A method and device for building seepage annotation based on robot cruise

Abstract

The present application discloses a building seepage annotation method, device, equipment and medium based on robot cruise. The method includes: obtaining an infrared image captured by a robot during the cruise of a building to be detected, inputting the infrared image into a pre-trained seepage detection model for seepage detection to obtain a plurality of candidate regions and corresponding seepage probabilities; screening the plurality of candidate regions based on the seepage probabilities and temperature data in the infrared image to obtain seepage regions; performing coordinate conversion based on the conversion relationship between the building drawing coordinate system and the detection coordinate system stored in advance to obtain the second coordinates of the seepage regions; determining the seepage area, and mapping the seepage regions to the building drawing of the building to be detected based on the second coordinates and the seepage area to obtain the building seepage annotation result. Through this technical solution, the detection efficiency of building seepage and the accuracy of the detection result can be improved, which is beneficial to improving the timeliness of seepage feedback.

Description

Technical Field

[0001] This application belongs to the technical field of building inspection, and particularly relates to a building water seepage annotation method, device, equipment and medium based on robot cruising. Background Art

[0002] With the development of social economy, the number of buildings is increasing continuously. To ensure the safety and stability of building use, the quality inspection of building floors, especially the detection of water seepage problems in building floors, becomes very important. The water seepage problem of building floors refers to the phenomenon that water penetrates through the internal structure of the floor to other areas due to various reasons during the use of the building floor, thus affecting the floor safety and humidity. Identifying and evaluating the penetration or moisture conditions at each position of the floor according to the physical characteristics of the building floor, and then determining whether there is a water seepage phenomenon can effectively avoid the problem of untimely detection of damage to the floor structure.

[0003] In the prior art, the detection method for water seepage in building floors is usually to attach or connect a humidity detection instrument to the building to be detected, send a detection instruction to the humidity detection instrument regularly, obtain the humidity data of the building to be detected, and determine whether there is a water seepage phenomenon in the building to be detected at the current moment by comparing the humidity data with the preset humidity data. Then, according to the installation position of the humidity detection instrument, the area with the water seepage phenomenon is determined and marked on the corresponding CAD drawing of the building to be detected.

[0004] However, the prior art requires a large number of humidity detection instruments, which is not suitable for large-area water seepage detection. At the same time, due to weather reasons, the humidity in the air will affect the detection results of the humidity detection instrument, resulting in inaccurate detection results for the water seepage of the building to be detected. At the same time, the prior art needs to manually mark the water seepage in the CAD drawing, resulting in the problem of untimely feedback of the water seepage situation. Summary of the Invention

[0005] The purpose of the embodiments of this application is to provide a building water seepage annotation method, device, equipment and medium based on robot cruising, which solves the problems of limited application scope, inaccurate detection results and untimely feedback of water seepage situations existing in the building water seepage detection using the prior art. By identifying the water seepage situation of the building floor according to the physical characteristics of the building floor materials using infrared images, determining the water seepage area according to the water seepage probability of the infrared image and the preset water seepage probability threshold, and converting the water seepage area to the building drawing coordinate system for building water seepage annotation based on robot cruising, the purpose of automatically detecting and annotating water seepage based on infrared images can be achieved, improving the detection efficiency and accuracy of building water seepage, and at the same time facilitating the timely feedback of the water seepage situation.

[0006] In a first aspect, an embodiment of the present application provides a method for marking building water seepage based on robot cruising. The method includes:

[0007] Obtain an infrared image captured by a robot during cruising of a building to be detected, input the infrared image into a pre-trained water seepage detection model, perform water seepage detection based on the water seepage detection model to obtain multiple candidate regions and corresponding water seepage probabilities in the infrared image, and the infrared image includes temperature data of multiple pixel points;

[0008] Screen the multiple candidate regions based on the water seepage probability and temperature data to obtain the water seepage regions in the infrared image;

[0009] Obtain the first coordinates of the water seepage region in the detection coordinate system, and based on the conversion relationship between the building drawing coordinate system and the detection coordinate system stored in advance, convert the first coordinates to the building drawing coordinate system to obtain the second coordinates of the water seepage region;

[0010] Identify the coordinates of multiple boundary pixels of the water seepage region in the building drawing coordinate system, determine the water seepage area based on the coordinates of the multiple boundary pixels, and map the water seepage region to the building drawing of the building to be detected based on the second coordinates and the water seepage area to obtain the marking result of building water seepage based on robot cruising.

[0011] Optionally, screening the multiple candidate regions based on the water seepage probability and temperature data includes:

[0012] Group the multiple candidate regions based on the temperature data to obtain multiple groups of candidate regions;

[0013] Determine the overall water seepage probability of the same group of candidate regions based on the water seepage probability, and screen the multiple candidate regions based on the overall water seepage probability.

[0014] Optionally, grouping the multiple candidate regions based on the temperature data includes:

[0015] Determine the temperature distribution information of the pixel points corresponding to each candidate region based on the temperature data;

[0016] Determine the water seepage similarity between the multiple candidate regions based on the temperature distribution information of the pixel points, and group the multiple candidate regions based on the water seepage similarity.

[0017] Optionally, screening the multiple candidate regions based on the overall water seepage probability includes:

[0018] Calculate the average group water seepage probability of the multiple groups of candidate regions based on the overall water seepage probability;

[0019] Identify the magnitude relationship between the water seepage probability corresponding to each candidate region and the average group water seepage probability, and filter out the candidate regions with a water seepage probability less than the average group.

[0020] Optionally, before screening multiple candidate regions based on the seepage probability and temperature data, the method further includes:

[0021] Calculating the temperature difference data of the candidate region based on the temperature data of multiple pixel points, and performing accuracy verification on the seepage probability based on the temperature difference data;

[0022] Updating the seepage probability based on the accuracy verification result to obtain the final seepage probability.

[0023] Optionally, performing accuracy verification on the seepage probability based on the temperature difference data includes:

[0024] Identifying the association relationship between the temperature difference data and the preset temperature difference range, where the preset temperature difference range includes the preset material temperature difference range and the preset seepage temperature difference range;

[0025] When the temperature difference data is within the preset seepage temperature difference range, it is determined that the seepage probability is accurate;

[0026] When the temperature difference data is within the preset material temperature difference range, it is determined that the seepage probability is inaccurate.

