Remote sensing image processing method and device supporting expert experience fusion mechanism

Abstract

The invention discloses a remote sensing image processing method and device supporting an expert experience fusion mechanism. The method comprises the following steps: acquiring to-be-processed remote sensing image information; preprocessing the to-be-processed remote sensing image information to obtain target processed remote sensing image information; and analyzing and processing the target processing remote sensing image information to obtain target remote sensing image analysis result information.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a remote sensing image processing method and device supporting an expert experience fusion mechanism. Background Art

[0002] The rapid and accurate identification of ground objects and facilities from satellite remote sensing imagery provides important technical support and regulatory basis for a variety of scenarios, including urban planning and construction, land resources planning and management, land use monitoring, and engineering surveying. However, in practical applications, available, ideal data sources for high-resolution satellite remote sensing imagery are often limited or even absent. Under these conditions, the efficient and comprehensive utilization of satellite optical remote sensing imagery of varying resolutions to identify useful information, achieving "what is available, effective identification, and rapid response," has become a critical issue in improving current remote sensing identification technology. This requires identification algorithms to be more universal across remote sensing imagery from different sensors and at multiple resolutions, a common difficulty faced by current automatic remote sensing information identification algorithms. When using multi-resolution satellite optical remote sensing imagery for ground object identification, the spectral response of the same ground object from different data sources varies due to differences in the spectral response functions of different satellite sensors, increasing the difficulty of identifying information from cross-sensor, multi-resolution remote sensing imagery. Through their efforts, researchers have proposed a wealth of remote sensing image classification or target extraction methods from the perspectives of spatial-spectral features, features at different levels, different analysis units, and different classifiers. Within the remote sensing application industry, software such as ENVI, ERDAS, and eCognition have been developed to provide users with supervised, unsupervised, and object-oriented classification capabilities, which has greatly promoted the application of medium- and low-resolution remote sensing imagery. However, when these methods and technical systems are applied to high-resolution remote sensing imagery, due to the rich ground-object information details and image diversity, it is difficult to obtain satisfactory extraction results. In recent years, deep learning has overcome the limitations of traditional manual feature recognition through its powerful ability to self-learn sample features, opening up a new path for the intelligent extraction of remote sensing information. In the remote sensing interpretation research community, strategies such as multi-layer perception, spatial feature enhancement, spatial scale optimization, and superpixel enhancement are continuously improving the self-learning capabilities of deep learning models for spatial details and variable-scale features of semantic objects in high-resolution remote sensing imagery. This has enabled automated remote sensing interpretation for tasks such as water body extraction, road extraction, and land cover classification. Model accuracy in test areas has approached 90% and even exceeded 95%. However, in practical applications, intelligent remote sensing interpretation technology has not yet reached the level of common image interpretation applications such as facial and fingerprint recognition. A key factor contributing to this situation is that existing remote sensing deep learning methods generally use supervised deep learning or transfer learning approaches, primarily training models by constructing large numbers of samples. This makes model accuracy highly dependent on the diversity and quantity of the samples.The main challenges faced in practical application of this model are: First, the availability of high-resolution satellite imagery for specific areas and time periods is often scarce, making it impossible to construct a large sample using images of the area to be surveyed. Furthermore, satellite imaging conditions are more complex in some areas, making it difficult to fully capture all possible conditions. Second, compared to general remote sensing monitoring, remote sensing identification of ground objects requires higher accuracy and timely feedback. Third, the scarcity of imagery necessitates the maximum possible utilization of multi-resolution satellite remote sensing imagery from different sensors. Therefore, how to quickly and accurately identify remote sensing image information in applications with limited sample sizes, across multiple sensors, and at multiple resolutions has become a pressing need for satellite remote sensing imagery target identification, requiring innovation in remote sensing deep learning models. This paper proposes a remote sensing image processing method and device that supports an expert experience fusion mechanism. This approach uses deep learning technology to improve the accuracy of remote sensing image analysis, thereby enabling the rapid and accurate identification of ground objects using multi-resolution satellite optical remote sensing imagery. This approach addresses the need for rapid, multi-resolution remote sensing identification responses and applications across multiple sensors under limited data conditions. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a remote sensing image processing method and device that supports an expert experience fusion mechanism, which is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and then realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0004] In order to solve the above technical problems, the first aspect of the embodiment of the present invention discloses a remote sensing image processing method, the method comprising:

[0005] Obtain remote sensing image information to be processed;

[0006] Preprocessing the remote sensing image information to be processed to obtain target processed remote sensing image information;

[0007] The target remote sensing image information is analyzed and processed to obtain target remote sensing image analysis result information.

[0008] The analyzing and processing the target remote sensing image information to obtain target remote sensing image analysis result information includes:

[0009] Determining first remote sensing image analysis result information based on the remote sensing image processing model and the target processed remote sensing image information;

[0010] Based on the first remote sensing image analysis result information, target remote sensing image analysis result information is determined.

[0011] The remote sensing image processing model includes a first feature extraction module, a second feature extraction module, a first feature fusion module, a second feature fusion module, a third feature fusion module and an image segmentation module; wherein,

[0012] The input end of the first feature extraction module is configured to receive the first model input of the remote sensing image processing model, and the output end of the first feature extraction module is connected to the input end of the first feature fusion module; the input end of the first feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the first feature fusion module is connected to the input end of the third feature fusion module; the input end of the second feature extraction module is configured to receive the second model input of the remote sensing image processing model; the output end of the second feature fusion module is connected to the input end of the second feature fusion module; the output end of the second feature fusion module is connected to the input end of the third feature fusion module; the input end of the third feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the third feature fusion module is connected to the input end of the image segmentation module; the output end of the image segmentation module is configured to output the model output of the remote sensing image processing model.

