Pipeline leakage detection method and device
Through the image processing technology combined with infrared cameras and visible light cameras, the problem of difficult positioning of colorless fluid leakage in complex industrial environments is solved, and the rapid and accurate detection of the leakage position of the pipeline is achieved.
Patent Information
- Application Number
- CN202411080953.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-08
AI Technical Summary
Existing pipeline leakage detection technology is difficult to accurately locate colorless fluid leakage in complex industrial environments, especially in small-scale leakage and high environmental noise, and the sensor method is not sensitive enough.
An infrared camera is used to collect thermal images of the pipeline area, and the edge information of the leakage profile is obtained through a visible light camera. Combined with image processing algorithms such as multi-threshold segmentation and edge detection, the closure of the leakage profile is calculated to determine the leakage position.
It realizes rapid and accurate detection of the leakage location of colorless fluids, improves the sensitivity and accuracy of detection, and is suitable for complex industrial environments.
Smart Images

Figure CN118602318B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence, and in particular to a pipeline leakage detection method and device. Background Art
[0002] Existing pipeline leak detection technologies mainly include sensor-based methods. However, in complex industrial environments, detection is still challenging, especially for leaks of colorless fluids (such as water). Specific problems include: sensor technology usually relies on physical measurements, such as water flow velocity or pressure changes, sensor methods are not sensitive enough to small-scale leaks, and it is difficult to accurately locate leaks when the pipeline layout is complex or the environmental noise is high. Therefore, how to accurately measure the leak point of colorless fluids has become a technical problem that people in this field need to solve urgently. Summary of the invention
[0003] In view of the above problems, the present invention provides a pipeline leakage detection method and device that overcome the above problems or at least partially solve the above problems.
[0004] In a first aspect, a pipeline leakage detection method comprises:
[0005] Collecting a thermal image of the pipeline area by an infrared camera, and detecting an area of interest whose temperature is lower than the ambient temperature based on the thermal image;
[0006] Acquire a visible light image of the region of interest by using a visible light camera, and detect edge information of a leakage contour according to the visible light image;
[0007] The closedness of the leakage contour is calculated according to the edge information, so as to determine the pipeline leakage position.
[0008] Optionally, in certain optional embodiments, collecting a thermal image of the pipeline area by an infrared camera, and detecting an area of interest having a temperature lower than the ambient temperature according to the thermal image, comprises:
[0009] Collect thermal images of the pipeline area through infrared cameras;
[0010] enhancing the contrast of the thermal image;
[0011] The thermal image is divided into blocks based on a multi-threshold segmentation technology to obtain an area of interest and a normal area, wherein the temperature of the area of interest is lower than the ambient temperature, and the temperature of the normal area is not lower than the ambient temperature.
[0012] Optionally, in some optional embodiments, enhancing the contrast of the thermal image includes:
[0013] The thermal image is processed using an image enhancement algorithm to enhance the contrast of the thermal image, wherein the image enhancement algorithm is: a histogram equalization algorithm, a logarithmic transformation algorithm or a contrast stretching algorithm.
[0014] Optionally, in some optional implementations, the multi-threshold segmentation technology is used to divide the thermal image into blocks to obtain the region of interest and the normal region, including:
[0015] Based on the multi-threshold segmentation technology, the thermal image after contrast enhancement is segmented to obtain multiple thermal image regions;
[0016] The thermal image area whose pixel gray value is greater than a preset gray threshold is divided into an area of interest;
[0017] The thermal image area whose pixel grayscale value is not greater than a preset grayscale threshold is divided into a normal area, wherein the preset grayscale threshold matches the ambient temperature.
[0018] Optionally, in some optional implementations, collecting a visible light image of the region of interest by a visible light camera, and detecting edge information of the leakage contour according to the visible light image, includes:
[0019] Obtaining coordinates of the region of interest;
[0020] Acquire a visible light image corresponding to the coordinates by a visible light camera;
[0021] enhancing leakage contours and edge features in the visible light image based on an image processing algorithm;
[0022] According to the leakage contour and the edge feature, edge detection is performed on the visible light image to obtain edge information of the leakage contour.