[0027] Optionally, before calculating the temperature difference data of the candidate region based on the temperature data of multiple pixel points, the method further includes:

[0028] Obtaining the environmental temperature data and the material temperature rise data corresponding to the candidate region;

[0029] Predicting the highest seepage temperature of the candidate region based on the environmental temperature data and the material temperature rise data.

[0030] Correspondingly, performing accuracy verification on the seepage probability based on the temperature difference data includes:

[0031] Determining the estimated minimum seepage temperature of the candidate region based on the temperature difference data and the highest seepage temperature, and identifying whether the actual minimum temperature in the temperature data of the candidate region is greater than the estimated minimum seepage temperature;

[0032] Performing accuracy verification on the seepage probability based on the actual minimum temperature identification result.

[0033] In a second aspect, an embodiment of the present application provides a building seepage annotation device based on robot cruising, and the device includes:

[0034] A seepage probability determination module, configured to obtain an infrared image captured by a robot during cruising of a building to be detected, input the infrared image into a pre-trained seepage detection model, perform seepage detection based on the seepage detection model to obtain multiple candidate regions and corresponding seepage probabilities in the infrared image, and the infrared image includes temperature data of multiple pixel points;

[0035] A seepage area detection module, configured to screen multiple candidate areas based on seepage probability and temperature data to obtain the seepage areas in the infrared image;

[0036] A seepage coordinate conversion module, configured to obtain the first coordinates of the seepage area in the detection coordinate system, and convert the first coordinates to the building drawing coordinate system based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, so as to obtain the second coordinates of the seepage area;

[0037] A seepage area annotation module, configured to identify multiple boundary pixel coordinates of the seepage area in the building drawing coordinate system, determine the seepage area based on the multiple boundary pixel coordinates, and map the seepage area to the building drawing of the building to be detected based on the second coordinates and the seepage area, so as to obtain the building seepage annotation result based on robot cruising.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0040] In a fifth aspect, an embodiment of the present application further provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium, and at least one processor of the device reads and executes the computer program, so that the device executes the method described in the first aspect.

[0041] In an embodiment of the present application, an infrared image captured by a robot during a cruise inspection of a building to be detected is obtained, and the infrared image is input into a pre-trained water seepage detection model. Water seepage detection is performed based on the water seepage detection model to obtain multiple candidate regions and corresponding water seepage probabilities in the infrared image. The infrared image includes temperature data of multiple pixels; multiple candidate regions are screened based on the water seepage probability and temperature data to obtain water seepage regions in the infrared image; a first coordinate of the water seepage region in the detection coordinate system is obtained, and based on the conversion relationship between the building drawing coordinate system and the detection coordinate system stored in advance, the first coordinate is converted to the building drawing coordinate system to obtain a second coordinate of the water seepage region; multiple boundary pixel coordinates of the water seepage region in the building drawing coordinate system are identified, the water seepage area is determined based on the multiple boundary pixel coordinates, and the water seepage region is mapped to the building drawing of the building to be detected based on the second coordinate and the water seepage area to obtain a building water seepage annotation result based on robot cruise. Through the above-mentioned building water seepage annotation method based on robot cruise, the problems of low detection efficiency, inaccurate detection results, and untimely feedback of water seepage conditions existing in building water seepage detection using the prior art are solved. By determining the water seepage region according to the water seepage probability of the infrared image and a preset water seepage probability threshold, and converting the water seepage region to the building drawing coordinate system for building water seepage annotation based on robot cruise, the purpose of automatically performing water seepage detection and water seepage annotation based on the infrared image can be achieved, the detection efficiency of building water seepage and the accuracy of the detection results are improved, and at the same time, it is beneficial to timely feedback the water seepage situation. Description of the Drawings

[0042] Figure 1 is a flowchart of a method for annotating building water seepage based on robot cruise provided by an embodiment of the present application;

[0043] Figure 2 is an infrared schematic diagram of building water seepage to be detected provided by the present application;

[0044] Figure 3 is a flowchart of screening candidate regions provided by an embodiment of the present application;

[0045] Figure 4 is a flowchart of another method for annotating building water seepage based on robot cruise provided by an embodiment of the present application;

[0046] Figure 5 is a structural block diagram of a device for annotating building water seepage based on robot cruise provided by an embodiment of the present application;

[0047] Figure 6 is a structural block diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0048] To make the objectives, technical solutions and advantages of this application clearer, the following provides a more detailed description of specific embodiments of this application with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. Additionally, it should be noted that, for ease of description, only parts related to this application rather than all of the content are shown in the drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. When the operations are completed, the process can be terminated, but there may also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0049] The following will clearly describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application belong to the scope of protection of this application.

[0050] The terms "first", "second", etc. in the description and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "and / or" in the description and claims means at least one of the connected objects, and the character " / ", generally represents an "or" relationship between the associated objects before and after.

[0051] First, the usage scenario of this solution can be a scenario for detecting building water seepage, especially a scenario for automatically detecting the water seepage situation of building floors by using a robot to cruise and capture infrared images. By determining the water seepage area based on the water seepage probability of the infrared image and a preset water seepage probability threshold, and converting the water seepage area to the building drawing coordinate system for building water seepage annotation based on robot cruise, the purpose of automatically detecting and annotating water seepage based on infrared images can be achieved, improving the detection efficiency and accuracy of building water seepage, and at the same time facilitating the timely feedback of the water seepage situation. Based on the above usage scenario, it can be understood that the execution entity of this solution can be an electronic device, such as intelligent terminals like mobile phones, tablets, and desktop computers.

[0052] The following will combine the accompanying drawings and, through specific embodiments and their application scenarios, elaborate in detail on a method, device, equipment, and medium for building seepage annotation based on robot cruising provided by the embodiments of the present application.

[0053] Figure 1 It is a flowchart of a method for building seepage annotation based on robot cruising provided by the embodiments of the present application. As Figure 1 shown, the specific steps are as follows:

[0054] S101, Obtain the infrared image captured by the robot during the cruise of the building to be detected, input the infrared image into a pre-trained seepage detection model, perform seepage detection based on the seepage detection model, and obtain multiple candidate regions and corresponding seepage probabilities in the infrared image. The infrared image includes temperature data of multiple pixel points.