[0013] The first feature fusion module includes a first convolution unit, a second convolution unit, a first normalization unit, a second normalization unit, a first activation unit, a second activation unit and a first fusion unit; wherein,

[0014] The input end of the first convolution unit is connected to the output end of the first feature extraction module; the first convolution unit, the first normalization unit, the first activation unit and the first fusion unit are connected in sequence; the input end of the first fusion unit is also configured to receive the first model input of the remote sensing image processing model; the first fusion unit, the second convolution unit, the second normalization unit and the second activation unit are connected in sequence; the output end of the second activation unit is connected to the input end of the third feature fusion module.

[0015] The third feature fusion module includes a second fusion unit, a third fusion unit, a fourth fusion unit, a first pooling unit, a third convolution unit, a third normalization unit and a third activation unit; wherein,

[0016] The input end of the third fusion unit is connected to the output end of the first feature fusion module; the input end of the third fusion unit is also configured to receive the first model input of the remote sensing image processing model; the output end of the third fusion unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the second fusion unit; the input end of the second fusion unit is also connected to the output end of the second feature fusion module; the output end of the second fusion unit is connected to the input end of the fourth fusion unit; the input end of the fourth fusion unit is also connected to the output end of the second feature fusion module; the fourth fusion unit, the third convolution unit, the third normalization unit and the third activation unit are connected in sequence; the output end of the third activation unit is connected to the input end of the image segmentation module.

[0017] The first feature extraction module includes a fourth convolution unit, a fifth convolution unit, a sixth convolution unit, a seventh convolution unit, a fourth normalization unit, a fifth normalization unit, a sixth normalization unit, a seventh normalization unit, an eighth normalization unit, a ninth normalization unit, a tenth normalization unit, an eleventh normalization unit, a twelfth normalization unit, a thirteenth normalization unit, a fourth activation unit, a fifth activation unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a first connection unit, a second pooling unit, a third pooling unit and a fourth pooling unit; wherein,

[0018] The input end of the fourth convolution unit is configured as the input end of the first feature extraction module; the fourth convolution unit, the fourth normalization unit, the fourth activation unit, the fifth convolution unit, the fifth normalization unit, the fifth activation unit, the sixth normalization unit, the sixth activation unit, the seventh normalization unit, the second pooling unit, the eighth normalization unit, the seventh activation unit, the sixth convolution unit, the ninth normalization unit, the eighth activation unit, the tenth normalization unit, the ninth activation unit, the eleventh normalization unit, the third pooling unit, the twelfth normalization unit, the tenth activation unit, the seventh convolution unit, the thirteenth normalization unit, the eleventh activation unit, the fourth pooling unit and the first connection unit are sequentially connected; the output end of the first connection unit is configured as the output end of the first feature extraction module;

[0019] The image segmentation module includes a fourth fusion unit, an eighth convolution unit, a fourteenth normalization unit, a twelfth activation unit, a thirteenth activation unit and a second connection unit; wherein,

[0020] The input end of the fourth fusion unit is respectively connected to the output end of the third feature fusion module and the output end of the thirteenth activation unit; the fourth fusion unit, the eighth convolution unit, the fourteenth normalization unit, the twelfth activation unit, the second connection unit and the fourteenth activation unit are connected in sequence; the output end of the fourteenth activation unit is configured to output the model output of the remote sensing image processing model.

[0021] The determining of target remote sensing image analysis result information based on the first remote sensing image analysis result information includes:

[0022] Based on the remote sensing image processing model, the target remote sensing image information collected at each moment is processed to obtain the corresponding first remote sensing image analysis results;

[0023] Perform fusion calculation on the first remote sensing image analysis results at all times to obtain target remote sensing image analysis result information;

[0024] The expression of the fusion calculation is:

[0025]

[0026] Among them, y i is the analysis result of the first remote sensing image at time i, and y0 are the maximum, minimum and average values ​​of the first remote sensing image analysis results at all times, respectively, and y is the target remote sensing image analysis result information.

[0027] The fusion calculation expression uses the maximum, minimum, and average values ​​of the first remote sensing image analysis results at all times to construct weight coefficients, adaptively adjusting the weights of the results at each time point based on the data distribution. Values ​​close to the average and in the middle of the data distribution are given relatively larger weights, highlighting stable and reliable analysis results. Outliers that deviate significantly from the mean are weighted less, effectively filtering out noise and abnormal fluctuations, improving the accuracy and stability of the analysis results. This formula fully considers the characteristics of time series data when processing remote sensing images collected at different times. By fusing results from multiple times, it avoids analysis bias caused by factors such as weather changes and sensor errors in a single image at a single time point. By integrating information from multiple times, it can more comprehensively and objectively reflect the true state and changing trends of the ground features. This is particularly suitable for dynamic monitoring scenarios, such as vegetation growth and urban expansion monitoring. It ensures that the analysis results of the target remote sensing image are more relevant to the actual situation and enhances the reliability of remote sensing image time series analysis. Compared to traditional simple averaging or weighted averaging methods, this fusion calculation expression constructs nonlinear weights based on the statistical characteristics of the data, exploring potential connections and patterns between data and mathematically optimizing the output of remote sensing image processing models. By integrating the analysis results at each moment in a more scientific manner, it provides more accurate data support for subsequent decision-making based on the target remote sensing image analysis results (such as resource assessment and disaster warning), thereby enhancing the practicality and application value of the entire remote sensing image processing method.

[0028] A second aspect of an embodiment of the present invention discloses a remote sensing image processing device, comprising:

[0029] Acquisition module, used to obtain remote sensing image information to be processed;

[0030] A first processing module is used to pre-process the remote sensing image information to be processed to obtain target processed remote sensing image information;

[0031] The second processing module is used to analyze and process the target remote sensing image information to obtain target remote sensing image analysis result information.