[0023] Optionally, in some optional embodiments, the enhancing the leakage contour and edge features in the visible light image based on an image processing algorithm comprises:
[0024] The visible light image is sequentially subjected to Gaussian filtering, median filtering and top-hat transformation processing, thereby enhancing leakage contours and edge features in the visible light image.
[0025] Optionally, in some optional implementations, performing edge detection on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour includes:
[0026] Using the Scharr operator, edge detection is performed on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour.
[0027] Optionally, in some optional implementations, calculating the closure of the leakage contour according to the edge information, thereby determining the pipeline leakage location, includes:
[0028] Selecting a starting point on an edge pixel of the leakage contour according to the edge information;
[0029] Starting from the starting point, using the Moore-neighbor tracking algorithm, tracking along the edge pixels to determine whether the leakage contour is successfully closed;
[0030] If the leakage contour is successfully closed, it is determined that the pipeline leaks at the corresponding position of the leakage contour.
[0031] Optionally, in some optional embodiments, after calculating the closure of the leakage contour according to the edge information to determine the pipeline leakage position, the method further includes:
[0032] Generate corresponding pipeline leak detection report.
[0033] Optionally, in some optional embodiments, after calculating the closure of the leakage contour according to the edge information to determine the pipeline leakage position, the method further includes:
[0034] According to the preset inspection path, the system automatically inspects the next inspection point and executes the above pipeline leakage detection method again.
[0035] In a second aspect, a pipeline leakage detection device includes: an infrared image acquisition unit, a visible light image acquisition unit, and a leakage position determination unit;
[0036] The infrared image acquisition unit is used to acquire a thermal image of the pipeline area through an infrared camera, and detect an area of interest whose temperature is lower than the ambient temperature based on the thermal image;
[0037] The visible light image acquisition unit is used to acquire the visible light image of the region of interest through a visible light camera, and detect edge information of the leakage contour according to the visible light image;
[0038] The leakage position determination unit is used to calculate the closure of the leakage contour according to the edge information, so as to determine the pipeline leakage position.
[0039] By means of the above technical solution, the present invention provides a pipeline leakage detection method and device, which can collect thermal images of the pipeline area through an infrared camera, and detect an area of interest whose temperature is lower than the ambient temperature based on the thermal image; collect visible light images of the area of interest through a visible light camera, and detect edge information of the leakage contour based on the visible light image; calculate the closure of the leakage contour based on the edge information, so as to determine the pipeline leakage position. It can be seen from this that the present invention can perform detection and calculation based on the images of the infrared camera and the visible light camera, and quickly and accurately determine the leakage position of the pipeline, especially for detecting the leakage position of colorless fluids.
[0040] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0042] Figure 1 A flow chart of a first pipeline leakage detection method provided by the present invention is shown;
[0043] Figure 2 A flow chart of a second pipeline leakage detection method provided by the present invention is shown;
[0044] Figure 3 A flow chart of a third pipeline leakage detection method provided by the present invention is shown;
[0045] Figure 4 A flow chart of a fourth pipeline leakage detection method provided by the present invention is shown;
[0046] Figure 5 A flow chart of a fifth pipeline leakage detection method provided by the present invention is shown;
[0047] Figure 6 A schematic structural diagram of a pipeline leakage detection device provided by the present invention is shown;
[0048] Figure 7 A structural schematic diagram of an electronic device provided by the present invention is shown. DETAILED DESCRIPTION
[0049] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.
[0050] like Figure 1 As shown, the present invention provides a pipeline leakage detection method, including: S100, S200 and S300;
[0051] S100, collecting a thermal image of the pipeline area by an infrared camera, and detecting an area of interest whose temperature is lower than the ambient temperature according to the thermal image;
[0052] Optionally, the present invention can be used to automatically detect the leakage position of the industrial pipeline of the power plant. Therefore, the infrared camera of the present invention can collect thermal images of the industrial pipeline area of the power plant, and the present invention does not limit this.
