A method and device for automatically extracting sea surface oil film based on optical satellite data
By using an automatic oil slick extraction method based on optical satellite data, and employing preprocessing and an oil slick identification model to identify oil slick areas on the sea surface, this method solves the problems of untimely and inaccurate detection of oil spill accidents in existing technologies, and achieves efficient oil slick identification and ecological protection.
Patent Information
- Application Number
- CN202411223770.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-09-03
AI Technical Summary
Existing technologies make it difficult to detect oil spills on the sea surface in a timely and accurate manner and to determine the oil slick area, resulting in ecological damage that is difficult to repair quickly.
An automatic oil film extraction method based on optical satellite data is adopted. By preprocessing the sea surface image, the oil film is identified by combining the imaging parameters and spectral reflectance with a pre-trained oil film recognition model to determine the oil film area on the sea surface.
It improves the accuracy and efficiency of oil slick identification on the sea surface, enabling timely and accurate detection of oil spills and reducing the long-term impact of ecological damage.
Smart Images

Figure CN118762292B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of machine learning, and in particular to a method and device for automatically extracting sea surface oil film based on optical satellite data. Background Art
[0002] The oil film on the sea surface is an important object of marine environmental monitoring. Marine oil mainly comes from natural leakage of submarine oil and gas reservoirs and various oil spills in human activities. In an oil spill, the soluble compounds in the oil will dissolve in the seawater and form a suspended substance similar to a mousse layer under the water surface, and then form a thick residue on the seabed, which will have a long-term and serious negative impact on marine life and the marine environment. Even if the floating oil on the sea surface is eventually cleaned up, the ecological damage caused by the accident will take a long time to repair, and some damage may even be permanent.
[0003] Therefore, how to timely and accurately detect oil spill accidents on the sea surface and determine the oil film area of the oil spill accident on the sea surface has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention
[0004] The purpose of the present invention is to provide a method and device for automatically extracting sea surface oil film based on optical satellite data, so as to timely and accurately discover oil spill accidents on the sea surface and determine the oil film area of the sea surface oil spill accident.
[0005] In order to achieve the above object, the present invention provides the following technical solutions:
[0006] A method for automatically extracting sea surface oil film based on optical satellite data, comprising:
[0007] Preprocessing a sea surface image of a target sea area to obtain sub-images of the sea surface image, wherein the sea surface image is optical satellite data;
[0008] Using the pre-trained oil film recognition model and combining the imaging parameters of each sub-image, determine the angle between the sensor observation direction and the mirror reflection direction of the solar incident light when each sub-image is imaged; according to the pixel radiance, Rayleigh scattering radiance, solar zenith angle and solar incident irradiance of each sub-image, determine the spectral reflectance of the sub-image;
[0009] and performing oil film recognition on the sub-images according to the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectivity, and determining the oil film image in the sub-images;
[0010] The oil film area in the target sea area is determined according to the oil film image.
[0011] In an optional implementation manner of the present application, the preprocessing of the sea surface image of the target sea area to obtain each sub-image of the sea surface image includes:
[0012] Performing radiation calibration and Rayleigh correction processing on the first image of the target sea area to obtain a Rayleigh corrected reflectivity image of the target sea area;
[0013] According to the geographic information of the target sea area, performing land pixel masking on the Rayleigh corrected reflectivity image to obtain a sea surface image of the target sea area;
[0014] The sea surface image is segmented by sliding window to obtain sub-images of the sea surface image.
[0015] In an optional implementation manner of the present application, each of the sub-images includes a candidate oil film region;
[0016] The step of performing oil film recognition on the sub-image to determine the oil film image in the sub-image includes:
[0017] Oil film recognition is performed on the candidate oil film regions in the sub-image to determine the oil film regions in the candidate oil film regions.
