Pipeline siltation risk assessment method and system based on desilting detection

Abstract

The invention discloses a pipeline siltation risk assessment method and system based on desilting detection, and relates to the technical field of image processing. The method comprises the following steps: acquiring detection images of a plurality of positions in a to-be-dredged pipeline, and performing feature extraction on each detection image to obtain siltation target features in each detection image; for each detection image, determining a pipeline siltation type and a risk value of a corresponding position of the detection image according to each siltation target feature in the detection image; generating a risk unit corresponding to the pipeline siltation type and the risk value of each position, and generating a target three-dimensional map of the to-be-dredged pipeline in combination with each risk unit; and determining a first risk area and a second risk area which do not conform to the siltation risk standard in the target three-dimensional map, and generating a pipeline siltation risk assessment report of the to-be-dredged pipeline based on risk units in the first risk area and the second risk area. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of pipeline siltation risk assessment based on desilting detection is achieved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a pipeline siltation risk assessment method, system, electronic device and storage medium based on dredging detection. Background Art

[0002] With the acceleration of urbanization and the continuous improvement of infrastructure, underground pipe networks play a vital role in modern cities. Drainage pipes, as the "blood vessels" of cities, undertake the crucial task of draining rainwater and transporting sewage. However, over time, siltation can form on the inner walls of these pipes. This not only affects their normal operation but can also cause a range of problems, such as blockages and overflows, adversely impacting urban operations and residents' lives.

[0003] Currently, existing pipeline siltation risk assessment methods based on silt removal inspections primarily rely on camera-based image data from inside the pipeline, which is then analyzed by human workers to assess the risk of siltation. However, in practice, due to the widespread distribution of pipeline networks, it is often difficult to comprehensively analyze and assess widespread siltation using only local image analysis, resulting in low accuracy in pipeline siltation risk assessments based on silt removal inspections. Summary of the Invention

[0004] The present application provides a pipeline siltation risk assessment method and system based on silt removal detection, which has the effect of improving the accuracy of pipeline siltation risk assessment based on silt removal detection.

[0005] In a first aspect, the present application provides a pipeline siltation risk assessment method based on silt removal detection, comprising: Acquire detection images of multiple locations in the pipeline to be desilted, and perform feature extraction on each of the detection images to obtain multiple siltation target features in each of the detection images; For each of the detection images, determining the pipeline siltation type and risk value at the corresponding position of the detection image according to each of the siltation target features in the detection image; Generating risk units corresponding to the pipeline siltation type and risk value at each of the locations, and generating a target three-dimensional map of the pipeline to be desilted by combining the risk units; A first risk area and a second risk area that do not meet the siltation risk standard in the target three-dimensional map are determined, and a pipeline siltation risk assessment report for the pipeline to be desilted is generated based on risk units in the first risk area and the second risk area.

[0006] In a second aspect of the present application, a pipeline siltation risk assessment system based on silt removal detection is provided.

[0007] An image acquisition module is used to acquire detection images of multiple locations in the pipeline to be desilted, and perform feature extraction on each of the detection images to obtain multiple siltation target features in each of the detection images; An image recognition module is configured to determine, for each of the detection images, the type and risk value of the pipeline siltation at the corresponding position of the detection image based on each of the siltation target features in the detection image; a three-dimensional map determination module, configured to generate risk units corresponding to the pipeline siltation type and risk value at each location, and generate a target three-dimensional map of the pipeline to be desilted by combining the risk units; The risk assessment module is used to determine the first risk area and the second risk area in the target three-dimensional map that do not meet the siltation risk standard, and generate a pipeline siltation risk assessment report for the pipeline to be desilted based on the risk units in the first risk area and the second risk area.

[0008] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored on the memory and executable on the processor, wherein the program can implement a pipeline siltation risk assessment method based on dredging detection when loaded and executed by the processor.

[0009] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a pipeline siltation risk assessment method based on silt removal detection.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solution, by acquiring images from multiple locations within the pipeline and utilizing image feature extraction technology to accurately identify and assess the type and risk of internal siltation, and constructing risk units and three-dimensional risk maps, this method achieves a holistic detection and analysis of internal pipeline siltation risks. Compared to existing manual assessment methods, which struggle to comprehensively grasp widespread siltation, this technical solution, through automated image processing and feature extraction, precise risk value calculation, three-dimensional risk visualization, and multi-level risk area identification, comprehensively grasps the widespread siltation in pipelines undergoing desilting, assesses the siltation risk of these pipelines, and thus improves the accuracy of pipeline siltation risk assessments. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a flow chart of a pipeline siltation risk assessment method based on silt removal detection provided in an embodiment of the present application; Figure 2This is a schematic structural diagram of a pipeline siltation risk assessment system based on silt removal detection provided in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0012] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0014] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0015] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0016] The present application embodiment provides a pipeline siltation risk assessment method based on silt removal detection. In one embodiment, please refer to Figure 1 , Figure 1 This is a flow chart of a pipeline siltation risk assessment method based on silt removal detection, provided in an embodiment of the present application. This method can be implemented using a computer program, which can be integrated into an application or run as a standalone tool application. This method can also be implemented using a single-chip microcomputer or run on a pipeline siltation risk assessment system based on silt removal detection, which is based on a von Neumann architecture. Specifically, this method may include the following steps: Step 101: Acquire detection images of multiple locations in the pipeline to be desilted, and perform feature extraction on each detection image to obtain multiple siltation target features in each detection image.

