Gas leakage position positioning method and device

Abstract

The embodiment of the invention provides a gas leakage position positioning method and device, and the method comprises the steps: collecting spectral images corresponding to a plurality of wave bands for a gas leakage region through an unmanned plane, and carrying out the fusion of the spectral images corresponding to the plurality of wave bands, and obtaining a multispectral image; extracting multispectral features of the multispectral image, and constructing a gas concentration thermodynamic diagram corresponding to the gas leakage area according to the multispectral features; carrying out concentration image feature recognition on the gas concentration thermodynamic diagram, and determining an abnormal image region in the gas concentration thermodynamic diagram according to a recognition result; and constructing a flight path for the unmanned aerial vehicle in the gas leakage area according to the abnormal image area, and driving the unmanned aerial vehicle to position a gas leakage position based on the flight path.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of image processing technology, and in particular to a method and device for locating a gas leakage position. Background Art

[0002] Chemicals widely used in industrial production processes, especially flammable and toxic gas chemicals, pose potential threats to the environment and human health. In industries such as petrochemicals, fertilizer manufacturing, and metallurgy, the leakage or excessive emissions of toxic gases can cause serious air pollution. Therefore, toxic gas monitoring technology has been applied. Existing toxic gas monitoring technology mainly relies on fixed sensor network systems. Such sensors are usually installed in specific locations in factories and storage areas, and monitor the concentration of specific gases in the air through a predetermined sampling frequency. When the gas concentration exceeds the preset threshold, the system issues an alarm. Although this method can achieve the monitoring purpose, it has certain limitations. First, fixed sensors can only cover a limited space and cannot monitor the entire factory or storage area in real time, resulting in monitoring blind spots in some areas. Secondly, the deployment and maintenance costs of fixed sensor systems are high. Especially in harsh environments, sensors are easily damaged or fail, thereby reducing the reliability and effectiveness of monitoring. Therefore, an effective solution is urgently needed to solve the above problems. Summary of the invention

[0003] In view of this, an embodiment of this specification provides a method for locating a gas leak position. One or more embodiments of this specification also relate to a gas leak position locating device, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a method for locating a gas leakage position is provided, comprising: Using a drone to collect spectral images corresponding to multiple bands of the gas leakage area, and fusing the spectral images corresponding to the multiple bands to obtain a multispectral image; Extracting multispectral features of the multispectral image, and constructing a gas concentration heat map corresponding to the gas leakage area according to the multispectral features; Performing concentration image feature recognition on the gas concentration thermodynamic map, and determining an abnormal image area in the gas concentration thermodynamic map according to the recognition result; A flight path is constructed for the drone in the gas leakage area according to the abnormal image area, and the drone is driven to locate the gas leakage position based on the flight path.

[0005] According to a second aspect of an embodiment of this specification, a gas leakage position positioning device is provided, comprising: The acquisition module is configured to acquire spectral images corresponding to a plurality of bands respectively for the gas leakage area through the drone, and fuse the spectral images corresponding to the plurality of bands respectively to obtain a multi-spectral image; an extraction module, configured to extract multispectral features of the multispectral image, and construct a gas concentration heat map corresponding to the gas leakage area according to the multispectral features; A recognition module is configured to perform concentration image feature recognition on the gas concentration thermodynamic map, and determine an abnormal image area in the gas concentration thermodynamic map according to the recognition result; The positioning module is configured to construct a flight path for the drone in the gas leakage area according to the abnormal image area, and drive the drone to locate the gas leakage position based on the flight path.

[0006] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned gas leakage position locating method are implemented.

[0007] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned gas leakage location locating method are implemented.

[0008] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program or instructions, which implement the steps of the above-mentioned gas leakage location positioning method when executed by a processor.

[0009] The gas leakage location positioning method provided in this embodiment can quickly and accurately locate the gas leakage location, and can be unaffected by the spatial position. The spectral images corresponding to multiple bands can be collected by the drone for the gas leakage area, and then the spectral images corresponding to the multiple bands are fused to obtain a multi-spectral image; the multi-spectral image can carry the change information of the gas concentration in different areas of the air. Therefore, the multi-spectral features of the multi-spectral image can be extracted, and the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multi-spectral features; the gas concentration heat map can intuitively reflect the gas changes in different areas, and in order to quickly locate the gas leakage location. The concentration image feature recognition can be performed on the gas concentration heat map, and the abnormal image area can be determined in the gas concentration heat map according to the recognition result; then the flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, and the drone can be driven to continue to locate based on the flight path, so as to locate the gas leakage location. In order to achieve the rapid detection of the gas leakage location by installing the sensor away from the fixed position, the risks brought by human detection can be avoided, and the safety and flexibility of gas leakage detection can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a flow chart of a method for locating a gas leak position provided by an embodiment of this specification; Figure 2 It is a schematic diagram of collecting images in a gas leakage location positioning method provided by an embodiment of this specification; Figure 3 It is a process flow chart of a method for locating a gas leak position provided by an embodiment of this specification; Figure 4 It is a structural schematic diagram of a gas leakage position locating device provided by an embodiment of this specification; Figure 5 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0011] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0012] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0013] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0014] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0015] First, the terms involved in one or more embodiments of this specification are explained.

[0016] Linear Discriminant Analysis (LDA) is a classic statistical learning and data analysis technique. The core idea of ​​LDA is to project data into a new space through linear transformation, so that samples of the same category are as compact as possible, while samples of different categories are as separated as possible. Specifically, LDA aims to find a linear combination of features to maximize the ratio of between-class variance to within-class variance, that is, the Fisher criterion. To achieve this goal, LDA needs to calculate the intra-class scatter matrix (reflecting the degree of discreteness between samples of the same category) and the inter-class scatter matrix (reflecting the differences between samples of different categories), and find the line or hyperplane that can best project.

[0017] In this specification, a gas leakage position locating method is provided. This specification also relates to a gas leakage position locating device, a computing device, a computer-readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0018] In practical applications, in order to solve the limitations of fixed sensors, some portable and mobile detection equipment, such as handheld gas detectors, have been applied. Such equipment can be carried by staff and can be detected anytime and anywhere. However, this method also has certain shortcomings. Due to its reliance on manpower, handheld detectors are difficult to meet the needs of high-frequency and wide-range real-time monitoring, especially in high-risk environments, where frequent exposure to toxic gases may endanger the health and safety of detection personnel. In addition, the detection range of handheld devices is small, and it is difficult to generate a gas concentration distribution map of the area in real time. In order to achieve more efficient wide-area monitoring, vehicle-mounted mobile detection systems are also used in traditional methods. Such systems are installed on special vehicles and use the movement of vehicles to detect gases in the area. However, the flexibility of vehicle-mounted systems is poor and cannot cover some areas with complex terrain, especially inside factories with more height restrictions or multi-story structures. In addition, the moving speed of the vehicle is limited, and fine-grained, dynamic real-time monitoring cannot be achieved. Therefore, in large-area, high-frequency toxic gas monitoring scenarios, traditional fixed sensors, handheld detectors, and vehicle-mounted detection systems each have their own shortcomings. Especially when the leak source needs to be located quickly and accurately, the limitations of these systems are more obvious. Therefore, an effective solution is urgently needed to solve the above problems.