[0053] Optionally, in the thermal image, areas with different temperatures have different images. That is, the thermal image can reflect the temperature conditions at different locations of the pipeline to a certain extent. It should be noted that: since the fluid transported in the pipeline is generally lower than the ambient temperature, when the imaging color of a certain area of the pipeline in the thermal image is obviously different from the surrounding imaging color (for example, the high temperature area appears red, and the low temperature area appears blue), it means that there may be fluid leakage in this area of the pipeline, and the present invention does not limit this.
[0054] For example, Figure 2 As shown, in some optional embodiments, the S100 includes: S110, S120 and S130;
[0055] S110, collecting a thermal image of the pipeline area by using an infrared camera;
[0056] S120, enhancing the contrast of the thermal image;
[0057] For example, in some optional embodiments, the S120 includes: step 1.1;
[0058] Step 1.1, using an image enhancement algorithm to process the thermal image to enhance the contrast of the thermal image, wherein the image enhancement algorithm is: a histogram equalization algorithm, a logarithmic transformation algorithm or a contrast stretching algorithm.
[0059] Alternatively, histogram equalization is often used to increase the global contrast of many images, especially when the contrast of the useful data of the images is quite close. In this way, the brightness can be better distributed on the histogram. This can be used to enhance local contrast without affecting the overall contrast. Histogram equalization achieves this function by effectively expanding the common brightness.
[0060] Optionally, the logarithmic transformation algorithm is a common nonlinear transformation method in image processing, which is used to emphasize the low-grayscale part of the image and expand the dark pixels in the compressed high-value image.
[0061] Optionally, the contrast stretching algorithm is an image processing technique that is mainly used to improve the visual effect of an image by expanding the dynamic range of the image's grayscale. This algorithm is a type of grayscale transformation that uses the simplest piecewise linear transformation function. Its core idea is to increase the dynamic range of grayscale during image processing. Contrast stretching is similar to histogram equalization, both of which are for a balanced distribution of pixels, making bright areas brighter and dark areas darker, thereby making the image more delicate.
[0062] S130. Divide the thermal image into blocks based on a multi-threshold segmentation technology to obtain an area of interest and a normal area, wherein the temperature of the area of interest is lower than the ambient temperature, and the temperature of the normal area is not lower than the ambient temperature.
[0063] For example, in some optional embodiments, the S130 includes: step 2.1, step 2.2 and step 2.3;
[0064] Step 2.1, segmenting the thermal image after contrast enhancement based on a multi-threshold segmentation technique to obtain a plurality of thermal image regions;
[0065] Optionally, the present invention can apply multi-threshold segmentation technology (such as Otsu algorithm) or region-based adaptive threshold segmentation to divide the thermal image into multiple regions, and then classify them into regions of interest (potential leakage regions) or normal regions (non-potential leakage regions) based on the relationship between the pixel grayscale value and the preset threshold. The present invention is not limited to this.
[0066] Step 2.2, dividing the thermal image area whose pixel grayscale value is greater than a preset grayscale threshold into a region of interest;
[0067] Step 2.3: classify the thermal image area whose pixel grayscale value is not greater than a preset grayscale threshold as a normal area, wherein the preset grayscale threshold matches the ambient temperature.
[0068] Optionally, the preset grayscale threshold mentioned in the present invention can be set according to actual needs, and the present invention does not limit this. It should be noted that: as mentioned above, the thermal image is divided into multiple blocks, and all thermal image areas with pixel grayscale values greater than the preset grayscale threshold are uniformly divided into areas of interest, and all thermal image areas with pixel grayscale values not greater than the preset grayscale threshold are uniformly divided into normal areas, and the present invention does not limit this.
[0069] S200, collecting a visible light image of the region of interest by using a visible light camera, and detecting edge information of a leakage contour according to the visible light image;
[0070] Optionally, as mentioned above, after determining the region of interest, the present invention can obtain the coordinates of the region of interest, and then use a visible light camera to capture a visible light image of the coordinates. That is, the present invention can use a visible light camera to capture a visible light image corresponding to the region of interest, and the present invention is not limited to this.
