A remote sensing intelligent application model updating method and device

Abstract

The present invention discloses a method and device for updating a remote sensing intelligent application model. The method comprises: obtaining a remote sensing intelligent application basic model and a training data set; processing the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set; and processing the first application optimization model using a measured data set and the training data label set to obtain a remote sensing intelligent application optimization model. Based on user needs and sample location and classification accuracy, the present invention controls the increment of training sample data, iterating the intelligent model with continuously updated data, thereby improving the continuous updating and learning capabilities of the remote sensing data intelligent model.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and remote sensing data processing, and in particular to a remote sensing intelligent application model updating method and device. Background Art

[0002] The integration of artificial intelligence and remote sensing data has become a mainstream approach to remote sensing technology applications. In practical applications, after offline training and achieving general performance, intelligent remote sensing models, once operational, are deployed to different user groups and application scenarios, requiring the models to focus on different areas. Furthermore, as time passes, surface features constantly change, and remote sensing observation data is continuously updated, the distribution of objects of interest and their characteristics will also shift. This requires intelligent remote sensing data models to be able to continuously update and learn based on new data. However, training the model directly with new data causes it to forget knowledge from previous data. While updating the model with both new and historical data allows for a balanced balance of knowledge, the computational cost of training increases as new data instances accumulate. Implementing customized updates and iterations of intelligent models based on user needs and constantly updated data is crucial to ensuring the usability and durability of intelligent remote sensing models. The present invention controls the increment of training sample data based on the accuracy of sample positioning and classification, proposes a set of online updating methods for remote sensing intelligent application model training data based on user needs, and uses continuously updated data to update and iterate the intelligent model, thereby improving the continuous update and learning ability of the remote sensing data intelligent model. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a remote sensing intelligent application model updating method and device, which improves the iterative optimization efficiency of the remote sensing image object intelligent positioning model, thereby enhancing the continuous update learning ability of the remote sensing data intelligent model.

[0004] In order to solve the above technical problems, the first aspect of the embodiment of the present invention discloses a remote sensing intelligent application model updating method, which includes:

[0005] S1, obtain the basic model and training data set of remote sensing intelligent application;

[0006] S2, processing the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set;

[0007] S3: Processing the first application optimization model using the measured data set and the training data label set to obtain a remote sensing intelligent application optimization model.

[0008] As an optional implementation, in the first aspect of the embodiment of the present invention, the processing of the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set includes:

[0009] S21, obtaining the training data set;

[0010] S22, dividing the training data set according to a preset ratio to obtain a data training set and a data test set;

[0011] Set the number of training times to 1;

[0012] S23, using the remote sensing intelligent application basic model, processing the data training set to obtain first image object information;

[0013] S24, based on the model loss function, using the first image object information and the training data label set to update the parameters of the remote sensing intelligent application basic model;

[0014] S25, determining whether the training number value is greater than a preset training number threshold, and obtaining a training number determination result;

[0015] When the result of the training number judgment is yes, executing S23;

[0016] When the result of the training number judgment is no, the training number value is increased by 1, and S26 is executed;

[0017] S26, using the remote sensing intelligent application basic model, processing the data test set to obtain second image object information;

[0018] S27, comparing the second image object information with the data test label set to obtain prediction accuracy information;

[0019] S28, determining whether the prediction accuracy information is greater than a preset accuracy threshold, and obtaining an accuracy determination result;

[0020] When the accuracy determination result is no, executing S22;

[0021] If the accuracy determination result is yes, a first application optimization model is obtained and S29 is executed;

[0022] S29, fusing the data training label set and the data test label set to obtain a training data label set.

