Methane leakage point and smoke plume identification method suitable for hyperspectral imager

Abstract

The invention relates to a methane leakage point and smoke plume identification method suitable for a hyperspectral imager, and the method comprises the following steps: S1, carrying out the inversion of a methane concentration grayscale image through employing a matched filtering method and point source type hyperspectral data of a target region, and removing a water body and a shadow region in the methane concentration grayscale image to obtain methane concentration basic data; s2, reducing background noise in the methane concentration basic data by using a density-based DBSCAN noise reduction algorithm, and improving the signal-to-noise ratio of the image to obtain methane concentration noise reduction data; s3, using a YOLO image classification model to remove pseudo methane anomaly caused by other types of objects in the methane concentration noise reduction data; s4, segmenting methane smoke plumes from the methane concentration noise reduction data by using a smoke plume recognition algorithm based on pixel connectivity; and S5, superposing the methane plume with the wind speed data and the atmospheric pressure data, and estimating the methane plume emission by using an IME algorithm, thereby solving the problem that the real image data is affected due to noise reduction based on a filter.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image recognition, and particularly relates to a method for identifying methane leakage points and plumes applicable to hyperspectral imagers. Background Art

[0002] Methane (CH4) is a potent greenhouse gas with a much higher global warming potential than carbon dioxide, and its concentration in the atmosphere is increasing year by year. The main sources of methane emissions include fossil fuel extraction, agricultural activities, landfills, and natural sources such as wetlands. Given the significant impact of methane on climate change, how to accurately monitor its emissions and develop effective emission reduction strategies has become the focus of global attention. In recent years, with the rapid development of remote sensing technology, satellite-based methane monitoring methods have gradually matured. In particular, imaging spectrometers in the short-wave infrared (SWIR) band have provided important data support for global methane emission monitoring. According to different observation purposes, current methane satellite payloads can be divided into two categories: regional and point-source types. Regional satellites such as GOSAT and Sentinel-5P have high spectral resolution and concentration measurement accuracy, and can monitor the atmospheric methane column concentration globally. These satellites usually have a large observation swath and a short revisit period, and are suitable for monitoring methane emissions at the regional and global scales. However, due to their low spatial resolution (about 5 - 50 km), regional satellites are difficult to identify small-scale point-source emissions. In contrast, point-source satellites such as GHGSat, PRISMA, and China's GF5-02 have high spectral resolution and spatial resolution (about 10 - 100 m), and can detect high-concentration methane plumes near point sources. These satellites are mainly used to identify and quantify large point-source emissions, such as oil wells, storage tanks, coal mines, and landfills. In the research on methane concentration inversion based on point-source hyperspectral satellite data, the Matched Filtering (MF) method is widely used. This algorithm realizes the identification and concentration estimation of the target gas by maximizing the matching degree between the spectral characteristics of the target gas and a known reference spectral library. However, factors such as complex terrain conditions, surface reflection characteristics, spectrally similar features, and instrument noise will interfere with the inversion results, resulting in a large amount of background noise in the inversion results, which is not conducive to the identification of methane leakage points and methane plumes. At present, many studies have explored methods for identifying methane leakage points and methane plumes. Most of the existing methane leakage point identification methods use simple Gaussian filtering to remove background noise in the methane concentration grayscale image, and then perform threshold segmentation to identify methane leakage points and leakage areas. This filter-based noise reduction will cause damage to the real data of the image, resulting in problems such as loss of original pixel values and decrease in image resolution, affecting the accuracy of methane leakage point identification. At the same time, due to factors such as complex terrain, uneven surface reflection, and spectrally similar ground objects in reality, there are a large number of false alarm signals in the methane leakage points obtained by the threshold segmentation method; Current methods for identifying the range of methane plumes include visual discrimination, using a meteorological data model to simulate single-point plume emissions of methane leakage points and match them with a methane concentration map to obtain the optimal matching plume, and using 2-D plume image simulations under various wind speed conditions and background noise to train a convolutional neural network model to identify methane plumes. Visual discrimination has high labor costs and low accuracy and cannot be widely applied. The meteorological data model matching method has a large amount of model calculations, high operating costs, and low simulation accuracy under complex terrain, and its applicability is not strong in practical applications. The training of the convolutional neural network model requires a large number of real and manually labeled methane plume images. In reality, the data volume is insufficient. To pursue high accuracy, a large-volume model needs to be used, which has extremely high requirements for the amount of calculation and the size of the database. At the same time, the neural network model performs poorly when the methane plume concentration is low. Some studies have tried to use large-eddy simulation (LES) to simulate actual observed plume data for training machine learning models. However, its calculation cost is high and it is not conducive to practical deployment.