[0017] Among them, the pipeline to be desilted refers to a pipeline system that needs to be desilted. In the embodiment of the present application, it can be understood as an urban drainage network or other pipeline system that may be blocked, which is used to carry fluids such as sewage and rainwater to ensure the normal operation of the city or facilities.

[0018] The detection image refers to the image of the inside of the pipeline collected by a camera or other equipment. In the embodiment of the present application, it can be understood as a digital image of the inner wall and lumen of the pipeline, which is used to reflect the actual situation inside the pipeline.

[0019] The sedimentation target feature refers to the visual attributes representing the sediment extracted from the detection image. In the embodiment of the present application, it can be understood as including visual information such as the color, texture, shape, and size of the sediment. It is used to describe the visual morphology of the sediment and provide basic data for distinguishing different types of sediment and assessing sedimentation risks.

[0020] Specifically, to fully understand the siltation situation inside the pipeline, it is necessary to capture images at multiple locations within the pipeline. Using a distributed camera network, multiple sets of image acquisition devices are designed, including cameras, lighting, and other modules, so that they can operate at different locations within the pipeline. In this way, image data from different locations within the pipeline can be obtained. Then, to accurately extract siltation targets from the images, deep learning target detection algorithms, such as YOLO, are used to process the images. These algorithms can efficiently and automatically extract multiple features from the image, such as color, texture, and shape. After algorithmic processing, multiple siltation targets in the image can be located, and their spatial coordinate frames in the image and their corresponding categories can be output. The effect of this is that all siltation targets and their features in the image at each location can be automatically and efficiently extracted without the need for manual image review and target extraction. This can address pipeline siltation situations in different scenarios, more comprehensively and accurately analyze the pipeline siltation status at each location, and provide rich image analysis support for subsequent pipeline siltation risk assessment.

[0021] Based on the above embodiment, as an optional embodiment, in step 101: extracting features from each detection image to obtain multiple siltation target features in each detection image, this step may also include the following steps: Step 201: performing image preprocessing on each detection image to obtain a sample image after preprocessing of each detection image.

[0022] Among them, the sample image refers to the pre-processed internal detection image of the pipeline. In the embodiment of the present application, it can be understood as a digital image of the inner wall and lumen of the pipeline that has been optimized by algorithms such as white balance, denoising, and sharpening, and is used as an image input source for feature extraction and intelligent analysis.

[0023] Specifically, due to the complex lighting conditions inside pipelines, inspection images may exhibit uneven brightness, low contrast, and noise. Direct analysis of the raw images can negatively impact subsequent feature extraction and risk analysis. Therefore, image preprocessing is necessary to enhance the quality of inspection images. Image enhancement algorithms, including white balancing, denoising, sharpening, and correction, are employed. White balancing adjusts the image's color temperature for a more natural look. Denoising effectively suppresses image noise. Sharpening highlights the edges of the pipeline's inner wall and sediment. Correction reduces chromatic aberration caused by uneven lighting. These preprocessing algorithms effectively enhance the legibility and detail of inspection images, ensuring better image quality for subsequent intelligent analysis. After preprocessing, clear, natural, and detailed sample images are obtained. Key information, such as the pipe wall edge and sediment surface texture, is more prominent in these sample images. This provides a higher-quality image source for subsequent algorithms to extract target features. Even under complex pipeline lighting conditions, uniform sample images can be obtained, ensuring more stable and efficient feature extraction and analysis.

[0024] Step 202: Using a preset target detection algorithm, extract the color features, texture features, and shape features in each sample image; and use the color features, texture features, and shape features in each sample image as multiple siltation target features in the detection image corresponding to each sample image.

[0025] Among them, the preset target detection algorithm refers to a pre-designed target detection model algorithm based on deep learning. In the embodiment of this application, it can be understood as a pre-trained target detection neural network model such as YOLO and Faster R-CNN, which is used to automatically and efficiently extract the target area in the image and realize the intelligent positioning and detection of sediment in the pipeline.

[0026] Color features, texture features, and shape features refer to three types of visual features extracted from images that describe the visual properties of sediment. In this application embodiment, these can be understood as digital features such as the RGB channel statistical characteristics, histogram, and contour area of ​​the sediment area. They are used to visually depict the color, surface roughness, and shape of the sediment, providing a basic feature description for intelligent algorithm analysis of the sediment. Color features reflect the color distribution of the sediment; texture features reflect whether the sediment surface is smooth or rough; and shape features describe the outer contour of the sediment.

[0027] Specifically, to accurately extract the features of sediment targets from sample images, an intelligent target detection algorithm is required. Color, texture, and shape features are three key aspects of describing sediment. Deep learning-based target detection algorithms, such as Faster R-CNN, utilize convolutional neural networks to efficiently and automatically extract target regions within an image and generate coordinate frames and classification results for each target region. This allows each individual sediment target in the sample image to be located. Then, within each sediment target location frame, color features are extracted to capture the RGB color distribution and color statistics of the sediment region; texture features are extracted to capture information such as the thickness and orientation of the sediment texture; and shape features are extracted to describe the sediment's contour, shape, area, and size. By combining these three types of features, the sediment target features for each sediment target region are obtained. Finally, the features of all sediment targets within each sample image are aggregated to form the sediment target features for the corresponding detection image. This can automatically and efficiently extract all the sedimentation features in the sample image, including the three key visual attributes of color, texture, and shape, with sufficient description to support subsequent intelligent analysis. Compared with manual feature engineering, it can greatly reduce the extraction workload and improve efficiency.