[0019] The gas leakage location positioning method provided in this embodiment can quickly and accurately locate the gas leakage location, and can be unaffected by the spatial position. The spectral images corresponding to multiple bands can be collected by the drone for the gas leakage area, and then the spectral images corresponding to the multiple bands are fused to obtain a multi-spectral image; the multi-spectral image can carry the change information of the gas concentration in different areas of the air. Therefore, the multi-spectral features of the multi-spectral image can be extracted, and the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multi-spectral features; the gas concentration heat map can intuitively reflect the gas changes in different areas, and in order to quickly locate the gas leakage location. The concentration image feature recognition can be performed on the gas concentration heat map, and the abnormal image area can be determined in the gas concentration heat map according to the recognition result; then the flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, and the drone can be driven to continue to locate based on the flight path, so as to locate the gas leakage location. In order to achieve the rapid detection of the gas leakage location by installing the sensor away from the fixed position, the risks brought by human detection can be avoided, and the safety and flexibility of gas leakage detection can be improved.

[0020] See also Figure 1 , Figure 1 A flow chart of a gas leakage location positioning method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0021] Step S102: Using a drone to collect spectral images corresponding to a plurality of bands in the gas leakage area, and fusing the spectral images corresponding to the plurality of bands to obtain a multi-spectral image.

[0022] The gas leakage location positioning method provided in this embodiment can be applied to the location of the source in any gas leakage scenario, such as toxic gas leakage in high-risk environments such as industrial areas and storage areas, or gas leakage in residential areas, or toxic gas leakage in laboratories, etc. This embodiment takes toxic gas leakage in industrial areas as an example to illustrate the gas leakage location positioning method provided in this embodiment. For descriptions of other scenarios, please refer to the same or corresponding descriptions in this embodiment, and this embodiment does not make any limitation here.

[0023] It should be noted that the gas leakage location positioning method provided in this embodiment can be used not only for toxic gas leakage, but also for locating the leakage location of gas stored in any confined space, thereby avoiding the impact of leaked gas on the environment.

[0024] Specifically, the gas leakage area refers to industrial areas, storage areas, residential areas and other areas where there are gas leaks that pollute the environment. Correspondingly, multiple bands specifically refer to the bands of the drone that collect spectral images of the gas leakage area. The imaging effects of spectral images collected in different bands are different. Spectral images specifically refer to images obtained after the spectral sensor configured by the drone collects images of the gas leakage area. In practical applications, different sensors can be selected for different gases in combination with their characteristic spectral bands. Correspondingly, multi-spectral images specifically refer to spectral images of the corresponding gas leakage area obtained by fusing the spectral images corresponding to multiple bands. It contains information from multiple bands and can improve the positioning accuracy of the gas leakage position.

[0025] The gas leakage location positioning method provided in this embodiment can quickly and accurately locate the gas leakage location, and can be unaffected by the spatial position. The spectral images corresponding to multiple bands can be collected by the drone for the gas leakage area, and then the spectral images corresponding to the multiple bands are fused to obtain a multi-spectral image; the multi-spectral image can carry the change information of the gas concentration in different areas of the air. Therefore, the multi-spectral features of the multi-spectral image can be extracted, and the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multi-spectral features; the gas concentration heat map can intuitively reflect the gas changes in different areas, and in order to quickly locate the gas leakage location. The concentration image feature recognition can be performed on the gas concentration heat map, and the abnormal image area can be determined in the gas concentration heat map according to the recognition result; then the flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, and the drone can be driven to continue to locate based on the flight path, so as to locate the gas leakage location. In order to achieve the rapid detection of the gas leakage location by installing the sensor away from the fixed position, the risks brought by human detection can be avoided, and the safety and flexibility of gas leakage detection can be improved.

[0026] Furthermore, when collecting spectral images by drones and fusing them to construct multispectral images, in order to ensure that the fused multispectral images can be used for subsequent gas leakage location positioning, an image registration strategy can be used for image fusion processing. In this embodiment, the specific implementation method is as follows: The multispectral sensor of the UAV is used to collect images of the gas leakage area at a set angle to obtain spectral images corresponding to multiple bands; the spectral images corresponding to the multiple bands are fused according to the image registration strategy to obtain a multispectral image.

[0027] Specifically, multispectral sensors can be selected according to the characteristic spectral absorption bands of toxic gases (CO, H2S, etc.). Correspondingly, the image registration strategy specifically refers to the strategy of matching and superimposing two or more images acquired at different times, different sensors (imaging equipment) or under different conditions (weather, illumination, camera position and angle, etc.), with the aim of finding the spatial mapping relationship between the pixels of one image and the pixels of another image, thereby ensuring that the multispectral image has a true mapping relationship with the gas leakage area.

[0028] Based on this, in order to ensure that the gas leakage location can be detected according to the multispectral image in the future, the multispectral sensor of the drone can be used to collect images of the gas leakage area at a set angle to obtain spectral images corresponding to multiple bands; then, the spectral images corresponding to multiple bands can be fused according to the image registration strategy to obtain a multispectral image for subsequent use.

[0029] In practical applications, gas detection sensors can also be configured on drones to detect gas through the short-wave infrared (SWIR) band and the ultraviolet (UV) band, and to determine the gas concentration through the difference in absorption and scattering, so as to construct a thermal map later. In specific implementation, when installing a multispectral camera on a drone, it is necessary to ensure that the camera can shoot stably and avoid vibration interference. Therefore, a gimbal can be used to meet the requirements of clear image shooting during inspections. In addition, calibration is required on the ground to ensure the consistency and accuracy of multispectral images taken at different heights and angles.