[0003] Due to the above factors, there are a large number of false alarm signals in the results identified by the existing methane leakage point identification methods. Methane plume identification methods have problems such as inaccurate methane plume range, large amount of computation, high labor and data costs, etc. So far, there is no methane leakage point and plume identification method in the public domain that has high automation, strong applicability, high accuracy, and small algorithm calculation amount. Summary of the Invention

[0004] The purpose of the present invention is to provide a methane leakage point and plume identification method applicable to a hyperspectral imager to solve the problems existing in the above-mentioned prior art.

[0005] The above technical purpose of the present invention is achieved through the following technical solutions: A methane leakage point and plume identification method applicable to a hyperspectral imager includes the following steps: Step S1, using a matched filtering method and point-source type hyperspectral data of the target area, inversely calculating a methane concentration grayscale image, and removing water bodies and shadow areas in the methane concentration grayscale image to obtain basic methane concentration data; Step S2: Use the density-based DBSCAN denoising algorithm to reduce the background noise in the basic methane concentration data and improve the signal-to-noise ratio of the image to obtain the methane concentration denoised data; Step S3: Use the YOLO image classification model to remove the pseudo-methane anomalies caused by other types of objects in the methane concentration denoised data described in Step S2; Step S4: Use the plume recognition algorithm based on pixel connectivity to segment the methane plume from the methane concentration denoised data described in Step S2; Step S5: Superimpose the methane plume with the wind speed data and the atmospheric pressure data, use the IME algorithm to estimate the methane plume emission, and finally perform error analysis.

[0006] In a further embodiment, the Step S2 further includes: Step S21: Use the threshold segmentation method to remove the low-concentration part in the basic methane concentration data. The formula is: , where 、 、are the basic methane concentration and the methane concentration after threshold segmentation respectively, is the methane concentration threshold set according to the specific situation of the project; Step S22: Use the concave function to perform a non-linear transformation on the segmented basic methane concentration data to obtain the non-linearly transformed methane concentration. The formula is: , where is the non-linearly transformed methane concentration, making the data of the plume part denser in the concentration dimension and easier to be clustered into clusters; Step S23: Use the DBSCAN algorithm to perform clustering in the horizontal, vertical, and concentration dimensions of the pixels. Further divide the non-linearly transformed basic methane concentration data described in Step S22 into a methane plume area and a background noise area. The methane plume area is a set of pixel areas clustered into the same cluster by the algorithm, and the noise area is a set of pixel areas that cannot meet the clustering conditions of the algorithm and thus cannot be clustered into any cluster. The value range of the DBSCAN algorithm parameter min_sample is: 5 - 10, and the value range of the eps parameter is: 1 - 5. The eps parameter refers to the neighborhood distance threshold of a certain sample point, and the min_sample parameter refers to the threshold of the total number of sample points contained in the neighborhood where the distance of a certain sample point is the eps; Subtract the background noise area from the non-linearly transformed basic methane concentration data to obtain the methane concentration denoised data; This denoising algorithm is a lossless denoising method that does not lose the original pixel values and does not change the resolution.

[0007] In a further embodiment, the Step S3 further includes: Step S31: Training dataset production. Collect historical public data of methane leakage points in the target area, download Sentinel-2 cloud-free optical image slices centered on the leakage point with a length and width of 100 pixels each and a resolution of 10 meters, and recheck and correct them through manual interpretation, dividing them into a "methane leakage area" and a "non-methane leakage area" as the training dataset; Step S32: Use the training dataset in Step S31 to train a YOLO image classification model to obtain a binary classification model that divides Sentinel-2 cloud-free optical image slices into a "methane leakage area" and a "non-methane leakage area"; Step S33: Perform threshold division on the methane concentration noise reduction data in Step S2, and define the polygon as a candidate methane leakage area, is a custom threshold, and determine the point corresponding to the highest methane concentration value in the methane leakage area as the candidate methane leakage point; obtain the coordinates of each candidate methane leakage point, and download Sentinel-2 cloud-free optical image slices centered on this point with a length and width of 100 pixels each and a resolution of 10 meters; Step S34: Deploy the binary classification model in Step S32 and use the model to perform predictive inference on all Sentinel-2 cloud-free optical image slices in Step S33, retain the part predicted as the "methane leakage area", and mark the corresponding candidate methane leakage points as pending methane leakage points.

