Carbon emission source rapid identification method based on satellite remote sensing and artificial intelligence

Abstract

The invention discloses a carbon emission source rapid identification method based on satellite remote sensing and artificial intelligence. The method comprises the following steps: acquiring a satellite remote sensing image of a carbon emission source; segmenting the satellite remote sensing image by using a K-means algorithm to obtain a segmented image; constructing a convolutional neural network model, and training the convolutional neural network model by using the segmented image; and an intelligent identification library of the carbon emission source is established. Therefore, the carbon emission source of the target position on the ground can be accurately and quickly identified, and the carbon emission management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission source identification, and in particular to a method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence. Background Art

[0002] As the global climate change problem becomes increasingly serious, reducing carbon emissions has become the common responsibility of the international community. Accurately identifying carbon emission sources is a prerequisite for formulating emission reduction policies and taking emission reduction measures. Traditional carbon emission source identification methods mainly rely on ground monitoring and statistical data. These methods have problems such as limited monitoring range and untimely data updates, and it is difficult to meet the needs of rapid and accurate identification of carbon emission sources. Satellite remote sensing technology has the advantages of wide coverage, high monitoring frequency, and fast data acquisition. It has been widely used in environmental monitoring, resource survey and other fields. Artificial intelligence technology has achieved remarkable results in image recognition, speech recognition, natural language processing and other aspects. Combining satellite remote sensing technology with artificial intelligence technology for rapid identification of carbon emission sources has important practical significance. Summary of the invention

[0003] The purpose of this application is to provide a method for quickly identifying carbon emission sources based on satellite remote sensing and artificial intelligence, which can quickly and accurately identify carbon emission sources within a target range.

[0004] To achieve the above objectives:

[0005] In a first aspect, an embodiment of the present application provides a method for quickly identifying carbon emission sources based on satellite remote sensing and artificial intelligence, the method comprising:

[0006] Obtain satellite remote sensing images of carbon emission sources;

[0007] Segmenting the satellite remote sensing image using a K-means algorithm to obtain a segmented image;

[0008] Constructing a convolutional neural network model, and training the convolutional neural network model using the segmented image;

[0009] Establish an intelligent identification database for carbon emission sources.

[0010] In one embodiment, the segmenting of the remote sensing image using the K-means algorithm before obtaining the segmented image includes:

[0011] The satellite remote sensing image is subjected to geometric correction, light and color uniformity, and mosaicking.

[0012] In one embodiment, segmenting the satellite remote sensing image using a K-means algorithm to obtain a segmented image includes:

[0013] Randomly obtain K points from the satellite remote sensing image as the first cluster center, and perform first pixel allocation on the satellite remote sensing image according to the principle of being closest to the initial cluster center;

[0014] Calculating a second cluster center according to the first pixel allocation result, and performing a second pixel allocation on the satellite remote sensing image again based on the second cluster center;

[0015] Calculating a third cluster center according to the second pixel allocation result;

[0016] When the variation range of the position of the third cluster center does not exceed a preset range, a corresponding cluster label is allocated to each pixel according to the second pixel allocation result, and a segmented image is generated based on the cluster label.

[0017] In one embodiment, the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence further includes: calculating the distance from the satellite remote sensing image to the first cluster center by the following formula:

[0018] d ij =||x i -c j ||2;

[0019] Calculate the average value of all data points in each cluster as the new cluster center. The formula is as follows:

[0020]

[0021] Among them, c j is the first cluster center, x i is the satellite remote sensing image, d ij is the distance from the satellite remote sensing image to the first cluster center, c' j is the new cluster center, For clustering The number of satellite remote sensing images in the

[0022] In one embodiment, the using the segmented image to train the convolutional neural network model includes:

[0023] The component is based on a semantic tag library, which manually interprets the carbon emission source information and normalizes it into a pixel-level tag library to support the intelligent and automated interpretation of carbon emission sources based on artificial intelligence algorithms.

[0024] In one embodiment, the step of establishing an intelligent identification library of carbon emission sources includes:

[0025] A training data sample set is established through labeled source domain images and unlabeled target domain images, and the carbon emission sources in the satellite remote sensing images are intelligently identified through the data in the sample set.

