Building outer wall water seepage monitoring method and system, equipment and medium

Abstract

The invention relates to the technical field of building safety supervision, and provides a building outer wall water seepage monitoring method and system, equipment and a medium, and in the scheme of the invention, a pre-trained outer wall water seepage detection model is utilized to calculate and obtain a building outer wall water seepage detection result based on a building outer wall image. The deep learning method is used for efficient and automatic building outer wall water seepage detection, and the building outer wall water seepage detection efficiency and accuracy can be improved.

Description

Technical Field

[0001] This application relates to the field of building safety monitoring technology, and in particular to a method, system, equipment, and medium for monitoring water seepage in building exterior walls. Background Technology

[0002] Building exterior walls are constantly exposed to natural elements such as wind, rain, temperature fluctuations, and ultraviolet radiation, making them prone to water seepage due to cracks, aging waterproofing layers, or construction defects. If not detected and addressed promptly, moisture will gradually erode the wall structure, leading to concrete carbonization, steel reinforcement corrosion, insulation failure, and even internal mold growth, severely impacting the building's durability, safety, and occupant comfort. Furthermore, severe water seepage can affect indoor electrical systems, posing safety hazards. Therefore, continuous monitoring of exterior wall seepage not only helps in early detection of potential problems, scientifically assessing the extent of damage, and developing precise repair plans, but also extends the building's lifespan, reduces maintenance costs, and ensures resident safety.

[0003] Traditional methods for detecting water seepage in building exterior walls primarily rely on manual inspections. Workers examine the walls visually or using simple tools, which not only requires working at heights, posing significant safety risks, but is also inefficient and unable to cover large areas of the building facade. Furthermore, the results are highly dependent on the experience and subjective judgment of the personnel, making it prone to missed detections, misjudgments, or inconsistent standards. Summary of the Invention This application provides a method, system, equipment, and medium for monitoring water seepage in building exterior walls, in order to solve the problems of low detection efficiency and reliance on personnel experience and subjective judgment in the existing manual inspection of water seepage in building exterior walls, which can easily lead to missed detections, misjudgments, or inconsistent standards.

[0004] The first aspect of this application provides a method for monitoring water seepage in building exterior walls. The method includes: acquiring images of building exterior walls; and using a pre-trained water seepage detection model to calculate water seepage detection results based on the building exterior wall images.

[0005] In some embodiments of this application, building exterior wall images are obtained in the following manner: using a drone equipped with a camera device to photograph the building exterior wall to obtain building exterior wall images.

[0006] In some embodiments of this application, building exterior wall images are obtained in the following manner: Using a drone equipped with an infrared thermal imager, the exterior walls of buildings are photographed to obtain infrared images of the building exterior walls, which are then used as building exterior wall images.

[0007] In some embodiments of this application, the pre-trained exterior wall seepage detection model is trained in the following manner: acquiring labeled images of building exterior walls and forming a dataset, wherein the labels indicate the true value of the seepage category of the building exterior walls; using the dataset to iteratively train the initialized deep learning model until convergence, so as to obtain the building exterior wall seepage detection model.

[0008] In some embodiments of this application, a unique thermal coding method is used to encode the type of water seepage on the exterior walls of buildings and use it as a label.

[0009] In some embodiments of this application, the deep learning model takes labeled building exterior wall images as input and outputs the predicted value of the seepage category of the building exterior wall images. The step of training the deep learning model multiple times until convergence using the dataset includes: updating the parameters of the deep learning model based on the loss function determined by the actual value of the seepage category and the predicted value of the seepage category during each iteration of training.

[0010] In some embodiments of this application, the method further includes: calculating risk warning information for the building's exterior walls based on the results of water seepage detection.

[0011] The second aspect of this application provides a building exterior wall seepage monitoring system. The system includes: a drone for flying around the building exterior wall; a camera device mounted on the drone for taking pictures of the building exterior wall to obtain images of the building exterior wall; and an image processor configured with a pre-trained exterior wall seepage detection model for calculating the building exterior wall seepage detection results based on the building exterior wall images.

[0012] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in any of the first aspects of the above embodiments.

[0013] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the first aspects of the above embodiments.