[0028] Step 102: For each detection image, determine the pipeline siltation type and risk value at the corresponding position of the detection image based on each siltation target feature in the detection image.

[0029] Among them, the pipeline sedimentation type refers to the category of sediment that may appear in the pipeline. In the embodiment of the present application, it can be understood as sedimentation categories of different properties such as sludge, scale, biochemical alluvium, etc., which is used to indicate the specific component type of sediment inside the pipeline and to distinguish and identify the types of sediment.

[0030] The risk value refers to a quantitative description of the degree of hazard of the siltation condition in the pipeline. In the embodiment of the present application, it can be understood as a numerical value obtained by evaluating the detection image, which is used to indicate the severity of the blockage risk of the siltation in the current pipeline.

[0031] Specifically, after acquiring the siltation target features from each detection image, the specific siltation type and risk value for each pipeline location corresponding to each image must be determined to lay the foundation for subsequent risk assessment. A siltation type feature template library is established, containing color, texture, and shape composite feature templates for different siltation types (such as sludge, scale, and biochemical alluvial deposits). Then, the siltation target features in each detection image are matched against the siltation type feature templates in the template library. The highest similarity is calculated to determine the most likely siltation type for the siltation target. After determining the siltation type, a pre-set risk assessment algorithm is used to quantify the risk of that type of siltation. This assessment model uses a weighted calculation method to determine the risk value based on the siltation target features and the importance weights of the corresponding types. Different siltation types can have different feature weight combinations. Finally, the siltation type and risk value results for each pipeline location corresponding to each detection image are obtained. This provides a detailed siltation assessment analysis for each pipeline location, including the type and risk level. Through intelligent template matching and risk assessment algorithms, automatic identification and quantification of different siltation types and risk levels can be achieved, making pipeline siltation monitoring and management more refined.

[0032] Based on the above embodiment, as an optional embodiment, in step 102, determining the pipeline siltation type and risk value at the corresponding position of the detection image based on the features of each siltation target in the detection image may further include the following steps: Step 301: establishing a preset pipeline congestion type feature template library, wherein the preset pipeline congestion type feature template library includes a plurality of preset pipeline congestion types and feature templates corresponding to each preset pipeline congestion type.

[0033] Among them, the preset pipeline sedimentation type feature template library refers to a pre-established database containing visual feature templates of various pipeline sedimentation types. In the embodiment of the present application, it can be understood as a collection of color, texture, and shape composite feature templates of sedimentation types such as sludge, scale, and impact sedimentation. It is used as a matching library for intelligent identification of sedimentation types in pipelines, and automatic classification of sedimentation types is achieved by template matching with the detected sedimentation feature vectors.

[0034] Specifically, to accurately identify the type of siltation within a pipeline, it is necessary to establish a pipeline siltation type feature template library containing feature templates for different siltation types. This library provides the foundation for subsequent intelligent matching and identification. First, sample images of various possible siltation types are collected, such as sludge siltation, biofouling on pipe walls, and impact siltation. Then, an object detection algorithm is applied to each sample image type to extract the color, texture, and shape features of the siltation target, forming a composite feature description template for that type of siltation. This process is repeated to form a set of feature templates for all major siltation types, constructing a siltation type feature template library. This library contains multiple siltation type categories, each corresponding to an image feature template. During pipeline inspection, the detected unknown siltation features are matched against the templates in the template library, the similarity is calculated, and the category of the most similar template is output, completing the siltation type identification.

[0035] Step 302: performing similarity matching between each siltation target feature and a feature template corresponding to each preset pipeline siltation type in a preset pipeline siltation type feature template library, and obtaining the preset pipeline siltation type with the highest similarity as the pipeline siltation type at the corresponding position of the detection image.

[0036] Specifically, based on the establishment of a siltation type feature template library, the template matching method can be used to identify the type of detected unknown siltation. The color, texture, and shape composite features of each siltation target extracted from the detection image are compared with the vector similarity of each type template in the template library one by one, and the distance or correlation between the feature vectors is calculated. The template library contains multiple types of templates. After traversal and comparison, the matching similarity score between the current siltation target and each type of template can be obtained. Among them, the type with the highest similarity, that is, the type with the closest feature vector distance, is the siltation type that the current siltation target is most likely to correspond to. For example, if the similarity between the siltation target and the sludge template is 0.85, the siltation target is judged to be sludge-type siltation. Similarly, the most likely siltation type to which each siltation target in the image belongs can be obtained. Through intelligent matching with the preset template library, the siltation type can be automatically and efficiently determined, and the recognition accuracy can be improved.

[0037] Step 303: Based on a preset risk coefficient mapping table, determine a risk weight combination corresponding to the pipeline siltation type, where the risk weight combination includes a weight coefficient corresponding to each siltation target feature.

[0038] Among them, the preset risk coefficient mapping table refers to a database of pre-established correspondences between pipeline sedimentation types and feature weights. In the embodiment of the present application, it can be understood as a mapping table that lists each sedimentation type (such as sludge, impact sedimentation, etc.) and its corresponding color, texture, and shape feature weight coefficients in the risk calculation. It is used to find its feature weight combination according to the identified sedimentation type, and provide a reference basis for the calculation of intelligent risk values ​​based on the sedimentation type.