[0055] Among them, the building to be detected can be a building that needs to be subjected to seepage detection or the internal structure of a building, such as: the ceiling of a floor, the floor of a floor, etc. The infrared image can be a distribution map of the surface temperature values of the floor generated by capturing the infrared radiation emitted or reflected by the building to be detected using an infrared camera. The infrared image reflects the temperature difference on the surface of the building to be detected, and different pixel values represent different temperature values. The pre-trained seepage detection model can be a model used to perform image recognition on the infrared image to predict the seepage situation of the building structure corresponding to the infrared image. The candidate region can be a region in the infrared image predicted by the seepage detection model where seepage may occur. The seepage probability can be data used to describe the possibility of seepage in each candidate region. The temperature data can be the temperature value of the position of the building structure corresponding to each pixel point in the infrared image.

[0056] In one embodiment, the infrared image captured by the robot during the cruise of the building to be detected can be received in real time, input into a pre-trained seepage detection model, and the infrared image is subjected to image recognition and processing through the seepage detection model to output an infrared image with the seepage area outlined. The infrared image output by the seepage detection model includes multiple candidate regions that may have seepage phenomena outlined by the model and the corresponding seepage probability for each candidate region. The infrared image includes the temperature data of each pixel point.

[0057] Taking the example of detecting water seepage in the internal floors of a building to be inspected, a lidar device can be pre-configured on the cruise robot, and the cruise robot can be placed inside the building to be inspected. The robot can use lidar in combination with SLAM (Simultaneous Localization and Mapping) technology for autonomous navigation. SLAM technology allows the robot to build a map and locate itself in real time in an unknown environment, thus ensuring that it can automatically plan a cruise path within the floors of the building to be inspected, avoid collisions, and ensure coverage of all water seepage inspection areas. The lidar can provide high-precision environmental modeling and provide input data for the SLAM algorithm, enabling the robot to complete accurate positioning and mapping in a complex environment. During the autonomous cruise of the robot, the floors are scanned in real time by the infrared camera mounted on it to capture temperature differences and identify potential water seepage areas based on the temperature differences.

[0058] Figure 2 It is an infrared schematic diagram of water seepage in the building to be inspected provided by this application.

[0059] As Figure 2 shown, the figure includes dark strip areas and light large areas. Among them, the dark strip areas are the areas with water seepage in the building to be inspected, that is, the candidate areas. The darker the color of the candidate area, the more serious the water seepage degree in this area, and the higher the water seepage probability predicted by the water seepage detection model. The large light areas in the figure are the areas without water seepage in the building to be inspected. The numbers in the figure represent the pixel point temperature data at that point.

[0060] By using the infrared camera to sense the temperature changes on the surface of the building floor, the water seepage areas usually exhibit different temperature characteristics from the surrounding areas due to the influence of moisture. Preprocessing operations such as denoising, enhancing contrast, and temperature calibration can be performed on the acquired infrared images, and the infrared images are presented in white-hot mode to improve the accuracy of water seepage detection. The water seepage areas of the building floor usually show lower temperature differences due to the influence of moisture. In the preprocessed infrared images, these areas affected by moisture and the areas not affected by moisture will show different color depths, and the areas with darker colors are regarded as the areas with potential signs of water seepage.

[0061] The water seepage detection model in this solution is a ResNet (Residual Networks) deep learning model. ResNet has extremely strong expressiveness and stability in image recognition tasks and is suitable for water seepage detection problems in complex environments. By using the residual learning mechanism of ResNet, the problem of gradient disappearance in the training of deep networks can be effectively avoided, and the detection accuracy can be improved. Before training the water seepage detection model, a large number of labeled infrared image data need to be collected in advance. The labels include information such as whether there is a water seepage area in the image, the specific location of the water seepage area, and the water seepage probability value of the area. The training set of infrared image data is enhanced to improve the robustness and generalization ability of the model. The data enhancement methods include rotation, scaling, cropping, and simulating water seepage areas of different angles and sizes to improve the model's ability to adapt to different scenarios; it also includes simulating infrared images under different temperature conditions to improve the model's adaptability to different temperature environments. During the model training process, the unlabeled infrared images in the training set are used as the model input, and the infrared image data with the labels of the area where the water seepage phenomenon is framed and the water seepage probability value label of the area are used as the output to train the water seepage detection model. The cross-entropy loss function is used to minimize the error between the label and the prediction result, and GPU acceleration is used for training. The network parameters are optimized by the gradient descent optimizer Adam. After the model training is completed, the trained ResNet model is used to predict the water seepage area of new infrared images. During the process of the water seepage detection model predicting the infrared image, the model analyzes each pixel point in the image and predicts whether the area composed of multiple pixel points is a water seepage area and what the probability of this area being a water seepage area is. The output of the water seepage detection model is the water seepage area probability value.

[0062] The technology of using the robot for automatic cruise to collect infrared images and combining deep learning for automatic analysis of infrared images adopted in this solution can enable the robot to autonomously inspect the water seepage phenomenon on the building floors and achieve the purpose of automatically identifying the water seepage area.

[0063] S102, Screen multiple candidate areas based on the water seepage probability and temperature data to obtain the water seepage area in the infrared image.

[0064] Among them, the water seepage area can be the area where there must be a water seepage phenomenon in the building to be detected.

[0065] In one embodiment, the sum of the water seepage probability and the temperature data of each candidate region can be calculated, and the sums of multiple candidate regions can be sorted from largest to smallest. The candidate regions with the top preset number of sum values are used as the water seepage regions in the infrared image. It is also possible to preset the water seepage probability weight and the temperature data weight, and by calculating the weighted sum of the water seepage probability, the water seepage probability weight, the temperature data, and the temperature data weight for each candidate region respectively, multiple candidate regions are screened, and the candidate region with the largest weighted sum is used as the water seepage region in the infrared image. It is also possible to preset the water seepage probability threshold and the temperature data threshold, and respectively compare whether the water seepage probability of each candidate region is higher than the preset water seepage probability threshold, and whether the sum of the pixel temperature data of each candidate region is higher than the preset temperature data threshold. When the water seepage probability is higher than the preset water seepage probability threshold and the sum of the pixel temperature data is higher than the preset temperature data threshold, it is determined that the candidate region is the water seepage region in the infrared image.

[0066] S103. Obtain the first coordinates of the water seepage region in the detection coordinate system, and based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, convert the first coordinates to the building drawing coordinate system to obtain the second coordinates of the water seepage region.