[0071] For example, Figure 3 As shown, in some optional embodiments, the S200 includes: S210, S220, S230 and S240;
[0072] S210, obtaining the coordinates of the region of interest;
[0073] S220, collecting a visible light image corresponding to the coordinates by using a visible light camera;
[0074] S230, enhancing the leakage contour and edge features in the visible light image based on an image processing algorithm;
[0075] For example, in some optional embodiments, the S230 includes: step 3.1;
[0076] Step 3.1, sequentially perform Gaussian filtering, median filtering and top-hat transformation processing on the visible light image, so as to enhance the leakage contour and edge features in the visible light image.
[0077] Optionally, the present invention can input the original visible light image into a Gaussian filter module so that the Gaussian filter module performs Gaussian filter processing on the visible light image. Gaussian filter processing can smooth the image and reduce noise, and the present invention does not limit this.
[0078] Optionally, the output of the Gaussian filter module can be input to a median filter module so that the median filter module performs median filtering processing. The median filtering processing can further remove residual noise and retain details.
[0079] Optionally, the output of the median filter module can be input to a top-hat transform module so that the top-hat transform module can perform a top-hat transform process. The top-hat transform process can highlight subtle features in the image. It should be noted that the neighborhood size of the top-hat transform can be 35×35 pixels, and the present invention does not limit this.
[0080] Optionally, after Gaussian filtering, median filtering and top-hat transformation processing, the leakage contour and edge features in the image are enhanced to a certain extent, but the specific position or boundary of the leakage area is not directly detected. Therefore, edge detection is required in subsequent steps, and the present invention does not limit this.
[0081] S240: Perform edge detection on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour.
[0082] For example, in some optional embodiments, the S240 includes: step 4.1;
[0083] Step 4.1: Use the Scharr operator to perform edge detection on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour.
[0084] Optionally, the Scharr operator is an operator used for image edge detection, which is similar to the Sobel operator, but has a stronger response to edges. It can be used to detect features such as edges and contours in an image. That is, the visible light image processed by the Scharr operator should contain edge information of the leaked contour.
[0085] Optionally, although there is a sequence in image processing between thermal images and visible light images, the visible light camera and the infrared camera can synchronously capture images of the pipeline area to avoid errors caused by different moments of capturing images, and the present invention does not limit this. That is, the visible light camera and the infrared camera can synchronously capture images of the same pipeline area, and after determining the coordinates of the area of interest, the visible light image corresponding to the coordinates of the area of interest is determined from the captured image, and the present invention does not limit this.
[0086] Optionally, the pixels of the visible light camera and the infrared camera can be at least 5 million pixels, and a dustproof, waterproof and high temperature resistant camera housing is used. It should be noted that the present invention can also be provided with a flash to configure the camera shooting. The intensity of the flash can be automatically adjusted according to the ambient light, and the present invention does not limit this.
[0087] S300: Calculate the closure of the leakage contour according to the edge information, so as to determine the pipeline leakage position.
[0088] For example, Figure 4 As shown, in some optional embodiments, the S300 includes: S310, S320 and S330;
[0089] S310, selecting a starting point on an edge pixel of the leakage contour according to the edge information;
[0090] S320, starting from the starting point, using the Moore-neighbor tracking algorithm, tracking along the edge pixels to determine whether the leakage contour is successfully closed;
[0091] S330: If the leakage contour is successfully closed, determine that the pipeline leaks at a corresponding position of the leakage contour.
[0092] Optionally, a suitable starting point is selected inside the visible light image corresponding to the known region of interest, and the starting point is ensured to be located on an edge pixel. Then, starting from this starting point, the edge pixels are tracked according to the rules of the Moore-neighbor tracking algorithm to determine whether the leakage contour is successfully closed. It should be noted that a successfully closed contour is regarded as a leakage location.
[0093] Optionally, the chain code length of the Moore-neighbor tracking algorithm can be dynamically set according to the size of the region of interest, and the present invention does not impose any limitation on this.
