Field image recording and remote monitoring method, system and equipment and storage medium

Abstract

The invention provides an on-site image recording and remote monitoring method, system and device, and a storage medium, and the method comprises the following steps: deploying a camera at a key position of a construction site, and collecting the panoramic image data of the construction site in real time; according to the method, the camera is used for collecting data, format conversion and compression are carried out through the deep learning algorithm, the defects of manual recording are overcome, the labor cost is reduced, mistakes and omissions of key construction details and parameters are reduced, and reliable data support is provided for subsequent engineering links; data are transmitted in real time through the 5G communication technology, a remote server intelligently analyzes and processes the data and establishes a data management index, a user can check the construction progress in real time, the system can also automatically compare the actual progress with the preset progress, early warning is conducted in time when the progress is abnormal, and a report is generated; besides, a progress prediction model established by using big data and artificial intelligence technology is integrated with multi-dimensional information to predict future progress, a decision basis is provided for construction management, and construction period delay and cost increase are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering monitoring, and in particular to a method, system, device and storage medium for on-site image recording and remote monitoring. Background Art

[0002] In the fields of various engineering construction projects, such as building construction, road and bridge construction, and water conservancy projects, the scale is large, the links are complex, and the impact is far-reaching. Accurately recording the construction process and real-time monitoring of the construction progress are extremely critical. From the perspective of project quality, detailed records can be used to quickly locate and resolve problems when they arise; from the perspective of project safety, potential hidden dangers can be detected in a timely manner to ensure personnel safety and project progress; in terms of cost control, cost expenditures can be clearly reflected and resource waste can be avoided; when it comes to project delivery, it can help to arrange plans reasonably to ensure on-time delivery, thereby comprehensively ensuring the quality and safety of the project, achieving effective cost control and achieving the goal of on-time delivery, which is of great significance to the company's reputation and market competitiveness. However, traditional construction record and progress monitoring methods have many significant shortcomings.

[0003] Traditional construction record keeping methods rely mainly on manual labor. Recorders need to frequently travel to various areas of the construction site to collect data and record information. This consumes a lot of time and energy, increases labor costs, and significantly reduces recording efficiency. Manual recording is also susceptible to subjective interference. The recorder's professional level and work attitude can affect the accuracy and completeness of the records. In complex construction scenarios, such as chemical engineering construction, key construction details and parameters can easily be missed due to negligence, posing serious risks to subsequent engineering links. Traditional construction progress monitoring relies heavily on regular on-site inspections and manual reporting. Construction workers report back after regular on-site inspections by management personnel. This approach is significantly time-consuming and fails to fully and timely reflect actual construction progress. Progress deviations between inspections are difficult to detect, and if deviations occur and go undetected, effective adjustments cannot be made, leading to construction delays and increased costs. Furthermore, manual reporting is susceptible to subjective factors, and construction workers may exaggerate or conceal progress for their own benefit, making progress monitoring even more difficult. To this end, a method, system, device and storage medium for on-site image recording and remote monitoring are proposed. Summary of the Invention

[0004] In view of this, the embodiments of the present invention hope to provide a method, system, device and storage medium for on-site image recording and remote monitoring to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0005] To solve the above technical problems, a technical solution adopted in this application is: a method for on-site image recording and remote monitoring, comprising the following steps: Step 1: Deploy cameras at key locations on the construction site to collect panoramic image data of the construction site in real time; Step 2: Automatically convert the format of the panoramic image data using a deep learning-based image format adaptive conversion algorithm, and compress the panoramic image data using a lossless compression algorithm; Step 3: Establish a data transmission link between the camera and the remote server, and transmit the compressed panoramic image data to the remote server in real time; Step 4: The remote server uses the built-in deep learning framework and image processing algorithm library to intelligently analyze and process the panoramic image data, classify and store it, and establish a data management index; Step 5: After the user enters the smart user access interface and logs into the system through a smart device, he or she can view the panoramic image data of the construction site and the completion percentage of the construction progress in real time according to the data management index; Step 6: The remote server automatically classifies and stores the panoramic image data collected by the camera in chronological order and by construction stage to form a construction image archive; Step 7: Based on the construction image archive, use big data analysis and artificial intelligence technology to establish a construction progress prediction model, and integrate multi-dimensional information to predict and analyze the future construction progress.

[0006] As a further preferred embodiment of the present technical solution, in step three, the data transmission link is established using 5G communication technology, and data encryption processing is performed by combining quantum encryption technology with blockchain technology.

[0007] As a further preferred embodiment of the present technical solution, in step four, the deep learning framework adopts TensorFlow or PyTorch; the image processing algorithm library includes an image recognition algorithm, an image enhancement algorithm and a target detection algorithm.

[0008] As a further preferred embodiment of the present technical solution, in step six, the storage of the construction image archive adopts a distributed storage architecture with scalability, and adds metadata tags for each panoramic image data; the metadata tags include construction time, location, construction content and participants.

[0009] As a further preferred embodiment of the present technical solution, in step five, the smart devices include computers, tablets, mobile phones and wearable smart devices, and the smart user access interface adopts a responsive design to adapt to the screen size and resolution of different devices; the completion percentage of the construction progress is automatically calculated and analyzed using image recognition and data analysis technology, and the actual construction progress is compared with the preset progress requirements in an intuitive and visual manner. When the progress is abnormal, the system automatically issues a warning message and generates a deviation analysis report.

[0010] As a further preferred embodiment of the present technical solution, in step seven, the construction progress prediction model is trained and optimized using a machine learning algorithm; the multi-dimensional information includes historical construction data, real-time image data, weather factors, equipment status, and personnel attendance.

[0011] As a further preferred embodiment of the present technical solution, in step one, the camera resolution reaches 8K or above, and the camera viewing angle range covers a 360° panoramic view of key areas of the construction site.