[0023] As an optional implementation, in the first aspect of the embodiment of the present invention, the first application optimization model is processed using the measured data set and the training data label set to obtain the remote sensing intelligent application optimization model, including:

[0024] S31, obtaining a target area vector mask set;

[0025] S32, processing the measured data set based on the target area vector mask set to obtain a first positioning classification data set and a second positioning classification data set;

[0026] The first positioning classification data set includes a plurality of first positioning classification data;

[0027] The second positioning classification data set includes a plurality of second positioning classification data;

[0028] S33, using a target uncertainty acquisition model to process the training data set, the first positioning classification data set, and the second positioning classification data set to obtain a training data increment set;

[0029] S34, labeling the training data incremental set based on the training data label set to obtain an incremental data label set;

[0030] S35, based on the incremental data label set, using the incremental training data set to process the first application optimization model to obtain a second application optimization model;

[0031] S36, fusing the incremental training label set and the training data label set to obtain a historical label set;

[0032] Increase the number of incremental processing times by 1;

[0033] S37, determining whether the number of incremental processing times is greater than the number of iterations, and obtaining an iteration determination result;

[0034] When the iterative judgment result is no, the training data increment set is updated to the training data set, the historical label set is updated to the training data label set, and S32 is executed;

[0035] When the iterative judgment result is yes, the second remote sensing image object classification optimization model is updated to the remote sensing intelligent application optimization model.

[0036] As an optional implementation manner, in the first aspect of the embodiment of the present invention, obtaining the target area vector mask set includes:

[0037] S311, acquiring a remote sensing image set of the target area;

[0038] S312, traversing the target area remote sensing image set to obtain all the target area remote sensing images;

[0039] S313, using the first application optimization model, processing any of the target area remote sensing images to obtain target positioning classification result information;

[0040] S314, verifying the target positioning and classification result information to obtain a target area vector mask;

[0041] S315, using the regional vector mask acquisition model to process the target regional vector mask to obtain a target regional vector mask set;

[0042] The regional vector mask acquisition model expression is:

[0043]

[0044] Wherein, A represents the target area vector mask set; A i ; represents the i-th target region vector mask; i represents the index of the target region; U represents the union calculation.

[0045] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the target uncertainty acquisition model is used to process the training data set, the first positioning classification data set, and the second positioning classification data set to obtain a training data increment set, including:

[0046] S331, processing the training data set and the first positioning classification data set to obtain a first incremental training sample subset;

[0047] The first incremental training sample subset includes a plurality of first incremental training samples;

[0048] S332: Process the second positioning classification data set based on the uncertainty calculation model to obtain a second incremental training sample subset;

[0049] The second incremental training sample subset includes a plurality of second incremental training samples;

[0050] S333: All the first incremental training samples and the second incremental training samples are arranged and combined in order to obtain an incremental set of training data.

[0051] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the target uncertainty acquisition model expression is:

[0052] IA{img i}=1-AP50(TL(img i), PR(img i ));.

[0053] Among them, i represents the index of the remote sensing image; img i is the i-th remote sensing image; IA{imgg i} represents the target uncertainty of the i-th remote sensing image; TL(img i ) is the target object label in the i-th remote sensing image; PR(img i ) is the prediction result of the i-th remote sensing image; AP50() represents the first threshold accuracy of calculating the i-th remote sensing image.

[0054] As an optional implementation manner, in the first aspect of the embodiment of the present invention, processing the training dataset and the first positioning classification dataset to obtain a first incremental training sample subset includes:

[0055] S3311: Perform a combination calculation on the training dataset and the first positioning classification dataset to obtain a third positioning classification dataset;

[0056] S3312, traverse the third positioning classification data set to obtain all third positioning classification data;

[0057] S3313: Process any of the third positioning classification data using the first application optimization model to obtain positioning target type information;

[0058] The positioning target type information includes target quantity information and target type information;

[0059] S3314: Arrange and combine all the third positioning classification data in order according to the target quantity information to obtain a fourth positioning classification data set;

[0060] S3315: Perform uniform sampling processing on the fourth positioning classification data set to obtain a first incremental training sample subset.

[0061] As an optional implementation manner, in the first aspect of the embodiment of the present invention, processing the first application optimization model using the incremental set of training data to obtain a second application optimization model includes:

[0062] S351, obtaining the training data increment set;

[0063] The incremental training data set includes a plurality of incremental training data; the incremental training data is training data or first classification positioning data or second classification positioning data;

[0064] S352, traversing the training data incremental set to obtain all incremental training data;

[0065] S353, parsing any of the incremental training data to obtain data type information;

[0066] S354, performing matching processing on the training data label set based on the data type information to obtain incremental training label information;

[0067] S355: All the incremental training label information is combined in order to obtain an incremental training label set.