[0032] A third aspect of the present invention discloses another remote sensing image processing device, comprising:

[0033] a memory storing executable program code;

[0034] a processor coupled to the memory;

[0035] The processor calls the executable program code stored in the memory to execute part or all of the steps in the remote sensing image processing method disclosed in the first aspect of the embodiment of the present invention.

[0036] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the remote sensing image processing method disclosed in the first aspect of the embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 is a scene diagram of a remote sensing image processing system provided by an embodiment of the present invention;

[0039] Figure 2 This is a flowchart of a remote sensing image processing method disclosed in an embodiment of the present invention;

[0040] Figure 3 is a structural diagram of a remote sensing image processing device disclosed in an embodiment of the present invention;

[0041] Figure 4 is a structural diagram of another remote sensing image processing device disclosed in an embodiment of the present invention;

[0042] Figure 5 is a structural diagram of a remote sensing image processing model disclosed in an embodiment of the present invention;

[0043] Figure 6 is a structural diagram of a first feature extraction module disclosed in an embodiment of the present invention;

[0044] Figure 7 It is a structural diagram of an image segmentation module disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0047] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] In this application, the word "exemplary" is used to mean "serving as an example, illustration, or illustration." Any embodiment described in this application as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that one of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0049] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, the corresponding data exist for the computer device to process. The details will not be repeated here.

[0050] It should be noted that the artificial intelligence related technologies that may be involved in this application are briefly described. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision-making.

[0051] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0052] Computer vision (CV) is the science of making machines "see." Specifically, it refers to machine vision, where cameras and computers replace the human eye in identifying and measuring objects, performing further image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (OCR), video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0053] Unimodal information is data consisting of only one type, such as text, images, audio, video, or electromagnetic signals. Multimodal information is data that includes at least two types of unimodal information. Furthermore, multimodal information is suitable for complex tasks that require integrating multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can often be achieved on the task.

[0054] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model generally refers to a model with hundreds of millions to trillions of parameters. Models usually need to be trained on large-scale data sets and require a large amount of computing resources to be optimized and adjusted. Large models are generally used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is an AI that can create new content and ideas, including conversations, stories, images, videos, and music. In the embodiment of the present application, the large model can be ChatGPT, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Tongwen Qianyi model, MiniMax model, Spark model, Llama model, 360GPT model, Qwen model, Baichuan model, Skylark model, vivoLM model, Wenxin Yiyan and other large-scale language models, which are not limited in the embodiment of the present application.

[0055] The embodiments of the present application provide a remote sensing image processing method, apparatus, computer equipment, and computer-readable storage medium, which are described in detail below.

[0056] See also Figure 1 , Figure 1 This is a scene diagram of a remote sensing image processing system provided in an embodiment of the present application. The remote sensing image processing system may include a computer device 100, in which a remote sensing image processing device is integrated, such as Figure 1 Computer equipment in.

[0057] In the embodiment of the present application, the computer device 100 is mainly used to obtain remote sensing image information to be processed;

[0058] Preprocessing the remote sensing image information to be processed to obtain target processed remote sensing image information;

[0059] The target remote sensing image information is analyzed and processed to obtain target remote sensing image analysis result information.

[0060] It can improve the accuracy of remote sensing image analysis through deep learning technology, and then realize the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0061] In the embodiments of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiments of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. A cloud server is composed of a large number of computers or network servers based on cloud computing.

[0062] It is understood that the computer device 100 used in the embodiments of the present application can be a device that includes both receiving and transmitting hardware, that is, a device that has receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device that has a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. The specific computer device 100 can be a desktop terminal or a mobile terminal. The computer device 100 can also be a mobile phone, a tablet computer, a laptop computer, etc.

[0063] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or fewer computer devices as shown in Figure 1 Only one computer device is shown in the figure. It can be understood that the remote sensing image processing system can also include one or more other services, which are not limited here.

[0064] In addition, if Figure 1 As shown, the remote sensing image processing system may further include a memory 200 for storing data, such as image data, location information, and the like.

[0065] It should be noted that Figure 1 The scene diagram of the remote sensing image processing system shown is only an example. The remote sensing image processing system and scene described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of remote sensing image processing systems and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0066] This invention discloses a remote sensing image processing method and device that supports an expert experience fusion mechanism. These methods facilitate the use of deep learning technology to improve the accuracy of remote sensing image analysis, thereby enabling the rapid and precise identification and application of multi-resolution satellite optical remote sensing imagery for ground features and facilities. This approach addresses the need for rapid, multi-resolution remote sensing recognition responses and applications across sensors when data is limited. These are described in detail below.

[0067] Example 1

[0068] See also Figure 2 , Figure 2 This is a flow chart of a remote sensing image processing method disclosed in an embodiment of the present invention. Figure 2 The remote sensing image processing method described is applied to a management system, such as a local server or cloud server for management, and the embodiment of the present invention does not limit this. Figure 2 As shown, the remote sensing image processing method may include the following operations:

[0069] 101. Obtain remote sensing image information to be processed.

[0070] 102. Preprocess the remote sensing image information to be processed to obtain target processed remote sensing image information.

[0071] 103. Analyze and process the target remote sensing image information to obtain target remote sensing image analysis result information.

[0072] It should be noted that the above-mentioned remote sensing image information to be processed includes remote sensing image information integrated with expert experience and remote sensing image information taken by satellites, which is not limited in the embodiment of the present invention.

[0073] Furthermore, the target processed remote sensing image information includes first remote sensing image information obtained by processing remote sensing image information integrated with expert experience and second remote sensing image information obtained by processing remote sensing image information taken by satellite, which is not limited in the embodiment of the present invention.

[0074] Furthermore, the first model input is the first remote sensing image information, and the second model input represents the second remote sensing image information.

[0075] Furthermore, the above-mentioned preprocessing of the remote sensing image information to be processed includes first performing mean filtering on the image, and then smoothing the image through Gaussian filtering to remove clutter in the image, thereby improving the image quality, and finally adjusting the image size. The embodiment of the present invention does not limit this.