[0018] In an optional implementation manner of the present application, the determining the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged by combining the imaging parameters of each sub-image includes:
[0019] Acquire the sensor zenith angle, solar zenith angle and relative azimuth angle between the observation satellite and the sun corresponding to the sub-image;
[0020] The angle between the sensor observation direction and the mirror reflection direction of the incident solar light when the sub-image is formed is determined according to the sensor zenith angle, the solar zenith angle and the relative azimuth angle between the observation satellite and the sun.
[0021] In an optional implementation manner of the present application, the spectral reflectance of the sub-image is obtained by the following formula:
[0022] ;
[0023] in, represents the spectral reflectance; Represents pixel radiance; represents the Rayleigh scattering radiance; represents the solar incident irradiance; represents the solar zenith angle.
[0024] In an optional implementation of the present application, it also includes:
[0025] Preprocessing the sample sea surface image to obtain each sample sub-image of the sample sea surface image, wherein the sample sub-image is an oil film image;
[0026] Determine, in combination with imaging parameters of each of the sample sub-images, a sample angle between a sensor observation direction and a mirror reflection direction of incident sunlight when each of the sample sub-images is imaged;
[0027] Determining the sample spectral reflectance of the sample sub-image according to the sample pixel radiance, the sample Rayleigh scattering radiance, the sample solar zenith angle and the sample solar incident irradiance of each of the sample sub-images;
[0028] Determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance;
[0029] The sample sub-image and the oil film properties are used as training samples to train a pre-built oil film recognition model.
[0030] In an optional implementation manner of the present application, determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance includes:
[0031] Determining whether the sample angle is greater than a preset angle, and determining whether the sample spectral reflectance is greater than the background seawater reflectance;
[0032] When the sample angle is less than or equal to the preset angle and the sample spectral reflectance is greater than the background seawater reflectance, determining that the oil film attribute of the sample sub-image is a positive brightness contrast characteristic oil film;
[0033] When the sample angle is greater than the preset angle and the sample spectral reflectance is less than the background seawater reflectance, it is determined that the oil film property of the sample sub-image is a negative brightness contrast characteristic oil film.
[0034] Compared with the prior art, the method for automatic extraction of sea surface oil film based on optical satellite data provided by the present invention utilizes a pre-trained oil film recognition model in combination with the angle between the sensor observation direction and the mirror reflection direction of the incident solar light when imaging each sub-image of the target sea area, as well as the spectral reflectivity, to recognize the oil film on the sub-image, and then determine the oil film area in the target sea area, which is beneficial to improving the accuracy and efficiency of oil film recognition in the target sea area.
[0035] The present invention also provides a device for automatically extracting sea surface oil film based on optical satellite data, comprising:
[0036] A preprocessing unit, used for preprocessing a sea surface image of a target sea area to obtain various sub-images of the sea surface image, wherein the sea surface image is optical satellite data;
[0037] The first model processing unit is used to determine the angle between the sensor observation direction and the mirror reflection direction of the incident solar light when each sub-image is imaged by using the pre-trained oil film recognition model and combining the imaging parameters of each sub-image; and determine the spectral reflectance of each sub-image according to the pixel radiance, Rayleigh scattering radiance, solar zenith angle and incident solar irradiance of each sub-image;
[0038] A second model processing unit is used to identify the oil film on the sub-image according to the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectance, and determine the oil film image in the sub-image;
[0039] The oil film determining unit is used to determine the oil film area in the target sea area according to the oil film image.
[0040] Compared with the prior art, the beneficial effects of the automatic extraction device for sea surface oil film based on optical satellite data provided by the present invention are the same as the beneficial effects of the automatic extraction method for sea surface oil film based on optical satellite data described in the above technical solution, which will not be repeated here.
[0041] The present invention also provides an electronic device, comprising:
[0042] processor;
[0043] a memory for storing instructions executable by the processor;
[0044] The processor is used to execute the above-mentioned method for automatically extracting sea surface oil film based on optical satellite data by running the instructions in the memory.
[0045] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for automatic extraction of sea surface oil film based on optical satellite data described in the above technical solution, and will not be described in detail here.