[0039] Specifically, after identifying the sedimentation type, it is necessary to determine the corresponding risk weight combination based on the type to prepare for risk value calculation. First, a pre-set risk factor mapping table is created, listing each sedimentation type and its corresponding feature weight coefficient combination. For example, for sludge-type sedimentation, the weight coefficient for color features is 0.2, the weight coefficient for texture features is 0.5, and the weight coefficient for shape features is 0.3. After determining that a sedimentation target belongs to the sludge type, the feature weight combination corresponding to the sludge type can be found in the mapping table, resulting in a weight of 0.2 for color features, 0.5 for texture features, and 0.3 for shape features. Different sedimentation types place different importance on various visual features, and the corresponding weight coefficient combinations also have different emphases. This mapping table can determine weights by analyzing a sample of the types. Once the feature weight combinations are determined, the three types of features can be combined according to different weight ratios when calculating the risk value to obtain an intelligent risk assessment result that takes the sedimentation type into account. This method implements dynamic risk assessment based on sedimentation type, making the assessment results more accurate.

[0040] Step 304: Based on the risk weight combination, perform weighted calculation on the sampling values ​​corresponding to each siltation target feature to obtain the risk value of the corresponding position of the detection image.

[0041] Specifically, after obtaining the risk weight combination corresponding to the siltation type, various visual features can be weighted calculated based on these weight coefficients to obtain the final risk value. The three types of visual features of the siltation target extracted from the detection image, namely color, texture, and shape, are digitized to obtain color sampling values, texture sampling values, and shape sampling values. Then, according to the weight combination corresponding to the siltation type, the three types of sampling values ​​are weighted and summed to achieve color sampling value * color weight + texture sampling value * texture weight + shape sampling value * shape weight. After weighted calculation, the risk value can be obtained, which is the risk index of the siltation target. Compared with the direct equal-weight combination of features, this weighted calculation based on siltation type can make the risk assessment more in line with the actual situation, differentiate the hazards of different types of siltation, and the assessment results are more accurate. It realizes the intelligent and refined risk calculation of different siltation types and locations inside the pipeline, providing basic data support for the subsequent overall risk analysis of the pipeline network.

[0042] Step 103: Generate risk units corresponding to the pipeline siltation type and risk value at each location, and generate a target three-dimensional map of the pipeline to be desilted by combining each risk unit.

[0043] Among them, the risk unit refers to the risk data group that encapsulates the siltation type and risk value results of individual locations in the pipeline. In the embodiment of the present application, it can be understood as structured data containing siltation type, risk value and corresponding pipeline spatial coordinate information, which is used to construct a pipeline unit with risk attributes on the three-dimensional pipeline model to achieve spatial representation and visualization of the risk distribution inside the pipeline.

[0044] The target three-dimensional map refers to the three-dimensional model of the pipeline that integrates all risk analysis results. In the embodiment of this application, it can be understood as a digital three-dimensional pipeline map that includes the pipeline spatial model and all risk units. It is used to intuitively and accurately display the sedimentation types and risk distribution at different locations inside the pipeline, thereby realizing the overall visualization and risk monitoring of internal pipeline risks.

[0045] Specifically, after obtaining the siltation type and risk value results for the pipeline location corresponding to each detection image, these results need to be converted into risk units and integrated to generate a three-dimensional risk map. A three-dimensional pipeline model containing location coordinates can be established. The siltation type and risk value of each detection location then constitute a risk unit data set, and these risk units are associated with the corresponding three-dimensional pipeline model locations. For example, the siltation type "sludge" and risk value of a certain detection image are converted into a risk unit and matched with the corresponding detection location in the pipeline model. This process is repeated, and eventually the risk analysis results of all detection locations are converted into risk units on the pipeline model. The three-dimensional pipeline model containing all risk units is then output as the target risk map. In this way, the originally independent detection results can be spatially mapped and associated on the three-dimensional pipeline model, realizing a visual expression of the risk of the entire pipeline, facilitating spatial risk distribution analysis, and providing map support for intelligent pipeline network supervision.

[0046] Based on the above embodiment, as an optional embodiment, in step 103, generating risk units corresponding to the pipeline siltation type and risk value at each location, and combining each risk unit to generate a target three-dimensional map of the pipeline to be desilted, this step may also include the following steps: Step 401: Obtain a three-dimensional outline of the pipeline to be desilted; establish a risk unit data structure, and fill the pipeline siltation type and risk value at each location into the risk unit data structure to generate multiple risk units.

[0047] Among them, the three-dimensional contour map refers to a three-dimensional model map showing the spatial structure of the pipeline. In the embodiment of the present application, it can be understood as a digital three-dimensional map containing the pipeline shape contour obtained through CAD design or laser scanning, which is used to provide basic spatial structure information for constructing a three-dimensional pipeline map for risk monitoring.

[0048] The risk unit data structure refers to a set of numerical fields used to store and represent the risk information of a single pipeline inspection location. In the embodiment of the present application, it can be understood as a structured data format containing elements such as siltation type, risk value, and coordinate location. It is used to convert risk analysis results into standardized structured data to facilitate the construction of risk units and the generation of risk maps.

[0049] Specifically, in order to display the risk distribution on the three-dimensional structure of the pipeline, it is necessary to first obtain the three-dimensional contour map of the pipeline, establish the data structure of the risk unit, and fill the detection results into the generated risk unit. First, obtain the three-dimensional contour structure map of the pipeline space from the pipeline design CAD drawing or laser scanning, which contains the precise spatial information of the pipeline. Then customize the structured data format of a risk unit, which includes three fields: siltation type, risk value, and spatial coordinates. Next, take out the siltation type identification result and risk assessment value of each detection location, as well as the corresponding spatial coordinates, and fill them into the data structure of the risk unit. In this way, multiple risk units are formed, each unit contains the risk information and spatial coordinates of a detection location. Through this process, the detection results are associated with the spatial position of the three-dimensional pipeline, and the early detection and analysis results are structured, laying the foundation for the next step of risk visualization expression.