[0094] Optionally, in some optional embodiments, after S300, the method further includes: step 5.1;
[0095] Step 5.1: Generate a corresponding pipeline leakage detection report.
[0096] Optionally, the present invention can automatically generate a test report based on the aforementioned test results of the leakage location, trigger an alarm or maintenance operation when necessary, and store the test data for subsequent analysis, but the present invention is not limited to this.
[0097] Optionally, in some optional embodiments, after S300, the method further includes: step 6.1;
[0098] Step 6.1: According to the preset inspection path, automatically inspect to the next inspection point and execute the above-mentioned method from S100 to S300 again.
[0099] Optionally, the present invention can automatically navigate to the next detection point according to a preset inspection path, and repeat the above steps until the detection of all predetermined detection points is completed.
[0100] Optionally, the present invention may configure an automatic guided vehicle (AGV), and the AGV navigates to the pipeline area to be inspected according to a preset path, and the present invention is not limited to this.
[0101] In order to further clarify the solution of the present invention, the present invention provides Figure 5 The overall flow chart shown in the figure, please refer to the above explanation for the content in the figure, and the present invention will not repeat it any more.
[0102] In summary, the present invention has the following advantages:
[0103] 1. Automation and accuracy. Realize automated detection, reduce human errors, and improve the accuracy of leak detection.
[0104] 2. Environmental adaptability. It can operate stably in a variety of industrial environments without being restricted by lighting and climatic conditions.
[0105] 3. Real-time. Quickly respond to leaks and provide detection reports in a timely manner, reducing potential downtime and repair costs.
[0106] 4. Cost-effectiveness. Low long-term operating costs, reducing losses caused by manual inspections and leaks.
[0107] like Figure 6 As shown, the present invention provides a pipeline leakage detection device, comprising: an infrared image acquisition unit 100, a visible light image acquisition unit 200 and a leakage position determination unit 300;
[0108] The infrared image acquisition unit 100 is used to acquire a thermal image of the pipeline area through an infrared camera, and detect an area of interest whose temperature is lower than the ambient temperature based on the thermal image;
[0109] The visible light image acquisition unit 200 is used to acquire a visible light image of the region of interest through a visible light camera, and detect edge information of the leakage contour according to the visible light image;
[0110] The leakage position determination unit 300 is used to calculate the closure of the leakage contour according to the edge information, so as to determine the pipeline leakage position.
[0111] Optionally, in some optional implementations, the infrared image acquisition unit 100 includes: an infrared image acquisition subunit, a contrast enhancement subunit and an image blocking subunit;
[0112] The infrared image acquisition subunit is used to acquire a thermal image of the pipeline area through an infrared camera;
[0113] The contrast enhancement subunit is used to enhance the contrast of the thermal image;
[0114] The image segmentation subunit is used to segment the thermal image based on a multi-threshold segmentation technology to obtain an area of interest and a normal area, wherein the temperature of the area of interest is lower than the ambient temperature, and the temperature of the normal area is not lower than the ambient temperature.
[0115] Optionally, in certain optional embodiments, the contrast enhancement subunit comprises: an algorithm enhancement subunit;
[0116] The algorithm enhancement subunit is used to process the thermal image using an image enhancement algorithm to enhance the contrast of the thermal image, wherein the image enhancement algorithm is: a histogram equalization algorithm, a logarithmic transformation algorithm or a contrast stretching algorithm.
[0117] Optionally, in some optional embodiments, the image block subunit includes: an image segmentation subunit, a first region division subunit and a second region division subunit;
[0118] The image segmentation subunit is used to segment the thermal image after contrast enhancement based on a multi-threshold segmentation technology to obtain a plurality of thermal image regions;
[0119] The first region division subunit is used to divide the thermal image region whose pixel grayscale value is greater than a preset grayscale threshold into a region of interest;
[0120] The second area division subunit is used to divide the thermal image area whose pixel grayscale value is not greater than a preset grayscale threshold into a normal area, wherein the preset grayscale threshold matches the ambient temperature.