[0046] The present invention also provides a computer storage medium, in which instructions are stored. When the instructions are executed, the above-mentioned method for automatically extracting sea surface oil film based on optical satellite data is implemented.
[0047] Compared with the prior art, the beneficial effects of the computer storage medium provided by the present invention are the same as the beneficial effects of the method for automatic extraction of sea surface oil film based on optical satellite data described in the above technical solution, and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0049] Figure 1 A flow chart of a method for automatically extracting sea surface oil film based on optical satellite data provided in an embodiment of the present application;
[0050] Figure 2 A training flow chart of the oil film recognition model provided in the embodiment of the present application;
[0051] Figure 3 A structural diagram of an automatic extraction device for sea surface oil film based on optical satellite data provided in an embodiment of the present application;
[0052] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0053] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and their order is not limited. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.
[0054] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0055] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.
[0056] The oil film on the sea surface is an important object of marine environmental monitoring. Marine oil mainly comes from natural leakage of submarine oil and gas reservoirs and various oil spills in human activities. In an oil spill, the soluble compounds in the oil will dissolve in the seawater and form a suspended substance similar to a mousse layer under the water surface, and then form a thick residue on the seabed, which will have a long-term and serious negative impact on marine life and the marine environment. Even if the floating oil on the sea surface is eventually cleaned up, the ecological damage caused by the accident will take a long time to repair, and some damage may even be permanent.
[0057] Therefore, how to timely and accurately detect oil spill accidents on the sea surface and determine the oil film area of the oil spill accident on the sea surface has become a technical problem that technical personnel in this field urgently need to solve.
[0058] In order to solve the above technical problems, the present application provides a method and device for automatic extraction of sea surface oil film based on optical satellite data, which are described in detail one by one in the following embodiments.
[0059] The present application embodiment first provides a method for automatically extracting sea surface oil film based on optical satellite data. Figure 1 , Figure 1 A flow chart of a method for automatically extracting sea surface oil film based on optical satellite data provided in an embodiment of the present application.
[0060] like Figure 1 As shown, the method for automatically extracting sea surface oil film based on optical satellite data includes the following S101 to S104:
[0061] S101, preprocessing a sea surface image of a target sea area to obtain sub-images of the sea surface image, wherein the sea surface image is optical satellite data.
[0062] In the embodiment of the present application, the sea surface image of the target sea area is obtained by conducting ocean observation of the target sea area through optical remote sensing technology. In recent years, theoretical and practical breakthroughs in optical remote sensing have made it play an increasingly important role in marine environmental monitoring. Compared with microwave radar monitoring, optical remote sensing has the advantages of rich data sources, large width, and low acquisition cost, which can largely make up for the lack of effective images caused by clouds and fog.
[0063] In actual application, ocean observation of the target sea area can be achieved through the Haiyang-1C / D satellite (HY-1C / D), equipped with a Coastal Zone Imager (CZI) for oil film monitoring.
[0064] Specifically, the above S101 includes:
[0065] The first image of the target sea area is subjected to radiation calibration and Rayleigh correction processing to obtain a Rayleigh-corrected reflectance image of the target sea area; according to the geographic information of the target sea area, the Rayleigh-corrected reflectance image is subjected to land pixel masking to obtain a sea surface image of the target sea area; the sea surface image is subjected to sliding window segmentation to obtain various sub-images of the sea surface image.
[0066] Among them, the first image of the target sea area can be understood as the original image of the target sea area collected by optical remote sensing technology, and radiation calibration refers to the process of converting digital numbers (DN) in the first image into physical units, usually radiant brightness or radiant illumination; Rayleigh correction is a part of atmospheric correction, which is used to remove the contribution of Rayleigh scattering from the pixel radiance to obtain a value closer to the actual reflectivity of the surface.
[0067] After performing radiation correction and Rayleigh correction on the first image, the land pixels of the first image can be masked according to the geographical location of the picture taken by the first image, thereby achieving land and sea separation, and finally retaining only the sea surface area in the first image as the sea surface image.