[0050] Step 402: Based on the corresponding position of each risk unit, each risk unit is mapped to a corresponding area in the three-dimensional contour map to obtain a target three-dimensional map of the pipeline to be desilted.

[0051] Specifically, after obtaining risk cells containing risk information, the next step is to map these cells to corresponding areas on the 3D contour map to form a target risk map. Since risk cells already contain spatial coordinates, their mapping locations on the 3D pipeline contour map can be determined based on the cell's coordinate information. The siltation type and risk value information for the risk cell are then rendered or annotated in the pipeline block at that location on the 3D contour map. For example, different colors are used to represent different risk levels. This process is repeated, mapping the information of all risk cells to the corresponding 3D contour map areas. Ultimately, a 3D pipeline map with risk information is formed, enabling intuitive visualization of the risk distribution within the pipeline.

[0052] Step 104: Determine a first risk area and a second risk area in the target three-dimensional map that do not meet the siltation risk standard, and generate a pipeline siltation risk assessment report for the pipeline to be desilted based on the risk units in the first risk area and the second risk area.

[0053] Among them, the first risk area refers to the area where the number of risk units inside the pipeline exceeds the upper limit of the number in the siltation risk standard. In the embodiment of the present application, it can be understood as the pipeline section where the density of risk units in the target three-dimensional map is too high and exceeds the warning threshold. It is used to indicate a high-risk area with a large number of siltation hazards inside the pipeline, which requires priority remediation and disposal.

[0054] The second risk area refers to the area where the average risk value of the risk units inside the pipeline exceeds the upper limit of the risk value in the siltation risk standard. In the embodiment of the present application, it can be understood as the pipeline section where the average risk value of the risk units in the target three-dimensional map is high and exceeds the warning threshold. It is used to indicate a larger risk area with more moderate siltation hazards inside the pipeline, which requires strengthened monitoring and disposal.

[0055] The sedimentation risk standard refers to the technical specifications or threshold requirements for judging the pipeline sedimentation risk. In the embodiment of the present application, it can be understood as a technical standard set for the number of risk units in the first risk area and the risk value of the second risk area, which is used to quantitatively define the pipeline sedimentation risks at different levels as a basis for judging high-risk areas.

[0056] The pipeline sedimentation risk assessment report refers to a comprehensive analysis report on the sedimentation risk status inside the pipeline. In the embodiment of the present application, it can be understood as a pipeline risk assessment file generated based on the judgment results of the first risk area and the second risk area, which is used to display the details of the risk distribution inside the pipeline and provide a decision-making basis for risk management.

[0057] Specifically, first, based on the preset siltation risk standards, the area where the number of risk units in the target three-dimensional map exceeds the limit is judged as the first risk area, which requires priority remediation. At the same time, the area where the average risk value of the risk unit exceeds the limit is judged as the second risk area, which requires strengthened monitoring. Then, detailed data of all risk units in these two areas is extracted, including the precise siltation type, risk value, etc. Finally, the specific information of the two risk areas and the content of the relevant risk units are summarized to generate a risk assessment report. In this way, by analyzing the three-dimensional risk map, high-risk areas can be intuitively discovered, and detailed risk assessment reports can be produced, providing data support for pipeline risk management decisions and silt removal work.

[0058] Based on the above embodiment, as an optional embodiment, in step 104: determining the first risk area in the target three-dimensional map that does not meet the siltation risk standard, this step may further include the following steps: Step 501: Divide the target three-dimensional map into multiple grid areas of preset space size; determine the number of risk units in each grid area based on the position of each risk unit and the position of each grid area in the target three-dimensional map.

[0059] Among them, the grid area refers to a spatial grid unit of a preset size on the target three-dimensional map. In the embodiment of the present application, it can be understood as regularly dividing the continuous three-dimensional pipeline space into regular grid blocks, which is used to discretize the pipeline space and facilitate risk statistical analysis of local areas.

[0060] Specifically, the constructed target 3D map is divided into multiple 3D grids of equal size. The grid size can be pre-set, for example, 10 meters by 10 meters. The specific location coordinates of each risk unit are then traversed to determine which grid area of ​​the 3D map it falls within. Next, the number of risk units within each grid is counted one by one. Through this process, each grid area is matched to the number of risk units it contains, resulting in a distribution of the number of risk units within the map grid. In this way, grid division on the 3D map discretizes the continuous pipeline space, facilitating risk analysis in local areas and supporting regional risk management.

[0061] Step 502: Grid areas with a number of risk units greater than a threshold are selected as candidate risk areas; the candidate risk areas are merged to obtain a first risk area in the target three-dimensional map that does not meet the sedimentation risk standard.

[0062] Among them, the candidate risk area refers to a suspected area that may have risks. In the embodiment of the present application, it can be understood as a grid area where the number of risk units exceeds the threshold. It is used to represent a local block of the pipeline that may have potential risks and requires further evaluation and judgment to confirm its risk status.