[0067] Among them, the detection coordinate system can be a two-dimensional coordinate system constructed for the internal overall structure of the entire building to be detected. The detection coordinate system in this solution can be constructed by controlling the robot to move on the internal ground of the building to be detected, scanning the internal overall structure of the entire building to be detected, and using lidar combined with SLAM technology to construct the detection coordinate system of the entire building to be detected. The detection coordinate system of lidar combined with SLAM technology is initially a three-dimensional coordinate system. In order to realize the subsequent coordinate conversion with the building coordinate system and map the water seepage region to the building drawing, the three-dimensional coordinate system needs to be mapped to a two-dimensional coordinate system. The two-dimensional detection coordinate system in this solution takes the initial position of the robot moving on the internal ground of the building to be detected as the coordinate origin, the positive front direction of the robot as the positive direction of the x-axis of the coordinate system, and the left side of the robot as the positive direction of the y-axis of the coordinate system. After the detection coordinate system is constructed, it will not change with the movement of the robot, and the robot can real-time locate its position coordinates in the detection coordinate system when cruising inside the building to be detected, and calculate the position coordinates of the infrared image scanned during the cruising process and each region inside the infrared image in the detection coordinate system. The first coordinates can be the position coordinates of the water seepage region in the detection coordinate system. The building drawing coordinate system can be the coordinate system corresponding to the plane drawing of the building to be detected. The conversion relationship between the building drawing coordinate system and the detection coordinate system can be the calculation formula for converting the coordinates in the building drawing coordinate system to the corresponding coordinates in the detection coordinate system. The second coordinates can be the position coordinates of the water seepage region in the building drawing coordinate system.

[0068] In one embodiment, the first coordinates of the water seepage area in the detection coordinate system can be obtained by reading the cruise data of the robot. Based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, the coordinates obtained by converting the first coordinates to the building drawing coordinate system are calculated to obtain the second coordinates of the water seepage area.

[0069] The detection coordinate system in this solution is a SLAM two-dimensional coordinate system. During the robot's cruise, the robot uses a lidar to scan the internal environment of the building to be detected and gradually constructs a map containing internal features of the building such as building structures, walls, and obstacles through SLAM technology, usually a two-dimensional grid map or a point cloud map. SLAM technology can not only help the robot to locate in real time but also integrate the internal environment information of the building to be detected into the map for subsequent location of the water seepage area. The building drawing in this solution is a CAD drawing, which is a two-dimensional plan view of the internal environment of the building to be detected. The building drawing coordinate system is pre-drawn based on the local coordinate system of the building to be detected. There is a coordinate system conversion relationship between the detection coordinates of the water seepage area in the detection coordinate system and the actual coordinates in the building drawing coordinate system. In the internal environment of the building to be detected, some reference points with known positions, such as the positions of fixed objects like doorways and corners, can be selected as reference points for coordinate conversion. By obtaining the first coordinates of these reference points in the detection coordinate system and the second coordinates in the building drawing coordinate system respectively, an affine transformation is used to calculate the conversion matrix between the detection coordinate system and the building drawing coordinate system, aligning the detection coordinate system with the building drawing coordinate system, and then converting the position coordinates detected in the SLAM system to the position coordinates in the CAD drawing coordinate system. Through coordinate registration, the coordinates of the water seepage area detected by the robot in the SLAM system can be mapped to the corresponding positions in the CAD drawing to mark the water seepage area. The marking of the water seepage area includes information such as the temperature anomaly degree, position, and area of the water seepage. The robot pushes the detection results of the water seepage area and its position annotation on the CAD drawing to the maintenance personnel of the building to be detected in real time through a 5G wireless network for the maintenance personnel to view the detailed information of the water seepage area in a timely manner using intelligent terminals such as mobile devices, tablets, or computers.

[0070] This solution combines SLAM technology for environment mapping and robot positioning. Through coordinate registration, it ensures that the water seepage detection information is highly aligned with the CAD drawing of the building, achieving a more accurate and comprehensive water seepage recognition ability and intelligent cruise and real-time detection of water seepage information. Through real-time data collection and water seepage area feedback during the robot's cruise, automatically marking the water seepage position on the CAD drawing of the building based on the coordinate conversion relationship, and pushing it to the maintenance personnel in real time through a wireless network, the timeliness of water seepage feedback and water seepage maintenance can be improved.

[0071] S104. Identify the coordinates of multiple boundary pixels of the water seepage area in the building drawing coordinate system, determine the water seepage area based on the coordinates of the multiple boundary pixels, and map the water seepage area to the building drawing of the building to be detected based on the second coordinate and the water seepage area, so as to obtain the building water seepage annotation result based on robot cruise.

[0072] Among them, the boundary pixel coordinates can be the coordinates of the edge pixel points of the water seepage area in the building drawing coordinate system. The building water seepage annotation result is the building drawing data after marking the water seepage position coordinates and the water seepage area data of the building to be detected on the building drawing.

[0073] In one embodiment, the edge pixels of the water seepage area can be identified, and the corresponding boundary pixel coordinates of each edge pixel in the building drawing coordinate system are obtained respectively, and the water seepage area is calculated according to the boundary pixel coordinates. Determine the position of the water seepage area on the building drawing according to the second coordinate, determine the range of the water seepage area on the building drawing according to the water seepage area, and map the water seepage area to the building drawing of the building to be detected according to the position and range, so as to mark the water seepage area on the building drawing and obtain the building water seepage annotation result based on robot cruise.

[0074] The technical solution provided by the embodiments of the present application is to obtain the infrared image captured by the robot during the cruise of the building to be detected, input the infrared image into the pre-trained water seepage detection model, perform water seepage detection based on the water seepage detection model, and obtain multiple candidate areas and corresponding water seepage probabilities in the infrared image. The infrared image includes the temperature data of multiple pixel points; filter the multiple candidate areas based on the water seepage probability and the temperature data to obtain the water seepage area in the infrared image; obtain the first coordinate of the water seepage area in the detection coordinate system, and based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, convert the first coordinate to the building drawing coordinate system to obtain the second coordinate of the water seepage area; identify the coordinates of multiple boundary pixels of the water seepage area in the building drawing coordinate system, determine the water seepage area based on the coordinates of the multiple boundary pixels, and map the water seepage area to the building drawing of the building to be detected based on the second coordinate and the water seepage area, so as to obtain the building water seepage annotation result based on robot cruise. Through the above-mentioned building water seepage annotation method based on robot cruise, the problems of low detection efficiency, inaccurate detection results and untimely feedback of water seepage conditions existing in building water seepage detection using the existing technology are solved. By determining the water seepage area according to the water seepage probability of the infrared image and the preset water seepage probability threshold, and converting the water seepage area to the building drawing coordinate system for building water seepage annotation based on robot cruise, the purpose of automatically detecting and annotating water seepage based on infrared images can be achieved, improving the detection efficiency of building water seepage and the accuracy of detection results, and at the same time facilitating the timely feedback of water seepage conditions.