[0068] Sliding window segmentation is an image processing technology that uses a fixed-size window to slide on the sea surface image and processes the image in the window to obtain the sub-image. The size of the window can be set according to the detection requirements, and the moving step size of the window (the number of pixels in the horizontal or vertical direction) can be fixed or variable, and this application does not impose any restrictions on this.
[0069] In the embodiment of the present application, the automatic extraction of sea surface oil film based on optical satellite data is actually to identify whether each sub-image contains an oil film area. In the actual application process, in order to improve the recognition accuracy of the oil film area, the sub-image can also be firstly identified as a candidate oil film area to determine the sub-image containing the candidate oil film area, and then the sub-image containing the candidate oil film area can be further identified as an oil film area to determine whether the candidate oil film area is an oil film area. Specifically, the identification of the candidate oil film area of the sub-image can be determined by the relevant staff through work experience.
[0070] S102, using a pre-trained oil film recognition model and combining the imaging parameters of each of the sub-images, determine the angle between the sensor observation direction and the mirror reflection direction of the solar incident light when each of the sub-images is imaged; and determine the spectral reflectance of the sub-image based on the pixel radiance, Rayleigh scattering radiance, solar zenith angle and solar incident irradiance of each of the sub-images.
[0071] The oil film identification model can be understood as a machine learning model. Machine learning (a multi-disciplinary interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines) is specifically used to study how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning usually includes artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning and other technologies. Machine learning is a branch of artificial intelligence (AI) technology.
[0072] The step of determining the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged by combining the imaging parameters of the sub-images comprises:
[0073] The sensor zenith angle, solar zenith angle and relative azimuth angle between the observation satellite and the sun corresponding to the sub-image are obtained; and the angle between the sensor observation direction and the mirror reflection direction of the incident solar light when the sub-image is imaged is determined according to the sensor zenith angle, solar zenith angle and relative azimuth angle between the observation satellite and the sun.
[0074] Specifically, the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight during the imaging of the sub-image can be determined by the following formula (1):
[0075] (1);
[0076] in, represents the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when the sub-image is formed; represents the solar zenith angle; represents the sensor zenith angle; Indicates the relative azimuth angle between the observation satellite and the sun.
[0077] Furthermore, the sub-image spectral reflectance can be understood as the ratio of the radiation reflected by the sea surface to the total radiation incident on the sea surface under the same conditions, so as to describe the reflection characteristics of light of different wavelengths.
[0078] The sub-image spectral reflectance can be determined by the following formula (2):
[0079] (2);
[0080] in, represents the spectral reflectance; Represents pixel radiance; represents the Rayleigh scattering radiance; represents the solar incident irradiance; represents the solar zenith angle.
[0081] S103, performing oil film recognition on the sub-image according to the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectivity, and determining the oil film image in the sub-image.
[0082] The above S103 means that the oil film recognition model trained in advance is used to identify the oil film on the sub-image in combination with the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectivity, thereby determining the oil film image in the sub-image.
[0083] Specifically, when the sub-image input to the oil film recognition model includes the candidate oil film area, performing oil film recognition on the sub-image is actually performing oil film recognition on the candidate oil film area in the sub-image, and determining the oil film area in the candidate oil film area; when the sub-image input to the oil film recognition model does not include the candidate oil film area, performing oil film recognition on the sub-image is actually performing oil film recognition on the sub-image itself, determining whether there is an oil film in the sub-image, and using the sub-image with oil film as the oil film image.
[0084] Specifically, in an optional implementation of the present application, the oil film recognition model can be a YOLO (You Only Look Once) deep learning network model. YOLO uses a single deep convolutional neural network for target detection, divides the sub-image into a grid, and each grid unit is responsible for detecting the category appearing in the grid unit and outputting the category probability.