[0076] It should be noted that the method of this application, based on obtaining a basic element segmentation model and a key facility and target detection model that meet longitude requirements, solidifies the model algorithm in the Python + TensorFlow environment. In the VS2015 integrated development environment, using the C++ language, introducing the QGIS secondary development package, the TensorFlow library, the GDAL library, and the OpenCV library, calls the trained remote sensing image processing model to achieve key facility identification based on multi-resolution satellite optical remote sensing imagery, which is not limited in the present embodiment.

[0077] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0078] In an optional embodiment, the target remote sensing image information is analyzed and processed to obtain target remote sensing image analysis result information, including:

[0079] Processing the remote sensing image information based on the remote sensing image processing model and the target, determining first remote sensing image analysis result information;

[0080] Based on the first remote sensing image analysis result information, target remote sensing image analysis result information is determined.

[0081] It should be noted that the determination of the target remote sensing image analysis result information based on the first remote sensing image analysis result information is performed by using a target detection model to identify the target object in the first remote sensing image analysis result information, thereby obtaining the target remote sensing image analysis result information in which the target object is identified. This is not limited in the present embodiment. Furthermore, the target detection model can be constructed based on a YOLO series model or a large model, which is not limited in the present embodiment.

[0082] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0083] In another optional embodiment, Figure 5 As shown, the remote sensing image processing model includes a first feature extraction module, a second feature extraction module, a first feature fusion module, a second feature fusion module, a third feature fusion module and an image segmentation module; wherein,

[0084] The input end of the first feature extraction module is configured to receive the first model input of the remote sensing image processing model, and the output end of the first feature extraction module is connected to the input end of the first feature fusion module; the input end of the first feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the first feature fusion module is connected to the input end of the third feature fusion module; the input end of the second feature extraction module is configured to receive the second model input of the remote sensing image processing model; the output end of the second feature fusion module is connected to the input end of the second feature fusion module; the output end of the second feature fusion module is connected to the input end of the third feature fusion module; the input end of the third feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the third feature fusion module is connected to the input end of the image segmentation module; the output end of the image segmentation module is configured to output the model output of the remote sensing image processing model.

[0085] It should be noted that the above-mentioned remote sensing image processing model supports the fusion of external expert prior knowledge, and is mainly used for the fusion of external prior knowledge, to perform intensive feature comparison between query images and support images, and to learn and simulate the ability of people to analyze the same features and difference features when identifying objects. The embodiment of the present invention does not limit this. Furthermore, the remote sensing image processing model uses a cross-validation training method, that is, the training set and the validation set are input into the model at the same time. After each training, a batch size of data is randomly selected from the validation set to calculate the loss and accuracy, optimize the training of the model, adopt the cross entropy loss function of binary classification, and adopt the stochastic gradient descent (SGD) optimization algorithm to optimize the objective function. In terms of image input size and batch size, since the model training has high requirements for the GPU memory of the computer, the method of the present invention uses an image of size 512*512 as the input of the network, the batch size is set to 4, the number of rounds is set to 50 rounds, the number of iterations per round is 4000, and the initial learning rate is set to 1e-4. In addition, in order to better train the model, the learning rate will be automatically adjusted as the number of training rounds increases, that is, the learning rate will be reduced by 10 times every 20 rounds. Combined with the optimizer, the convergence of the network can be accelerated, which is not limited in the embodiment of the present invention.

[0086] Furthermore, the training samples used to train the remote sensing image processing model can be implemented based on the following methods:

[0087] Principles of sample library collection:

[0088] Remote sensing image target representation varies due to factors such as imaging conditions, sensor characteristics, weather conditions, climate conditions, solar altitude, background environment, and high light reflection. Furthermore, multi-resolution imagery involves different satellite sensors, which greatly increases the difficulty of identifying important facilities and targets in multi-resolution satellite remote sensing images. Therefore, to improve model accuracy, when building a target identification sample library using existing sample libraries and self-collected samples, it is important to cover as many factors and complex conditions as possible.

[0089] Principles for constructing a training library: Sample selection must be representative. Samples for each facility type and facility element need to be diverse, covering different situations such as different resolutions, different sensors, different imaging conditions, and different backgrounds. The number of samples for each target type and covering various typical situations must reach a certain number. The number of samples covering various typical situations should be distributed as evenly as possible.

[0090] Sample library collection method:

[0091] The present invention produces conventional samples according to the above-mentioned sample collection methods and principles. To further transform the conventional sample data set into the sample set required by the present invention and meeting the small sample model training requirements, the present invention proposes a remote sensing sample construction method process with expert interpretation experience expression and transmission.

[0092] Sample production process:

[0093] Unlike conventional sample production, multi-resolution sample production, which expresses and transfers interpretation experience, begins by analyzing expert interpretation experience and patterns based on a conventional sample library. Then, artificial experience-based expression methods such as saliency feature maps and exponential feature maps are selected to express these expert interpretation patterns, forming a multi-channel expert interpretation experience map. Finally, this map, along with the original remote sensing imagery and labels from manual interpretations, serves as training samples to provide prior knowledge for the deep learning model.

[0094] Experts interpret the expression of empirical laws:

[0095] During manual visual interpretation of remote sensing imagery, interpretation professionals can accurately identify ground features and facilities through shape, texture, color features, and different spectral combinations. To transform this expert visual interpretation experience into prior knowledge, express it, and pass it on to deep learning models to guide their learning and convergence, this paper primarily utilizes existing texture feature extraction methods, geometric morphology feature extraction methods, color saliency extraction methods, and exponential factor extraction methods to extract the texture, geometry, color, and spectral features experienced by expert interpretation. These features are then normalized and synthesized into a multi-channel expert interpretation experience map.