[0008] In a further embodiment, Step S4 further includes: Step S41: Binarize the methane concentration noise reduction data in Step S2, set the pixels with methane concentration greater than the pixels in Step S21 to 1, and set other pixels to 0 to obtain methane concentration binarized data; Step S42: Use a convolutional kernel of size k×k to perform convolution on the binarized image to obtain a neighborhood connectivity number result map of size (w - k + 1)×(h - k + 1), where w and h are the width and height of the original methane concentration binarized data map respectively, and the value of each pixel in the map is the number of non-zero pixel points in the k-neighborhood around the corresponding pixel point in the original methane concentration binarized data map. Use a threshold n to extract the pixel positions with values greater than n in the neighborhood connectivity number result map to obtain multiple plume polygons; Step S43: Use the 8-neighborhood connectivity domain algorithm to cluster all the plume polygons to obtain all candidate plume polygons; Step S44: Traverse the candidate plume polygons, and if the methane concentration contained in them is less than the threshold in Step S33 Filter out the candidate plume patches; Mark the candidate plume patches containing the pending methane leakage points with m steps S34 as methane plume masks, where m >= 1, and cluster the m pending methane leakage points, with each cluster being a methane leakage point, and its coordinates being the geometric center of the pending methane leakage points belonging to the cluster; Filter out the candidate plume patches that do not contain the pending methane leakage points; Filter out the pending methane leakage points that do not belong to any candidate plume patches; Step S45, Traverse the methane plume mask, and index and fill the methane concentration values in the methane concentration basic data map described in step S1 according to the coverage range thereof to obtain all methane plumes.

[0009] In summary, the present invention has the following beneficial effects: 1. The present invention applies the DBSCAN clustering algorithm to denoise the methane concentration grayscale image inverted by the matched filtering algorithm, solves the problem that the real data of the image is affected by filter denoising, and improves the signal-to-noise ratio of the image without losing the original pixel value and without changing the resolution. The algorithm is simple and efficient.

[0010] 2. The present invention uses Sentinel-2 optical images and the YOLO model to remove pseudo-methane anomaly points, can accurately filter a large number of abnormal pseudo-methane leakage areas, and greatly improves the accuracy and efficiency of methane leakage point recognition compared with the prior art, with high innovation.

[0011] 3. The present invention designs a plume recognition algorithm based on pixel connectivity in view of the characteristics of methane plume diffusion, with small computational complexity and strong applicability to actual cases.

[0012] 4. The present invention adopts the idea of an integrated algorithm to improve the accuracy of the final result: The candidate plume patches obtained by the methane plume recognition algorithm are intersected and fused with the pending methane leakage points obtained by the YOLO classification algorithm, and finally the methane leakage points and methane plumes are obtained, with high accuracy of the obtained methane leakage points and more accurate methane plume range. Description of the Drawings

[0013] Figure 1 is a flowchart of a method for identifying methane leakage points and plumes applicable to a hyperspectral imager according to the present invention; Figure 2 is an image before processing and denoising the methane concentration grayscale image using the DBSCAN denoising algorithm; Figure 3 is an image during the processing and denoising of the methane concentration grayscale image using the DBSCAN denoising algorithm; Figure 4 is an image after processing and denoising the methane concentration grayscale image using the DBSCAN denoising algorithm; Figure 5 is the normalized confusion matrix of the YOLO image classification model test set; Figure 6 are the identification results of the methane leakage point and methane plume in the embodiment. Detailed implementation manners

[0014] The present invention will be further described in detail below with reference to the accompanying drawings.

[0015] Among them, the same parts are denoted by the same reference numerals. It should be noted that the terms "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to the directions in the Figure 1 accompanying drawings, and the terms "bottom surface" and "top surface", "inner" and "outer" respectively refer to the directions facing or away from the geometric center of a specific component. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this specification, "a plurality" means two or more unless otherwise specifically defined.

