaly analysis module 24 performs a focused anomaly analysis on the historical site image set to obtain a key monitoring location of the construction site and an anomaly processing image set corresponding to the key monitoring location, it is specifically configured to:

[0154] Perform anomaly analysis on each image in the historical on-site image collection to obtain the shooting area and image anomaly type corresponding to each image;

[0155] Summarize the abnormal marking points according to the shooting area to obtain the first marking point set corresponding to each shooting area at different time nodes;

[0156] Statistically dividing the abnormal marker point set according to the same image position coordinates to obtain a second marker point set corresponding to different position coordinates of each shooting area;

[0157] Determine whether the number of abnormal marking points corresponding to the second marking point set exceeds a preset abnormal number. If so, mark the position of the shooting area corresponding to the number of abnormal marking points to obtain the key monitoring position of the construction site;

[0158] The exception handling information corresponding to the key monitoring locations is collected, and the exception handling information, shooting area and image exception type are respectively bound to the corresponding historical on-site images to obtain the exception handling image set corresponding to the key monitoring locations.

[0159] In another possible implementation of the embodiment of the present application, when the similarity processing module 26 performs similarity processing on the first-priority image based on the exception processing image set to obtain the construction information of the first-priority image, it is specifically configured to:

[0160] Determine, based on the current set of scene images, a common view scene image that is adjacent to the time position node of the first priority image and has a key monitoring position;

[0161] Performing three-dimensional simulation processing based on the first priority image and the common viewing scene image to obtain an abnormal three-dimensional image with image abnormality;

[0162] Determining abnormal coordinate information in the abnormal three-dimensional image and abnormal descriptor information corresponding to the abnormal coordinate information;

[0163] Based on the image feature points of the key monitoring positions in the abnormal three-dimensional image, a multi-dimensional spatial data search is performed on the abnormal images in the abnormal processing image set to obtain a matching image set;

[0164] Performing similarity analysis on the first priority image and each abnormal image in the matching image set according to the abnormal coordinate information and the abnormal descriptor information to obtain similarity information;

[0165] Based on the similarity information, a similarity mean is determined, and it is judged whether the similarity mean meets the preset similarity range. If so, the target processing information, target area and target abnormality type corresponding to the similarity mean in the abnormal processing image set are determined, and the target processing information, target area and target abnormality type are respectively bound to the first priority image to obtain the construction information of the first priority image.

[0166] In another possible implementation of the embodiment of the present application, the system 20 further includes: an image determination module, a flight control module, a flight monitoring module, and a data update module, wherein:

[0167] An image determination module, configured to determine, when there is no image anomaly in the first priority image, based on the current on-site image set, that there is no second priority image at the key monitoring location;

[0168] a flight control module, configured to determine whether there is an image anomaly in the second-priority image; if so, determine a monitoring anomaly location where the image anomaly exists in the second-priority image; generate a UAV flight instruction based on the monitoring anomaly location; and control the UAV to fly from an initial location to the monitoring anomaly location for monitoring;

[0169] The flight monitoring module is used to collect construction monitoring images sent by the drone and determine whether the construction monitoring images contain preset construction anomalies. If so, it determines the information to be processed and the type of processing to be performed based on the construction anomaly standard;

[0170] The data update module is used to pre-update the key monitoring locations of the construction site and the abnormal processing image sets corresponding to the key monitoring locations according to the monitored abnormal locations, the information to be processed and the type to be processed, and obtain the updated key monitoring locations and the updated abnormal processing image sets.

[0171] In another possible implementation of the embodiment of the present application, the system 20 further includes: a data acquisition module, a frequency determination module, and a data elimination module, wherein:

[0172] A data acquisition module is used to acquire data reflecting that an image anomaly exists in a first-priority image within a preset time;

[0173] A frequency determination module is used to determine the abnormal frequency occurring at the key monitoring location based on the reflected data, and to determine whether the abnormal frequency exceeds a preset abnormal frequency;

[0174] The data elimination module is used to eliminate and update the key monitoring position and the abnormal processing image set corresponding to the key monitoring position when the abnormal frequency does not exceed the preset abnormal frequency, and obtain the updated key monitoring position and abnormal processing image set.

[0175] In another possible implementation of the embodiment of the present application, the anomaly analysis module 24 performs an anomaly analysis on each image in the historical scene image set to obtain the shooting area and image anomaly type corresponding to each image, specifically for:

[0176] Each image in the historical on-site image collection is input into the preset anomaly detection model for anomaly detection analysis to obtain the shooting area and image anomaly type corresponding to each image.