[0012] To solve the above technical problems, another technical solution adopted by the present application is: an on-site image recording and remote monitoring system, the system comprising an image acquisition module, a data preprocessing module, a data transmission module, a data analysis module, a data storage module, a user interaction module and a progress prediction module; The image acquisition module is configured to deploy cameras at key locations on the construction site to collect panoramic image data of the construction site in real time; The data preprocessing module is configured as an image format adaptive conversion algorithm based on deep learning to automatically convert the format of the panoramic image data and compress the panoramic image data using a lossless compression algorithm; The data transmission module is configured to establish a data transmission link between the camera and the remote server, and transmit the compressed panoramic image data to the remote server in real time; The data analysis module is configured as a remote server that uses a built-in deep learning framework and image processing algorithm library to perform intelligent analysis and processing on the panoramic image data, classify and store it, and establish a data management index; The data storage module is configured so that after a user enters the smart user access interface through a smart device and logs into the system, the user can view the panoramic image data of the construction site and the completion percentage of the construction progress in real time according to the data management index; The user interaction module is configured so that the remote server automatically classifies and stores the panoramic image data collected by the camera in chronological order and by construction stage to form a construction image archive; The progress prediction module is configured to establish a construction progress prediction model based on construction image archives using big data analysis and artificial intelligence technology, and to perform prediction and analysis on future construction progress by integrating multi-dimensional information.

[0013] To solve the above technical problems, another technical solution adopted in this application is: an electronic device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of a field image recording and remote monitoring method as described above.

[0014] In order to solve the above technical problems, another technical solution adopted in this application is: a storage medium storing program instructions that can implement a field image recording and remote monitoring method as described above.

[0015] The embodiment of the present invention adopts the above technical solution, which has the following advantages: 1. This invention uses 8K and higher resolution, 360° panoramic cameras to collect data, and uses deep learning algorithms for format conversion and compression. This avoids the shortcomings of manual recording and can comprehensively, accurately, and efficiently record the construction process, reducing labor costs, and reducing errors and omissions in key construction details and parameters, providing reliable data support for subsequent engineering links. 2. The present invention uses 5G communication technology to transmit data in real time, and the remote server intelligently analyzes and processes data and establishes a data management index. Users can view the construction progress in real time. The system can also automatically compare the actual progress with the preset progress, and issue timely warnings and generate reports in case of abnormalities. In addition, the progress prediction model established using big data and artificial intelligence technology integrates multi-dimensional information to predict future progress, providing a decision-making basis for construction management, effectively avoiding delays in construction period and increased costs.

[0016] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flow chart of a method for on-site image recording and remote monitoring according to the present invention; Figure 2 This is a functional module diagram of a field image recording and remote monitoring system according to the present invention; Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0020] It should be clear that the following embodiments of the present disclosure are described through specific concrete examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0021] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0022] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The illustrations only show components related to the present disclosure and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0023] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0024] Figure 1 It is a flow chart of a method for recording and remotely monitoring on-site images according to an embodiment of the present invention. It should be noted that the method of the present application is not limited to the method of recording and remotely monitoring on-site images according to an embodiment of the present invention. Figure 1 The process sequence shown is limited. Figure 1 A method for recording and remotely monitoring on-site images includes the following steps: Step 1: Deploy cameras at key locations on the construction site to collect panoramic image data of the construction site in real time; Specifically, first, based on the scale, layout and construction process of the construction site, with the help of professional engineering planning tools and on-site surveys, key locations are accurately selected. For example, at a construction site, cameras will be installed at the top of the tower crane, at the height of fixed scaffolding around the building, and at the entrance to the construction site. The camera at the top of the tower crane can overlook the entire construction area and obtain large-scale construction scene images. The camera at the height of the fixed scaffolding can focus on specific construction surfaces of the building and capture construction details. The camera at the entrance of the site can record the entry and exit of personnel and equipment. In road and bridge construction projects, for bridge construction, cameras will be installed at key locations such as the pier construction area and on both sides of the main construction section of the bridge. For road construction, cameras will be deployed at the starting and end points of the road and at key construction nodes (such as curves, tunnel entrances and exits), thereby achieving full coverage of the entire construction area. Next, choose cameras with a resolution of 8K or higher and a 360-degree panoramic view covering key areas of the construction site. These cameras can provide ultra-high-definition images, ensuring that construction details are clearly visible. For example, the binding of rebar and the operating status of equipment during construction can be accurately presented. The wide viewing angle allows the camera to capture images of a wide area without frequent angle adjustments, reducing blind spots caused by viewing angle limitations and improving comprehensive monitoring. In addition, the camera's protective performance must be considered to ensure that it can adapt to the complex environmental conditions of the construction site, such as waterproofing, dustproofing, shockproofing, and high or low temperature resistance. This ensures that the camera operates stably in harsh environments and continuously collects image data. Next, securely install the camera in the selected location using a professional mounting bracket and fixing accessories. During the installation process, strictly follow relevant safety regulations and operating procedures to ensure the personal safety of the installers. After installation, debug the camera. By connecting it to a computer or dedicated debugging equipment, adjust the camera's focal length, aperture, exposure and other parameters to ensure clear images and high color reproduction. At the same time, set the automatic dimming function according to the lighting conditions of the construction site so that the camera can obtain high-quality image data in different lighting environments. In addition, fine-tune the camera's shooting angle to ensure that its field of view covers the predetermined key construction area and avoid blind spots. Finally, connect the camera to the data acquisition device to build a stable data acquisition system. The data acquisition device is responsible for receiving the image data collected by the camera and performing preliminary caching and preprocessing. To ensure the real-time nature of the data, use a high-speed data transmission cable or wireless transmission module (such as 5 wireless transmission equipment) to connect the camera to the data acquisition device to reduce data transmission delays. At the same time, set the data acquisition frequency in the data acquisition device. According to the construction progress and monitoring requirements, determine the number of frames of the image collected per second or per minute to ensure that key changes in the construction process can be captured in time, providing continuous and accurate image data for subsequent construction records and monitoring.