[0121] Optionally, in some optional embodiments, the visible light image acquisition unit 200 includes: a coordinate acquisition subunit, a visible light image acquisition subunit, a visible light image enhancement subunit and an edge detection subunit;
[0122] The coordinate acquisition subunit is used to obtain the coordinates of the region of interest;
[0123] The visible light image acquisition subunit is used to acquire the visible light image corresponding to the coordinates through a visible light camera;
[0124] The visible light image enhancement subunit is used to enhance the leakage contour and edge features in the visible light image based on an image processing algorithm;
[0125] The edge detection subunit is used to perform edge detection on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour.
[0126] Optionally, in certain optional embodiments, the visible light image enhancement subunit includes: a filtering transformation subunit;
[0127] The filtering and transforming subunit is used to sequentially perform Gaussian filtering, median filtering and top-hat transform processing on the visible light image, thereby enhancing the leakage contour and edge features in the visible light image.
[0128] Optionally, in certain optional implementations, the edge detection subunit includes: an edge information acquisition subunit;
[0129] The edge information obtaining subunit is used to use the Scharr operator to perform edge detection on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour.
[0130] Optionally, in some optional implementations, the S300 includes: a starting point selection subunit, a closure judgment subunit, and a leakage position determination subunit;
[0131] The starting point selection subunit is used to select a starting point on the edge pixel of the leakage contour according to the edge information;
[0132] The closure judgment subunit is used to start from the starting point and use the Moore-neighbor tracking algorithm to track along the edge pixels to determine whether the leakage contour is successfully closed;
[0133] The leakage position determination subunit is used to determine that the pipeline leaks at the corresponding position of the leakage contour if the leakage contour is successfully closed.
[0134] Optionally, in some optional embodiments, the device further comprises:
[0135] The method is used to generate a corresponding pipeline leakage detection report after calculating the closedness of the leakage contour based on the edge information to determine the pipeline leakage position.
[0136] Optionally, in some optional embodiments, the device further comprises:
[0137] The method is used to automatically inspect the next inspection point according to a preset inspection path and perform the above pipeline leakage detection method again after calculating the closedness of the leakage contour according to the edge information to determine the pipeline leakage position.
[0138] The present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the pipeline leakage detection method described in any one of the above items is implemented.
[0139] like Figure 7 As shown, the present invention provides an electronic device 70, which includes at least one processor 701, and at least one memory 702 and a bus 703 connected to the processor 701; wherein the processor 701 and the memory 702 communicate with each other through the bus 703; the processor 701 is used to call the program instructions in the memory 702 to execute any of the above-mentioned pipeline leakage detection methods.
[0140] In the present invention, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0141] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0142] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined in the present invention may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in the present invention, but will conform to the widest scope consistent with the principles and novel features disclosed in the present invention.
[0143] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims
1. A pipeline leakage detection method, characterized in that: include: Collecting a thermal image of the pipeline area by an infrared camera, and detecting an area of interest whose temperature is lower than the ambient temperature based on the thermal image; Obtaining coordinates of the region of interest; Acquire a visible light image corresponding to the coordinates by a visible light camera; sequentially performing Gaussian filtering, median filtering and top-hat transformation processing on the visible light image, thereby enhancing leakage contours and edge features in the visible light image; Using a Scharr operator, according to the leakage contour and the edge feature, edge detection is performed on the visible light image to obtain edge information of the leakage contour; Calculating the closure of the leakage contour according to the edge information, thereby determining the pipeline leakage location; triggering an alarm or maintenance operation based on the pipeline leakage location; The step of calculating the closure of the leakage contour according to the edge information, thereby determining the pipeline leakage location, includes: Selecting a starting point on an edge pixel of the leakage contour according to the edge information; Starting from the starting point, using the Moore-neighbor tracking algorithm, tracking along the edge pixels to determine whether the leakage contour is successfully closed; If the leakage contour is successfully closed, it is determined that the pipeline leaks at the corresponding position of the leakage contour.