[0026] In a second aspect, the embodiment of the present application provides a device for quickly identifying carbon emission sources based on satellite remote sensing and artificial intelligence, which is characterized by comprising:

[0027] An acquisition module, used to acquire satellite remote sensing images of carbon emission sources;

[0028] A segmentation module, used to segment the satellite remote sensing image using a K-means algorithm to obtain a segmented image;

[0029] A training module, used to construct a convolutional neural network model, and train the convolutional neural network model using the segmented image;

[0030] Establish a module for building an intelligent identification library of carbon emission sources.

[0031] In one embodiment, the device further comprises a preprocessing module for performing geometric correction, light and color uniformity, and mosaicking on the satellite remote sensing image.

[0032] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor;

[0033] a memory for storing instructions executable by the processor;

[0034] In which, the processor is configured to execute the instructions to implement the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence as described in any one of the first aspects.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor, a method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence as described in any one of the first aspects is implemented.

[0036] The embodiments of the present application provide a method, device, electronic device and computer storage medium for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence. The method includes: obtaining satellite remote sensing images of carbon emission sources; segmenting the satellite remote sensing images using the K-means algorithm to obtain segmented images; constructing a convolutional neural network model, and training the convolutional neural network model using the segmented images; and establishing an intelligent identification library for carbon emission sources. The embodiments of the present application provide a method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence. The satellite remote sensing images of carbon emission sources are segmented using the K-means algorithm, and the convolutional neural network model is trained using the segmented images to identify carbon emission sources, and an intelligent identification library for carbon emission sources is established. In this way, carbon emission sources within the target range can be identified quickly and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a process for rapidly identifying carbon emission sources based on satellite remote sensing and artificial intelligence provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of the structure of a device for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0041] It should be noted that, in this article, the terms "include", "comprises" 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 includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0042] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these 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 this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of..." or "when..." or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising", "including" indicate the presence of the described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the presence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Thus, “A, B, or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will occur only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0043] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0044] It should be noted that in this article, step codes such as S1 and S2 are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the order. When implementing the step, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the scope of protection of this application.

[0045] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0047] See also Figure 1 , which is a flow chart of a method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence provided in an embodiment of the present application. The method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence can be executed by an electronic device provided in an embodiment of the present application. The electronic device can be implemented in software and / or hardware, such as a server or other electronic device. In this embodiment, the execution subject of the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence is a server as an example. The method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence provided in this embodiment includes:

[0048] Step S1, obtaining satellite remote sensing images of carbon emission sources.

[0049] Here, the satellite remote sensing images of carbon emission sources may come from some commercial satellite data providers or academic databases, etc., and are not specifically limited here.

[0050] Step S2, using the K-means algorithm to segment the satellite remote sensing image to obtain a segmented image.

[0051] It can be understood that the K-Means algorithm is a simple and efficient clustering algorithm with relatively low computational complexity, and can quickly process large-scale satellite remote sensing image data. And the segmented images can be further used for target detection, classification, change monitoring and other tasks, thus providing a basis for the identification and monitoring of carbon emission sources.

[0052] Optionally, the segmenting of the remote sensing image by using the K-means algorithm, before obtaining the segmented image, includes: performing geometric correction, light and color uniformity, and mosaicking on the satellite remote sensing image.

[0053] Understandably, satellite remote sensing images may be affected by a variety of factors during the acquisition process, resulting in geometric deformation of the image, such as terrain undulations, sensor attitude changes, etc. Geometric correction can eliminate these deformations, match the image with the actual geographic coordinate system, and ensure the accuracy and availability of the image. In addition, through geometric correction, the pixels in the image can be accurately mapped to the geographic space, improving the spatial position accuracy of the image, and facilitating subsequent quantitative analysis and measurement. When processing multiple satellite remote sensing images, geometric correction can ensure the geometric consistency between images, facilitate image stitching and fusion, and generate images with a larger range or higher resolution. Through uniform light and color, the contrast, clarity and color fidelity of the image can be improved, the quality of the image can be improved, and the image can more accurately reflect the characteristics and information of the ground object. Before the image is segmented, the uniform light and color processing can reduce the errors caused by illumination and color differences and improve the accuracy of the analysis results. Through mosaic processing, the transition between adjacent images can be ensured to be natural, avoid obvious stitching marks, maintain the continuity and integrity of the image, and the panoramic image obtained through mosaic processing is convenient for comprehensive analysis and monitoring of large areas, such as environmental change monitoring and resource surveys. Simply put, by performing geometric correction, light and color saturation, and mosaicking on satellite remote sensing images, the quality, accuracy, and availability of satellite remote sensing images can be improved, providing a better foundation for subsequent image analysis, interpretation, and application.