[0063] Specifically, a threshold number of cells, such as 50, is first set as the criterion for determining candidate risk areas. The number of risk cells is then counted grid by grid, and grids with more than 50 cells are selected and identified as candidate risk areas. Risk grids may be scattered and unable to effectively reflect the overall regional risk. Therefore, adjacent candidate risk grids need to be merged to form a unified overall risk area. Finally, the merged candidate risk grids constitute the first risk area, representing a high-risk area for pipelines with a serious number of exceeding standards. Through grid statistics and merged determination, the first risk area on the three-dimensional map can be effectively identified, achieving quantitative risk identification.

[0064] Based on the above embodiment, as an optional embodiment, in step 104: determining a second risk area in the target three-dimensional map that does not meet the siltation risk standard, this step may further include the following steps: Step 503: For each grid area, based on the risk value of each risk unit in the grid area, calculate the risk mean of the grid area.

[0065] Specifically, each defined grid area is first traversed, accessing all risk cells within it. Next, the risk value of each risk cell is extracted. This is the quantitative indicator obtained during the risk assessment. Next, the arithmetic mean of the risk values ​​of all risk cells within the grid area is calculated, representing the risk mean for that grid area. Thus, each grid area is assigned a corresponding risk mean value representing its overall risk level. The purpose of calculating the risk mean value is to provide a quantitative basis for evaluating secondary risk areas. By comparing the mean value with a threshold, it is determined whether it is too high, thereby identifying pipeline areas with overall higher risks.

[0066] Step 504: If the risk mean of the grid area is greater than the risk mean threshold, or there is a risk unit with a risk value greater than the risk value threshold in the grid area, the grid area is regarded as a second risk area that does not meet the sedimentation risk standard in the target three-dimensional map.

[0067] Specifically, it is first necessary to preset a risk mean threshold and a risk value threshold as the judgment criteria. Then, the risk mean value of each grid area is determined. If it exceeds the risk mean threshold, the grid area is determined to be a second risk area. At the same time, the detailed risk value of each risk unit in the grid is checked. If there is a unit that exceeds the risk value threshold, the grid is also determined to be a second risk area. Finally, the grid areas in both cases are screened out and merged to form the second risk area, indicating the pipeline area with a higher risk value. In this way, through the dual judgment criteria, both the overall risk level of the grid and the risk value of the local unit are taken into account, making the identification of the second risk area more comprehensive and accurate.

[0068] Based on the above embodiment, as an optional embodiment, in step 104: generating a pipeline siltation risk assessment report for the pipeline to be desilted based on the risk units in the first risk area and the second risk area, this step may further include the following steps: Step 505: Determine the relative distance between any two risk units in the first risk area and the second risk area; if the relative distance is less than the distance threshold, merge the any two risk units into one associated risk area, and repeat the step of merging any two risk units into one associated risk area to obtain multiple associated risk areas.

[0069] Among them, the associated risk area refers to a set of areas formed by merging adjacent risk units. In the embodiment of the present application, it can be understood as combining the risk units that are closer to each other in the first risk area and the second risk area to identify pipeline risk areas with a more concentrated range, making the risk assessment more holistic and continuous.

[0070] Specifically, a distance threshold is first preset to determine whether the units are close enough. Then, in the first risk area and the second risk area, the spatial distance between any two risk units is searched pair by pair. Next, it is determined whether the distance between the two units is less than the preset distance threshold. If so, the two units are merged as an associated risk area. This judgment and merging process is repeated until all units that are close and can be associated are merged. Finally, an associated risk area consisting of multiple adjacent and associated risk units is obtained. In this way, unit merging can eliminate scattered small-scale risk points, identify associated areas with more concentrated risks, and make risk judgment more holistic.

[0071] Step 506: Determine the shortest desilting path based on the location of each associated risk area in the pipeline to be desilted, and determine the risk level of each associated risk area based on the risk value of each risk unit in each associated risk area.

[0072] Among them, the dredging path refers to the spatial path that the pipeline dredging operation needs to pass through. In the embodiment of the present application, it can be understood as the optimal route from the pipeline network entrance to the target associated risk area, which is used to guide the spatial movement trajectory of the dredging device to reach the risk area, making the dredging operation more targeted and efficient.

[0073] The risk level refers to the grading result of the risk severity. In the embodiment of the present application, it can be understood as a grading indicator determined based on the average risk value of the risk units in the associated risk area, which is used to evaluate the risk severity of different areas and divide them into high, medium and low risk levels.

[0074] Specifically, first, the locations of all identified associated risk areas are marked on the three-dimensional pipeline network map. Then, the shortest spatial distance from each associated risk area to the pipeline network entrance and exit is calculated, and the optimal dredging path from the entrance to each area is determined. At the same time, the detailed risk values ​​of all risk units in each associated risk area are counted, and the average risk value is calculated. Finally, based on the average risk value of the area, the risk level of each associated risk area is determined. For example, there are three preset intervals: risk values ​​in the range of 0 to 30 correspond to low-risk low levels, risk values ​​in the range of 30 to 70 correspond to medium-risk levels, and risk values ​​above 70 correspond to high-risk levels. The mapping relationship between the risk level and the risk value is set based on the historically collected risk values ​​and the actual risk situation. In this way, the dredging path and risk level of each associated risk area are clarified, providing a basis for formulating dredging plans and making dredging more targeted and efficient.

[0075] Step 507: Integrate the risk levels and dredging paths of the associated risk areas to obtain a pipeline siltation risk assessment report for the pipeline to be dredged.