[0075] Figure 3It is a flowchart for screening candidate regions provided by an embodiment of the present application. As Figure 3 shown, it specifically includes the following steps:

[0076] S301, group multiple candidate regions based on temperature data to obtain multiple groups of candidate regions.

[0077] Among them, the group of candidate regions can be a group obtained by grouping candidate regions with the same or similar pixel temperatures.

[0078] In one embodiment, the average pixel temperature of each candidate region can be calculated according to the temperature data, and candidate regions with smaller differences in average pixel temperature are divided into the same group based on the clustering algorithm to obtain multiple groups of candidate regions.

[0079] In one embodiment, optionally, grouping multiple candidate regions based on temperature data includes:

[0080] Determine the pixel point temperature distribution information corresponding to each candidate region based on the temperature data;

[0081] Determine the seepage similarity between multiple candidate regions based on the pixel point temperature distribution information, and group the multiple candidate regions based on the seepage similarity.

[0082] Among them, the pixel point temperature distribution information can be information used to describe in which temperature ranges the pixel point temperature data in the same candidate region is distributed. The seepage similarity can be used to describe whether the seepage degrees between different candidate regions are the same. The pixel point temperature distribution information can represent the seepage degree of each candidate region. The lower the temperature in the pixel point temperature distribution information concentration, the more serious the seepage degree. According to the similarity between the pixel point temperature distribution information, the similarity of the seepage degrees between multiple candidate regions can be determined.

[0083] In one embodiment, the data that is relatively concentrated in the pixel temperature data corresponding to each candidate region can be determined as the pixel point temperature distribution information corresponding to each candidate region, calculate the distance between the pixel point temperature distribution information of multiple different candidate regions, and determine the seepage similarity between multiple candidate regions. According to the seepage similarity, candidate regions with higher similarity are divided into the same group to obtain the grouping results of multiple candidate regions. A similarity threshold can be preset, and multiple candidate regions with similarity higher than the preset similarity threshold are divided into the same group; alternatively, the number of groups can be preset, and based on the number of candidate regions and the preset number of groups, the number of candidate regions in each group is determined, and multiple candidate regions are grouped according to the number of candidate regions in each group in descending order of similarity.

[0084] In this solution, by determining the pixel temperature distribution information corresponding to each candidate region based on temperature data, determining the seepage similarity between multiple candidate regions, and grouping the multiple candidate regions based on the seepage similarity, it is possible to achieve the purpose of dividing subsequent regions with similar seepage degrees into the same group, thereby improving the rationality of grouping.

[0085] S302, determine the overall seepage probability of the same candidate region group based on the seepage probability, and screen the multiple candidate regions based on the overall seepage probability.

[0086] Among them, the overall seepage probability can be data used to describe the seepage possibility of the same group.

[0087] In one embodiment, the sum of the seepage probabilities corresponding to multiple candidate regions in each group can be calculated to determine the overall seepage probability of the same candidate region group; alternatively, the seepage probabilities corresponding to multiple candidate regions in each group can be sorted according to their magnitude relationship, and the maximum value of the seepage probabilities in each group can be determined as the overall seepage probability of the same candidate region group. According to the overall seepage probability, all candidate regions corresponding to the group with the smallest overall seepage probability among the multiple groups are filtered out.

[0088] In one embodiment, optionally, screening the multiple candidate regions based on the overall seepage probability includes:

[0089] Calculate the average group seepage probability of multiple candidate region groups based on the overall seepage probability;

[0090] Identify the magnitude relationship between the seepage probability corresponding to each candidate region and the average group seepage probability, and filter out the candidate regions with seepage probabilities less than the average group.

[0091] In one embodiment, the average group seepage probability of multiple candidate region groups can be calculated according to the overall seepage probability and the number of candidate region groups. Compare the magnitude relationship between the seepage probability corresponding to each candidate region and the average group seepage probability, and filter out the candidate regions with seepage probabilities less than the average group.

[0092] In this solution, by calculating the average group seepage probability of multiple candidate region groups based on the overall seepage probability, and filtering out the candidate regions with seepage probabilities less than the average group according to the magnitude relationship between the seepage probability corresponding to each candidate region and the average group seepage probability, it is possible to achieve the purpose of screening seepage regions based on the overall seepage situation of candidate regions, avoid the problem that the seepage detection model is not accurate enough in identifying the seepage probability of infrared images due to external environmental interference, and improve the flexibility and accuracy of seepage region identification.

[0093] The technical solution provided by the embodiments of the present application groups multiple candidate areas according to temperature data, calculates the overall water seepage probability of the same candidate area group according to the water seepage probability, and screens multiple candidate areas based on the overall water seepage probability, so as to achieve the purpose of judging the water seepage area by combining temperature data and water seepage probability, and improve the accuracy of the water seepage area recognition result.

[0094] Figure 4 It is a flowchart of another building water seepage annotation method based on robot cruise provided by the embodiments of the present application. As Figure 4 shown, the specific steps are as follows:

[0095] S401, obtain the infrared image captured by the robot during the cruise of the building to be detected, input the infrared image into a pre-trained water seepage detection model, perform water seepage detection based on the water seepage detection model, obtain multiple candidate areas and corresponding water seepage probabilities in the infrared image, and the infrared image includes temperature data of multiple pixels.

[0096] S402, calculate the temperature difference data of the candidate area based on the temperature data of multiple pixels, and perform accuracy verification on the water seepage probability based on the temperature difference data.

[0097] Among them, the temperature difference data can be the difference between the highest pixel temperature and the lowest pixel dimension in each candidate area. The accuracy verification can be an operation for identifying whether the water seepage probability of each candidate area is accurate. The water seepage detection model in this solution is based on the water seepage probability of each candidate area obtained by image recognition of the infrared image. When there is an object occlusion problem in the building structure to be detected corresponding to the infrared image, due to the difference in materials between the occluding object and the building to be detected, there will be a situation where the image color corresponding to the occluding object in the captured infrared image is the same as or similar to the image color of the water seepage area. At this time, it is necessary to identify the water seepage probability according to the temperature data of the pixels.