[0025] Step 2: Automatically convert the format of the panoramic image data using a deep learning-based image format adaptive conversion algorithm, and compress the panoramic image data using a lossless compression algorithm; The specific implementation of the format conversion of the panoramic image data is as follows: First, the basic information of the image, such as format, resolution, and color mode, is analyzed. The current image format is determined by reading the header information of the image file. At the same time, the network status of the construction site is analyzed. For example, by real-time monitoring of network bandwidth, latency and other parameters, the data transmission volume that the current network environment can withstand is determined. Then, based on the analyzed image information and network conditions, the trained deep learning model is used to make format conversion decisions. If the network bandwidth is low, the model will choose to convert the image to a format with a higher compression ratio, such as JPEG2000. If special information such as image transparency needs to be preserved, the model will choose PNG format. The model will automatically adjust the parameters of the conversion process based on the content and characteristics of the image to ensure that the converted image quality meets the requirements. For example, for images with a lot of details, the model will adopt a more refined conversion strategy. Finally, based on the decision result, the corresponding image format conversion function or library is called to convert the panoramic image data into a different format. For example, Python's Pillow library or OpenCV library can be used to convert between different formats. During the conversion process, necessary pre-processing and post-processing operations are performed on the image, such as adjusting the image size and color space, to ensure that the converted image meets the requirements of subsequent processing and transmission. Among them, the training process of the deep learning model is as follows: First, select a deep learning model suitable for image format conversion, such as ResNet or U-Net in convolutional neural networks (CNN). These models have powerful feature extraction and image conversion capabilities. Then, a large amount of panoramic image data in different formats, including common JPEG, PNG, BMP and other formats, is collected to build a training dataset. The data is annotated with the target format to be converted and relevant image feature information. Finally, the selected deep learning model is trained using the training dataset, and the model parameters, such as learning rate and number of iterations, are adjusted to improve the accuracy and efficiency of the model in the image format conversion task.

[0026] The specific implementation of compressing panoramic image data is as follows: First, select an appropriate lossless compression algorithm, such as the DEFLATE algorithm or the Lempel-Ziv-Welch (LZW) algorithm used by PNG. These algorithms can effectively reduce the size of image data without sacrificing image quality. Based on actual needs and image characteristics, configure the parameters of the lossless compression algorithm, such as the compression level and dictionary size, to balance the compression ratio and compression speed. At the same time, check the converted panoramic image data to ensure its integrity and accuracy, and perform necessary filtering and noise reduction on the image to improve the compression effect. Then, the selected lossless compression algorithm is called to compress the image data. The image data is input into the compression algorithm and the compression operation is performed according to the configured parameters. During the compression process, the compression ratio and compression time are monitored in real time, and the compression parameters are adjusted according to the actual situation to achieve the best compression effect. Next, the compressed image data is decompressed and the decompressed image is compared with the original image to verify whether the image quality is lossless. Finally, check whether the compressed data size meets the requirements of network transmission and storage. If not, you need to readjust the compression parameters or select another compression algorithm.

[0027] By integrating image format conversion and lossless compression modules into the entire on-site image recording and remote monitoring system, it ensures seamless connection with the front-end image acquisition module and the back-end remote server, realizes data transmission and interaction between modules, and accurately transmits compressed image data to the remote server for storage and processing.

[0028] Step 3: Establish a data transmission link between the camera and the remote server, and transmit the compressed panoramic image data to the remote server in real time; Specifically, first, 5G communication technology is used to establish a data transmission link, taking advantage of the high speed, low latency, and large capacity of the 5G network to ensure that the compressed panoramic image data can be transmitted quickly and stably. In areas with good 5G base station coverage, its theoretical transmission rate can reach 10Gbps, which can greatly shorten the transmission time of image data. At the same time, quantum encryption technology and blockchain technology are combined to encrypt data. Quantum encryption uses the principles of quantum mechanics to prevent eavesdroppers from obtaining information without interfering with the quantum state, thus ensuring the security of data transmission. Blockchain technology verifies and stores transmitted data through distributed ledgers and encryption algorithms to prevent data tampering and ensure data integrity and credibility. Then, on the camera side, a module that supports 5G communication is installed to ensure that it can effectively connect to the 5G network. This module must have a connection method that matches the camera's data output interface and can stably receive compressed panoramic image data. On the remote server side, the corresponding 5G receiving equipment is also set up, and encryption and decryption equipment and blockchain nodes corresponding to quantum encryption and blockchain technology are configured to ensure that the server-side equipment can correctly receive, decrypt and verify the transmitted data. Next, configure the network parameters of the camera and remote server, including IP addresses, port numbers, etc., and set appropriate network protocols, such as TCP / IP, to ensure the orderliness and reliability of data transmission. At the same time, monitor the network status in real time and make dynamic adjustments based on network bandwidth, latency, etc. For example, when the network bandwidth is low, appropriately reduce the transmission frame rate of image data to ensure the stability of data transmission; when the network latency is high, optimize the data transmission route to reduce transmission latency. Finally, the data transmission task is started to transmit the compressed panoramic image data from the camera end to the remote server in real time. During the transmission process, a data monitoring mechanism is established to record the status of data transmission in real time, such as the amount of data transmitted, transmission speed, packet loss rate, etc.; once a transmission abnormality occurs, such as a high packet loss rate or transmission interruption, the emergency plan is immediately activated, which can automatically retransmit the lost data or switch to the backup network link for transmission to ensure data integrity and continuity.