[0085] In an embodiment of the present application, the category probability is specifically the probability of the existence of an oil film in the sub-image. When the sub-image includes a candidate oil film area, the category probability is specifically the probability that the candidate oil film area is an oil film area. When the probability of the existence of an oil film in the sub-image output by the oil film recognition model or the probability that the candidate oil film area in the sub-image is an oil film area is greater than a preset probability threshold, the sub-image is considered to be an oil film image, or the candidate oil film area is considered to be an oil film area.
[0086] Furthermore, in order to facilitate understanding of the process of the oil film recognition model in the above steps S102 and S103 performing oil film recognition on the sub-image, the following describes it in detail in conjunction with the training of the oil film recognition model.
[0087] Please refer to Figure 2 , Figure 2 The training flow chart of the oil film recognition model provided in the embodiment of the present application is as follows: Figure 2 As shown, the training of the oil film recognition model includes: first, preprocessing the sample sea surface image; second, extracting the oil film properties of each sample sub-image of the sample sea surface image, the oil film properties including positive brightness contrast characteristic oil film and negative brightness contrast characteristic oil film; finally, using the oil film properties and the sample sub-image as training samples to train the oil film recognition model.
[0088] Specifically, the training of the oil film recognition model includes the following S1 to S5:
[0089] S1, preprocessing a sample sea surface image to obtain each sample sub-image of the sample sea surface image, wherein the sample sub-image is an oil film image.
[0090] The sample sea surface image can be understood as a sea surface image of any sea area collected by optical remote sensing technology. The process of preprocessing the sample sea surface image is similar to the preprocessing process of the sea surface image of the target sea area in the above S101. The relevant parts can be referred to the introduction of S101, which will not be repeated here.
[0091] S2, combining the imaging parameters of each of the sample sub-images, determining a sample angle between the sensor observation direction and the mirror reflection direction of the incident solar light when each of the sample sub-images is imaged.
[0092] The calculation of the sample angle between the sensor observation direction and the mirror reflection direction of the incident solar light when each sample sub-image is imaged can be obtained by using the formula (1) in S102. For relevant details, please refer to the introduction of formula (1) above and no further details will be given here.
[0093] S3, determining the sample spectral reflectance of the sample sub-image according to the sample pixel radiance, the sample Rayleigh scattering radiance, the sample solar zenith angle and the sample solar incident irradiance of each of the sample sub-images.
[0094] The calculation of the sample spectral reflectance can be obtained by using the formula (2) in the above S102. For relevant details, please refer to the introduction of the formula (2) above, which will not be repeated here.
[0095] S4, determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance.
[0096] The above S4 includes:
[0097] Determine whether the sample angle is greater than a preset angle, and determine whether the sample spectral reflectance is greater than the background seawater reflectance; wherein the preset angle can be set to 13°.
[0098] When the sample angle is less than or equal to the preset angle and the sample spectral reflectance is greater than the background seawater reflectance, determining that the oil film attribute of the sample sub-image is a positive brightness contrast characteristic oil film;
[0099] When the sample angle is greater than the preset angle and the sample spectral reflectance is less than the background seawater reflectance, it is determined that the oil film property of the sample sub-image is a negative brightness contrast characteristic oil film.
[0100] S5, using the sample sub-image and the oil film attribute as training samples to train a pre-built oil film recognition model.
[0101] After obtaining the oil film properties of the sample sub-image, the oil film properties are used as labels of the sample sub-image, and the sample sub-image and the oil film properties are input into the oil film recognition model for training, thereby obtaining the prediction weights corresponding to each level of the oil film recognition model, so that the oil film recognition model can perform oil film recognition based on the prediction weights.
[0102] S104: Determine the oil film area in the target sea area according to the oil film image.
[0103] The above S104 means that after the oil film images are determined from the sub-images, the oil film images are spliced to further determine the oil film area in the target sea area.
[0104] In an optional implementation manner of the present application, when the sub-image includes a candidate oil film area, determining the oil film area in the target sea area according to the oil film image includes:
[0105] The oil film area in the target sea area is determined according to the oil film areas in the candidate oil film areas, that is, the oil film areas in the candidate oil film areas are spliced to obtain the oil film area in the target sea area.