[0098] In one embodiment, the temperature difference data of the corresponding candidate area can be calculated according to the maximum temperature value and the minimum temperature value of multiple pixels in each candidate area, compare the consistency between the temperature difference data of each candidate area and the water seepage probability, and determine the inconsistent water seepage probability as an inaccurate probability. The water seepage possibility of each candidate area can be sorted according to the size of the temperature difference data. The larger the temperature difference data, the higher the water seepage possibility; at the same time, the water seepage possibility of each candidate area is sorted according to the size of the water seepage probability. The larger the water seepage probability, the higher the water seepage possibility. Compare whether the positions of the same candidate area in the two sorts are the same, and determine the candidate area at the same position as the one where the temperature difference data is consistent with the water seepage probability, that is, the water seepage probability of this candidate area is accurate.

[0099] In one embodiment, optionally, accuracy verification of the water seepage probability based on the temperature difference data includes:

[0100] Identifying the association relationship between the temperature difference data and a preset temperature difference range, where the preset temperature difference range includes a preset material temperature difference range and a preset water seepage temperature difference range;

[0101] When the temperature difference data is within the preset water seepage temperature difference range, determining that the water seepage probability is accurate;

[0102] When the temperature difference data is within the preset material temperature difference range, determining that the water seepage probability is inaccurate.

[0103] Among them, the preset material temperature difference range can be a temperature data region composed of the maximum and minimum values of the temperature difference of pixel points caused by material differences set in advance. The preset water seepage temperature difference range is a temperature data region composed of the maximum and minimum values of the temperature difference of pixel points caused by water seepage set in advance.

[0104] In one embodiment, the temperature difference data of each candidate region can be compared with the preset material temperature difference range and the preset water seepage temperature difference range respectively to identify the association relationship between the temperature difference data and the preset temperature difference range. When the temperature difference data is within the preset water seepage temperature difference range, it indicates that the temperature difference in the candidate region is caused by the water seepage problem. At this time, the water seepage probability can be determined to be accurate; when the temperature difference data is within the preset material temperature difference range, it indicates that the temperature difference in the candidate region is caused by different materials. At this time, the water seepage probability can be determined to be inaccurate.

[0105] In this solution, by identifying the association relationship between the temperature difference data and the preset temperature difference range and determining whether the water seepage probability is accurate, the efficiency of accurately identifying the water seepage probability can be improved.

[0106] In one embodiment, optionally, before calculating the temperature difference data of the candidate region based on the temperature data of multiple pixel points, the method further includes:

[0107] Obtaining the ambient temperature data and the material temperature rise data corresponding to the candidate region;

[0108] Predicting the highest water seepage temperature of the candidate region based on the ambient temperature data and the material temperature rise data.

[0109] Correspondingly, accuracy verification of the water seepage probability based on the temperature difference data includes:

[0110] Determining the estimated lowest water seepage temperature of the candidate region based on the temperature difference data and the highest water seepage temperature, and identifying whether the actual lowest temperature in the temperature data of the candidate region is greater than the estimated lowest water seepage temperature;

[0111] Based on the identification result of the actual lowest temperature, accuracy verification of the water seepage probability is performed.

[0112] Among them, the material temperature rise data can be the temperature variable of the material of the building to be detected corresponding to the candidate area that changes with the ambient temperature. The highest seepage temperature can be the highest temperature of the building to be detected corresponding to the case where there is seepage in the candidate area. The estimated lowest seepage temperature of the candidate area can be the lowest temperature of the area determined according to its actual temperature difference data in the case where there is seepage in the candidate area.

[0113] In one embodiment, ambient temperature data and material temperature rise data corresponding to the candidate area can be obtained, and the highest seepage temperature corresponding to the candidate area can be calculated based on the ambient temperature data and the material temperature rise data. The estimated lowest seepage temperature in the case where there is seepage in the candidate area can be calculated based on the temperature difference data and the highest seepage temperature. Identify the minimum temperature data in the pixel point temperature data to obtain the actual lowest temperature of the candidate area, and compare whether the actual lowest temperature is greater than the estimated lowest seepage temperature. In the case where the actual lowest temperature is greater than the estimated lowest seepage temperature, it is determined that there is no seepage in the candidate area, and it is identified whether the seepage probability at this time is 0. If it is not 0, it is determined that the seepage probability is inaccurate; in the case where the actual lowest temperature is less than or equal to the estimated lowest seepage temperature, it is determined that there is seepage in the candidate area, and it is identified whether the seepage probability at this time is 0. If it is not 0, it is determined that the seepage probability is accurate.

[0114] In this solution, by predicting the highest seepage temperature of the candidate area based on the ambient temperature data and the material temperature rise data, determining the estimated lowest seepage temperature of the candidate area based on the temperature difference data and the highest seepage temperature, and performing accuracy verification on the seepage probability based on the actual lowest temperature identification result, the purpose of taking into account the influence factor of the temperature difference change caused by the material temperature rise in the process of seepage probability identification can be achieved, improving the comprehensiveness of the accuracy evaluation of the seepage probability and the accuracy of the final identification result of the seepage probability.

[0115] S403. Update the seepage probability based on the accuracy verification result to obtain the final seepage probability.

[0116] In one embodiment, it can be determined whether the seepage probability is accurate according to the accuracy verification result, and the inaccurate seepage probability can be set to 0 to obtain the final seepage probability. Since the seepage probability prediction error is caused by object occlusion, when there is object occlusion between the building to be detected and the infrared camera and there is no seepage, the seepage probability is not 0. At this time, the seepage probability is inaccurate, and setting it to 0 can update the inaccurate seepage probability.

[0117] S404. Screen multiple candidate areas based on the seepage probability and temperature data to obtain the seepage area in the infrared image.

[0118] S405. Obtain the first coordinate of the water seepage area in the detection coordinate system, and based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, convert the first coordinate to the building drawing coordinate system to obtain the second coordinate of the water seepage area.

[0119] S406. Identify the multiple boundary pixel coordinates of the water seepage area in the building drawing coordinate system, determine the water seepage area based on the multiple boundary pixel coordinates, and map the water seepage area to the building drawing of the building to be detected based on the second coordinate and the water seepage area to obtain the building water seepage annotation result based on robot cruising.