[0029] Step 4: The remote server uses the built-in deep learning framework and image processing algorithm library to intelligently analyze and process the panoramic image data, classify and store it, and establish a data management index; The specific implementation of intelligent analysis and processing of panoramic image data is as follows: First, select a suitable deep learning framework from TensorFlow or PyTorch and install and deploy it based on the server's hardware resources and performance requirements. If the server is equipped with a high-performance GPU, choose a version that supports GPU acceleration to fully utilize the hardware's advantages and improve processing efficiency. For example, on a server with an NVIDIA GPU, install the corresponding CUDA version of TensorFlow or PyTorch and configure the CUDA environment variables to enable the framework to use GPU resources for calculations. Then, image processing algorithm libraries, such as image recognition algorithms, image enhancement algorithms, and object detection algorithms, are integrated into the server system. For image recognition algorithms, such as classification algorithms based on convolutional neural networks (CNNs), trained model files are imported into the project. For image enhancement algorithms, such as histogram equalization and contrast adaptive stretching, the algorithm codes are integrated into a unified processing module. Object detection algorithms, such as YOLO and Faster R-CNN, are selected and deployed according to actual needs to ensure compatibility and collaboration between algorithm libraries. Next, the selected deep learning framework is used to extract features from the panoramic image data. Using a convolutional neural network as an example, multiple convolutional and pooling layers are used to automatically extract key features from the image, such as the shape of the crane, the posture of the personnel, and the outline of the equipment during construction. These features will serve as the basis for subsequent analysis and processing. Subsequently, image recognition algorithms are used to identify and classify the extracted features. For example, the type of construction equipment in the image and the status of the construction area (whether construction is in progress, whether there are safety hazards, etc.) are identified. By comparing these features with predefined category labels, the corresponding category information is annotated for each image or different areas in the image. Image enhancement algorithms are used to optimize the captured panoramic images for problems such as uneven lighting and blurring, and histogram equalization algorithms are used to improve image contrast and make image details clearer. For dark areas caused by insufficient light, an adaptive histogram equalization algorithm is used to enhance local contrast, ensuring that important information in the image (such as construction signs and equipment details) can be clearly presented. Finally, with the help of target detection algorithms, specific target objects are detected in panoramic images and their positions are determined. In construction site scenarios, targets such as personnel, vehicles, and dangerous areas are detected, and the algorithm outputs the bounding box coordinates of the target to achieve accurate positioning of the target, facilitating subsequent tracking and analysis of the target.

[0030] The specific implementation of data classification storage is as follows: First, develop a classification strategy for panoramic image data based on the characteristics and needs of the construction project. Classify by construction time, and store image data collected at different time periods in corresponding folders or database tables. Classify by construction phase, such as foundation construction, main structure construction, and decoration and renovation construction, and store image data for each corresponding phase. Image content can also be classified, such as equipment images, personnel images, and site environment images. Then, adopt a distributed storage architecture and select highly reliable and scalable storage devices, such as distributed file systems (Ceph, GlusterFS, etc.) or cloud storage services. Configure storage system parameters, such as data redundancy strategies and storage capacity expansion methods, to ensure the storage of massive amounts of panoramic image data while ensuring data security and availability. Then, according to the classification strategy, the panoramic image data after intelligent analysis and processing is stored in the corresponding storage location. During the storage process, detailed metadata is added to each image, including shooting time, shooting location, image size, image format, processing results and other information to facilitate subsequent data retrieval and management.

[0031] The specific implementation of establishing the data management index is as follows: First, select an indexing technology suitable for image data management, such as a hash index based on a hash function, a B-tree index, or an inverted index. Hash indexes are suitable for quickly finding specific images, B-tree indexes are more efficient for range queries and sorting operations, and inverted indexes are more suitable for content-based retrieval. Based on actual needs and data characteristics, select one or more indexing technologies for combined use. Then, based on the selected indexing technology, a data management index structure is constructed. Taking the inverted index as an example, an index table is created for key image features (such as category labels, target object names, etc.), and the features are associated with the corresponding image data storage locations. For example, for an image containing a tower crane, "tower crane" is used as the keyword, and the image's storage path and related metadata information are recorded in the index table. As new panoramic image data is continuously stored, the data management index is updated in a timely manner. When image data is modified, deleted or reclassified, the index structure is updated synchronously to ensure the accuracy and consistency of the index information so that the required image data can be retrieved quickly and accurately.

[0032] Step 5: After the user enters the smart user access interface and logs into the system through a smart device, he or she can view the panoramic image data of the construction site and the completion percentage of the construction progress in real time according to the data management index; Specifically, first, the user opens an application or visits a web page on the smart device, enters the login interface, and enters the pre-registered account and password. The system sends the account information to the remote server for verification. The server verifies the correctness of the account and password based on the stored user information. If the account and password are correct, the server returns an authorization token, and the smart device saves the token, and the user successfully logs in. If the account and password are incorrect, the user is prompted to re-enter the password and the number of incorrect attempts is recorded. After a certain number of attempts, the account is locked to enhance security. After the user logs in, the smart device sends a request to the remote server to obtain image data and construction progress based on the data management index. The server quickly retrieves relevant data based on the index, and packages the panoramic image data of the construction site and the construction progress completion percentage data and sends them back to the smart device. After receiving the data, the smart device displays the panoramic image in real time on the interface to ensure smooth image loading and clear display. At the same time, the construction progress completion percentage data is filled into the progress display area and presented to the user in an intuitive and visual way. If there is an abnormality in the construction progress, the system automatically issues an early warning message, notifies the user through pop-up windows, sound prompts, etc., and generates a deviation analysis report, providing a viewing entrance on the interface for users to understand the details.

[0033] Among them, corresponding adapter programs are developed or responsive web design technology is adopted for the operating systems (such as Windows, iOS, Android, etc.) and screen sizes (from small screens of mobile phones to large screens of computers) of different smart devices; for mobile phones, the interface layout is optimized and the function buttons are designed to be more suitable for finger operation; for computers, the advantages of large screens are fully utilized to display more detailed information; at the same time, the resolutions of different devices are adapted to ensure that image data and interface elements are clearly displayed. For example, on a high-resolution mobile phone screen, images can be presented in high-definition mode and text can be clearly distinguished.