[0106] In summary, the method for automatic extraction of sea surface oil film based on optical satellite data provided in the embodiment of the present application utilizes a pre-trained oil film recognition model in combination with the angle between the sensor observation direction and the mirror reflection direction of the incident solar light when imaging each sub-image of the target sea area, as well as the spectral reflectivity, to perform oil film recognition on the sub-image, and then determine the oil film area in the target sea area, which is beneficial to improving the accuracy and efficiency of oil film recognition in the target sea area.
[0107] The present application also provides an automatic extraction device for sea surface oil film based on optical satellite data. Figure 3 , Figure 3 Structural diagram of the automatic extraction device of sea surface oil film based on optical satellite data provided in an embodiment of the present application.
[0108] like Figure 3 As shown, the automatic extraction device for sea surface oil film based on optical satellite data includes:
[0109] A preprocessing unit 301 is used to preprocess the sea surface image of the target sea area to obtain each sub-image of the sea surface image, wherein the sea surface image is optical satellite data;
[0110] The first model processing unit 302 is used to determine the angle between the sensor observation direction and the mirror reflection direction of the incident solar light when each of the sub-images is imaged by using the pre-trained oil film recognition model and combining the imaging parameters of each of the sub-images; and determine the spectral reflectance of the sub-image according to the pixel radiance, Rayleigh scattering radiance, solar zenith angle and incident solar irradiance of each of the sub-images;
[0111] The second model processing unit 303 is used to identify the oil film on the sub-image according to the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectance, and determine the oil film image in the sub-image;
[0112] The oil film determining unit 304 is used to determine the oil film area in the target sea area according to the oil film image.
[0113] In an optional implementation manner of the present application, the preprocessing of the sea surface image of the target sea area to obtain each sub-image of the sea surface image includes:
[0114] Performing radiation calibration and Rayleigh correction processing on the first image of the target sea area to obtain a Rayleigh corrected reflectivity image of the target sea area;
[0115] According to the geographic information of the target sea area, performing land pixel masking on the Rayleigh corrected reflectivity image to obtain a sea surface image of the target sea area;
[0116] The sea surface image is segmented by sliding window to obtain sub-images of the sea surface image.
[0117] In an optional implementation manner of the present application, each of the sub-images includes a candidate oil film region;
[0118] The step of performing oil film recognition on the sub-image to determine the oil film image in the sub-image includes:
[0119] Oil film recognition is performed on the candidate oil film regions in the sub-image to determine the oil film regions in the candidate oil film regions.
[0120] In an optional implementation manner of the present application, combining the imaging parameters of each of the sub-images to determine the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each of the sub-images is imaged includes:
[0121] Acquire the sensor zenith angle, solar zenith angle and relative azimuth angle between the observation satellite and the sun corresponding to the sub-image;
[0122] The angle between the sensor observation direction and the mirror reflection direction of the incident solar light when the sub-image is formed is determined according to the sensor zenith angle, the solar zenith angle and the relative azimuth angle between the observation satellite and the sun.
[0123] In an optional implementation manner of the present application, the spectral reflectance of the sub-image is obtained by the following formula:
[0124] ;
[0125] in, represents the spectral reflectance; Represents pixel radiance; represents the Rayleigh scattering radiance; represents the solar incident irradiance; represents the solar zenith angle.
[0126] In an optional embodiment of the present application, the device is also used for:
[0127] Preprocessing the sample sea surface image to obtain each sample sub-image of the sample sea surface image, wherein the sample sub-image is an oil film image;
[0128] Determine, in combination with imaging parameters of each of the sample sub-images, a sample angle between a sensor observation direction and a mirror reflection direction of incident sunlight when each of the sample sub-images is imaged;
[0129] Determining the sample spectral reflectance of the sample sub-image according to the sample pixel radiance, the sample Rayleigh scattering radiance, the sample solar zenith angle and the sample solar incident irradiance of each of the sample sub-images;
[0130] Determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance;
[0131] The sample sub-image and the oil film properties are used as training samples to train a pre-built oil film recognition model.