[0096] Furthermore, the above-mentioned remote sensing image processing model can effectively integrate expert knowledge into the model training and reasoning process to improve the model's understanding and analysis capabilities of remote sensing images. In this way, the model can better capture subtle changes in remote sensing images and improve the accuracy of change detection. At the same time, it can also adapt to different application scenarios, such as urban planning, environmental monitoring, etc., which are not limited in the embodiments of the present invention.

[0097] It should be noted that the model architecture of the above-mentioned first feature extraction module and the second feature extraction module are consistent, and the embodiments of the present invention do not limit this. Furthermore, the above-mentioned first feature extraction module and the second feature extraction module are twin structures. Furthermore, the twin structure feature extraction module is mainly used to extract common features of intermediate feature acquisition, learning and comparison objects that do not have category differentiation functions. The embodiments of the present invention do not limit this. Furthermore, the first feature extraction module and the second feature extraction module of the two twin structures share exactly the same architecture and weights. The first feature extraction module and the second feature extraction module in the twin network have the same parameters and weights. During the network training process, the parameters are updated jointly on the first feature extraction module and the second feature extraction module. The twin neural network helps to discover the similarities and correlations between different structures. The first feature extraction module and the second feature extraction module in the twin network share weights, which means that training requires fewer parameters, that is, less data is required and it is not easy to overfit. The embodiments of the present invention do not limit this.

[0098] It should be noted that the model architectures of the first feature fusion module and the second feature fusion module are consistent, and are not limited in the embodiments of the present invention. Furthermore, the first feature fusion module and the second feature fusion module are mainly used to fuse the prior knowledge extracted by experts with the mid-level features extracted by the twin network, providing rich shared knowledge and rules for feature comparison, and are not limited in the embodiments of the present invention.

[0099] It should be noted that the third feature fusion module is mainly used to learn and compare similar features of the target category in the support image and the query image, which is not limited in the embodiment of the present invention.

[0100] It should be noted that due to the influence of external factors such as imaging conditions, there are certain differences in the spectrum and appearance of the same category in the remote sensing image. Dense comparison can only match part of the object, which is not enough to accurately segment or identify the object in the image. The initial segmentation or recognition results can provide important rough spatial position information of the identification target, so the image segmentation module will continuously use iterative optimization to achieve segmentation. Since the residual structure in the residual network has strong feature reuse and information transmission capabilities, the recursive iterative prediction segmentation submodule is mainly implemented using the residual structure, which is not limited in the embodiment of the present invention.

[0101] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0102] In another optional embodiment, Figure 5 As shown, the first feature fusion module includes a first convolution unit, a second convolution unit, a first normalization unit, a second normalization unit, a first activation unit, a second activation unit and a first fusion unit; wherein,

[0103] The input end of the first convolution unit is connected to the output end of the first feature extraction module; the first convolution unit, the first normalization unit, the first activation unit and the first fusion unit are connected in sequence; the input end of the first fusion unit is also configured to receive the first model input of the remote sensing image processing model; the first fusion unit, the second convolution unit, the second normalization unit and the second activation unit are connected in sequence; the output end of the second activation unit is connected to the input end of the third feature fusion module.

[0104] It should be noted that the convolution kernels of the above-mentioned first convolution unit and the second convolution unit can be one of 1×1, 3×1, 3×3, 5×1, 5×3, 5×5, 7×5 and 7×7, with a step size of 1, which is not limited in this embodiment of the present invention.

[0105] It should be noted that the above-mentioned first normalization unit and second normalization unit are constructed based on the batch normalization layer, which is not limited in this embodiment of the present invention.

[0106] It should be noted that the above-mentioned first activation unit and second activation unit are constructed based on the RELU activation function, which is not limited in the embodiment of the present invention.

[0107] It should be noted that the above-mentioned first fusion unit is constructed based on the splicing operation, which is not limited in this embodiment of the present invention.

[0108] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0109] In another optional embodiment, Figure 5As shown, the third feature fusion module includes a second fusion unit, a third fusion unit, a fourth fusion unit, a first pooling unit, a third convolution unit, a third normalization unit and a third activation unit; wherein,

[0110] The input end of the third fusion unit is connected to the output end of the first feature fusion module; the input end of the third fusion unit is also configured to receive the first model input of the remote sensing image processing model; the output end of the third fusion unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the second fusion unit; the input end of the second fusion unit is also connected to the output end of the second feature fusion module; the output end of the second fusion unit is connected to the input end of the fourth fusion unit; the input end of the fourth fusion unit is also connected to the output end of the second feature fusion module; the fourth fusion unit, the third convolution unit, the third normalization unit and the third activation unit are connected in sequence; the output end of the third activation unit is connected to the input end of the image segmentation module.

[0111] It should be noted that the second fusion unit, the third fusion unit, and the fourth fusion unit are constructed based on a splicing operation, which is not limited in this embodiment of the present invention.

[0112] It should be noted that the above-mentioned first pooling unit is constructed based on the maximum pooling layer, which is not limited in this embodiment of the present invention.

[0113] It should be noted that the convolution kernel of the above-mentioned third convolution unit can be one of 1×1, 3×1, 3×3, 5×1, 5×3, 5×5, 7×5 and 7×7, with a step size of 1, which is not limited in this embodiment of the present invention.

[0114] It should be noted that the third normalization unit is constructed based on the batch normalization layer, which is not limited in this embodiment of the present invention.

[0115] It should be noted that the third activation unit is constructed based on the RELU activation function, which is not limited in this embodiment of the present invention.