[0120] The technical solution provided by the embodiments of the present application, before screening multiple candidate areas based on the water seepage probability and temperature data, calculates the temperature difference data of the candidate areas based on the temperature data of multiple pixel points, performs accuracy verification on the water seepage probability based on the temperature difference data, and updates the water seepage probability based on the accuracy verification result to obtain the final water seepage probability, which can improve the accuracy of the water seepage area recognition result and is conducive to the accurate judgment of building water seepage.

[0121] Figure 5 It is the structural block diagram of a building water seepage annotation device based on robot cruising provided by the embodiments of the present application. As Figure 5 shown, it specifically includes the following:

[0122] The water seepage probability determination module 501 is used to obtain the infrared image captured by the robot during the cruise of the building to be detected, input the infrared image into the pre-trained water seepage detection model, perform water seepage detection based on the water seepage detection model to obtain multiple candidate areas and corresponding water seepage probabilities in the infrared image, and the infrared image includes the temperature data of multiple pixel points;

[0123] The water seepage area detection module 502 is used to screen multiple candidate areas based on the water seepage probability and temperature data to obtain the water seepage area in the infrared image;

[0124] The water seepage coordinate conversion module 503 is used to obtain the first coordinate of the water seepage area in the detection coordinate system, and based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, convert the first coordinate to the building drawing coordinate system to obtain the second coordinate of the water seepage area;

[0125] The water seepage area annotation module 504 is used to identify multiple boundary pixel coordinates of the water seepage area in the building drawing coordinate system, determine the water seepage area based on the multiple boundary pixel coordinates, and map the water seepage area to the building drawing of the building to be detected based on the second coordinate and the water seepage area to obtain the building water seepage annotation result based on robot cruising.

[0126] Optionally, the water seepage area detection module 502 is specifically used for:

[0127] Group multiple candidate regions based on temperature data to obtain multiple groups of candidate regions;

[0128] Determine the overall seepage probability of the same group of candidate regions based on the seepage probability, and screen multiple candidate regions based on the overall seepage probability.

[0129] Optionally, the seepage area detection module 502 is specifically configured to:

[0130] Determine the temperature distribution information of the pixel points corresponding to each candidate region based on the temperature data;

[0131] Determine the seepage similarity between multiple candidate regions based on the temperature distribution information of the pixel points, and group multiple candidate regions based on the seepage similarity.

[0132] Optionally, the seepage area detection module 502 is specifically configured to:

[0133] Calculate the average group seepage probability of multiple groups of candidate regions based on the overall seepage probability;

[0134] Identify the magnitude relationship between the seepage probability corresponding to each candidate region and the average group seepage probability, and filter out the candidate regions with seepage probability less than the average group.

[0135] Optionally, the device further includes:

[0136] An accuracy verification module, configured to calculate the temperature difference data of the candidate region based on the temperature data of multiple pixel points, and perform accuracy verification on the seepage probability based on the temperature difference data;

[0137] A seepage probability update module, configured to update the seepage probability based on the accuracy verification result to obtain the final seepage probability.

[0138] Optionally, the accuracy verification module is specifically configured to:

[0139] Identify the correlation between the temperature difference data and the preset temperature difference range, and the preset temperature difference range includes a preset material temperature difference range and a preset seepage temperature difference range;

[0140] When the temperature difference data is within the preset seepage temperature difference range, determine that the seepage probability is accurate;

[0141] When the temperature difference data is within the preset material temperature difference range, determine that the seepage probability is inaccurate.

[0142] Optionally, the device further includes:

[0143] A temperature data acquisition module, configured to acquire ambient temperature data and the material temperature rise data corresponding to the candidate region;

[0144] The maximum temperature prediction module is used to predict the maximum seepage temperature of the candidate area based on the ambient temperature data and the material temperature rise data.

[0145] Correspondingly, the accuracy verification module is specifically used for:

[0146] Determine the estimated minimum seepage temperature of the candidate area based on the temperature difference data and the maximum seepage temperature, and identify whether the actual minimum temperature in the temperature data of the candidate area is greater than the estimated minimum seepage temperature;

[0147] Based on the actual minimum temperature identification result, perform accuracy verification on the seepage probability.

[0148] In the technical solution provided by the embodiment of the present application, the seepage probability determination module is used to obtain the infrared image taken by the robot during the cruise of the building to be detected, input the infrared image into the pre-trained seepage detection model, perform seepage detection based on the seepage detection model, and obtain multiple candidate areas and corresponding seepage probabilities in the infrared image; the seepage area detection module is used to screen multiple candidate areas based on the seepage probability and temperature data to obtain the seepage area in the infrared image; the seepage coordinate conversion module is used to obtain the first coordinate of the seepage area in the detection coordinate system, and based on the pre-stored conversion relationship between the building drawing coordinate system and the detection coordinate system, convert the first coordinate to the building drawing coordinate system to obtain the second coordinate of the seepage area; the seepage area annotation module is used to identify multiple boundary pixel coordinates of the seepage area in the building drawing coordinate system, determine the seepage area based on the multiple boundary pixel coordinates, and map the seepage area to the building drawing of the building to be detected based on the second coordinate and the seepage area to obtain the building seepage annotation result based on the robot cruise. Through the above-mentioned building seepage annotation device based on robot cruise, the problems of low detection efficiency, inaccurate detection results and untimely feedback of seepage conditions existing in building seepage detection using the prior art are solved. By determining the seepage area according to the seepage probability of the infrared image and the preset seepage probability threshold, and converting the seepage area to the building drawing coordinate system for building seepage annotation based on robot cruise, the purpose of automatically performing seepage detection and seepage annotation based on infrared images can be achieved, the detection efficiency of building seepage and the accuracy of detection results are improved, and at the same time, it is beneficial to timely feedback the seepage situation.

[0149] An apparatus for marking building water seepage based on robot cruise in an embodiment of the present application can be configured in a device, or in components, integrated circuits, or chips in a terminal. The apparatus can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0150] An apparatus for marking building water seepage based on robot cruise in an embodiment of the present application can be an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0151] An apparatus for marking building water seepage based on robot cruise provided in an embodiment of the present application can implement each process implemented in the above method embodiments. To avoid repetition, it will not be elaborated here.