[0034] Step 6: The remote server automatically classifies and stores the panoramic image data collected by the camera in chronological order and by construction stage to form a construction image archive; Specifically, the remote server continuously monitors the data transmission link from the camera. When receiving compressed panoramic image data, it first performs a data integrity check to verify the data's file header, checksum, and other information to ensure that the received data has not been lost or damaged during transmission. It then decompresses the data using a lossless decompression algorithm that matches the camera end and converts the decompressed image data into a format that can be uniformly processed within the server, such as the common JPEG or PNG formats, for subsequent classification, storage, and analysis. Divide the image data into different time intervals based on its acquisition time. It can be divided according to granularity such as year, month, day, and hour. For example, create a storage path with a directory structure of "year / month / day" and store the image data collected every day in the corresponding date directory. This allows users to quickly find and browse construction images of a specific time period according to the time dimension. At the same time, combine the specific planning and schedule of the construction project to determine different construction phases, such as foundation construction, main structure construction, and decoration and renovation construction. Establish association rules between construction phases and image data on the server side. Image recognition technology can be used to identify key elements and construction scenes in the image and automatically determine the construction phase to which the image belongs. Construction phase labels can also be added to image data based on construction plans and manual annotation information. Data classification storage uses a distributed storage architecture, such as Ceph and GlusterFS, to disperse and store panoramic image data across multiple storage nodes. This architecture is highly scalable and fault-tolerant, and can meet the storage needs of large-scale image data. During the storage process, image data is stored in the corresponding storage location according to the data classification rules. At the same time, a database is established to record the metadata of the image data, including image file name, storage path, acquisition time, construction stage, image resolution, etc. At the same time, indexes are created for the records in the database, such as creating a composite index based on time and construction stage, to quickly retrieve and query image data under specific conditions. Integrate the classified and stored image data and the corresponding metadata to form a complete construction image archive. The relevant images and metadata can be packaged into a file in a certain format (such as PDF, XML, etc.), or a unified archive management system can be established to centrally manage and maintain all image data. In order to ensure the security and reliability of construction image archives, necessary security measures such as data encryption and access control should be taken, and archive data should be backed up regularly and stored in off-site data centers or cloud storage services to prevent data loss due to local storage device failures, natural disasters, etc.

[0035] Step 7: Based on the construction image archive, a construction progress prediction model is established using big data analysis and artificial intelligence technology to predict and analyze the future construction progress by integrating multi-dimensional information; Specifically, we first extract key information from construction image archives, such as the characteristics of different construction stages, equipment usage, and personnel activities. We then clean the images to remove fuzzy, duplicate, or invalid image data, and annotate the image data, such as marking the start and end images of different construction stages, as well as images where key construction events occurred. This helps subsequent models learn the changing patterns of construction progress. At the same time, we collect historical construction data, real-time image data, weather factors, equipment status, and personnel attendance, and integrate this multi-dimensional information to build a comprehensive dataset, providing rich input for model training. Next, select a machine learning algorithm suitable for construction progress prediction, such as a long short-term memory network (LSTM) or random forest. LSTM can process sequential data and is suitable for analyzing changes in construction progress over time. Random forest can process high-dimensional data and comprehensively consider the impact of multiple factors on construction progress. Using LSTM as an example, design a suitable network structure, including input, hidden, and output layers. The input layer receives multi-dimensional information data, the hidden layer learns the features and patterns in the data, and the output layer predicts the future construction progress. Finally, determine the model's hyperparameters, such as the learning rate, number of iterations, and number of hidden layer neurons, and optimize model performance through experimentation and tuning. Next, the integrated data set is divided into a training set, a validation set, and a test set. The training set is used for model learning and parameter adjustment, the validation set is used to evaluate the performance of the model during training, and the test set is used to ultimately evaluate the generalization ability of the model. The model is trained using the training set, and the model parameters are continuously adjusted through the back-propagation algorithm to minimize the error between the predicted results and the actual construction progress. During the training process, the validation set is used to monitor the performance of the model to prevent overfitting. If the performance of the model on the validation set no longer improves, strategies such as early stopping of training can be adopted. Methods such as cross-validation and grid search are used to optimize the model's hyperparameters to improve the model's accuracy and stability. Ensemble learning methods can also be tried to combine multiple different models to further improve prediction performance. Subsequently, real-time multi-dimensional information is fed into the trained model, which then predicts future construction progress based on the learned patterns. The prediction results can be presented in the form of time nodes, completion percentages, and other metrics. At the same time, the model's predictions are evaluated using a test set, using metrics such as mean squared error (MSE) and mean absolute error (MAE) to measure the deviation between the predictions and actual conditions. Based on the evaluation results, the model is further adjusted and improved to continuously improve the accuracy of the predictions. Finally, the construction progress forecast results are provided to the construction management team to provide a decision-making basis for them to formulate resource allocation plans and adjust construction strategies. For example, if a construction stage is predicted to be delayed, more manpower and equipment resources can be arranged in advance; as construction progresses, actual construction progress data is continuously collected and compared with the model's forecast results. The comparison results are fed back to the model, and the model is continuously updated and optimized to enable the model to adapt to changes in the construction process and improve the reliability of the forecast.

[0036] In one embodiment, specifically, in step three, a data transmission link is established using 5G communication technology, and data encryption is performed by combining quantum encryption technology with blockchain technology; The specific applications of quantum encryption technology are as follows: First, quantum key distribution (QKD) technology is used to generate encryption keys. Quantum key distribution devices are deployed on both the camera and remote server ends, securely distributing the keys through quantum channels. This utilizes the quantum properties of single photons, such as the non-cloning nature of quantum states, to ensure the security of the keys during transmission. Any attempt by a third party to eavesdrop would alter the quantum state, making it detectable to both communicating parties. During the key distribution process, the state of the quantum channel is continuously monitored to ensure the accuracy and security of key generation and transmission. Then, the generated quantum key is applied to data encryption; on the camera side, the compressed panoramic image data is encrypted using the quantum key. A symmetric encryption algorithm, such as AES (Advanced Encryption Standard), can be used in combination with the quantum key to encrypt the data. The encrypted data is transmitted to the remote server via a 5G communication link. On the remote server side, the same quantum key is used for decryption to restore the original image data. During the encryption and decryption process, the operating procedures of quantum encryption are strictly followed to ensure the safe storage and use of the key.

[0037] The specific applications of blockchain technology are as follows: First, build blockchain nodes on the camera and remote server. Choose a suitable blockchain platform, such as Ethereum or Hyperledger, and build the nodes according to the platform's technical specifications. During the node construction process, configure the node's network parameters and consensus algorithm. For example, use PBFT (Practical Byzantine Fault Tolerance) as the consensus algorithm to ensure the efficiency and consistency of the blockchain network. Each node must maintain a complete copy of the blockchain ledger to record data transmission and verification information. During the data transmission process, the encrypted panoramic image data and its related metadata (such as timestamp, data source, etc.) are encapsulated into blockchain transactions; each transaction generates a unique hash value through a hash algorithm to ensure the integrity and traceability of the data; the transaction is broadcast in the blockchain network and verified by each node; after verification, the transaction is added to the block of the blockchain, forming an unalterable transaction record; when receiving data, the remote server can not only verify the security of the data through quantum encryption technology, but also verify the integrity and reliability of the source of the data with the help of blockchain technology; through the distributed storage characteristics of the blockchain, the data is stored on multiple nodes, further improving the security and reliability of the data and preventing data loss or tampering.