[0014] This application has the following beneficial effects: This application proposes a building exterior wall seepage monitoring scheme. In this scheme, a pre-trained exterior wall seepage detection model is used to calculate the building exterior wall seepage detection results based on building exterior wall images. This method of using deep learning for efficient and automated building exterior wall seepage detection can improve the efficiency and accuracy of building exterior wall seepage detection. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0016] Figure 1 This is a flowchart illustrating the first embodiment of the building exterior wall seepage monitoring method provided in this application; Figure 2 This is an example schematic diagram of an infrared image of a building exterior wall obtained by taking a picture of the building exterior wall using an infrared thermal imager, as provided in this application. Figure 3 This is a flowchart illustrating an embodiment of the external wall seepage detection model training method provided in this application; Figure 4 This is a flowchart illustrating the second embodiment of the building exterior wall seepage monitoring method provided in this application; Figure 5 This is a schematic diagram of the framework of an embodiment of the building exterior wall seepage monitoring system provided in this application; Figure 6 This is a schematic diagram of the framework of an embodiment of the electronic device provided in this application; Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0017] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0018] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0019] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this document means two or more. Moreover, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0020] As described in the background section, traditional building exterior wall seepage detection mainly relies on manual inspections. Workers check the walls visually or with simple tools, which not only requires working at heights, posing significant safety risks, but also has low efficiency and is difficult to cover large areas of building facades. Furthermore, the detection results are highly dependent on the experience and subjective judgment of personnel, easily leading to missed detections, misjudgments, or inconsistent standards.

[0021] To address the aforementioned issues, this application proposes a novel automated building exterior wall seepage monitoring scheme. In this scheme, deep learning methods are used for efficient and automated building exterior wall seepage detection, which can improve the efficiency and accuracy of building exterior wall seepage detection.

[0022] This application will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0023] According to one embodiment of this application, a method for monitoring water seepage in building exterior walls is proposed, such as... Figure 1 As shown, the method includes: S1, acquiring images of the building's exterior walls; S2, using a pre-trained exterior wall seepage detection model to calculate the building's exterior wall seepage detection results based on the building's exterior wall images.

[0024] As described above, the embodiments of this application utilize a pre-trained exterior wall seepage detection model to calculate the building exterior wall seepage detection results based on the building exterior wall images. This efficient and automated method of using deep learning for building exterior wall seepage detection can improve the efficiency and accuracy of building exterior wall seepage detection.

[0025] The following is a detailed explanation of steps S1 and S2.

[0026] I. Step S1 According to one embodiment of this application, step S1 includes: using a drone equipped with a camera device to take pictures of the building's exterior wall to obtain an image of the building's exterior wall.

[0027] As described above, compared to traditional methods of manual climbing or scaffolding for photography, the embodiments of this application allow drones to flexibly navigate different heights and angles outside buildings, easily covering areas such as high-rise exterior walls and corners that are difficult for humans to reach. This effectively overcomes spatial limitations, significantly improves the comprehensiveness and completeness of building exterior wall image acquisition, and avoids the omission of key information due to blind spots. Furthermore, drone photography eliminates the need for humans to be directly exposed to high-altitude working environments, fundamentally reducing safety risks such as falls from heights and being struck by objects, significantly improving operational safety. It also saves the cumbersome process and time cost of scaffolding erection and dismantling, enabling faster and more efficient image acquisition and providing high-quality, timely data support for subsequent detection and analysis based on building exterior wall images.

[0028] Furthermore, the inventors discovered through research that because water seepage in building exterior walls causes the temperature of the seepage area to be lower than that of other exterior wall parts, infrared thermography can be used to detect water seepage in building exterior walls with facing brick cladding. By analyzing the differences in the temperature field of the wall surface, it can be determined whether there is water seepage in the building exterior walls.

[0029] Therefore, according to one embodiment of this application, step S1 further includes: using a drone equipped with an infrared thermal imager to photograph the exterior wall of the building to obtain an infrared image of the building's exterior wall, i.e. Figure 2 As shown, the infrared image of the building's exterior wall is used as the building's exterior wall image.