[0030] Furthermore, after the configuration is completed, when the drone collects spectral images of the gas leakage location, it can take off from a corner of a certain area, and the drone can realize the action of looking around, and make the multispectral sensor shoot at fixed angles to obtain multispectral images of the surroundings. Multispectral sensors usually collect images of different bands and can simultaneously generate multiple images of different wavelengths (such as near infrared, ultraviolet, etc.). After that, the images of different bands can be fused into a complete spectral image according to the image registration strategy, so that the data of each spectral channel comprehensively show the concentration distribution of toxic gases. So that the image can be used to locate the gas leakage location later.

[0031] For example, a toxic gas detection device in an industrial area issues an alarm, which indicates that a sealed tank containing toxic gas is leaking. In order to quickly locate the sealed tank where the gas leak occurs, a drone can be used to locate the gas leak. At this time, a drone equipped with a spectral sensor can be used to collect spectral images of various areas in the industrial area where gas may leak, such as Figure 2 As shown in the schematic diagram, spectral images corresponding to different bands will be obtained through acquisition. Then, the images of different bands can be fused in combination with the image registration strategy to obtain a multi-spectral image, so that the concentration distribution of toxic gases can be reflected through the image for subsequent positioning.

[0032] In summary, by collecting spectral images of different bands by drones and fusing them to construct multispectral images, the multispectral images can carry the concentration distribution information of toxic gases, which makes it easier to locate the gas leak by subsequent image analysis.

[0033] Step S104: extracting multispectral features of the multispectral image, and constructing a gas concentration heat map corresponding to the gas leakage area according to the multispectral features.

[0034] Specifically, after obtaining the multispectral image that records the distribution information of toxic gases corresponding to different bands, in order to facilitate the subsequent positioning of the gas leakage position, the multispectral features of the multispectral image can be extracted first, and then the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multispectral features. The gas concentration corresponding to different areas can be reflected through the gas concentration heat map, and then the drone can be controlled to move to the area with high concentration according to the gas concentration, so as to quickly and accurately locate the gas leakage position.

[0035] Among them, the multispectral image feature specifically refers to the vector expression obtained after feature extraction of the multispectral image. Correspondingly, the gas concentration heat map specifically refers to the heat map reflecting the gas concentration in different regions, and in this map, different colors can be used to represent the concentration, such as displaying a certain area in red for high concentration and blue for low concentration, etc., to clearly visualize the distribution of the gas.

[0036] Furthermore, when constructing a gas concentration heat map, considering that the map can show the gas concentration at different locations in the area, the concentration distribution prediction can be completed in combination with the trained regression model and mapped to the spectral image to obtain a heat map. In this embodiment, the specific implementation method is as follows: The multispectral image is processed by a linear discriminant algorithm to obtain multispectral image features; the multispectral image features are input into a regression model for processing to obtain gas concentration value distribution information corresponding to the gas leakage area; the gas concentration value distribution information is mapped to the multispectral image, and a gas concentration heat map corresponding to the gas leakage area is generated according to the mapping result.

[0037] Specifically, the linear discriminant algorithm specifically refers to the LDA algorithm. Correspondingly, the regression model specifically refers to a trained model that can calculate the gas concentration value corresponding to each area based on the multispectral image features. In other words, the regression model learns the mapping relationship between gas concentration and spectral image features. After inputting the multispectral image features, the model can calculate the gas concentration value of each area based on the learned knowledge and output it for use in constructing a gas concentration heat map. Correspondingly, the gas concentration value distribution information specifically refers to the distribution information corresponding to all gas concentration values ​​obtained after calculating the gas concentration value for each pixel point, which includes not only the gas concentration value but also the spatial distribution information.

[0038] Based on this, after obtaining the multispectral image, the linear discriminant algorithm can be used to process the multispectral image to obtain the multispectral image features; thereafter, in order to be able to map from the image to the gas concentration value and then construct a thermal map, the multispectral image features can be input into the regression model for processing to obtain the gas concentration value distribution information corresponding to the gas leakage area; at this time, the gas concentration value distribution information can be mapped to the multispectral image, thereby generating a gas concentration thermal map corresponding to the gas leakage area according to the mapping results.

[0039] In practical applications, linear discriminant analysis (LDA) dimensionality reduction technology can be used to extract significant features of specified toxic gases in multispectral images. LDA can find the best linear combination to distinguish gas areas with different concentrations. Therefore, after reducing the multispectral data to a small number of key features, the computational efficiency can be significantly improved. On this basis, concentration estimation and heat map generation can be performed. Specifically, a regression algorithm can be applied to the extracted multispectral feature data to estimate the gas concentration value, and then it can be mapped to the spatial position of the image to generate a gas concentration heat map.

[0040] In the specific implementation, considering that the gas concentration heat map can directly reflect the gas concentration in different areas, it can be directly handed over to the relevant personnel for viewing, so pseudo color coding can be used to display high-concentration areas in red and low-concentration areas in blue to clearly visualize the distribution of gas. This makes it easier for operation and maintenance personnel and firefighters to visually observe the leakage point when they find a suspected leakage source, which is convenient for their subsequent security enhancement work.

[0041] Following the above example, after obtaining the multispectral image, the LDA technology can be used to process the multispectral image, so as to obtain the multispectral image feature V corresponding to the multispectral image. Then, the multispectral image feature V is processed in combination with the regression algorithm to estimate the gas concentration value corresponding to each pixel. Then, it is mapped to the multispectral image to obtain the gas concentration heat map of the corresponding gas leakage area, so that the map can be analyzed later to quickly locate the gas leakage location.

[0042] In summary, by using regression algorithm combined with LDA technology to complete the construction of the thermal map, it can be ensured that the thermal map is more in line with the actual situation, thereby effectively improving the accuracy and efficiency of gas leakage location positioning.

[0043] Step S106, performing concentration image feature recognition on the gas concentration thermodynamic map, and determining an abnormal image area in the gas concentration thermodynamic map according to the recognition result.

[0044] Specifically, after obtaining the gas concentration heat map corresponding to the gas leakage area as mentioned above, considering that the gas concentration heat map can characterize the gas concentration value corresponding to each area, in order to quickly locate the gas leakage position, concentration image feature recognition can be performed on the gas concentration heat map. By performing feature recognition at the image level, it is possible to determine the abnormal image area in the gas concentration heat map according to the recognition result, so as to subsequently drive the drone to move in combination with the abnormal image area, thereby quickly locating the gas leakage position.

[0045] Among them, the concentration image feature recognition specifically refers to the recognition of the features representing the gas concentration in the gas concentration thermodynamic map, and the identification and processing operation of determining the abnormal image area with the highest risk of gas leakage. Accordingly, the abnormal image area specifically refers to the image area corresponding to the pixel point with the highest gas concentration value in the gas concentration thermodynamic map, which can indicate that the real geographical area corresponding to the image area has the highest risk of gas leakage.