[0116] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0117] In an optional embodiment, if Figure 6As shown, the first feature extraction module includes a fourth convolution unit, a fifth convolution unit, a sixth convolution unit, a seventh convolution unit, a fourth normalization unit, a fifth normalization unit, a sixth normalization unit, a seventh normalization unit, an eighth normalization unit, a ninth normalization unit, a tenth normalization unit, an eleventh normalization unit, a twelfth normalization unit, a thirteenth normalization unit, a fourth activation unit, a fifth activation unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a first connection unit, a second pooling unit, a third pooling unit and a fourth pooling unit; wherein,

[0118] The input end of the fourth convolution unit is configured as the input end of the first feature extraction module; the fourth convolution unit, the fourth normalization unit, the fourth activation unit, the fifth convolution unit, the fifth normalization unit, the fifth activation unit, the sixth normalization unit, the sixth activation unit, the seventh normalization unit, the second pooling unit, the eighth normalization unit, the seventh activation unit, the sixth convolution unit, the ninth normalization unit, the eighth activation unit, the tenth normalization unit, the ninth activation unit, the eleventh normalization unit, the third pooling unit, the twelfth normalization unit, the tenth activation unit, the seventh convolution unit, the thirteenth normalization unit, the eleventh activation unit, the fourth pooling unit and the first connection unit are connected in sequence; the output end of the first connection unit is configured as the output end of the first feature extraction module.

[0119] It should be noted that the convolution kernels of the fourth convolution unit, the fifth convolution unit, the sixth convolution unit, and the seventh convolution unit can be one of 1×1, 3×1, 3×3, 5×1, 5×3, 5×5, 7×5, and 7×7, with a step size of 1, which is not limited in this embodiment of the present invention.

[0120] It should be noted that the above-mentioned fourth normalization unit, fifth normalization unit, sixth normalization unit, seventh normalization unit, eighth normalization unit, ninth normalization unit, tenth normalization unit, eleventh normalization unit, twelfth normalization unit, and thirteenth normalization unit are constructed based on the batch normalization layer, which is not limited in the embodiment of the present invention.

[0121] It should be noted that the above-mentioned fourth activation unit, fifth activation unit, sixth activation unit, seventh activation unit, eighth activation unit, ninth activation unit, tenth activation unit, and eleventh activation unit are constructed based on the RELU activation function, which is not limited in the embodiment of the present invention.

[0122] It should be noted that the above-mentioned first connection unit is constructed based on the fully connected layer, which is not limited in the embodiment of the present invention.

[0123] It should be noted that the second pooling unit, the third pooling unit and the fourth pooling unit are constructed based on the maximum pooling layer, which is not limited in this embodiment of the present invention.

[0124] It should be noted that the module composed of the above-mentioned (normalization unit-activation unit-convolution unit-normalization unit-activation unit) is a basic feature extraction, and the unit module composed of (normalization unit-activation unit-normalization unit-pooling unit) is a connection unit connecting the basic feature extraction module to reduce the size of the feature map and the number of feature maps. The embodiment of the present invention does not limit this. Furthermore, the use of this multi-level feature extraction method enables the model to have a strong feature accumulation transmission and multi-layer feature integration capability. The embodiment of the present invention does not limit this. Furthermore, in order to maximize the transmission of feature information between two neural layers, the first feature extraction module connects all layers together in a deep convolutional neuron network connection method, so that each layer in training can access the loss gradient formed at the end of the model and the beginning of the structure. The use of a dense connection mode can effectively improve the information flow between layers, making the model easier to train. The embodiment of the present invention does not limit this.

[0125] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0126] In another optional embodiment, Figure 7 As shown, the image segmentation module includes a fourth fusion unit, an eighth convolution unit, a fourteenth normalization unit, a twelfth activation unit, a thirteenth activation unit and a second connection unit; wherein,

[0127] The input end of the fourth fusion unit is respectively connected to the output end of the third feature fusion module and the output end of the thirteenth activation unit; the fourth fusion unit, the eighth convolution unit, the fourteenth normalization unit, the twelfth activation unit, the second connection unit and the fourteenth activation unit are connected in sequence; the output end of the fourteenth activation unit is configured to output the model output of the remote sensing image processing model.

[0128] It should be noted that the fourth fusion unit is constructed based on a splicing operation, which is not limited in this embodiment of the present invention.

[0129] It should be noted that the convolution kernel of the above-mentioned eighth convolution unit can be one of 1×1, 3×1, 3×3, 5×1, 5×3, 5×5, 7×5 and 7×7, with a step size of 1, which is not limited in this embodiment of the present invention.

[0130] It should be noted that the fourteenth normalization unit is constructed based on the batch normalization layer, which is not limited in this embodiment of the present invention.

[0131] It should be noted that the twelfth activation unit and the thirteenth activation unit are constructed based on the RELU activation function, which is not limited in this embodiment of the present invention.

[0132] It should be noted that the above-mentioned second connection unit is constructed based on the fully connected layer, which is not limited in the embodiment of the present invention.

[0133] It can be seen that the implementation of the remote sensing image processing method described in the embodiment of the present invention is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, and further realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0134] Example 2

[0135] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a remote sensing image processing device disclosed in an embodiment of the present invention. Figure 3 The described device can be applied to a management system, such as a local server or a cloud server for management, etc., and the embodiment of the present invention does not limit this. Figure 3 As shown, the device may include:

[0136] An acquisition module 201 is used to acquire remote sensing image information to be processed;

[0137] The first processing module 202 is used to pre-process the remote sensing image information to be processed to obtain target processed remote sensing image information;

[0138] The second processing module 203 is used to analyze and process the target remote sensing image information to obtain target remote sensing image analysis result information.

[0139] It can be seen that implementation Figure 3 The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0140] In another optional embodiment, Figure 3 As shown, the target remote sensing image information is analyzed and processed to obtain the target remote sensing image analysis result information, including:

[0141] Processing the remote sensing image information based on the remote sensing image processing model and the target, determining first remote sensing image analysis result information;

[0142] Based on the first remote sensing image analysis result information, target remote sensing image analysis result information is determined.