[0132] In an optional implementation manner of the present application, determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance includes:
[0133] Determining whether the sample angle is greater than a preset angle, and determining whether the sample spectral reflectance is greater than the background seawater reflectance;
[0134] When the sample angle is less than or equal to the preset angle and the sample spectral reflectance is greater than the background seawater reflectance, determining that the oil film attribute of the sample sub-image is a positive brightness contrast characteristic oil film;
[0135] When the sample angle is greater than the preset angle and the sample spectral reflectance is less than the background seawater reflectance, it is determined that the oil film property of the sample sub-image is a negative brightness contrast characteristic oil film.
[0136] The above-mentioned device embodiment provided in this embodiment belongs to the same application concept as the method embodiment of this application, and can execute the automatic extraction method of sea surface oil film based on optical satellite data provided in any of the above-mentioned embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the automatic extraction method of sea surface oil film based on optical satellite data. For technical details not fully described in this embodiment, please refer to the specific processing content of the automatic extraction method of sea surface oil film based on optical satellite data provided in the above-mentioned embodiments of this application, which will not be repeated here.
[0137] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.
[0138] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.
[0139] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
[0140] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.
[0141] The present application also provides an electronic device, such as Figure 4 As shown, Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0142] like Figure 4 As shown, the electronic device comprises:
[0143] Processor 210;
[0144] A memory 200 for storing instructions executable by the processor 210;
[0145] The processor 210 is used to execute the method for automatically extracting sea surface oil film based on optical satellite data disclosed in any of the above embodiments by running the instructions in the memory 200.
[0146] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.
[0147] A bus may include a pathway that transfers information between components of a computer system.
[0148] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0149] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.
[0150] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.
[0151] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a touch screen, etc.
[0152] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.
[0153] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.
[0154] The processor 210 executes the program stored in the memory 200 and calls other devices, and can be used to implement each step of any one of the methods for automatic extraction of sea surface oil film based on optical satellite data provided in the above embodiments of the present application.
[0155] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for automatic extraction of sea surface oil film based on optical satellite data in various embodiments of the present application.
[0156] The computer program product may be written in any combination of one or more programming languages to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0157] In addition, the embodiments of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the method for automatic extraction of sea surface oil film based on optical satellite data in various embodiments of the present application.
[0158] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, 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 present application.
[0159] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0160] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.
[0161] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.
[0162] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.
[0163] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0164] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.
[0165] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0166] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0167] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0168] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for automatic extraction of sea surface oil film based on optical satellite data, It is characterized in that include: Preprocessing a sea surface image of a target sea area to obtain sub-images of the sea surface image, wherein the sea surface image is optical satellite data; Using the pre-trained oil film recognition model and combining the imaging parameters of each sub-image, determine the angle between the sensor observation direction and the mirror reflection direction of the solar incident light when each sub-image is imaged; according to the pixel radiance, Rayleigh scattering radiance, solar zenith angle and solar incident irradiance of each sub-image, determine the spectral reflectance of the sub-image; and, according to the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectance, performing oil film recognition on the sub-image to determine the oil film image in the sub-image; The oil film area in the target sea area is determined according to the oil film image.
2. The method for automatically extracting sea surface oil film based on optical satellite data according to claim 1, It is characterized in that The preprocessing of the sea surface image of the target sea area to obtain each sub-image of the sea surface image includes: Performing radiation calibration and Rayleigh correction processing on the first image of the target sea area to obtain a Rayleigh corrected reflectivity image of the target sea area; According to the geographic information of the target sea area, performing land pixel masking on the Rayleigh corrected reflectivity image to obtain a sea surface image of the target sea area; The sea surface image is segmented by sliding window to obtain sub-images of the sea surface image.
3. The method for automatically extracting sea surface oil film based on optical satellite data according to claim 1, It is characterized in that Each of the sub-images includes a candidate oil film area; The step of performing oil film recognition on the sub-image to determine the oil film image in the sub-image includes: Oil film recognition is performed on the candidate oil film regions in the sub-image to determine the oil film regions in the candidate oil film regions.