[0046] Furthermore, when determining the abnormal image area through image recognition, the image detection and determination of the abnormal image area can be completed by gradient calculation. In this embodiment, the specific implementation is as follows: A gradient calculation is performed on the gas concentration thermogram to obtain gradient change information between gas concentration values ​​and thermogram pixel points in the gas concentration thermogram; the gas concentration thermogram is detected according to the gradient change information based on a preset sliding window, and abnormal image areas are determined in the gas concentration thermogram based on the detection results.

[0047] Specifically, the gradient change information between the gas concentration value and the pixel point of the heat map specifically refers to the trend information of the gas concentration value changing with the position, which is used to locate the abnormal image area. Correspondingly, the sliding window specifically refers to a window of a set size for detecting each pixel point in the gas concentration heat map.

[0048] Based on this, after obtaining the gas concentration heat map, considering that the gas concentration heat map can reflect the gas concentration values ​​corresponding to different areas, at the image level, the gradient calculation can be performed on the gas concentration heat map first to obtain the gradient change information between the gas concentration value and the heat map pixel point in the gas concentration heat map; at this time, the gas concentration heat map can be detected according to the gradient change information based on the preset sliding window, and the abnormal image area can be determined in the gas concentration heat map according to the detection results, so as to subsequently plan the flight path of the drone according to the area, and then quickly and accurately locate the gas leakage area.

[0049] Furthermore, in order to ensure the accuracy of determining the abnormal image area, the concentration value of each pixel in the image can be determined and compared. In this embodiment, the specific implementation method is as follows: According to the detection results, multiple candidate thermogram pixel points that meet the gas leakage detection conditions are determined in the gas concentration thermogram; the candidate gas concentration value corresponding to each candidate thermogram pixel point is determined, and the candidate gas concentration value is compared with a preset concentration threshold; according to the comparison result, the candidate thermogram pixel points corresponding to the candidate gas concentration value greater than the concentration threshold are selected to construct a pixel point set; a weighted average calculation is performed on the thermogram pixel points included in the pixel point set, and the abnormal image area is determined in the gas concentration thermogram according to the calculation result.

[0050] Specifically, the gas leakage detection condition specifically refers to the condition for comparing the gas concentration value corresponding to each pixel point in the gas concentration thermodynamic map, and the candidate thermodynamic map pixel points can be screened out according to the comparison result. Correspondingly, the candidate gas concentration value specifically refers to the pixel value corresponding to each candidate thermodynamic map pixel point.

[0051] Based on this, when locating the abnormal image area, considering that the gas concentration heat map is composed of the image and the gas concentration value corresponding to each pixel point, after obtaining the gradient change information, pixel point detection can be performed based on the sliding window according to the gradient change information. At this time, multiple candidate heat map pixel points that meet the gas leakage detection conditions can be screened out in the gas concentration heat map according to the detection results; then the candidate gas concentration value corresponding to each candidate heat map pixel point can be determined, and the candidate gas concentration value can be compared with the preset concentration threshold; a pixel point set is constructed by selecting the candidate heat map pixel points corresponding to the candidate gas concentration value greater than the concentration threshold; and a weighted average calculation is performed on the heat map pixel points contained in the pixel point set, so that the abnormal image area can be determined in the gas concentration heat map according to the calculation results, thereby facilitating the subsequent use of the abnormal image area for drone path planning.

[0052] In practical applications, it is assumed that after a multispectral image is collected by a drone for a gas leakage area, a two-dimensional thermal map I(x, y) containing gas concentration is generated based on the collected image, where (x, y) represents the position of the image pixel and I(x, y) represents the gas concentration value at that position. On this basis, the trend of gas concentration changing with position can be identified by calculating the gradient of the thermal map. The concentration gradient can be expressed by the following formula (1): (1) Among them, the modulus of the gradient It indicates the rate of concentration change. A larger gradient value indicates a significant concentration change.

[0053] After obtaining the concentration gradient, in order to identify the high-concentration area in the thermodynamic map, a window size of w can be set, such as w=5, and the pixel point with the local maximum gas concentration value in the thermodynamic map can be found within the window. For each pixel point (x, y) in the thermodynamic map, if its concentration value is I (x, y), the following formula (2) must be satisfied: (2) At this time, (x, y) is the pixel point of the local maximum gas concentration value, that is, the area corresponding to this point may be a high concentration peak area, which can be understood as an abnormal image area. Among them, i and j represent the values ​​of half the length and half the width of the window.

[0054] Furthermore, a preset concentration threshold T can be used to filter out local peaks of low concentration, thereby ensuring that the detected pixel points are real high-concentration areas. If a pixel point with a local maximum gas concentration value satisfies I (x, y) > T, the concentration value corresponding to the pixel point can be marked as a high concentration score.

[0055] Finally, considering that the pixels corresponding to the stable peak value can better reflect the true distribution of gas concentration, the weighted average position can be calculated based on a set of pixels corresponding to high concentration values, so as to locate the abnormal image area. Assume that the pixel corresponding to the detected high concentration value can be , whose concentration is , then the center point of the abnormal image area can be expressed by the following formula (3): (3) Based on the above processing, a smooth center position corresponding to the abnormal image area can be obtained, which can be used as an estimate of the high-concentration area under the current drone position. Through the above processing, the abnormal image area corresponding to the high-concentration peak can be determined in the gas concentration heat map, and the potential location of the gas leak can be located. The drone can then send the real-time generated gas concentration heat map to the ground control center through wireless transmission through the central control system, and save the data for subsequent analysis.

[0056] In the specific implementation, considering that the drone collects images for the gas leakage area at each set angle, in order to facilitate the location of the gas leakage, the images collected at multiple angles can be spliced ​​to generate a panoramic concentration distribution map. Phase correlation image registration technology is used during splicing to align adjacent images in space. At the same time, the concentration data in each multispectral image is superimposed on the panoramic map according to angle and distance to generate a unified concentration heat map. This map can show the surrounding concentration distribution and help the drone locate the direction of high concentration. In the spliced ​​panoramic concentration heat map, the area with the highest gas concentration (peak) is identified. The position of this area will correspond to an angle, that is, the deflection angle from the front of the drone. The distance of the high concentration area is estimated by the depth information of the multispectral image and the height of the drone. This can be judged by calculating the gradient change rate of the concentration distribution map, that is, the high concentration area farther away from the drone will appear blurry in the image, while the concentration change in the closer area is more obvious.