[0016] Embodiment 1: As Figure 1 shown, a method for identifying methane leakage points and plumes applicable to a hyperspectral imager includes: Step S1: Using the matched filtering method and the point-source hyperspectral data of the target area, an inverse methane concentration grayscale image is obtained, and the water body and shadow areas in the methane concentration grayscale image are removed to obtain basic methane concentration data; Step S2: Using the density-based DBSCAN denoising algorithm to reduce the background noise in the basic methane concentration data and improve the signal-to-noise ratio of the image to obtain denoised methane concentration data. The specific steps are as follows; Step S21: Using the threshold segmentation method to remove the low-concentration part in the basic methane concentration data. The formula is: , where , are the basic methane concentration and the methane concentration after threshold segmentation respectively, and is the methane concentration threshold set according to the specific situation of the project. In this embodiment, it is taken as 100 ppb; Step S22: Using the concave function to perform a non-linear transformation on the segmented basic methane concentration data to obtain non-linearly transformed methane concentration. The formula is: , where is the non-linearly transformed methane concentration, making the data in the plume part denser in the concentration dimension and easier to be clustered into clusters; Step S23: Use the DBSCAN algorithm to perform clustering in the horizontal, vertical, and concentration dimensions of pixels, and further divide the basic methane concentration data after the non-linear transformation in Step S22 into a methane plume region and a background noise region. The methane plume region is a set of pixel regions clustered into the same cluster by the algorithm, and the noise region is a set of pixel regions that cannot meet the clustering conditions of the algorithm and thus cannot be clustered into any cluster. The value range of the DBSCAN algorithm parameter min_sample is: 8, and the value range of eps is: 2. The eps parameter refers to the neighborhood distance threshold of a certain sample point, and the min_sample parameter refers to the threshold of the total number of sample points contained in the neighborhood where the distance of a certain sample point is the eps; Subtract the background noise region from the basic methane concentration data after the non-linear transformation to obtain methane concentration noise reduction data; This noise reduction algorithm is a lossless noise reduction method that does not lose the original pixel values and does not change the resolution; After , the transformed methane concentration values are as Figure 2 shown. After separating the background noise by the DBSCAN noise reduction algorithm, as Figure 3 shown, finally, an image of the methane concentration value minus the separated background noise is obtained, as Figure 4 shown. It can be seen that this noise reduction algorithm can well separate the background noise and extract the basic methane concentration data; Step S3: Use the YOLO image classification model to remove the pseudo-methane anomalies caused by other types of objects in the methane concentration noise reduction data described in Step S2. The specific steps are as follows; Step S31: Production of the training dataset. Collect the historical public data of methane leakage points in the target area, download the Sentinel-2 cloud-free optical image slices with a length and width of 100 pixels and a resolution of 10 meters centered on the leakage point, and re-comb and correct them through manual interpretation, and divide them into a "methane leakage area" and a "non-methane leakage area" as the training dataset; Step S32: Use the training dataset described in Step S31 to train the YOLO image classification model to obtain a binary classification model that divides the Sentinel-2 cloud-free optical image slices into a "methane leakage area" and a "non-methane leakage area"; The types of underlying surfaces corresponding to methane leakage points are limited and concentrated in certain categories. Table 1 shows the classification statistics of methane leakage points in the carbonmapper aerial methane leakage point dataset in the United States from 2016 to 2024. Among them, the proportion of the top 3 methane leakage point types can reach 90%, which are oil and gas facilities, solid waste, and power facilities. These ground objects can be uniformly identified as the "methane leakage area", and other methane leakage points with a proportion of less than 10%, such as wastewater, grassland, photovoltaic panels, and plastic greenhouses, are grouped into the "non-methane leakage area";

[0017] Divide the training dataset into a training set and a test set in a ratio of 2:8, and use the YOLO11s image classification model for training. The main parameters are shown in Table 2:

[0018] Step S33: Perform threshold division on the methane concentration noise-reduced data in Step S2, and define the patches with methane concentration as candidate methane leakage areas, is a custom threshold, and determine the point corresponding to the highest methane concentration value in the methane leakage area as the candidate methane leakage point; obtain the coordinates of each candidate methane leakage point, and download a Sentinel-2 cloud-free optical image slice with a length and width of 100 pixels each centered on this point and a resolution of 10 meters; Step S34: Deploy the binary classification model in Step S32 and use the model to perform predictive inference on all the Sentinel-2 cloud-free optical image slices in Step S33. Retain the parts predicted as "methane leakage areas" and mark the corresponding candidate methane leakage points as pending methane leakage points; As Figure 5 shown, the normalized confusion matrix of the classification model test set can achieve a classification accuracy of 0.90 in the test set, indicating that the model classification results are reliable; Step S4: According to the Gaussian plume model, the methane plume starts to disperse from the leakage point. Along the axial and radial increasing directions, the edge of the plume gradually expands and the methane concentration gradually decreases until it converges with the background concentration. Correspondingly, in the methane concentration grayscale image, the pixels contained in the methane plume should have a certain density in space. Use a plume recognition algorithm based on pixel connectivity to segment the methane plume from the methane concentration noise-reduced data in Step S2. The specific steps are as follows: Step S41: Binarize the methane concentration noise-reduced data in Step S2. Set the pixels with methane concentration greater than in Step S21 to 1 and set other pixels to 0 to obtain the methane concentration binarized data; Step S42: Convolve the binarized image with a convolution kernel of size k×k to obtain a neighborhood connectivity number result image of size (w-k+1)×(h-k+1), where w and h are the width and height of the original methane concentration binarized data image respectively. The value of each pixel in the image is the number of non-zero pixel points in the k-neighborhood around the corresponding pixel point in the original methane concentration binarized data image. Use a threshold n to extract the pixel positions in the neighborhood connectivity number result image with values greater than n to obtain multiple plume patches. In this embodiment, k = 11 and n = 20 are taken; Step S43: Use the 8-neighborhood connected domain algorithm to cluster all the plume patches to obtain all the candidate plume patches; Step S44: Traverse the candidate plume patches, and filter out the candidate plume patches whose methane concentrations are all less than the threshold described in step S33. Filter out the candidate plume patches that contain m undetermined methane leakage points described in step S34; Mark the candidate plume patches that contain m undetermined methane leakage points as methane plume masks, where m >= 1, and cluster the m undetermined methane leakage points. Each cluster is a methane leakage point, and its coordinates are the geometric center of the undetermined methane leakage points belonging to the cluster; Filter out the candidate plume patches that do not contain the undetermined methane leakage points; Filter out the undetermined methane leakage points that do not belong to any candidate plume patches. Step S45: Traverse the methane plume masks, and according to the covered range, index the methane concentration values in the methane concentration basic data diagram described in step S1 and fill the range of the plume masks to obtain all methane plumes. As Figure 6 shown, for the methane leakage point and methane plume identification results, the methane concentration basic data is overlaid with the undetermined methane leakage points predicted as "methane leakage points" by the YOLO classification algorithm, which are represented by red circles; The methane concentration basic data is also overlaid with the methane plumes identified by the methane plume identification algorithm. The intersection of the undetermined methane leakage points and the methane plumes is the methane leakage points and methane plumes finally determined in this study. Visually judge the methane plumes obtained by the methane plume identification algorithm, screen out the real part of the methane plumes as the true value of the methane plumes, and compare it with the methane leakage points and methane plumes described in step S45. The accuracy rate of the present invention in the embodiment can be obtained. The comparison results are shown in Table 3, and the identification accuracy rate can reach 96.36%.

[0019] Step S5: Overlay the methane plumes with the wind speed data and atmospheric pressure data, use the IME algorithm to estimate the methane plume emissions, and finally conduct error analysis.

[0020] Specific implementation process: Use the matched filtering method and the point source type hyperspectral data of the target area to feedback the methane concentration grayscale image, and remove the water body and shadow areas in the methane concentration grayscale image to obtain the methane concentration basic data. Use the threshold segmentation method to remove the low-concentration part in the methane concentration basic data, perform a non-linear transformation on the segmented methane concentration basic data to obtain the non-linearly transformed methane concentration, and then further divide the non-linearly transformed methane concentration basic data into methane plume regions and background noise regions. Then subtract the background noise region from the non-linearly transformed methane concentration basic data to obtain the methane concentration noise reduction data.

[0021] In the embodiments disclosed by the present invention, terms such as "installation", "connection", "linkage", "fixation", etc. shall be understood in a broad sense. For example, "connection" may be a fixed connection, a detachable connection, or an integral connection; "linkage" may be a direct linkage or an indirect linkage through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments disclosed by the present invention may be understood according to specific circumstances.

[0022] This specific embodiment is only an interpretation of the present invention and is not a limitation thereof. After reading this specification, those skilled in the art may make modifications to this embodiment without creative contributions as needed, but as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A methane leak point and smoke plume identification method suitable for a hyperspectral imager, characterized in that: The following steps are involved: Step S1, using the matched filtering method and the point source hyperspectral data of the target area to invert the methane concentration grayscale image, and removing the water body and shadow area in the methane concentration grayscale image to obtain the basic data of methane concentration; Step S2, using the density-based DBSCAN denoising algorithm to reduce the background noise in the basic data of methane concentration, and improving the signal-to-noise ratio of the image to obtain methane concentration denoised data; Step S3, using the YOLO image classification model to remove pseudo methane anomalies caused by other types of objects in the methane concentration denoised data in step S2; Step S4, using a plume recognition algorithm based on pixel connectivity to segment the methane plume from the methane concentration denoised data in step S2; Step S5: superimpose the methane plume with the wind speed data and the atmospheric pressure data, use the IME algorithm to estimate the methane plume emission, and finally perform error analysis.