[0038] In one embodiment, specifically, in step 4, the deep learning framework adopts TensorFlow or PyTorch; Among them, TensorFlow supports large-scale distributed training and deployment, and is suitable for handling complex deep learning tasks. It provides a wealth of tools and libraries that enable efficient model training and inference. PyTorch is known for its dynamic computational graphs and ease of use, making it particularly suitable for researchers and developers to conduct rapid prototyping and experiments. The flexibility of PyTorch makes it very popular when dealing with complex deep learning tasks.

[0039] The image processing algorithm library includes image recognition algorithms, image enhancement algorithms, and target detection algorithms; Image recognition algorithms are used to identify objects, scenes, or specific features in images. For example, in images of a construction site, image recognition algorithms can identify construction equipment, building materials, and workers. Common image recognition algorithms include classification models based on convolutional neural networks (CNNs), such as ResNet and Inception. These models can extract features from images and classify them based on these features. Image enhancement algorithms are used to improve image quality, making them more suitable for subsequent analysis and processing. For example, images of construction sites can be affected by uneven lighting, blur, noise, and other issues. Image enhancement algorithms can optimize these images. Common image enhancement algorithms include histogram equalization, contrast stretching, and denoising algorithms. These algorithms can enhance image details, making them clearer and easier to identify and analyze. Object detection algorithms are used to locate and identify specific target objects in images. Unlike image recognition, object detection can not only identify objects but also determine their location in the image (usually represented by a bounding box). Commonly used object detection algorithms include YOLO (You Only Look Once), Faster R-CNN, and SSD (Single Shot MultiBox Detector). These algorithms can detect targets such as people, equipment, and dangerous areas in complex construction site images and determine their locations.

[0040] In one embodiment, specifically, in step six, the storage of the construction image archive adopts a distributed storage architecture with scalability, and metadata tags are added to each panoramic image data; Among them, the distributed storage architecture is a storage method that stores data in multiple nodes (servers or storage devices); Compared with traditional centralized storage, distributed storage has the following advantages: Scalability: Distributed storage systems can dynamically expand storage capacity based on data growth by simply adding new storage nodes without requiring large-scale modifications to the existing system. High reliability: Data is redundantly stored on multiple nodes. Even if a node fails, the data can still be accessed from other nodes, ensuring data security and availability. High performance: Distributed storage systems can process multiple data requests in parallel, improving data read and write speeds. This performance advantage is particularly evident when processing large amounts of data. In this system, construction image archives adopt a distributed storage architecture. Common distributed storage systems include Ceph, GlusterFS, etc. These systems can effectively manage massive panoramic image data and ensure high availability and reliability of the data.

[0041] Metadata tags include construction time, location, construction content, and participants; Metadata tags are additional information that describes data attributes and are used to help users better understand and manage data. In this system, metadata tags are added to each panoramic image data, specifically including the following information: Construction time: records the specific time of image acquisition to help users find and manage image data in chronological order; Location: Records the specific location where the image was captured to help users understand where the image was taken, especially on large construction sites where different areas may have different construction progress; Construction content: Describes the construction activities or stages in the image, such as foundation construction, main structure construction, and decoration and renovation. This helps users quickly understand the construction content reflected in the image. Participants: Records the construction workers or teams involved in the image, helping users track the work status of specific personnel; These metadata tags not only facilitate data classification and retrieval, but also provide important contextual information for subsequent data analysis and construction progress prediction.

[0042] In one embodiment, specifically, in step five, the smart devices include computers, tablets, mobile phones, and wearable smart devices. By supporting multiple devices, the system can meet the needs of different users. Users can easily access the system whether in the office, on the construction site, or on the go.

[0043] The intelligent user access interface adopts responsive design to adapt to the screen size and resolution of different devices; Among them, responsive design is a web design technology that can automatically adjust the interface layout according to the screen size and resolution of the device to ensure a good user experience on different devices; responsive design can automatically adjust the size and layout of interface elements according to the screen size of the device (such as the small screen of a mobile phone, the medium screen of a tablet, and the large screen of a computer). For example, on a mobile phone, the interface will be simplified and the function buttons will be enlarged for easy finger operation; on a computer, the interface can display more detailed information; in addition, responsive design can also adjust the display quality of images according to the resolution of the device. For example, on a high-resolution device, the image can be displayed in high-definition mode to ensure that details are clearly visible; on a low-resolution device, the system will automatically compress the image to ensure loading speed; through responsive design, users can get a consistent and friendly user experience no matter which device they use.

[0044] The completion percentage of construction progress is automatically calculated and analyzed using image recognition and data analysis technology. The actual construction progress is compared with the preset progress requirements in an intuitive and visual way. When the progress is abnormal, the system automatically issues an early warning message and generates a deviation analysis report. The specific process of the system automatically calculating the completion percentage of construction progress using image recognition and data analysis technology is as follows: First, the system uses deep learning models (such as convolutional neural networks) to analyze panoramic images of the construction site and identify key information such as the status of construction equipment, building materials, and the construction area. For example, the system can determine whether concrete pouring and rebar tying in a particular construction area have been completed. The system then automatically calculates the completion percentage of the current construction progress based on the image recognition results, combined with historical construction data and the preset construction plan. For example, if a construction phase is scheduled to take 10 days to complete, and the system detects through image recognition that 70% of the work has been completed, the system will calculate the current completion percentage as 70%. Through automated image recognition and data analysis, the system can accurately calculate construction progress in real time, reducing manual intervention and improving efficiency; The system compares the actual construction progress with the preset progress requirements and presents it to the user in an intuitive and visual way. Specifically: The system can use charts, progress bars, color coding, etc. to display the construction progress. For example, the progress bar can show the completion percentage of the current construction progress and use different colors to mark whether the progress is on track (green means on track, red means lagging behind); The system compares the actual progress with the planned progress, helping users quickly understand whether construction is proceeding as planned. For example, if the planned progress requires a certain stage to be completed by a certain date, but the actual progress lags behind, the system will visually highlight the lagging part. Through this intuitive visualization method, users can understand the construction progress at a glance and identify potential problems in a timely manner.