[0054] In one embodiment, segmenting the satellite remote sensing image using a K-means algorithm to obtain a segmented image includes:

[0055] Randomly obtain K points from the satellite remote sensing image as the first cluster center, and perform first pixel allocation on the satellite remote sensing image according to the principle of being closest to the initial cluster center;

[0056] Calculating a second cluster center according to the first pixel allocation result, and performing a second pixel allocation on the satellite remote sensing image again based on the second cluster center;

[0057] Calculating a third cluster center according to the second pixel allocation result;

[0058] When the variation range of the position of the third cluster center does not exceed a preset range, a corresponding cluster label is allocated to each pixel according to the second pixel allocation result, and a segmented image is generated based on the cluster label.

[0059] Here, if the change in the position of the third cluster center exceeds the preset range, the satellite remote sensing image is continuously allocated pixels based on the third cluster center until the position fluctuation of the obtained cluster center is within the preset range before the iteration is stopped. By continuously iteratively updating the cluster center and allocating pixels, the data is eventually divided into K clusters, so that the outliers in the satellite remote sensing image can be accurately identified, thereby improving the efficiency and accuracy of carbon emission source identification.

[0060] In one embodiment, the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence further includes: calculating the distance from the satellite remote sensing image to the first cluster center by the following formula:

[0061] d ij =||x i -c j ||2;

[0062] Calculate the average value of all data points in each cluster as the new cluster center. The formula is as follows:

[0063]

[0064] Among them, c j is the first cluster center, x i is the satellite remote sensing image, d ij is the distance from the satellite remote sensing image to the first cluster center, c' j is the new cluster center, For clustering The number of satellite remote sensing images in the

[0065] Step S3, constructing a convolutional neural network model, and using the segmented image to train the convolutional neural network model.

[0066] In one embodiment, the use of the segmented image to train the convolutional neural network model includes: constructing a semantic-based label library, manually interpreting carbon emission source information, and normalizing it into a pixel-level label library to support intelligent and automated interpretation of carbon emission sources based on artificial intelligence algorithms.

[0067] Here, labels can be used to obtain information such as the characteristics, type, and location of carbon emission sources. By manually observing and analyzing satellite remote sensing images, carbon emission sources in the images are identified and associated with corresponding semantic labels, which can accurately determine the type and location of carbon emission sources. The normalized pixel-level label library is used as training data to train models based on artificial intelligence algorithms to achieve intelligent and automated interpretation of carbon emission sources. These algorithms can learn the relationship between labels and image features, and automatically identify and classify carbon emission sources on new images.

[0068] In one embodiment, the step of establishing an intelligent identification library of carbon emission sources includes:

[0069] A training data sample set is established through labeled source domain images and unlabeled target domain images, and the carbon emission sources in the satellite remote sensing images are intelligently identified through the data in the sample set.

[0070] It can be understood that the transfer learning method is used here to combine the image data of the source domain and the target domain to establish a training sample set, and use the sample set to intelligently identify carbon emission sources in satellite remote sensing images. This method can improve the recognition efficiency and accuracy.

[0071] The method for quickly identifying carbon emission sources based on satellite remote sensing and artificial intelligence provided in the embodiment of the present application uses the K-means algorithm to segment satellite remote sensing images of carbon emission sources, uses the segmented images to train a convolutional neural network model to identify carbon emission sources, and establishes an intelligent identification library for carbon emission sources. In this way, carbon emission sources within the target range can be quickly and accurately identified.

[0072] Based on the same inventive concept as the above embodiments, the present application embodiment provides a device for quickly identifying carbon emission sources based on satellite remote sensing and artificial intelligence, such as Figure 2 As shown, the device comprises:

[0073] An acquisition module, used to acquire satellite remote sensing images of carbon emission sources;

[0074] A segmentation module, used to segment the satellite remote sensing image using a K-means algorithm to obtain a segmented image;

[0075] A training module, used to construct a convolutional neural network model, and train the convolutional neural network model using the segmented image;

[0076] Establish a module for building an intelligent identification library of carbon emission sources.

[0077] In one embodiment, the device further comprises:

[0078] The preprocessing module is used to perform geometric correction, light and color uniformity, and mosaicking on the satellite remote sensing image.