[0057] Continuing with the above example, after obtaining the gas concentration heat map corresponding to the gas leakage area, the trend of gas concentration changing with position can be calculated by the above formula (1). Then, the gas concentration heat map can be detected according to this trend and in combination with a sliding window of window size 5, and the pixel corresponding to the local maximum gas concentration value can be determined based on the detection result and formula (2). Furthermore, the gas concentration value corresponding to each pixel can be compared with the preset concentration threshold T to screen out pixels with sufficiently high gas concentration values ​​based on the comparison result and form a high-concentration point set. Thereafter, a weighted average calculation can be performed for the pixels contained in the high-concentration point set according to formula (3), and the center position coordinates (x 中 ,y 中 ), on this basis, the high concentration peak area can be determined in the gas concentration thermodynamic map according to the center position coordinates, indicating that there is a potential gas leakage risk in this area, so that the gas leakage position can be located in the area later.

[0058] In summary, by using image analysis and detection to determine the abnormal image area, the positioning accuracy of the abnormal image area can be guaranteed, which makes it easier to drive the drone to move according to the area, so that the gas leak location can be quickly and accurately located.

[0059] Step S108, constructing a flight path for the drone in the gas leakage area according to the abnormal image area, and driving the drone to locate the gas leakage position based on the flight path.

[0060] Specifically, after determining the abnormal image area from the gas concentration heat map, considering that the abnormal image area is the area in the image and there is a risk of gas leakage in this area, a flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, so that the drone can move to the gas leakage location according to the flight path and accurately locate the gas leakage location in the gas leakage area, so as to quickly carry out leakage treatment and avoid affecting the air.

[0061] The flight path specifically refers to the path planned for the flight direction, speed, altitude, angle, route, etc. of the drone, so that the drone can approach the gas leakage location along the path. Correspondingly, the gas leakage location specifically refers to the location where the toxic gas leakage occurs in the gas leakage area.

[0062] Furthermore, after determining the abnormal image area, in order to enable the drone to quickly locate the gas leak location, the drone needs to further monitor the area. Considering that there may be multiple abnormal image areas, in order to quickly locate the leak location, the path planning can be completed by matching the flight direction. In this embodiment, the specific implementation method is as follows: When the gas concentration heat map contains multiple abnormal image areas, each abnormal image area is matched with the flight direction of the UAV respectively; a target abnormal image area is determined according to the matching result, and a flight path is constructed for the UAV in the gas leakage area according to the target abnormal image area.

[0063] Specifically, the flight direction specifically refers to the direction in which the drone is currently moving. Correspondingly, the target abnormal image area specifically refers to the abnormal image area in the multiple abnormal image areas that matches the flight direction of the drone, which is used to avoid the drone from making multiple flight adjustments and can quickly fly to the area corresponding to the target abnormal image area, thereby improving the speed of locating the gas leak position.

[0064] Based on this, when the gas concentration heat map contains multiple abnormal image areas, if the drone is controlled to fly blindly, the time to locate the gas leakage position may be longer, causing more serious impact. Therefore, each abnormal image area can be matched with the flight direction of the drone respectively to determine the target abnormal image area according to the matching results. Thereafter, a flight path can be constructed for the drone in the gas leakage area according to the target abnormal image area, thereby prompting the drone to quickly locate the gas leakage position according to the flight path.

[0065] Furthermore, in order to enable the drone to quickly and accurately complete the subsequent monitoring process, the flight path planning can be performed by calculating the image distance. In this embodiment, the specific implementation method is as follows: Calculating the image distance between the abnormal image area and the drone according to the gradient change information, and comparing the image distance with a preset distance threshold; When the image distance is less than the distance threshold, determining original flight parameters corresponding to the UAV, and constructing a flight path for the UAV in the gas leakage area based on the original flight parameters; When the image distance is greater than or equal to the distance threshold, determine the flight parameter to be adjusted corresponding to the UAV; adjust the flight parameter to be adjusted according to the gradient change information and the image distance to obtain the target flight parameter; and construct a flight path for the UAV in the gas leakage area based on the target flight parameter.

[0066] Specifically, the image distance specifically refers to the distance between the abnormal image area and the current position of the drone in the image, and the distance calculation can be obtained based on the center position of the abnormal image area and the mapping position of the drone in the image. Correspondingly, the original flight parameters specifically refer to the flight parameters of the drone that are not currently adjusted. Correspondingly, the flight parameters to be adjusted specifically refer to the flight parameters of the drone that can be adjusted at the current moment. The target flight parameters are the flight parameters obtained after adjusting the flight parameters to be adjusted.

[0067] Based on this, when constructing the flight path, considering that different image distances require different path planning for the UAV, the image distance between the abnormal image area and the UAV can be calculated according to the gradient change information, and the image distance can be compared with the preset distance threshold.

[0068] When the image distance is less than the distance threshold, it means that the distance between the UAV and the position mapped to the abnormal image area in the actual space is relatively close. Therefore, the original flight parameters corresponding to the UAV can be directly determined, and a flight path can be constructed for the UAV in the gas leakage area based on the original flight parameters, so as to enable the UAV to quickly approach the location where the gas may be leaking.

[0069] When the image distance is greater than or equal to the distance threshold, it means that the distance between the UAV and the position mapped to the abnormal image area in the actual space is far. In order to enable the UAV to quickly approach the gas leakage location, the flight parameters to be adjusted corresponding to the UAV can be determined; and the flight parameters to be adjusted are adjusted according to the gradient change information and the image distance to obtain the target flight parameters; thereafter, a flight path can be constructed for the UAV in the gas leakage area based on the target flight parameters, so that the UAV can quickly approach the location where the gas may be leaking.

[0070] In practical applications, when planning the path for the UAV, considering that the abnormal image area has been determined, it is only necessary to locate the spatial area corresponding to the image area in the gas leakage area to make the UAV approach the gas leakage location. Therefore, it is assumed that the center point of the spatial area is located at . It is the angle relative to the current orientation of the drone. At this time, the drone should move toward this angle to gradually approach the high-concentration area corresponding to the abnormal image area.

[0071] In this process, if there are multiple abnormal image areas in the gas concentration thermodynamic map, the high-concentration area corresponding to the abnormal image area closest to the flight direction of the drone can be selected as the area to which the drone needs to fly. Furthermore, after determining the area to be flown, the concentration gradient change information of the gas concentration thermodynamic map can be used to estimate the distance between the area and the drone. In specific implementation, the gradient strength can be calculated using the following formula (4): (4) Among them, areas with higher gradients usually indicate larger concentration changes and may be closer to the gas leak location.