[0143] It can be seen that implementation Figure 3 The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0144] In another optional embodiment, Figure 3 As shown, the remote sensing image processing model includes a first feature extraction module, a second feature extraction module, a first feature fusion module, a second feature fusion module, a third feature fusion module and an image segmentation module; wherein,

[0145] The input end of the first feature extraction module is configured to receive the first model input of the remote sensing image processing model, and the output end of the first feature extraction module is connected to the input end of the first feature fusion module; the input end of the first feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the first feature fusion module is connected to the input end of the third feature fusion module; the input end of the second feature extraction module is configured to receive the second model input of the remote sensing image processing model; the output end of the second feature fusion module is connected to the input end of the second feature fusion module; the output end of the second feature fusion module is connected to the input end of the third feature fusion module; the input end of the third feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the third feature fusion module is connected to the input end of the image segmentation module; the output end of the image segmentation module is configured to output the model output of the remote sensing image processing model.

[0146] It can be seen that implementation Figure 3 The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0147] In another optional embodiment, Figure 3 As shown, the first feature fusion module includes a first convolution unit, a second convolution unit, a first normalization unit, a second normalization unit, a first activation unit, a second activation unit and a first fusion unit; wherein,

[0148] The input end of the first convolution unit is connected to the output end of the first feature extraction module; the first convolution unit, the first normalization unit, the first activation unit and the first fusion unit are connected in sequence; the input end of the first fusion unit is also configured to receive the first model input of the remote sensing image processing model; the first fusion unit, the second convolution unit, the second normalization unit and the second activation unit are connected in sequence; the output end of the second activation unit is connected to the input end of the third feature fusion module.

[0149] It can be seen that implementation Figure 3 The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0150] In another optional embodiment, Figure 3 As shown, the third feature fusion module includes a second fusion unit, a third fusion unit, a fourth fusion unit, a first pooling unit, a third convolution unit, a third normalization unit and a third activation unit; wherein,

[0151] The input end of the third fusion unit is connected to the output end of the first feature fusion module; the input end of the third fusion unit is also configured to receive the first model input of the remote sensing image processing model; the output end of the third fusion unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the second fusion unit; the input end of the second fusion unit is also connected to the output end of the second feature fusion module; the output end of the second fusion unit is connected to the input end of the fourth fusion unit; the input end of the fourth fusion unit is also connected to the output end of the second feature fusion module; the fourth fusion unit, the third convolution unit, the third normalization unit and the third activation unit are connected in sequence; the output end of the third activation unit is connected to the input end of the image segmentation module.

[0152] It can be seen that implementation Figure 3 The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0153] In another optional embodiment, Figure 3As shown, the first feature extraction module includes a fourth convolution unit, a fifth convolution unit, a sixth convolution unit, a seventh convolution unit, a fourth normalization unit, a fifth normalization unit, a sixth normalization unit, a seventh normalization unit, an eighth normalization unit, a ninth normalization unit, a tenth normalization unit, an eleventh normalization unit, a twelfth normalization unit, a thirteenth normalization unit, a fourth activation unit, a fifth activation unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a first connection unit, a second pooling unit, a third pooling unit and a fourth pooling unit; wherein,

[0154] The input end of the fourth convolution unit is configured as the input end of the first feature extraction module; the fourth convolution unit, the fourth normalization unit, the fourth activation unit, the fifth convolution unit, the fifth normalization unit, the fifth activation unit, the sixth normalization unit, the sixth activation unit, the seventh normalization unit, the second pooling unit, the eighth normalization unit, the seventh activation unit, the sixth convolution unit, the ninth normalization unit, the eighth activation unit, the tenth normalization unit, the ninth activation unit, the eleventh normalization unit, the third pooling unit, the twelfth normalization unit, the tenth activation unit, the seventh convolution unit, the thirteenth normalization unit, the eleventh activation unit, the fourth pooling unit and the first connection unit are connected in sequence; the output end of the first connection unit is configured as the output end of the first feature extraction module.

[0155] It can be seen that implementation Figure 3 The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0156] In another optional embodiment, Figure 3 As shown, the image segmentation module includes a fourth fusion unit, an eighth convolution unit, a fourteenth normalization unit, a twelfth activation unit, a thirteenth activation unit and a second connection unit; wherein,

[0157] The input end of the fourth fusion unit is respectively connected to the output end of the third feature fusion module and the output end of the thirteenth activation unit; the fourth fusion unit, the eighth convolution unit, the fourteenth normalization unit, the twelfth activation unit, the second connection unit and the fourteenth activation unit are connected in sequence; the output end of the fourteenth activation unit is configured to output the model output of the remote sensing image processing model.

[0158] It can be seen that implementation Figure 3The remote sensing image processing device described is conducive to improving the accuracy of remote sensing image analysis through deep learning technology, thereby realizing the rapid and accurate identification and application of multi-resolution satellite optical remote sensing images to ground objects and facilities, so as to solve the problem of achieving cross-sensor, multi-resolution rapid remote sensing recognition response and application under limited data conditions.

[0159] Example 3

[0160] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of another remote sensing image processing device disclosed in an embodiment of the present invention. Figure 4 The described device can be applied to a management system, such as a local server or a cloud server for management, etc., and the embodiment of the present invention does not limit this. Figure 4 As shown, the device may include:

[0161] A memory 301 storing executable program code;

[0162] a processor 302 coupled to the memory 301;

[0163] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the remote sensing image processing method described in the first embodiment.

[0164] Example 4

[0165] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the remote sensing image processing method described in the first embodiment.

[0166] Example 5

[0167] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the remote sensing image processing method described in the first embodiment.

[0168] The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0169] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0170] Finally, it should be noted that the remote sensing image processing method and device supporting the expert experience fusion mechanism disclosed in the embodiment of the present invention only discloses a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A remote sensing image processing method, characterized in that: The method comprises: Obtain remote sensing image information to be processed; Preprocessing the remote sensing image information to be processed to obtain target processed remote sensing image information; The target remote sensing image information is analyzed and processed to obtain target remote sensing image analysis result information.