4. The method for automatically extracting sea surface oil film based on optical satellite data according to claim 1, It is characterized in that The step of determining the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged by combining the imaging parameters of each sub-image comprises: Acquire the sensor zenith angle, solar zenith angle and relative azimuth angle between the observation satellite and the sun corresponding to the sub-image; The angle between the sensor observation direction and the mirror reflection direction of the incident solar light when the sub-image is formed is determined according to the sensor zenith angle, the solar zenith angle and the relative azimuth angle between the observation satellite and the sun.
5. The method for automatically extracting sea surface oil film based on optical satellite data according to claim 1, It is characterized in that The spectral reflectance of the sub-image is obtained by the following formula: ; in, represents the spectral reflectance; Represents pixel radiance; represents the Rayleigh scattering radiance; represents the solar incident irradiance; represents the solar zenith angle.
6. The method for automatically extracting sea surface oil film based on optical satellite data according to claim 1, It is characterized in that Also includes: Preprocessing the sample sea surface image to obtain each sample sub-image of the sample sea surface image, wherein the sample sub-image is an oil film image; Determine, in combination with imaging parameters of each of the sample sub-images, a sample angle between a sensor observation direction and a mirror reflection direction of incident sunlight when each of the sample sub-images is imaged; Determining the sample spectral reflectance of the sample sub-image according to the sample pixel radiance, the sample Rayleigh scattering radiance, the sample solar zenith angle and the sample solar incident irradiance of each of the sample sub-images; Determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance; The sample sub-image and the oil film properties are used as training samples to train a pre-built oil film recognition model.
7. The method for automatically extracting sea surface oil film based on optical satellite data according to claim 6, It is characterized in that The step of determining the oil film property of the sample sub-image according to the sample angle and the sample spectral reflectance includes: Determining whether the sample angle is greater than a preset angle, and determining whether the sample spectral reflectance is greater than the background seawater reflectance; When the sample angle is less than or equal to the preset angle and the sample spectral reflectance is greater than the background seawater reflectance, determining that the oil film attribute of the sample sub-image is a positive brightness contrast characteristic oil film; When the sample angle is greater than the preset angle and the sample spectral reflectance is less than the background seawater reflectance, it is determined that the oil film property of the sample sub-image is a negative brightness contrast characteristic oil film.
8. An automatic extraction device for sea surface oil film based on optical satellite data, It is characterized in that include: A preprocessing unit, used for preprocessing a sea surface image of a target sea area to obtain various sub-images of the sea surface image, wherein the sea surface image is optical satellite data; The first model processing unit is used to determine the angle between the sensor observation direction and the mirror reflection direction of the incident solar light when each sub-image is imaged by using the pre-trained oil film recognition model and combining the imaging parameters of each sub-image; and determine the spectral reflectance of each sub-image according to the pixel radiance, Rayleigh scattering radiance, solar zenith angle and incident solar irradiance of each sub-image; A second model processing unit is used to identify the oil film on the sub-image according to the angle between the sensor observation direction and the mirror reflection direction of the incident sunlight when each sub-image is imaged and the spectral reflectance, and determine the oil film image in the sub-image; The oil film determining unit is used to determine the oil film area in the target sea area according to the oil film image.
9. An electronic device, It is characterized in that include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the method for automatically extracting sea surface oil film based on optical satellite data as described in any one of claims 1 to 7 by running the instructions in the memory.
10. A computer storage medium, It is characterized in that The computer storage medium stores instructions, and when the instructions are executed, the method for automatic extraction of sea surface oil film based on optical satellite data as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Buoyage for tracking and locating spilled oil
CN101407249A
Marine oil overflow air slaking simulation system
CN101551321A
Oil film detector and oil film detection method
JP2007147448A
Oil film detection system and oil film detection method
JP2018169341A
KR20190133442A