[0068] S356: Based on the incremental training label set, the first application optimization model is processed using the training data incremental set to obtain a second application optimization model.

[0069] A second aspect of an embodiment of the present invention discloses a remote sensing intelligent application model update device, the device comprising:

[0070] Acquisition module, used to obtain remote sensing intelligent application basic models and training data sets;

[0071] A first processing module is configured to process the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set;

[0072] The second processing module is used to process the first application optimization model using the measured data set and the training data label set to obtain a remote sensing intelligent application optimization model.

[0073] A third aspect of the present invention discloses another remote sensing intelligent application model update device, the device comprising:

[0074] a memory storing executable program code;

[0075] a processor coupled to the memory;

[0076] The processor calls the executable program code stored in the memory to execute part or all of the steps in the remote sensing intelligent application model updating method disclosed in the first aspect of the embodiment of the present invention.

[0077] 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 intelligent application model updating method disclosed in the first aspect of the embodiment of the present invention.

[0078] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0079] In an embodiment of the present invention, the training data of the remote sensing intelligent application model is updated online based on user needs and usage feedback, and the intelligent model is updated and iterated using the continuously updated data, thereby improving the continuous update learning capability of the remote sensing data intelligent model. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] 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.

[0081] Figure 1 This is a scenario diagram of a remote sensing intelligent application model update system disclosed in an embodiment of the present invention;

[0082] Figure 2 This is a flow chart of a remote sensing intelligent application model updating method disclosed in an embodiment of the present invention;

[0083] Figure 3 This is a structural diagram of a remote sensing intelligent application model updating device disclosed in an embodiment of the present invention;

[0084] Figure 4 This is a structural diagram of another remote sensing intelligent application model updating device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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 instrumentation. As a scientific discipline, computer vision studies related theories and technologies, aiming 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.

[0093] 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.

[0094] 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, Qianyi Tongwen 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.

[0095] The embodiments of the present application provide a remote sensing intelligent application model updating method, apparatus, computer equipment, and computer-readable storage medium, which are described in detail below.

[0096] See also Figure 1 , Figure 1 This is a schematic diagram of an application scenario of the remote sensing intelligent application model update system provided in an embodiment of the present application in a remote sensing positioning system. The remote sensing positioning system may include a computer device 100, in which the remote sensing intelligent application model update system is integrated. Figure 1 Computer equipment in.

[0097] 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.

[0098] 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.

[0099] 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 system can also include one or more other services, which are not limited here.

[0100] In addition, if Figure 1 As shown, the remote sensing positioning system may further include a memory 200 for storing simulation data, such as training data and label data.

[0101] It should be noted that Figure 1The scenario diagram of the remote sensing positioning system shown is only an example. The multi-sample simulation control system and scenario for air-ground game 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 the simulation control management system 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.

[0102] This invention discloses a remote sensing intelligent application model update method and device. This method performs online updates of remote sensing intelligent application model training data based on user needs and usage feedback, and utilizes continuously updated data to iterate the intelligent model, thereby improving the continuous update and learning capabilities of the remote sensing data intelligent model. These are described in detail below.

[0103] Example 1

[0104] See also Figure 2 , Figure 2 This is a flow chart of a remote sensing intelligent application model update method disclosed in an embodiment of the present invention. Figure 2 The described remote sensing intelligent application model update method is applied to a remote sensing object positioning application system, such as a local server or cloud server for remote sensing object positioning system management, and the embodiment of the present invention does not limit this. Figure 2 As shown, the remote sensing intelligent application model update may include the following operations:

[0105] In order to solve the above technical problems, the first aspect of the embodiment of the present invention discloses a remote sensing intelligent application model updating method, which includes:

[0106] S1, obtain the basic model and training data set of remote sensing intelligent application;

[0107] S2, processing the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set;

[0108] S3: Processing the first application optimization model using the measured data set and the training data label set to obtain a remote sensing intelligent application optimization model.