[0030] As described above, the embodiments of this application, relying on the precise temperature difference capture capability of infrared thermal imaging technology, can directly transform the implicit characteristic of "low temperature" caused by water seepage in building exterior walls into visualized infrared image information. This overcomes the limitations of traditional visible light imaging in identifying potential water seepage hazards, clearly revealing previously invisible seepage areas and significantly improving the accuracy and sensitivity of seepage detection. Simultaneously, the acquired infrared images can be directly used as analytical basis, providing high-quality, highly targeted raw data support for subsequent judgment of seepage conditions based on temperature field differences. This ensures a complete and efficient technical loop for seepage detection, from image acquisition to result judgment, further guaranteeing the reliability and practicality of building exterior wall seepage detection.

[0031] II. Step S2 According to one embodiment of this application, such as Figure 3 As shown, step S2 includes: S21, acquiring images of building exterior walls with labels and forming a dataset, wherein the labels indicate the true value of the water seepage category of the building exterior walls; S22, using the dataset to iteratively train the initialized deep learning model until convergence, so as to obtain a building exterior wall water seepage detection model.

[0032] As can be seen from the above embodiments, the embodiments of this application utilize datasets with real-value labels to provide accurate training basis for the deep learning model, enabling the model to fully learn the characteristic patterns of building exterior wall seepage categories, thereby significantly improving the accuracy and reliability of subsequent seepage detection. Simultaneously, the iterative training method based on deep learning allows the model to continuously optimize its performance, possessing powerful feature extraction and pattern recognition capabilities, effectively addressing complex seepage scenarios and diverse seepage categories in building exterior wall images, breaking through the limitations of traditional detection methods. Furthermore, the seepage detection model constructed in this application can achieve automated and intelligent detection of building exterior wall seepage, significantly improving detection efficiency, reducing errors and costs caused by manual intervention, and providing an efficient, accurate, and engineering-practical technical solution for building exterior wall seepage detection, effectively guaranteeing the intelligent upgrading and large-scale application of building exterior wall seepage detection work.

[0033] In one embodiment of this application, a unique thermal coding method is used to encode the type of water seepage on the exterior walls of buildings and use it as a label.

[0034] In one embodiment of this application, the deep learning model takes labeled building exterior wall images as input and the predicted value of the seepage category of the building exterior wall images as output. The step of training the deep learning model multiple times until convergence using the dataset includes: updating the parameters of the deep learning model based on the loss function determined by the actual value of the seepage category and the predicted value of the seepage category during each iteration of training.

[0035] According to one embodiment of this application, the loss function is:

[0036] in, This indicates the label corresponding to the i-th building exterior wall image. Bit binary number, This represents the predicted water seepage category value for the i-th building's exterior wall image.

[0037] To better understand the data format of the labels and the calculation process of the loss function in this application's dataset, illustratively, for example, if there are 5 different types of external wall seepage states, the codes would be 00001, 00010, 00100, 01000, and 10000 respectively. The results are then compared with the output, and the loss function is used... Calculate the loss for a single image. For example, if the output is (0.1, 0.05, 0.8, 0.02, 0.03) and the label is (0, 0, 1, 0, 0), the loss calculation for a single image is as follows: It should be noted that the loss function used above is only one embodiment of this application. With the continuous development of neural network training methods, other loss functions that can further improve the performance of the external wall seepage detection model can be used, and no specific limitation is made here.

[0038] As described above, the one-hot encoding method used in the above embodiments of this application to encode the fault type of the device under test can avoid the size relationship between categories, making it easier for the external wall seepage detection model to learn the relationship between categories. It also facilitates the multi-class training and prediction of the external wall seepage detection model. It can improve the generalization ability of the external wall seepage detection model (because it can better represent the distance and similarity between categories, thereby improving the model's generalization ability for unknown data). Furthermore, the vector form of one-hot encoding is easy to calculate and process, and can be well matched with the calculation process of the external wall seepage detection model, thus improving the calculation efficiency.

[0039] According to one embodiment of this application, such as Figure 4 As shown, the method of this application also includes step S3: calculating the risk warning information of the building exterior wall based on the building exterior wall seepage detection results.