[0045] In one embodiment, specifically, in step seven, the construction progress prediction model is trained and optimized using a machine learning algorithm; Machine learning algorithms are the core of the construction progress prediction model. Through machine learning algorithms, the system can learn the changing patterns of construction progress from historical and real-time data and predict future construction progress. Common machine learning algorithms include: Long Short-Term Memory (LSTM): LSTM is a deep learning model suitable for time series data that can capture the trend of construction progress over time. Since construction progress is usually a time series problem (i.e., progress changes over time), LSTM is well suited for predicting future construction progress. Random Forest: Random Forest is an ensemble learning algorithm that can process high-dimensional data and comprehensively consider the impact of multiple factors on construction progress. It constructs multiple decision trees and performs voting to arrive at the final prediction result. Support Vector Machine (SVM): SVM is a commonly used classification and regression algorithm suitable for processing nonlinear data. It can be used to predict whether construction progress will lag or advance. These machine learning algorithms learn the changing patterns of construction progress by training historical data and use them to predict future construction progress.

[0046] Multi-dimensional information includes historical construction data, real-time image data, weather factors, equipment status, and personnel attendance; Historical construction data forms the basis for model training. By analyzing the construction progress data of similar projects in the past, the model can learn the changing patterns of construction progress, such as how long a construction phase typically takes to complete and what factors cause progress delays. Through image recognition technology, the system can extract the current construction status from real-time image data. For example, the system can identify whether concrete pouring, steel bar tying, and other work have been completed in a certain construction area, thereby judging the current construction progress. Weather factors have a significant impact on construction progress. For example, severe weather (such as heavy rain or snow) can cause construction to be suspended, thus affecting the overall progress. The system will combine weather forecast data to predict the impact of future weather on the construction progress. Equipment status can also affect construction progress. For example, equipment failure can cause construction delays. The system monitors the equipment's operating status in real time and, combined with equipment maintenance records, predicts the impact of equipment failure on construction progress. Staff attendance directly affects construction progress. For example, insufficient staff can slow down construction. The system combines staff attendance records to predict future staff attendance and analyze its impact on construction progress. By integrating this multi-dimensional information, the model can more comprehensively consider the various factors affecting the construction progress, thereby improving the accuracy of the prediction.

[0047] In one embodiment, specifically, in step one, the camera resolution reaches 8K or above. By using a camera with a resolution of 8K or above, the system can provide high-quality image data to ensure the accuracy and reliability of construction monitoring; the camera viewing angle covers a 360° panoramic view of key areas of the construction site. By using a 360° panoramic camera, the system can achieve all-round monitoring of the construction site to ensure comprehensive coverage of construction activities.

[0048] In summary, an embodiment of the present invention provides a method for on-site image recording and remote monitoring, which collects image data by deploying cameras with a resolution of 8K or above and a 360° panoramic view at key locations on the construction site, uses deep learning algorithms for format conversion and compression, and transmits data with the help of 5G communication technology in combination with quantum encryption and blockchain technology. The remote server uses a deep learning framework and an image processing algorithm library to analyze and process data, classify and store data, and establish an index. Users can view data and construction progress in real time through the responsive interfaces of various smart devices. At the same time, a prediction model is established based on the construction image archive, thereby achieving comprehensive, accurate, and real-time recording of the construction process, efficient monitoring of construction progress, timely detection and warning of progress anomalies, providing accurate decision-making basis for construction management, and improving the efficiency and quality of engineering construction management.

[0049] Figure 2 This is a functional module diagram of a field image recording and remote monitoring system according to an embodiment of the present application. Figure 2 As shown, a field image recording and remote monitoring system includes an image acquisition module, a data preprocessing module, a data transmission module, a data analysis module, a data storage module, a user interaction module and a progress prediction module; An image acquisition module is configured to deploy cameras at key locations on the construction site to collect panoramic image data of the construction site in real time; A data preprocessing module is configured as an image format adaptive conversion algorithm based on deep learning, which automatically converts the format of the panoramic image data and compresses the panoramic image data using a lossless compression algorithm; a data transmission module configured to establish a data transmission link between the camera and a remote server, and transmit the compressed panoramic image data to the remote server in real time; The data analysis module is configured as a remote server that uses a built-in deep learning framework and image processing algorithm library to intelligently analyze and process panoramic image data, classify and store it, and establish a data management index; The data storage module is configured so that after a user enters the smart user access interface through a smart device and logs into the system, they can view the panoramic image data of the construction site and the completion percentage of the construction progress in real time according to the data management index; The user interaction module is configured so that the remote server automatically classifies and stores the panoramic image data collected by the camera in chronological order and by construction stage to form a construction image archive; The progress prediction module is configured to establish a construction progress prediction model based on construction image archives using big data analysis and artificial intelligence technology, and to conduct a prediction and analysis of future construction progress by integrating multi-dimensional information.

[0050] In summary, the embodiment of the present invention provides an on-site image recording and remote monitoring system, which collects high-definition panoramic images through the image acquisition module, optimizes the data format and compresses it through the data preprocessing module, transmits data safely and efficiently through the data analysis module for intelligent processing and classified storage, provides data storage for users to view in real time, establishes a construction image archive through the user interaction module, and predicts the construction progress through the progress prediction module, thereby realizing comprehensive, real-time and accurate monitoring and management of the construction site, effectively solving the shortcomings of traditional construction recording and monitoring methods, improving construction management efficiency and scientific decision-making, and ensuring the smooth progress of the project.

[0051] For other details about the technical solutions for implementing each module in the on-site image recording and remote monitoring system in the above embodiment, please refer to the description of the on-site image recording and remote monitoring method in the above embodiment, which will not be repeated here.