2. The method according to claim 1, characterized in that The method of collecting a thermal image of the pipeline area by an infrared camera and detecting an area of interest whose temperature is lower than the ambient temperature according to the thermal image includes: Collect thermal images of the pipeline area through infrared cameras; enhancing the contrast of the thermal image; The thermal image is divided into blocks based on a multi-threshold segmentation technology to obtain an area of interest and a normal area, wherein the temperature of the area of interest is lower than the ambient temperature, and the temperature of the normal area is not lower than the ambient temperature.
3. The method according to claim 2, characterized in that The step of enhancing the contrast of the thermal image comprises: The thermal image is processed using an image enhancement algorithm to enhance the contrast of the thermal image, wherein the image enhancement algorithm is: a histogram equalization algorithm, a logarithmic transformation algorithm or a contrast stretching algorithm.
4. The method according to claim 2, characterized in that: The method of dividing the thermal image into blocks based on the multi-threshold segmentation technology to obtain the region of interest and the normal region includes: Based on the multi-threshold segmentation technology, the thermal image after contrast enhancement is segmented to obtain multiple thermal image regions; The thermal image area whose pixel gray value is greater than a preset gray threshold is divided into an area of interest; The thermal image area whose pixel grayscale value is not greater than a preset grayscale threshold is divided into a normal area, wherein the preset grayscale threshold matches the ambient temperature.
5. The method according to claim 1, characterized in that After calculating the closure of the leakage contour according to the edge information to thereby determine the pipeline leakage location, the method further includes: Generate corresponding pipeline leak detection report.
6. The method according to claim 1, characterized in that After calculating the closure of the leakage contour according to the edge information to thereby determine the pipeline leakage location, the method further includes: According to the preset inspection path, the next inspection point is automatically inspected and the method of claim 1 is executed again.
7. A pipeline leakage detection device, characterized in that: include: Infrared image acquisition unit, visible light image acquisition unit and leakage position determination unit; The infrared image acquisition unit is used to acquire a thermal image of the pipeline area through an infrared camera, and detect an area of interest whose temperature is lower than the ambient temperature based on the thermal image; The visible light image acquisition unit is used to acquire the visible light image of the region of interest through a visible light camera, and detect edge information of the leakage contour according to the visible light image; The leakage position determination unit is used to calculate the closure of the leakage contour according to the edge information, so as to determine the pipeline leakage position; and trigger an alarm or maintenance operation based on the pipeline leakage position; Wherein, the visible light image acquisition unit includes: a coordinate acquisition subunit, a visible light image acquisition subunit, a visible light image enhancement subunit and an edge detection subunit; The coordinate acquisition subunit is used to obtain the coordinates of the region of interest; The visible light image acquisition subunit is used to acquire the visible light image corresponding to the coordinates through a visible light camera; The visible light image enhancement subunit is used to sequentially perform Gaussian filtering, median filtering and top-hat transformation processing on the visible light image, so as to enhance the leakage contour and edge features in the visible light image; The edge detection subunit is used to use a Scharr operator to perform edge detection on the visible light image according to the leakage contour and the edge feature to obtain edge information of the leakage contour; Wherein, the leakage position determination unit comprises: a starting point selection subunit, a closure judgment subunit and a leakage position determination subunit; The starting point selection subunit is used to select a starting point on the edge pixel of the leakage contour according to the edge information; The closure judgment subunit is used to start from the starting point and use the Moore-neighbor tracking algorithm to track along the edge pixels to determine whether the leakage contour is successfully closed; The leakage position determination subunit is used to determine that the pipeline leaks at the corresponding position of the leakage contour if the leakage contour is successfully closed.
Citation Information
Patent Citations
Binocular-vision-based steam leakage positioning system and method
CN109854964A
Tunnel structure leaked water precise identifying device and method based on infrared thermal imaging
CN110529186A
Image detection method and system, vehicle and computer readable storage medium
CN117274128A
Method and system for automatically identifying pipeline thermal leakage based on image
CN117274697A
Infrared imaging gas leakage detection and interference removal method based on dual-light information
CN117315236A