[0040] As described above, the embodiments of this application transform the water seepage detection results from a simple judgment of water seepage into a risk warning with practical guidance significance. It can intuitively reflect the severity, spread trend and potential impact of water seepage problems, help relevant personnel quickly and accurately grasp the safety status of building exterior walls, provide scientific decision support for property management, safety supervision and other work, and comprehensively improve building safety.

[0041] Furthermore, according to one embodiment of this application, a building exterior wall seepage monitoring system is proposed, such as... Figure 5 As shown, the system of this application includes: a drone for flying around the exterior wall of a building; a camera device mounted on the drone for taking pictures of the exterior wall of the building to obtain images of the exterior wall; and an image processor configured with a pre-trained exterior wall seepage detection model for calculating the exterior wall seepage detection results based on the exterior wall images.

[0042] The drone can be either the portable M3E or the high-performance M300RTK+P1. The M3E drone is characterized by its small size and light weight; it allows for preparation in one minute; it enables automatic flight and modeling; photos include built-in time and GPS watermarks; and thermal imaging is optional. The M300RTK+P1 drone is wind and rain resistant, offering high safety; it improves 3D modeling efficiency; provides higher data accuracy; and automatically archives and saves data for easy later review; thermal imaging is also optional. It should be noted that the choice of drone is not limited to the examples above; the specific drone should be selected based on cost and performance requirements.

[0043] As described above, the building exterior wall seepage monitoring system of the above embodiments of this application uses a drone equipped with camera equipment to take all-round pictures of the building exterior wall, and combines the pre-trained exterior wall seepage detection model to perform intelligent analysis of the images. It can efficiently and accurately identify the seepage area of ​​the exterior wall, overcome the shortcomings of traditional manual detection which is low in efficiency, limited coverage and has safety hazards, realize rapid and automated monitoring of building exterior wall seepage problems, significantly improve detection efficiency and accuracy, and provide reliable technical support for building maintenance and safety management.

[0044] Based on the inventive concept of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method described in the above embodiments. The following is in conjunction with... Figure 6 Please provide a detailed explanation.

[0045] like Figure 6 As shown, it illustrates the electronic device 100 of this application, which may specifically include a processor 110 and a memory 120. The memory 120 is coupled to the processor 110.

[0046] Processor 110 is used to control the operation of electronic devices. Processor 110 may also be referred to as a CPU (Central Processing Unit). Processor 110 may be an integrated circuit chip with signal processing capabilities. Processor 110 may also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. The general-purpose processor may be a microprocessor, or processor 110 may be any conventional processor.

[0047] The memory 120 is used to store computer programs and may be RAM, ROM, or other types of storage terminals. Specifically, the memory 120 may include one or more computer-readable storage media, which may be non-transitory or transient. The memory 120 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage terminals or flash memory terminals. In some embodiments, the non-transitory computer-readable storage media in the memory 120 is used to store at least one line of program code.

[0048] The processor 110 is used to execute computer programs stored in the memory 120 to implement the methods described in the various method embodiments of this application.

[0049] In some embodiments, the electronic device may further include a peripheral terminal interface 130 and at least one peripheral terminal. The processor 110, memory 120, and peripheral terminal interface 130 may be connected via a bus or signal line. Each peripheral terminal may be connected to the peripheral terminal interface 130 via a bus, signal line, or circuit board. Specifically, the peripheral terminal includes at least one of a radio frequency circuit 140, a display screen 150, an audio circuit 160, and a power supply 170.

[0050] The peripheral terminal interface 130 can be used to connect at least one I / O (Input / Output) related peripheral terminal to the processor 110 and the memory 120. In some embodiments, the processor 110, memory 120 and peripheral terminal interface 130 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 110, memory 120 and peripheral terminal interface 130 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0051] The radio frequency (RF) circuit 140 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 140 communicates with communication networks and other IoT devices via electromagnetic signals; it is the communication circuit of the electronic device. The RF circuit 140 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 140 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, an operator identification module card, etc. The RF circuit 140 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 140 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0052] Display screen 150 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 150 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 110 for processing. In this case, display screen 150 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 150, located on the front panel of the electronic device; in other embodiments, there may be at least two display screens, located on different surfaces of the electronic device or in a folded design; in still other embodiments, display screen 150 may be a flexible display screen, located on a curved or folded surface of the electronic device. Furthermore, display screen 150 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. Display screen 150 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0053] The audio circuit 160 may include a microphone and a speaker. The microphone is used to collect sound waves from the operator and the environment, converting the sound waves into electrical signals that are input to the processor 110 for processing, or input to the radio frequency circuit 140 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned in a different part of the electronic device. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 110 or the radio frequency circuit 140 into sound waves. The speaker may be a conventional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 160 may also include a headphone jack.