[0072] Based on this, the abnormal image area with the highest concentration can be identified in the gas concentration heat map through the concentration gradient intensity or the depth information of the spectral image. The pixel point corresponding to this area can be After that, the pixel position and the current position of the drone can be calculated. Distance If the concentration gradient changes greatly, it further indicates that the distance is close. Conversely, the smaller the rate of change, the farther the distance is.

[0073] When the high-concentration area is far away, a larger step size (such as the standard flight speed of the drone) can be selected to speed up the flight speed. At the same time, as the drone approaches the high-concentration area, the step size can be gradually reduced so that the drone can more accurately lock the center of the high-concentration area. It can be dynamically adjusted according to the concentration gradient and distance, and the relationship is as follows (5): (5) Among them, k is an adjustment parameter, which can be between 0 and 1. Based on the above processing, the best flight path of the drone at the current moment can be planned so that it can quickly approach the gas leakage location.

[0074] In summary, in order to enable the UAV to quickly approach the gas leakage location, the flight path can be constructed by combining the gas concentration heat map and the abnormal image area, so that the path planning of the UAV can be more reasonable and efficient.

[0075] On this basis, each sampling period requires the drone to be located at the sampling position and moved to a new position to collect spectral images, and then a new round of positioning processing is performed. In this embodiment, the specific implementation method is as follows: The UAV is driven to move in the gas leakage area based on the flight path; when the position of the UAV after movement does not meet the positioning conditions, a new sampling position is calculated according to the heading angle of the UAV and the position of the UAV after movement; the UAV is driven to move to the new sampling position, and the steps of collecting spectral images corresponding to multiple bands respectively for the gas leakage area by the UAV are performed until the position of the UAV after movement meets the positioning conditions, thereby determining the gas leakage position.

[0076] Based on this, after completing the path planning for the UAV, the UAV can be driven to move in the gas leakage area based on the flight path; when the position of the UAV after moving does not meet the positioning conditions, it means that the position of the UAV is not close enough to the gas leakage position at this time, and it is necessary to control the UAV to move further, and then perform a new round of image acquisition and analysis. Therefore, the new sampling position can be calculated according to the heading angle of the UAV and the position of the UAV after moving; thereafter, the UAV can be driven to move to the new sampling position, and return to execute step S102; until the position of the UAV after moving meets the positioning conditions, it can be said that the current position of the UAV can locate the gas leakage position, so that the gas leakage position can be submitted to the operation and maintenance personnel to quickly take response measures, such as evacuating personnel, cutting off the leakage source, ventilation, etc.

[0077] In practical applications, after the flight path is built for the drone, the flight direction of the drone can be adjusted according to the flight path so that the drone should be oriented towards the high-concentration area. Move. The heading angle of the drone is adjusted to , so that it moves towards the concentration peak in the next step. Therefore, the new position of the next sampling point of the drone Calculate as follows formula (6):

[0078] (6) Based on the above-mentioned drone flight control, the drone can continuously narrow the detection range and gradually approach the high-concentration area. The direction and step length of each flight are dynamically adjusted based on the latest concentration heat map to ensure that the drone always moves along the most effective path and eventually reaches the location of the gas leak source. In this way, real-time path optimization is achieved at each step, ensuring that the drone effectively approaches the gas leak source with the least number of detections, thereby achieving fast inspection efficiency and high-precision detection results.

[0079] Using the above example, when determining the coordinates (x 中 ,y 中 ) corresponding to the high concentration peak area, the current position of the drone and (x 中 ,y 中 ) If the distance d is far, the drone needs to increase its flight speed to approach the area and enter the next image acquisition and processing. If the distance d is close, the drone's flight speed can be gradually reduced so that the drone can approach the gas leakage location more accurately. In this iteration, it is finally determined that a gas leak occurred in the sealed tank numbered 85 in the industrial zone. At this time, the staff near the sealed tank 85 can be evacuated, and the gas delivery pipeline of the sealed tank 85 can be cut off to avoid loss of personnel and assets.

[0080] The gas leakage location positioning method provided in this embodiment can quickly and accurately locate the gas leakage location, and can be unaffected by the spatial position. The spectral images corresponding to multiple bands can be collected by the drone for the gas leakage area, and then the spectral images corresponding to the multiple bands are fused to obtain a multi-spectral image; the multi-spectral image can carry the change information of the gas concentration in different areas of the air. Therefore, the multi-spectral features of the multi-spectral image can be extracted, and the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multi-spectral features; the gas concentration heat map can intuitively reflect the gas changes in different areas, and in order to quickly locate the gas leakage location. The concentration image feature recognition can be performed on the gas concentration heat map, and the abnormal image area can be determined in the gas concentration heat map according to the recognition result; then the flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, and the drone can be driven to continue to locate based on the flight path, so as to locate the gas leakage location. In order to achieve the rapid detection of the gas leakage location by installing the sensor away from the fixed position, the risks brought by human detection can be avoided, and the safety and flexibility of gas leakage detection can be improved.

[0081] The following combination Figure 3 Taking the application of the gas leakage location positioning method provided in this specification in a gas leakage scenario as an example, the gas leakage location positioning method is further described. Figure 3 A process flow chart of a gas leakage location positioning method provided in an embodiment of the present specification is shown, which specifically includes the following steps.

[0082] Step S302: The multispectral sensor of the drone collects images of the gas leakage area at a set angle to obtain spectral images corresponding to multiple bands.

[0083] Step S304: fusing the spectral images corresponding to the multiple bands according to the image registration strategy to obtain a multi-spectral image.

[0084] Step S306: Process the multispectral image using a linear discriminant algorithm to obtain multispectral image features.

[0085] Step S308: input the multispectral image features into the regression model for processing to obtain gas concentration value distribution information corresponding to the gas leakage area.

[0086] Step S310 , mapping the gas concentration value distribution information to the multispectral image, and generating a gas concentration heat map corresponding to the gas leakage area according to the mapping result.

[0087] Step S312, performing gradient calculation on the gas concentration thermodynamic map to obtain gradient change information between the gas concentration value and the thermodynamic map pixel points in the gas concentration thermodynamic map.

[0088] Step S314: Detect the gas concentration thermodynamic map according to the preset sliding window according to the gradient change information, and determine the abnormal image area in the gas concentration thermodynamic map according to the detection result.

[0089] Step S316, calculating the image distance between the abnormal image area and the drone according to the gradient change information, and comparing the image distance with a preset distance threshold.

[0090] Step S318, when the image distance is less than the distance threshold, determining the original flight parameters corresponding to the UAV, and constructing a flight path for the UAV in the gas leakage area based on the original flight parameters.