[0109] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can be implemented to update the remote sensing intelligent application model training data online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0110] In an optional embodiment, in the above step S2, the remote sensing intelligent application basic model is processed using the training data set to obtain the first application optimization model and the training data label set, including:

[0111] S21, obtaining the training data set;

[0112] S22, dividing the training data set according to a preset ratio to obtain a data training set and a data test set;

[0113] It should be noted that, in this embodiment, the preset ratio is 4:1;

[0114] Set the number of training times to 1;

[0115] S23, using the remote sensing intelligent application basic model, processing the data training set to obtain first image object information;

[0116] S24, based on the model loss function, using the first image object information and the training data label set to update the parameters of the remote sensing intelligent application basic model;

[0117] S25, determining whether the training number value is greater than a preset training number threshold, and obtaining a training number determination result;

[0118] When the result of the training number judgment is yes, executing S23;

[0119] When the result of the training number judgment is no, the training number value is increased by 1, and S26 is executed;

[0120] S26, using the remote sensing intelligent application basic model, processing the data test set to obtain second image object information;

[0121] S27, comparing the second image object information with the data test label set to obtain prediction accuracy information;

[0122] S28, determining whether the prediction accuracy information is greater than a preset accuracy threshold, and obtaining an accuracy determination result;

[0123] When the accuracy determination result is no, executing S22;

[0124] If the accuracy determination result is yes, a first application optimization model is obtained and S29 is executed;

[0125] S29, fusing the data training label set and the data test label set to obtain a training data label set;

[0126] It should be noted that the first application optimization model refers to the first remote sensing intelligent application optimization model obtained after training the remote sensing intelligent application basic model.

[0127] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention is implemented, and the remote sensing intelligent application basic model is processed using the training data set to obtain a first application optimization model. On this basis, the remote sensing intelligent application model training data can be updated online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update and learning ability of the remote sensing data intelligent model.

[0128] In an optional embodiment, in the above step S24, the remote sensing intelligent application basic model includes a model input terminal, a feature extraction module, a feature fusion module and a prediction output terminal;

[0129] The model input end, the feature extraction module, the feature fusion module and the prediction output end are sequentially data-connected;

[0130] The model loss function expression is:

[0131] L = A + αB + βC;

[0132] Among them, A represents classification loss; B represents position loss; C represents confidence loss; α represents the first weight coefficient; = represents the second weight coefficient;

[0133] It should be noted that, in this embodiment, the first weight coefficient is set to 1;

[0134] It should be noted that, in this embodiment, the second weight coefficient is set to 1.

[0135] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can be implemented to update the remote sensing intelligent application model training data online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0136] In an optional embodiment, in the above step S28, the fusing of the training data training set label information and the training data test set label information to obtain the training data label set includes:

[0137] S281, traversing the training data training set to obtain all historical training data;

[0138] S282, parsing any of the historical training data to obtain training data type information and training data label information;

[0139] S283, traversing the training data test set to obtain all historical test data;

[0140] S284, parsing any of the historical test data to obtain test data type information and test data label information;

[0141] S285, performing deduplication processing on the training data type information, the training data label information, the test data type information, and the test data label information to obtain a training data label set;

[0142] It should be noted that the deduplication process means retaining only one of multiple identical data types and data labels.

[0143] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can be implemented to update the remote sensing intelligent application model training data online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0144] In an optional embodiment, in the above step S3, the first application optimization model is processed using the measured data set and the training data label set to obtain the remote sensing intelligent application optimization model, including:

[0145] S31, obtaining a target area vector mask set;

[0146] S32, processing the measured data set based on the target area vector mask set to obtain a first positioning classification data set and a second positioning classification data set;

[0147] It should be noted that the first positioning classification data set includes several pieces of first positioning classification data;

[0148] It should be noted that the first classification positioning data represents the measured remote sensing image data with accurate positioning classification;

[0149] It should be noted that the second positioning classification data set includes a plurality of second positioning classification data;

[0150] It should be noted that the second classification positioning data refers to measured remote sensing image data with positioning classification errors, missed detections and false alarms;