[0054] Power supply 170 is used to supply power to various components in an electronic device. Power supply 170 can be alternating current, direct current, a disposable battery, or a rechargeable battery. When power supply 170 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0055] For a detailed description of the functions and execution processes of each functional module or component in the electronic device embodiments of this application, please refer to the descriptions in the above-described method embodiments of this application, which will not be repeated here.

[0056] In the embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the embodiments of the electronic devices described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some data may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0057] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0058] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0059] Based on the inventive concept of the above embodiments, this application also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, performs the steps of the method described in any of the above embodiments. The following is in conjunction with... Figure 7 This describes the execution process of the above embodiments on a computer-readable storage medium.

[0060] like Figure 7As shown, it illustrates the computer-readable storage medium of this application. The integrated units described above, if implemented as software functional units and sold or used as independent products, can be stored in the computer-readable storage medium 200. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions / computer programs to cause an Internet of Things device (which may be a personal computer, server, or network terminal, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, as well as electronic terminals such as computers, mobile phones, laptops, tablets, and cameras that have the aforementioned storage media.

[0061] The execution process of program data in a computer-readable storage medium can be described with reference to the above-described method embodiments of this application, and will not be repeated here.

[0062] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0063] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

Claims

1. A method for monitoring water seepage in building exterior walls, characterized in that, The method includes: Acquire images of building exterior walls; The pre-trained external wall seepage detection model is used to calculate the external wall seepage detection results based on the building's external wall images.

2. The method for monitoring water seepage in building exterior walls according to claim 1, characterized in that, The building exterior wall images were obtained using the following method: The drone, equipped with a camera, is used to capture images of the building's exterior walls.

3. The method for monitoring water seepage in building exterior walls according to claim 1, characterized in that, The building exterior wall images were obtained using the following method: An infrared thermal imager mounted on a drone is used to photograph the exterior wall of the building to obtain an infrared image of the building exterior wall, and this infrared image is used as the building exterior wall image.

4. The method for monitoring water seepage in building exterior walls according to claim 1, characterized in that, The pre-trained external wall seepage detection model was trained using the following method: Acquire labeled images of the building's exterior walls and construct a dataset, wherein the labels indicate the true values ​​of the water seepage category of the building's exterior walls; The initial deep learning model is trained iteratively multiple times using the dataset until convergence, in order to obtain a building exterior wall seepage detection model.

5. The method for monitoring water seepage in building exterior walls according to claim 4, characterized in that, The type of water seepage on the building's exterior walls is coded using a unique thermal coding method and used as a label.

6. The method for monitoring water seepage in building exterior walls according to claim 4, characterized in that, The deep learning model takes labeled images of the building's exterior walls as input and outputs a predicted value for the water seepage category of the building's exterior walls. The step of iteratively training the deep learning model using the dataset until convergence includes: During each training iteration, the parameters of the deep learning model are updated based on the loss function determined by the true value and the predicted value of the seepage category.

7. The method for monitoring water seepage in building exterior walls according to claim 3, characterized in that, The method further includes: Based on the water seepage detection results of the building's exterior walls, risk warning information for the building's exterior walls is calculated.

8. A building exterior wall seepage monitoring system, characterized in that, The system includes: Drones are used to fly around the exterior walls of buildings; A camera device, mounted on the drone, is used to photograph the exterior walls of the building to obtain images of the building's exterior walls; An image processor, equipped with a pre-trained external wall seepage detection model, is used to calculate the external wall seepage detection results based on images of the building's external walls.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images