[0076] Specifically, the names, locations, and risk levels of all associated risk areas are first compiled. Simultaneously, the optimal desilting path information corresponding to each area is calculated. Then, in the report template, the regional information, risk level, and desilting path for each associated risk area are filled in sequentially. Finally, a pipeline sedimentation risk assessment report is generated, containing details of all associated risk areas and corresponding desilting paths. This report intuitively displays the risk distribution within the pipeline, clarifies the severity of different risk zones, and recommends desilting paths. It serves as an important basis for risk management and control, and guides desilting work.

[0077] Reference Figure 2 , a pipeline siltation risk assessment system based on silt removal detection provided in an embodiment of the present application, the system includes: an image acquisition module, an image recognition module, a three-dimensional map determination module, and a risk assessment module, wherein: An image acquisition module is used to acquire detection images of multiple locations in the pipeline to be desilted, and perform feature extraction on each detection image to obtain multiple siltation target features in each detection image; An image recognition module is used to determine the pipeline siltation type and risk value at the corresponding position of each detection image based on the characteristics of each siltation target in the detection image; A three-dimensional map determination module is used to generate risk units corresponding to the pipeline siltation type and risk value at each location, and to generate a target three-dimensional map of the pipeline to be desilted by combining each risk unit; The risk assessment module is used to determine the first risk area and the second risk area that do not meet the siltation risk standard in the target three-dimensional map, and generate a pipeline siltation risk assessment report for the pipeline to be desilted based on the risk units in the first risk area and the second risk area.

[0078] Based on the above embodiment, the image acquisition module is also used to perform image preprocessing on each detection image to obtain a sample image after preprocessing of each detection image; using a preset target detection algorithm, the color features, texture features and shape features in each sample image are extracted; and the color features, texture features and shape features in each sample image are used as multiple sedimentation target features in the detection image corresponding to each sample image.

[0079] On the basis of the above embodiment, the image recognition module is also used to establish a preset pipeline congestion type feature template library, which contains multiple preset pipeline congestion types and feature templates corresponding to each preset pipeline congestion type; each congestion target feature is matched with the feature template corresponding to each preset pipeline congestion type in the preset pipeline congestion type feature template library for similarity, and the preset pipeline congestion type with the highest similarity is obtained as the pipeline congestion type at the corresponding position of the detection image; based on the preset risk coefficient mapping table, the risk weight combination corresponding to the pipeline congestion type is determined, and the risk weight combination includes the weight coefficient corresponding to each congestion target feature; based on the risk weight combination, the sampling value corresponding to each congestion target feature is weightedly calculated to obtain the risk value of the corresponding position of the detection image.

[0080] Based on the above embodiment, the three-dimensional map determination module is also used to obtain a three-dimensional contour map of the pipeline to be desilted; establish a risk unit data structure, and fill the pipeline siltation type and risk value of each location into the risk unit data structure to generate multiple risk units; based on the corresponding position of each risk unit, each risk unit is mapped to the corresponding area in the three-dimensional contour map to obtain a target three-dimensional map of the pipeline to be desilted.

[0081] Based on the above embodiment, the risk assessment module is also used to divide the target three-dimensional map into multiple grid areas of preset space sizes; determine the number of risk units in each grid area based on the position of each risk unit and the position of each grid area in the target three-dimensional map; screen out grid areas with a number of risk units greater than a quantity threshold as candidate risk areas; merge the candidate risk areas to obtain the first risk area in the target three-dimensional map that does not meet the siltation risk standard.

[0082] Based on the above embodiment, the risk assessment module is also used to calculate the risk mean of each grid area based on the risk value of each risk unit in the grid area; if the risk mean of the grid area is greater than the risk mean threshold, or there is a risk unit in the grid area whose risk value is greater than the risk value threshold, then the grid area is regarded as the second risk area in the target three-dimensional map that does not meet the siltation risk standard.

[0083] Based on the above embodiment, the risk assessment module is also used to determine the relative distance between any two risk units in the first risk area and the second risk area; if the relative distance is less than the distance threshold, any two risk units are merged into one associated risk area, and the step of merging any two risk units into one associated risk area is repeated to obtain multiple associated risk areas; based on the position of each associated risk area in the pipeline to be desilted, the shortest desilting path is determined, and based on the risk value of each risk unit in each associated risk area, the risk level of each associated risk area is determined; the risk level and desilting path of each associated risk area are integrated to obtain a pipeline siltation risk assessment report for the pipeline to be desilted.

[0084] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0085] This application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0086] The communication bus 302 is used to implement the connection and communication between these components.

[0087] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0088] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0089] The processor 301 may include one or more processing cores. Using various interfaces and circuits, the processor 301 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in the memory 305, as well as accesses data stored in the memory 305, to perform various server functions and process data. Optionally, the processor 301 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface graphics, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may also be implemented as a separate chip, rather than integrated into the processor 301.

[0090] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also optionally be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a pipeline siltation risk assessment method based on silt removal detection.

[0091] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a pipeline siltation risk assessment method based on dredging detection. When executed by one or more processors 301, the electronic device 300 executes one or more methods such as those in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0092] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0093] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0094] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0095] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0096] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion 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 memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0097] The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure in this specification and practice.

[0098] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The description and examples are to be considered as illustrative only.