[0177] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the digital supervision management system 20 applied to engineering projects described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0178] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 The electronic device 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the number of transceivers 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0179] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0180] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or one type of bus.

[0181] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0182] The memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.

[0183] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers and the like are also possible. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0184] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0185] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0186] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A digital supervision management method applied to engineering projects, characterized in that: include: Acquire construction site images, where the construction site images are site images corresponding to different time nodes within a preset construction site area; Performing fine processing on the construction site image to obtain a processed construction site image; Classify the processed construction site images into categories according to time nodes to obtain a historical site image set and a current site image set; Performing a key anomaly analysis on the historical on-site image set to obtain key monitoring locations of the construction site and a set of anomaly processing images corresponding to the key monitoring locations; Filtering the current scene image set based on the key monitoring location to obtain a first priority image containing the key monitoring location; Determining whether the first-priority image has an image anomaly, and if so, performing similarity processing on the first-priority image according to the anomaly processing image set to obtain construction information of the first-priority image, including: Determine, based on the current scene image set, a common view scene image that is adjacent to the time position node of the first priority image and has the key monitoring position; Performing three-dimensional simulation processing based on the first priority image and the common viewing scene image to obtain an abnormal three-dimensional image containing the image abnormality; Determining abnormal coordinate information in the abnormal three-dimensional image and abnormal descriptor information corresponding to the abnormal coordinate information; Performing a multi-dimensional spatial data search on the abnormal images in the abnormal processing image set based on the image feature points of the key monitoring positions in the abnormal three-dimensional image to obtain a matching image set; performing similarity analysis on the first priority image and each abnormal image in the matching image set according to the abnormal coordinate information and the abnormal descriptor information to obtain similarity information; Determining a similarity mean based on the similarity information, and judging whether the similarity mean satisfies a preset similarity range; if so, determining target processing information, target area, and target abnormality type corresponding to the similarity mean in the abnormal processing image set, and binding the target processing information, the target area, and the target abnormality type to the first priority image, respectively, to obtain construction information of the first priority image; Determine whether there is a preset construction anomaly in the construction information. If so, generate an alarm instruction and control the alarm device to output an alarm.

2. A digital supervision management method for engineering projects according to claim 1, characterized in that: The performing fine processing on the construction site image to obtain a processed construction site image includes: Performing edge filtering on the construction site image to obtain standard contour layers of different construction workers and construction equipment at the construction site and key contour layers of behavioral details of the construction workers and operating status details of the construction equipment at the construction site; Dividing the standard contour layer into a plurality of sub-regions, and collecting a regional histogram corresponding to each sub-region and an overall histogram corresponding to the standard contour layer, as well as a regional flatness corresponding to each sub-region and an overall flatness corresponding to the standard contour layer; Determining an overall contrast curve and an overall brightness curve corresponding to the standard contour layer according to the overall histogram and the overall flatness; Determining a regional contrast curve corresponding to each sub-region according to the sub-region histogram, and fusing the regional contrast curve with the overall contrast curve to obtain a fused contrast curve; determining a brightness curve adjustment weight corresponding to each sub-region according to the flatness of the sub-region, and fusing the overall brightness curve with the fused contrast curve based on the brightness curve adjustment weight to obtain a parameter adjustment curve; Adjusting each sub-region of the standard contour layer according to the parameter adjustment curve to obtain an adjusted standard contour layer; The adjusted standard contour layer is fused with the key contour layer to obtain a processed construction site image.

3. A digital supervision management method for engineering projects according to claim 1, characterized in that: The performing of key anomaly analysis on the historical on-site image set to obtain key monitoring locations of the construction site and a set of anomaly processing images corresponding to the key monitoring locations includes: Performing an anomaly analysis on each image in the historical scene image set to obtain a shooting area corresponding to each image and an image anomaly type; Summarize the abnormal marking points according to the shooting area to obtain a first marking point set corresponding to each shooting area at different time nodes; Statistically dividing the abnormal marking points according to the same image position coordinates to obtain a second marking point set corresponding to different position coordinates of each shooting area; Determine whether the number of abnormal marking points corresponding to the second marking point set exceeds a preset abnormal number. If so, mark the position of the shooting area corresponding to the number of abnormal marking points to obtain the key monitoring position of the construction site; Exception handling information corresponding to the key monitoring location is collected, and the exception handling information, the shooting area, and the image exception type are respectively bound to corresponding historical on-site images to obtain an exception handling image set corresponding to the key monitoring location.