[0052] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For system-related embodiments, since they are generally similar to method-related embodiments, their description is relatively simple. For relevant details, refer to the description of the method-related embodiments.

[0053] like Figure 3 The present invention provides a schematic structural diagram of an electronic device according to an embodiment of the present invention, which is suitable for implementing the electronic device according to an embodiment of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0054] like Figure 3 As shown, an electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) or programs loaded from a storage device into a random access memory (RAM). The RAM also stores various programs and data required for the operation of the electronic device. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0055] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes and hard disks; and communication devices. The communication device allows the electronic device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 3The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0056] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of a field image recording and remote monitoring method of an embodiment of the present disclosure are performed.

[0057] For detailed description of this embodiment, please refer to the corresponding description in the aforementioned embodiments, which will not be repeated here.

[0058] According to an embodiment of the present disclosure, a computer-readable storage medium stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the on-site image recording and remote monitoring method described in each embodiment of the present disclosure are executed.

[0059] The above-mentioned computer-readable storage media include, but are not limited to, optical storage media (e.g., CD-ROMs and DVDs), magneto-optical storage media (e.g., MOs), magnetic storage media (e.g., magnetic tapes or mobile hard disks), media with built-in rewritable non-volatile memory (e.g., memory cards), and media with built-in ROM (e.g., ROM cartridges).

[0060] For detailed description of this embodiment, please refer to the corresponding description in the aforementioned embodiments, which will not be repeated here.

[0061] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0062] In the present disclosure, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "including," "comprising," "having," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0063] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0064] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0065] Various changes, substitutions, and modifications may be made to the technology described herein without departing from the teachings defined by the appended claims. Moreover, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of things, means, methods, and actions described above. Currently existing or later developed processes, machines, manufactures, compositions of things, means, methods, or actions that perform substantially the same function or achieve substantially the same results as the corresponding aspects described herein may be utilized. Accordingly, the appended claims include within their scope such processes, machines, manufactures, compositions of things, means, methods, or actions.

[0066] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0067] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for on-site image recording and remote monitoring, characterized in that: The following steps are involved: Deploy cameras at key locations on the construction site to collect panoramic image data of the construction site in real time; An image format adaptive conversion algorithm based on deep learning automatically converts the format of panoramic image data and compresses the panoramic image data using a lossless compression algorithm; Establish a data transmission link between the camera and the remote server, and transmit the compressed panoramic image data to the remote server in real time; The remote server uses the built-in deep learning framework and image processing algorithm library to intelligently analyze and process the panoramic image data, classify and store it, and establish a data management index; After users enter the smart user access interface and log in to the system through smart devices, they can view the panoramic image data of the construction site and the completion percentage of the construction progress in real time based on the data management index; The remote server automatically classifies and stores the panoramic image data collected by the camera in chronological order and by construction stage, forming a construction image archive; Based on construction image archives, a construction progress prediction model is established using big data analysis and artificial intelligence technology, and multi-dimensional information is integrated to predict and analyze future construction progress.

2. The on-site image recording and remote monitoring method according to claim 1, characterized in that: The data transmission link is established by using 5G communication technology, and data encryption is performed by combining quantum encryption technology with blockchain technology.

3. The method for on-site image recording and remote monitoring according to claim 1, characterized in that: The deep learning framework adopts TensorFlow or PyTorch; the image processing algorithm library includes image recognition algorithm, image enhancement algorithm and target detection algorithm.

4. The on-site image recording and remote monitoring method according to claim 1, characterized in that: The storage of the construction image archive adopts a distributed storage architecture with scalability, and adds metadata tags to each panoramic image data; the metadata tags include construction time, location, construction content and participants.

5. The on-site image recording and remote monitoring method according to claim 1, characterized in that: The smart devices include computers, tablets, mobile phones and wearable smart devices. The smart user access interface adopts a responsive design to adapt to the screen size and resolution of different devices; the completion percentage of the construction progress is automatically calculated and analyzed using image recognition and data analysis technology, and the actual construction progress is compared with the preset progress requirements in an intuitive and visual manner. When the progress is abnormal, the system automatically issues a warning message and generates a deviation analysis report.

6. The on-site image recording and remote monitoring method according to claim 1, characterized in that: The construction progress prediction model is trained and optimized using a machine learning algorithm; the multi-dimensional information includes historical construction data, real-time image data, weather factors, equipment status, and personnel attendance.

7. The on-site image recording and remote monitoring method according to claim 1, characterized in that: The resolution of the camera is 8K or above, and the viewing angle of the camera covers a 360° panoramic view of key areas of the construction site.

8. A field image recording and remote monitoring system, applied to a field image recording and remote monitoring method according to any one of claims 1 to 7, characterized in that: The system includes an image acquisition module, a data preprocessing module, a data transmission module, a data analysis module, a data storage module, a user interaction module and a progress prediction module; The image acquisition module is configured to deploy cameras at key locations on the construction site to collect panoramic image data of the construction site in real time; The data preprocessing module is configured as an image format adaptive conversion algorithm based on deep learning to automatically convert the format of the panoramic image data and compress the panoramic image data using a lossless compression algorithm; The data transmission module is configured to establish a data transmission link between the camera and the remote server, and transmit the compressed panoramic image data to the remote server in real time; The data analysis module is configured as a remote server that uses a built-in deep learning framework and image processing algorithm library to perform intelligent analysis and processing on the panoramic image data, classify and store it, and establish a data management index; The data storage module is configured so that after a user enters the smart user access interface through a smart device and logs into the system, the user can view the panoramic image data of the construction site and the completion percentage of the construction progress in real time according to the data management index; The user interaction module is configured so that the remote server automatically classifies and stores the panoramic image data collected by the camera in chronological order and by construction stage to form a construction image archive; The progress prediction module is configured to establish a construction progress prediction model based on construction image archives using big data analysis and artificial intelligence technology, and to perform prediction and analysis on future construction progress by integrating multi-dimensional information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the on-site image recording and remote monitoring method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the on-site image recording and remote monitoring method described in any one of claims 1-7.

Images