[0091] Step S320: driving the drone to locate the gas leakage location based on the flight path, and uploading the gas leakage location to the server.

[0092] In summary, in order to quickly and accurately locate the gas leakage position, and not be affected by the spatial position, the spectral images corresponding to multiple bands can be collected by drones for the gas leakage area, and then the spectral images corresponding to the multiple bands can be fused to obtain multispectral images; the multispectral images can carry the change information of gas concentration in different areas of the air. Therefore, the multispectral features of the multispectral image can be extracted, and the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multispectral features; the gas concentration heat map can intuitively reflect the gas changes in different areas, and in order to quickly locate the gas leakage position. The concentration image feature recognition can be performed on the gas concentration heat map, and the abnormal image area can be determined in the gas concentration heat map according to the recognition result; then the flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, and the drone can be driven to continue positioning based on the flight path, so as to locate the gas leakage position. In order to achieve the rapid detection of the gas leakage position by installing the sensor away from the fixed position, the risks brought by human detection can be avoided, and the safety and flexibility of gas leakage detection can be improved.

[0093] Corresponding to the above method embodiment, this specification also provides a gas leakage position positioning device embodiment, Figure 4 FIG. 2 shows a schematic diagram of a gas leakage location positioning device provided by an embodiment of the present specification. Figure 4 As shown, the device comprises: The acquisition module 402 is configured to acquire spectral images corresponding to a plurality of bands respectively for the gas leakage area through a drone, and fuse the spectral images corresponding to the plurality of bands respectively to obtain a multi-spectral image; An extraction module 404 is configured to extract multispectral features of the multispectral image and construct a gas concentration heat map corresponding to the gas leakage area according to the multispectral features; An identification module 406 is configured to perform concentration image feature identification on the gas concentration thermodynamic map, and determine an abnormal image area in the gas concentration thermodynamic map according to the identification result; The positioning module 408 is configured to construct a flight path for the drone in the gas leakage area according to the abnormal image area, and drive the drone to locate the gas leakage position based on the flight path.

[0094] In an optional embodiment, the acquisition module 402 is further configured to: The multispectral sensor of the UAV is used to collect images of the gas leakage area at a set angle to obtain spectral images corresponding to multiple bands; the spectral images corresponding to the multiple bands are fused according to the image registration strategy to obtain a multispectral image.

[0095] In an optional embodiment, the extraction module 404 is further configured to: The multispectral image is processed by a linear discriminant algorithm to obtain multispectral image features; the multispectral image features are input into a regression model for processing to obtain gas concentration value distribution information corresponding to the gas leakage area; the gas concentration value distribution information is mapped to the multispectral image, and a gas concentration heat map corresponding to the gas leakage area is generated according to the mapping result.

[0096] In an optional embodiment, the identification module 406 is further configured to: A gradient calculation is performed on the gas concentration thermogram to obtain gradient change information between gas concentration values ​​and thermogram pixel points in the gas concentration thermogram; the gas concentration thermogram is detected according to the gradient change information based on a preset sliding window, and abnormal image areas are determined in the gas concentration thermogram based on the detection results.

[0097] In an optional embodiment, the identification module 406 is further configured to: According to the detection results, multiple candidate thermogram pixel points that meet the gas leakage detection conditions are determined in the gas concentration thermogram; the candidate gas concentration value corresponding to each candidate thermogram pixel point is determined, and the candidate gas concentration value is compared with a preset concentration threshold; according to the comparison result, the candidate thermogram pixel points corresponding to the candidate gas concentration value greater than the concentration threshold are selected to construct a pixel point set; a weighted average calculation is performed on the thermogram pixel points included in the pixel point set, and the abnormal image area is determined in the gas concentration thermogram according to the calculation result.

[0098] In an optional embodiment, the positioning module 408 is further configured to: When the gas concentration heat map contains multiple abnormal image areas, each abnormal image area is matched with the flight direction of the UAV respectively; a target abnormal image area is determined according to the matching result, and a flight path is constructed for the UAV in the gas leakage area according to the target abnormal image area.

[0099] In an optional embodiment, the positioning module 408 is further configured to: An image distance between the abnormal image area and the UAV is calculated according to the gradient change information, and the image distance is compared with a preset distance threshold; when the image distance is less than the distance threshold, original flight parameters corresponding to the UAV are determined, and a flight path is constructed for the UAV in the gas leakage area based on the original flight parameters.

[0100] In an optional embodiment, the positioning module 408 is further configured to: When the image distance is greater than or equal to the distance threshold, determine the flight parameter to be adjusted corresponding to the UAV; adjust the flight parameter to be adjusted according to the gradient change information and the image distance to obtain the target flight parameter; and construct a flight path for the UAV in the gas leakage area based on the target flight parameter.

[0101] In an optional embodiment, the positioning module 408 is further configured to: The UAV is driven to move in the gas leakage area based on the flight path; when the position of the UAV after movement does not meet the positioning conditions, a new sampling position is calculated according to the heading angle of the UAV and the position of the UAV after movement; the UAV is driven to move to the new sampling position, and the steps of collecting spectral images corresponding to multiple bands respectively for the gas leakage area by the UAV are performed until the position of the UAV after movement meets the positioning conditions, thereby determining the gas leakage position.

[0102] The gas leakage location positioning device provided in this embodiment can quickly and accurately locate the gas leakage location, and can be unaffected by the spatial position. The spectral images corresponding to multiple bands can be collected by the drone for the gas leakage area, and then the spectral images corresponding to the multiple bands are fused to obtain a multi-spectral image; the multi-spectral image can carry the change information of the gas concentration in different areas of the air. Therefore, the multi-spectral features of the multi-spectral image can be extracted, and the gas concentration heat map corresponding to the gas leakage area can be constructed according to the multi-spectral features; the gas concentration heat map can intuitively reflect the gas changes in different areas, and in order to quickly locate the gas leakage location. The concentration image feature recognition can be performed on the gas concentration heat map, and the abnormal image area can be determined in the gas concentration heat map according to the recognition result; then the flight path can be constructed for the drone in the gas leakage area according to the abnormal image area, and the drone can be driven to continue to locate based on the flight path, so as to locate the gas leakage location. In order to achieve the rapid detection of the gas leakage location by installing the sensor in a detached position, the risks brought by human detection can be avoided, and the safety and flexibility of gas leakage detection can be improved.

[0103] The above is a schematic scheme of a gas leakage position locating device of this embodiment. It should be noted that the technical scheme of the gas leakage position locating device and the technical scheme of the gas leakage position locating method described above belong to the same concept, and the details of the technical scheme of the gas leakage position locating device that are not described in detail can all be referred to the description of the technical scheme of the gas leakage position locating method described above.