[0079] For the specific definition of the carbon emission source rapid identification device based on satellite remote sensing and artificial intelligence, please refer to the definition of the data transmission method above, which will not be repeated here. Each module in the above-mentioned data transmission device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor of the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0080] Based on the same inventive concept as the above embodiments, an embodiment of the present invention provides an electronic device, such as Figure 3 As shown, the electronic device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 3 The processor 310 shown in the figure is not used to indicate that the number of the processor 310 is one, but is only used to indicate the positional relationship of the processor 310 relative to other devices. In actual applications, the number of the processor 310 may be one or more; similarly, Figure 3 The memory 311 shown in the figure has the same meaning, that is, it is only used to refer to the position relationship of the memory 311 relative to other devices. In practical applications, the number of memories 311 can be one or more. When the processor 310 runs the computer program, the above-mentioned method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence is implemented.

[0081] The electronic device may also include: at least one network interface 312. The various components in the electronic device are coupled together via a bus system 313. It is understood that the bus system 313 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 313 is not used in the following examples. Figure 3 Various buses are labeled as bus system 313.

[0082] The memory 311 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. The nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), direct memory bus random access memory (DRRAM). The memory 311 described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable types of memory.

[0083] The memory 311 in the embodiment of the present invention is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer program used to operate on the electronic device.

[0084] Based on the same inventive concept as the above-mentioned embodiment, this embodiment further provides a computer-readable storage medium, in which a computer program is stored. The computer-readable storage medium may be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); or various devices including one or any combination of the above-mentioned memories, such as a server. When the instructions stored therein are executed by a processor, the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence described in the above-mentioned embodiment is implemented.

[0085] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0086] In this document, the terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than those listed and may also include additional elements not expressly listed.

[0087] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence, characterized in that: include: Obtain satellite remote sensing images of carbon emission sources; Segmenting the satellite remote sensing image using a K-means algorithm to obtain a segmented image; Constructing a convolutional neural network model, and training the convolutional neural network model using the segmented image; Establish an intelligent identification database for carbon emission sources.

2. The method according to claim 1, characterized in that The step of segmenting the remote sensing image using the K-means algorithm to obtain the segmented image includes: The satellite remote sensing image is subjected to geometric correction, light and color uniformity, and mosaicking.

3. The method according to claim 1, characterized in that The step of segmenting the satellite remote sensing image using the K-means algorithm to obtain a segmented image includes: Randomly obtain K points from the satellite remote sensing image as the first cluster center, and perform first pixel allocation on the satellite remote sensing image according to the principle of being closest to the initial cluster center; Calculating a second cluster center according to the first pixel allocation result, and performing a second pixel allocation on the satellite remote sensing image again based on the second cluster center; Calculating a third cluster center according to the second pixel allocation result; When the variation range of the position of the third cluster center does not exceed a preset range, a corresponding cluster label is allocated to each pixel according to the second pixel allocation result, and a segmented image is generated based on the cluster label.

4. The method according to claim 3, characterized in that Also includes: The distance from the satellite remote sensing image to the first cluster center is calculated by the following formula: d ij =||x i -c j ||2; Calculate the average value of all data points in each cluster as the new cluster center. The formula is as follows: Among them, c j is the first cluster center, x i is the satellite remote sensing image, d ij is the distance from the satellite remote sensing image to the first cluster center, c' j is the new cluster center, For clustering The number of satellite remote sensing images in the 5. The method according to claim 1, characterized in that The using the segmented image to train the convolutional neural network model comprises: The component is based on a semantic tag library, which manually interprets the carbon emission source information and normalizes it into a pixel-level tag library to support the intelligent and automated interpretation of carbon emission sources based on artificial intelligence algorithms.

6. The method according to claim 5, characterized in that The establishment of an intelligent identification library for carbon emission sources includes: A training data sample set is established through labeled source domain images and unlabeled target domain images, and the carbon emission sources in the satellite remote sensing images are intelligently identified through the data in the sample set.

7. A device for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence, characterized in that: include: An acquisition module, used to acquire satellite remote sensing images of carbon emission sources; A segmentation module, used to segment the satellite remote sensing image using a K-means algorithm to obtain a segmented image; A training module, used to construct a convolutional neural network model, and train the convolutional neural network model using the segmented image; Establish a module for building an intelligent identification library of carbon emission sources.

8. The device according to claim 7, characterized in that Also includes: The preprocessing module is used to perform geometric correction, light and color uniformity, and mosaicking on the satellite remote sensing image.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor, the method for rapid identification of carbon emission sources based on satellite remote sensing and artificial intelligence as described in any one of claims 1 to 7 is implemented.

Images