4. A digital supervision management method for engineering projects according to claim 1, characterized in that: After determining whether the first-priority image has an image abnormality, the method further includes: If there is no image anomaly in the first priority image, determining based on the current on-site image set that there is no second priority image of the key monitoring location; determining whether there is an image anomaly in the second-priority image; if so, determining a monitoring anomaly location where the image anomaly exists in the second-priority image; generating a UAV flight instruction based on the monitoring anomaly location, and controlling the UAV to fly from an initial location to the monitoring anomaly location for monitoring; collecting the construction monitoring image sent by the drone, and determining whether the construction monitoring image contains a preset construction anomaly; if so, determining the information to be processed and the type of processing to be processed of the construction monitoring image based on the construction anomaly standard; The key monitoring locations of the construction site and the abnormality processing image set corresponding to the key monitoring locations are pre-updated according to the monitored abnormality locations, the information to be processed and the type to be processed to obtain updated key monitoring locations and updated abnormality processing image set.

5. A digital supervision management method for engineering projects according to claim 4, characterized in that: The method further includes pre-updating the key monitoring locations of the construction site and the abnormality processing image set corresponding to the key monitoring locations according to the abnormality monitoring locations, the information to be processed, and the type to be processed to obtain updated key monitoring locations and updated abnormality processing image set, and then further including: Acquire data reflecting that the first-priority image has an image anomaly within a preset time; Determining the abnormal frequency occurring at the key monitoring location according to the reflected data, and determining whether the abnormal frequency exceeds a preset abnormal frequency; When the abnormal frequency does not exceed the preset abnormal frequency, the key monitoring position and the abnormal processing image set corresponding to the key monitoring position are eliminated and updated to obtain an updated key monitoring position and abnormal processing image set.

6. A digital supervision management method for engineering projects according to claim 3, characterized in that: The performing of anomaly analysis on each image in the historical scene image set to obtain the shooting area and image anomaly type corresponding to each image includes: Each image in the historical scene image set is input into a preset anomaly detection model for anomaly detection analysis to obtain the shooting area and image anomaly type corresponding to each image.

7. A digital supervision management system applied to engineering projects, characterized in that: include: An image acquisition module is used to acquire construction site images, wherein the construction site images are site images corresponding to different time nodes within a preset construction site area; An image processing module is used to perform fine processing on the construction site image to obtain a processed construction site image; An image classification module is used to classify the processed construction site images according to time nodes to obtain a historical site image set and a current site image set; An anomaly analysis module, configured to perform a key anomaly analysis on the historical on-site image set to obtain a key monitoring location of the construction site and an anomaly processing image set corresponding to the key monitoring location; An image screening module, configured to screen the current scene image set based on the key monitoring location to obtain a first priority image containing the key monitoring location; a similarity processing module, configured to determine whether the first-priority image has an image anomaly, and if so, perform similarity processing on the first-priority image based on the anomaly processing image set to obtain construction information of the first-priority image; When the similarity processing module performs similarity processing on the first priority image according to the exception processing image set to obtain the construction information of the first priority image, the similarity processing module is specifically configured to: Determine, based on the current scene image set, a common view scene image that is adjacent to the time position node of the first priority image and has the key monitoring position; Performing three-dimensional simulation processing based on the first priority image and the common viewing scene image to obtain an abnormal three-dimensional image containing the image abnormality; Determining abnormal coordinate information in the abnormal three-dimensional image and abnormal descriptor information corresponding to the abnormal coordinate information; Performing a multi-dimensional spatial data search on the abnormal images in the abnormal processing image set based on the image feature points of the key monitoring positions in the abnormal three-dimensional image to obtain a matching image set; performing similarity analysis on the first priority image and each abnormal image in the matching image set according to the abnormal coordinate information and the abnormal descriptor information to obtain similarity information; Determining a similarity mean based on the similarity information, and judging whether the similarity mean satisfies a preset similarity range; if so, determining target processing information, target area, and target abnormality type corresponding to the similarity mean in the abnormal processing image set, and binding the target processing information, the target area, and the target abnormality type to the first priority image, respectively, to obtain construction information of the first priority image; The alarm control module is used to determine whether there is a preset construction anomaly in the construction information. If so, an alarm instruction is generated to control the alarm device to output an alarm.

8. An electronic device, characterized in that: It includes: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to: execute a digital supervision management method for engineering projects according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a digital supervision management method for engineering projects as described in any one of claims 1 to 6 is implemented.

Images