[0104] Figure 5 The structure block diagram of a computing device 500 provided according to an embodiment of the present specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0105] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0106] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0107] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 may also be a mobile or stationary server.

[0108] The processor 520 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned gas leakage location positioning method.

[0109] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned gas leakage location positioning method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned gas leakage location positioning method.

[0110] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned gas leakage location locating method.

[0111] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned gas leakage location positioning method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned gas leakage location positioning method.

[0112] An embodiment of the present specification also provides a computer program product, including a computer program or instructions, which implement the steps of the above-mentioned gas leakage location locating method when executed by a processor.

[0113] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above-mentioned gas leakage location positioning method belong to the same concept, and the details not described in detail in the technical scheme of the computer program product can be referred to the description of the technical scheme of the above-mentioned gas leakage location positioning method.

[0114] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0116] It should be noted that, for the above-mentioned 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 be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0117] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0118] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can understand and use this specification well.

Claims

1. A method for locating a gas leak, characterized in that: include: The spectral images corresponding to the multiple bands are collected by the drone for the gas leakage area, and the spectral images corresponding to the multiple bands are fused to obtain a multi-spectral image; Extracting multispectral features of the multispectral image, and constructing a gas concentration heat map corresponding to the gas leakage area according to the multispectral features; Performing concentration image feature recognition on the gas concentration thermodynamic map, and determining an abnormal image area in the gas concentration thermodynamic map according to the recognition result; A flight path is constructed for the drone in the gas leakage area according to the abnormal image area, and the drone is driven to locate the gas leakage position based on the flight path.

2. The method for locating a gas leakage position according to claim 1, characterized in that: The method of collecting spectral images corresponding to a plurality of bands respectively for the gas leakage area by using a drone, and fusing the spectral images corresponding to the plurality of bands respectively to obtain a multispectral image includes: The multi-spectral sensor of the drone is used to collect images of the gas leakage area at a set angle to obtain spectral images corresponding to multiple bands; The spectral images corresponding to the multiple bands are fused according to the image registration strategy to obtain a multispectral image.

3. The method for locating a gas leakage position according to claim 1, characterized in that: The extracting multispectral features of the multispectral image and constructing a gas concentration heat map corresponding to the gas leakage area according to the multispectral features includes: Processing the multispectral image using a linear discriminant algorithm to obtain multispectral image features; Inputting the multispectral image features into a regression model for processing to obtain gas concentration value distribution information corresponding to the gas leakage area; The gas concentration value distribution information is mapped to the multispectral image, and a gas concentration heat map corresponding to the gas leakage area is generated according to the mapping result.

4. The method for locating a gas leakage position according to claim 1, characterized in that: The performing concentration image feature recognition on the gas concentration thermodynamic map and determining the abnormal image area in the gas concentration thermodynamic map according to the recognition result includes: Performing gradient calculation on the gas concentration thermodynamic map to obtain gradient change information between gas concentration values ​​and thermodynamic map pixel points in the gas concentration thermodynamic map; The gas concentration thermodynamic map is detected according to the gradient change information based on a preset sliding window, and an abnormal image area is determined in the gas concentration thermodynamic map according to the detection result.

5. The method for locating a gas leakage position according to claim 4, characterized in that: Determining the abnormal image area in the gas concentration thermodynamic map according to the detection result includes: Determine, in the gas concentration thermodynamic map, a plurality of candidate thermographic pixel points that meet the gas leakage detection condition according to the detection result; Determine a candidate gas concentration value corresponding to each candidate thermal map pixel, and compare the candidate gas concentration value with a preset concentration threshold; According to the comparison result, candidate thermal map pixels corresponding to candidate gas concentration values ​​greater than the concentration threshold are selected to construct a pixel point set; A weighted average calculation is performed on the thermodynamic map pixels included in the pixel point set, and an abnormal image area is determined in the gas concentration thermodynamic map according to the calculation result.

6. The method for locating a gas leakage position according to claim 1, characterized in that: The step of constructing a flight path for the UAV in the gas leakage area according to the abnormal image area includes: When the gas concentration heat map contains multiple abnormal image areas, each abnormal image area is matched with the flight direction of the UAV; A target abnormal image region is determined according to the matching result, and a flight path is constructed for the UAV in the gas leakage area according to the target abnormal image region.

7. The method for locating a gas leakage position according to claim 4, characterized in that: The step of constructing a flight path for the UAV in the gas leakage area according to the abnormal image area includes: Calculating the image distance between the abnormal image area and the drone according to the gradient change information, and comparing the image distance with a preset distance threshold; When the image distance is less than the distance threshold, original flight parameters corresponding to the UAV are determined, and a flight path is constructed for the UAV in the gas leakage area based on the original flight parameters.

8. The method for locating a gas leakage position according to claim 7, characterized in that: After the step of comparing the image distance with a preset distance threshold is performed, the method further includes: When the image distance is greater than or equal to the distance threshold, determining the flight parameter to be adjusted corresponding to the UAV; Adjust the flight parameter to be adjusted according to the gradient change information and the image distance to obtain a target flight parameter; A flight path is constructed for the drone in the gas leak area based on the target flight parameters.

9. The method for locating a gas leakage position according to any one of claims 1 to 8, characterized in that: The method of driving the drone to locate the gas leakage position based on the flight path includes: driving the drone to move in the gas leakage area based on the flight path; When the position of the drone after moving does not meet the positioning condition, a new sampling position is calculated according to the heading angle of the drone and the position of the drone after moving; The drone is driven to move to the new sampling position, and the step of collecting spectral images corresponding to multiple bands respectively for the gas leakage area is performed by the drone until the position of the drone after movement meets the positioning condition, and the gas leakage position is determined.

10. A gas leakage location positioning device, characterized in that: include: The acquisition module is configured to acquire spectral images corresponding to a plurality of bands respectively for the gas leakage area through the drone, and fuse the spectral images corresponding to the plurality of bands respectively to obtain a multi-spectral image; an extraction module, configured to extract multispectral features of the multispectral image, and construct a gas concentration heat map corresponding to the gas leakage area according to the multispectral features; A recognition module is configured to perform concentration image feature recognition on the gas concentration thermodynamic map, and determine an abnormal image area in the gas concentration thermodynamic map according to the recognition result; The positioning module is configured to construct a flight path for the drone in the gas leakage area according to the abnormal image area, and drive the drone to locate the gas leakage position based on the flight path.

11. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the method described in any one of claims 1 to 9.

13. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

Images