Claims

1. A pipeline siltation risk assessment method based on silt removal detection, characterized in that: include: Acquire detection images of multiple positions in the pipeline to be desilted, and perform feature extraction on each of the detection images to obtain multiple siltation target features in each of the detection images; For each of the detection images, determining the pipeline siltation type and risk value at the corresponding position of the detection image according to each of the siltation target features in the detection image; Generate risk units corresponding to the pipeline siltation type and risk value at each of the locations, and generate a target three-dimensional map of the pipeline to be desilted by combining the risk units; A first risk area and a second risk area that do not meet the siltation risk standard in the target three-dimensional map are determined, and a pipeline siltation risk assessment report for the pipeline to be desilted is generated based on the risk units in the first risk area and the second risk area.

2. The pipeline siltation risk assessment method based on silt removal detection according to claim 1 is characterized in that: The feature extraction of each of the detection images to obtain a plurality of siltation target features in each of the detection images includes: Performing image preprocessing on each of the detection images to obtain a sample image after the preprocessing of each of the detection images; Using a preset target detection algorithm, extracting color features, texture features, and shape features from each of the sample images; The color features, texture features and shape features in each of the sample images are used as multiple siltation target features in the detection image corresponding to each of the sample images.

3. The pipeline siltation risk assessment method based on silt removal detection according to claim 1 is characterized in that: Determining the pipeline siltation type and risk value at the corresponding position of the detection image according to each siltation target feature in the detection image includes: Establishing a preset pipeline congestion type feature template library, wherein the preset pipeline congestion type feature template library includes a plurality of preset pipeline congestion types and feature templates corresponding to each of the preset pipeline congestion types; Performing similarity matching between each of the siltation target features and the feature templates corresponding to each of the preset pipeline siltation types in the preset pipeline siltation type feature template library, and obtaining the preset pipeline siltation type with the highest similarity as the pipeline siltation type at the corresponding position of the detection image; Based on a preset risk factor mapping table, determining a risk weight combination corresponding to the pipeline siltation type, the risk weight combination including a weight coefficient corresponding to each of the siltation target characteristics; Based on the risk weight combination, the sampling values ​​corresponding to each of the siltation target features are weightedly calculated to obtain the risk value of the corresponding position of the detection image.

4. The pipeline siltation risk assessment method based on silt removal detection according to claim 1 is characterized in that: The generating of the risk units corresponding to the pipeline siltation types and risk values ​​at the respective locations, and combining the risk units to generate a target three-dimensional map of the pipeline to be desilted, comprises: Obtaining a three-dimensional contour map of the pipeline to be desilted; Establishing a risk unit data structure, and filling the pipeline siltation type and risk value of each position into the risk unit data structure to generate a plurality of risk units; Based on the position corresponding to each of the risk units, each of the risk units is mapped to a corresponding area in the three-dimensional contour map to obtain a target three-dimensional map of the pipeline to be desilted.

5. The pipeline siltation risk assessment method based on silt removal detection according to claim 1 is characterized in that: Determining the first risk area in the target three-dimensional map that does not meet the siltation risk standard includes: Dividing the target three-dimensional map into a plurality of grid areas of preset space sizes; Determine the number of risk units within each of the grid areas based on the position of each of the risk units and the position of each of the grid areas in the target three-dimensional map; Screening out grid areas where the number of risk units is greater than a threshold value as candidate risk areas; The candidate risk areas are merged to obtain a first risk area in the target three-dimensional map that does not meet the siltation risk standard.

6. The pipeline siltation risk assessment method based on silt removal detection according to claim 5 is characterized in that: The determining of the second risk area in the target three-dimensional map that does not meet the siltation risk standard includes: For each of the grid areas, based on the risk values ​​of the risk units within the grid area, calculating the risk mean of the grid area; If the risk mean value of the grid area is greater than the risk mean value threshold, or there is a risk unit in the grid area whose risk value is greater than the risk value threshold, the grid area is regarded as a second risk area in the target three-dimensional map that does not meet the siltation risk standard.

7. The pipeline siltation risk assessment method based on silt removal detection according to claim 1 is characterized in that: The generating of the pipeline siltation risk assessment report of the pipeline to be desilted based on the risk units in the first risk area and the second risk area includes: Determine a relative distance between any two risk units in the first risk area and the second risk area; If the relative distance is less than the distance threshold, merging the two risk units into one associated risk area, and repeating the step of merging the two risk units into one associated risk area to obtain multiple associated risk areas; Determine the shortest desilting path based on the location of each associated risk area in the pipeline to be desilted, and determine the risk level of each associated risk area based on the risk value of each risk unit in each associated risk area; The risk level of each of the associated risk areas and the desilting path are integrated to obtain a pipeline siltation risk assessment report for the pipeline to be desilted.

8. A pipeline siltation risk assessment system based on silt removal detection, characterized in that: The system comprises: An image acquisition module is used to acquire detection images of multiple positions in the pipeline to be desilted, and perform feature extraction on each of the detection images to obtain multiple siltation target features in each of the detection images; An image recognition module, for determining, for each of the detection images, the type and risk value of pipeline siltation at a corresponding position of the detection image according to each of the siltation target features in the detection image; A three-dimensional map determination module is used to generate risk units corresponding to the pipeline siltation type and risk value at each of the locations, and generate a target three-dimensional map of the pipeline to be desilted in combination with each of the risk units; The risk assessment module is used to determine the first risk area and the second risk area that do not meet the siltation risk standard in the target three-dimensional map, and generate a pipeline siltation risk assessment report for the pipeline to be desilted based on the risk units in the first risk area and the second risk area.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the pipeline siltation risk assessment method based on dredging detection as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the pipeline siltation risk assessment method based on silt removal detection as described in any one of claims 1 to 7 is executed.

Images