2. The remote sensing image processing method according to claim 1, characterized in that: The analyzing and processing the target remote sensing image information to obtain target remote sensing image analysis result information includes: Determining first remote sensing image analysis result information based on the remote sensing image processing model and the target processed remote sensing image information; Based on the first remote sensing image analysis result information, target remote sensing image analysis result information is determined.

3. The remote sensing image processing method according to claim 2, characterized in that: The remote sensing image processing model includes a first feature extraction module, a second feature extraction module, a first feature fusion module, a second feature fusion module, a third feature fusion module and an image segmentation module; wherein, The input end of the first feature extraction module is configured to receive the first model input of the remote sensing image processing model, and the output end of the first feature extraction module is connected to the input end of the first feature fusion module; the input end of the first feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the first feature fusion module is connected to the input end of the third feature fusion module; the input end of the second feature extraction module is configured to receive the second model input of the remote sensing image processing model; the output end of the second feature fusion module is connected to the input end of the second feature fusion module; the output end of the second feature fusion module is connected to the input end of the third feature fusion module; the input end of the third feature fusion module is also configured to receive the first model input of the remote sensing image processing model; the output end of the third feature fusion module is connected to the input end of the image segmentation module; the output end of the image segmentation module is configured to output the model output of the remote sensing image processing model.

4. The remote sensing image processing method according to claim 3, characterized in that: The first feature fusion module includes a first convolution unit, a second convolution unit, a first normalization unit, a second normalization unit, a first activation unit, a second activation unit and a first fusion unit; wherein, The input end of the first convolution unit is connected to the output end of the first feature extraction module; the first convolution unit, the first normalization unit, the first activation unit and the first fusion unit are connected in sequence; the input end of the first fusion unit is also configured to receive the first model input of the remote sensing image processing model; the first fusion unit, the second convolution unit, the second normalization unit and the second activation unit are connected in sequence; the output end of the second activation unit is connected to the input end of the third feature fusion module.

5. The remote sensing image processing method according to claim 3, characterized in that: The third feature fusion module includes a second fusion unit, a third fusion unit, a fourth fusion unit, a first pooling unit, a third convolution unit, a third normalization unit and a third activation unit; wherein, The input end of the third fusion unit is connected to the output end of the first feature fusion module; the input end of the third fusion unit is also configured to receive the first model input of the remote sensing image processing model; the output end of the third fusion unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the second fusion unit; the input end of the second fusion unit is also connected to the output end of the second feature fusion module; the output end of the second fusion unit is connected to the input end of the fourth fusion unit; the input end of the fourth fusion unit is also connected to the output end of the second feature fusion module; the fourth fusion unit, the third convolution unit, the third normalization unit and the third activation unit are connected in sequence; the output end of the third activation unit is connected to the input end of the image segmentation module.

6. The remote sensing image processing method according to claim 3, characterized in that: The first feature extraction module includes a fourth convolution unit, a fifth convolution unit, a sixth convolution unit, a seventh convolution unit, a fourth normalization unit, a fifth normalization unit, a sixth normalization unit, a seventh normalization unit, an eighth normalization unit, a ninth normalization unit, a tenth normalization unit, an eleventh normalization unit, a twelfth normalization unit, a thirteenth normalization unit, a fourth activation unit, a fifth activation unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a first connection unit, a second pooling unit, a third pooling unit and a fourth pooling unit; wherein, The input end of the fourth convolution unit is configured as the input end of the first feature extraction module; the fourth convolution unit, the fourth normalization unit, the fourth activation unit, the fifth convolution unit, the fifth normalization unit, the fifth activation unit, the sixth normalization unit, the sixth activation unit, the seventh normalization unit, the second pooling unit, the eighth normalization unit, the seventh activation unit, the sixth convolution unit, the ninth normalization unit, the eighth activation unit, the tenth normalization unit, the ninth activation unit, the eleventh normalization unit, the third pooling unit, the twelfth normalization unit, the tenth activation unit, the seventh convolution unit, the thirteenth normalization unit, the eleventh activation unit, the fourth pooling unit and the first connection unit are sequentially connected; the output end of the first connection unit is configured as the output end of the first feature extraction module; The image segmentation module includes a fourth fusion unit, an eighth convolution unit, a fourteenth normalization unit, a twelfth activation unit, a thirteenth activation unit and a second connection unit; wherein, The input end of the fourth fusion unit is respectively connected to the output end of the third feature fusion module and the output end of the thirteenth activation unit; the fourth fusion unit, the eighth convolution unit, the fourteenth normalization unit, the twelfth activation unit, the second connection unit and the fourteenth activation unit are connected in sequence; the output end of the fourteenth activation unit is configured to output the model output of the remote sensing image processing model.

7. The remote sensing image processing method according to claim 2, characterized in that: The determining of target remote sensing image analysis result information based on the first remote sensing image analysis result information includes: Based on the remote sensing image processing model, the target remote sensing image information collected at each moment is processed to obtain the corresponding first remote sensing image analysis results; Perform fusion calculation on the first remote sensing image analysis results at all times to obtain target remote sensing image analysis result information; The expression of the fusion calculation is: Among them, y i is the analysis result of the first remote sensing image at time i, and y0 are the maximum, minimum and average values ​​of the first remote sensing image analysis results at all times, respectively, and y is the target remote sensing image analysis result information.

8. A remote sensing image processing device, characterized in that: The device comprises: Acquisition module, used to obtain remote sensing image information to be processed; A first processing module is used to pre-process the remote sensing image information to be processed to obtain target processed remote sensing image information; The second processing module is used to analyze and process the target remote sensing image information to obtain target remote sensing image analysis result information.

9. A remote sensing image processing device, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the remote sensing image processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the remote sensing image processing method according to any one of claims 1 to 7.

Images