[0151] It should be noted that the measured data set is a combination of the first classification positioning data set and the second classification positioning data set;

[0152] S33, using a target uncertainty acquisition model to process the training data set, the first positioning classification data set, and the second positioning classification data set to obtain a training data increment set;

[0153] S34, labeling the training data incremental set based on the training data label set to obtain an incremental data label set;

[0154] S35, based on the incremental data label set, using the incremental training data set to process the first application optimization model to obtain a second application optimization model;

[0155] It should be noted that the second application optimization model refers to a second remote sensing intelligent application optimization model obtained by iteratively processing the first application optimization model;

[0156] S36, fusing the incremental training label set and the training data label set to obtain a historical label set;

[0157] Increase the number of incremental processing times by 1;

[0158] S37, determining whether the number of incremental processing times is greater than the number of iterations, and obtaining an iteration determination result;

[0159] When the iterative judgment result is no, the training data increment set is updated to the training data set, the historical label set is updated to the training data label set, and S32 is executed;

[0160] When the iterative judgment result is yes, the second remote sensing image object classification optimization model is updated to the remote sensing intelligent application optimization model.

[0161] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention is implemented, and the first application optimization model is updated and iterated using the measured data set and the training data label set, thereby improving the continuous update learning capability of the remote sensing data intelligent model.

[0162] In an optional embodiment, in step 31 above, obtaining the target area vector mask set includes:

[0163] S311, acquiring a remote sensing image set of the target area;

[0164] S312, traversing the target area remote sensing image set to obtain all the target area remote sensing images;

[0165] S313, using the first application optimization model, processing any of the target area remote sensing images to obtain target positioning classification result information;

[0166] S314, verifying the target positioning and classification result information to obtain a target area vector mask;

[0167] It should be noted that the target positioning and classification result information represents the positioning and classification result of the model object in the region of interest;

[0168] It should be noted that the verification means matching and verifying the target location classification result information using a known target information database, eliminating false alarm target area data, and obtaining a target area vector mask;

[0169] S315, using the regional vector mask acquisition model to process the target regional vector mask to obtain a target regional vector mask set;

[0170] The regional vector mask acquisition model expression is:

[0171]

[0172] Wherein, A represents the target area vector mask set; A i ; represents the i-th target region vector mask; i represents the index of the target region; U represents the union calculation.

[0173] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can be implemented to update the remote sensing intelligent application model training data online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0174] In an optional embodiment, in step 33, the target uncertainty acquisition model is used to process the training data set, the first positioning classification data set, and the second positioning classification data set to obtain a training data increment set, including:

[0175] S331, processing the training data set and the first positioning classification data set to obtain a first incremental training sample subset;

[0176] The first incremental training sample subset includes a plurality of first incremental training samples;

[0177] S332: Process the second positioning classification data set based on the uncertainty calculation model to obtain a second incremental training sample subset;

[0178] The second incremental training sample subset includes a plurality of second incremental training samples;

[0179] S333: All the first incremental training samples and the second incremental training samples are arranged and combined in order to obtain an incremental set of training data.

[0180] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention is implemented, the target uncertainty is used to obtain the model, the training data set, the first positioning classification data set and the second positioning classification data set are processed to obtain an incremental set of training data. On this basis, the remote sensing intelligent application model training data can be updated online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0181] In an optional embodiment, in the above step S331, the target uncertainty acquisition model expression is:

[0182] IA{img i}=1-AP50(TL(img i ), PR(img i ));.

[0183] Among them, i represents the index of the remote sensing image; img i is the i-th remote sensing image; IA{img i} represents the target uncertainty of the i-th remote sensing image; TL(img i ) is the target object label in the i-th remote sensing image; PR(img i ) is the prediction result of the i-th remote sensing image; AP60() represents the first threshold accuracy of calculating the i-th remote sensing image.