2. The methane leakage point and smoke plume identification method applicable to a hyperspectral imager according to claim 1 is characterized in that: The step S2 further comprises: Step S21: Use the threshold segmentation method to remove the low-concentration part in the basic data of methane concentration. The formula is: ,in , They are basic methane concentration and methane concentration after threshold segmentation, The methane concentration threshold is set according to the specific circumstances of the project; Step S22: Use concave function Performing nonlinear transformation on the segmented methane concentration basic data to obtain nonlinearly transformed methane concentration basic data; Step S23, using the DBSCAN algorithm to perform clustering on the horizontal, vertical and concentration dimensions of pixels, and further dividing the basic data of methane concentration after the nonlinear transformation in step S22 into a methane plume area and a background noise area, wherein the methane plume area is a set of pixel areas clustered into the same cluster by the algorithm, and the background noise area is a set of pixel areas that cannot meet the clustering conditions of the algorithm and cannot be clustered into any cluster, and the denoised data of the basic data of methane concentration after the nonlinear transformation is obtained by subtracting the background noise area from the basic data of methane concentration after the nonlinear transformation.

3. The methane leakage point and smoke plume identification method applicable to a hyperspectral imager according to claim 2 is characterized in that: The step S3 further comprises: Step S31, training data set preparation, collecting historical public data of methane leakage points in the target area, downloading Sentinel-2 cloud-free optical image slices with a length and width of 100 pixels and a resolution of 10 meters centered on the leakage point, re-sorting out errors through manual interpretation, and dividing them into methane leakage areas and non-methane leakage areas as the training data set; Step S32, training the YOLO image classification model using the training data set described in step S31, and obtaining a binary classification model that divides the cloud-free optical image slices of Sentinel-2 into methane leakage areas and non-methane leakage areas; Step S33: threshold the methane concentration noise reduction data in step S2, and divide the methane concentration into The image patches are identified as candidate methane leakage areas. A custom threshold is set, and the point corresponding to the highest methane concentration in the methane leakage area is determined as a candidate methane leakage point; the coordinates of each candidate methane leakage point are obtained, and a Sentinel-2 cloud-free optical image slice with a length and width of 100 pixels and a resolution of 10 meters and centered on the point is downloaded; Step S34, deploy the binary classification model described in step S32 and use the model to perform predictive reasoning on all the Sentinel-2 cloud-free optical image slices described in step S33, retain the part predicted to be the methane leakage area, and mark the corresponding candidate methane leakage point as the pending methane leakage point.

4. The methane leakage point and smoke plume identification method applicable to a hyperspectral imager according to claim 3 is characterized in that: The step S4 further comprises: Step S41: Binarize the methane concentration denoising data in step S2, and binarize the methane concentration greater than that in step S21. Set the pixels of 1 to 1 and other pixels to 0 to obtain the binary data of methane concentration; Step S42, using a convolution kernel of size k×k to convolve the methane concentration binary data image, to obtain a neighborhood connectivity number result map of size (w-k+1)×(h-k+1), wherein w and h are respectively the width and height of the original image of the methane concentration binary data, and the value of each pixel in the map is the number of non-zero pixels in the k neighborhood around the corresponding pixel point in the original image of the methane concentration binary data, and using a threshold value n to extract the pixel positions whose values ​​are greater than n in the neighborhood connectivity number result map, to obtain a plurality of smoke plume spots; Step S43, clustering all the smoke plume spots using an 8-neighborhood connected domain algorithm to obtain all candidate smoke plume spots; Step S44: traverse the candidate plume image spots and select those whose methane concentration is less than the threshold value in step S33. The candidate plume spots are filtered out; the candidate plume spots containing m undetermined methane leakage points of step S34 are marked as methane plume masks; the candidate plume spots that do not contain the undetermined methane leakage points are filtered out; the undetermined methane leakage points that do not belong to any candidate plume spots are filtered out; Step S45, traverse the methane plume mask, and according to the range covered by it, index the methane concentration value in the methane concentration basic data map described in step S1 and fill the plume mask range to obtain all methane plumes.

Images