[0152] As Figure 6 shown, an embodiment of the present application further provides an electronic device 600, including a processor 601, a memory 602, a program or instruction stored on the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, it implements each process of the above method embodiment of an apparatus for marking building water seepage based on robot cruise, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0153] It should be noted that the electronic device in the embodiments of the present application includes the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0154] An embodiment of the present application further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above method embodiment of an apparatus for marking building water seepage based on robot cruise, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0155] Among them, the processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs, etc.

[0156] Another embodiment of the present application provides a program product, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps in the methods according to various exemplary embodiments of the present application described above. For example, the computer device can execute a method for building seepage annotation based on robot cruising recorded in an embodiment of the present application. The program product can be implemented by any combination of one or more readable media.

[0157] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the methods described can be performed in an order different from that described, and various steps can also be added, omitted, or combined. Additionally, features described with reference to certain examples can be combined in other examples.

[0158] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0159] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can still make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

[0160] The above is only the preferred embodiment of the present application and the technical principles applied. The present application is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments and substitutions that can be made by those skilled in the art will not depart from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments only. Without departing from the concept of the present application, it may also include more other equivalent embodiments, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for marking building water seepage based on robot cruise, characterized in that, The method includes: Obtaining an infrared image captured by a robot during a cruise of a building to be detected, inputting the infrared image into a pre-trained water seepage detection model, performing water seepage detection based on the water seepage detection model to obtain multiple candidate regions and corresponding water seepage probabilities in the infrared image, where the infrared image includes temperature data of multiple pixel points; Screening the multiple candidate regions based on the water seepage probability and the temperature data to obtain the water seepage regions in the infrared image; Obtaining the first coordinates of the water seepage regions in the detection coordinate system, and based on the conversion relationship between the pre-stored building drawing coordinate system and the detection coordinate system, converting the first coordinates to the building drawing coordinate system to obtain the second coordinates of the water seepage regions; Identifying multiple boundary pixel coordinates of the water seepage regions in the building drawing coordinate system, determining the water seepage area based on the multiple boundary pixel coordinates, and mapping the water seepage regions to the building drawing of the building to be detected based on the second coordinates and the water seepage area to obtain the building water seepage annotation result based on the robot cruise.

2. The method for annotating building water seepage based on robot cruise according to claim 1, wherein The screening of the multiple candidate regions based on the water seepage probability and the temperature data includes: Grouping the multiple candidate regions based on the temperature data to obtain multiple candidate region groups; Determining the overall water seepage probability of the same candidate region group based on the water seepage probability, and screening the multiple candidate regions based on the overall water seepage probability.

3. The method for marking building water seepage based on robot cruise according to claim 2, wherein The grouping of the multiple candidate regions based on the temperature data includes: Determining the pixel point temperature distribution information corresponding to each candidate region based on the temperature data; Determining the water seepage similarity between the multiple candidate regions based on the pixel point temperature distribution information, and grouping the multiple candidate regions based on the water seepage similarity.

4. The method for marking building water seepage based on robot cruise according to claim 2, characterized in that, The screening of the multiple candidate regions based on the overall water seepage probability includes: Calculating the average group water seepage probability of the multiple candidate region groups based on the overall water seepage probability; Identifying the magnitude relationship between the water seepage probability corresponding to each candidate region and the average group water seepage probability, and filtering out the candidate regions with a water seepage probability less than the average group water seepage probability.

5. The method for marking building water seepage based on robot cruise according to claim 1, wherein Before screening the multiple candidate regions based on the water seepage probability and the temperature data, the method further includes: Calculating the temperature difference data of the candidate regions based on the temperature data of the multiple pixel points, and performing accuracy verification on the water seepage probability based on the temperature difference data; Updating the water seepage probability based on the accuracy verification result to obtain the final water seepage probability.

6. The method for marking building water seepage based on robot cruise according to claim 5, characterized in that, The accuracy verification of the water seepage probability based on the temperature difference data includes: Identifying the association relationship between the temperature difference data and a preset temperature difference range, where the preset temperature difference range includes a preset material temperature difference range and a preset water seepage temperature difference range; Determining that the water seepage probability is accurate when the temperature difference data is within the preset water seepage temperature difference range; Determining that the water seepage probability is inaccurate when the temperature difference data is within the preset material temperature difference range.

7. The method for annotating building water seepage based on robot cruise according to claim 5, wherein Before calculating the temperature difference data of the candidate area based on the temperature data of the multiple pixel points, the method further includes: Obtaining ambient temperature data and the material temperature rise data corresponding to the candidate area; Predicting the highest seepage temperature of the candidate area based on the ambient temperature data and the material temperature rise data; Correspondingly, the accuracy verification of the seepage probability based on the temperature difference data includes: Determining the estimated lowest seepage temperature of the candidate area based on the temperature difference data and the highest seepage temperature, and identifying whether the actual lowest temperature in the temperature data of the candidate area is greater than the estimated lowest seepage temperature; Performing accuracy verification on the seepage probability based on the actual lowest temperature identification result.

8. An architectural seepage annotation device based on robot cruising, characterized in that, The device includes: A seepage probability determination module, configured to obtain an infrared image captured by a robot during a cruise inspection of a building to be detected, input the infrared image into a pre-trained seepage detection model, perform seepage detection based on the seepage detection model to obtain multiple candidate areas and corresponding seepage probabilities in the infrared image, where the infrared image includes temperature data of multiple pixel points; A seepage area detection module, configured to screen the multiple candidate areas based on the seepage probability and the temperature data to obtain the seepage area in the infrared image; A seepage coordinate conversion module, configured to obtain a first coordinate of the seepage area in a detection coordinate system, and based on a conversion relationship between a building drawing coordinate system pre-stored and the detection coordinate system, convert the first coordinate to the building drawing coordinate system to obtain a second coordinate of the seepage area; A seepage area annotation module, configured to identify multiple boundary pixel coordinates of the seepage area in the building drawing coordinate system, determine a seepage area based on the multiple boundary pixel coordinates, and map the seepage area to the building drawing of the building to be detected based on the second coordinate and the seepage area to obtain a building seepage annotation result based on the robot cruise.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements the steps of a building seepage annotation method according to any one of claims 1-7.

10. A readable storage medium, characterized in that, A program or instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, it implements the steps of a building seepage annotation method according to any one of claims 1-7.

Images