[0184] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can obtain target uncertainty according to user needs, update the remote sensing intelligent application model training data online based on the target uncertainty, and use the continuously updated data to update and iterate the intelligent model, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0185] In an optional embodiment, in step S331, the processing of the training dataset and the first positioning classification dataset to obtain a first incremental training sample subset includes:

[0186] S3311: Perform a combination calculation on the training dataset and the first positioning classification dataset to obtain a third positioning classification dataset;

[0187] S3312, traverse the third positioning classification data set to obtain all third positioning classification data;

[0188] S3313: Process any of the third positioning classification data using the first application optimization model to obtain positioning target type information;

[0189] The positioning target type information includes target quantity information and target type information;

[0190] S3314: Arrange and combine all the third positioning classification data in order according to the target quantity information to obtain a fourth positioning classification data set;

[0191] S3315: Perform uniform sampling processing on the fourth positioning classification data set to obtain a first incremental training sample subset.

[0192] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can be implemented to update the remote sensing intelligent application model training data online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0193] In an optional embodiment, in the above step S35, the first application optimization model is processed using the training data increment set to obtain a second application optimization model, including:

[0194] S351, obtaining the training data increment set;

[0195] The incremental training data set includes a plurality of incremental training data; the incremental training data is training data or first classification positioning data or second classification positioning data;

[0196] S352, traversing the training data incremental set to obtain all incremental training data;

[0197] S353, parsing any of the incremental training data to obtain data type information;

[0198] It should be noted that the parsing process means obtaining the data type information according to the value of the data type identification bit;

[0199] S354, performing matching processing on the training data label set based on the data type information to obtain incremental training label information;

[0200] It should be noted that the matching process means obtaining the training data labels in the training data label set that are consistent with the data type;

[0201] S355: All the incremental training label information is combined in order to obtain an incremental training label set.

[0202] S356: Based on the incremental training label set, the first application optimization model is processed using the training data incremental set to obtain a second application optimization model.

[0203] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention is implemented, the target uncertainty is used to obtain the model, the training data set, the first positioning classification data set and the second positioning classification data set are processed to obtain an incremental set of training data. On this basis, the remote sensing intelligent application model training data can be updated online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0204] In an optional embodiment, in step S353, the step of processing the first application optimization model based on the incremental training label set and using the incremental training data set to obtain the second application optimization model includes:

[0205] S3561, traverse the training data incremental set to obtain all incremental training data;

[0206] S3562: Analyze any incremental training data to obtain an incremental training sample type and incremental training sample data;

[0207] S3563, determining whether the incremental training sample type is equal to a specified type value, and obtaining an incremental type determination result;

[0208] It should be noted that, in this embodiment, the specified type value is set to 1;

[0209] S3564: When the incremental type determination result is yes, input the incremental training sample data into the first application optimization model based on the first loss function to obtain third image object classification information;

[0210] The first loss function expression is:

[0211] L ROI =LClass+αL locate +βL confi

[0212] Among them, L ROI represents the model loss value of the first application optimization model; LClass represents the classification loss value of the first application optimization model; L locate L represents the position loss value of the first application optimization model; confi represents the confidence loss value of the first application optimization model; α represents the third weight coefficient; β represents the fourth weight coefficient;

[0213] It should be noted that, in this embodiment, the third weight coefficient is set to 1;

[0214] It should be noted that, in this embodiment, the fourth weight coefficient is set to 1.

[0215] It should be noted that, when the incremental type determination result is yes, it indicates that the incremental training sample data is training data or first classification positioning data; the incremental training sample data is a remote sensing image of the target area;

[0216] When the incremental type determination result is no, inputting the incremental training sample data into the first application optimization model based on the second loss function to obtain third image object classification information;

[0217] The second loss function expression is:

[0218] L non-ROI =L locate +yL confi

[0219] Among them, L non-ROI represents the model loss value of the second application optimization model; L locate L represents the position loss value of the first application optimization model; confi represents the confidence loss value of the first application optimization model; Y represents the fifth weight coefficient;

[0220] It should be noted that, in this embodiment, the fifth weight coefficient is set to 0.5;

[0221] It should be noted that, when the incremental type determination result is no, it means that the incremental training sample data is second classification positioning data; the incremental training sample data is a remote sensing image of a non-target area;

[0222] S3565: Calculate and process the third image object classification information and the incremental training label set to obtain classification accuracy information;

[0223] It should be noted that the calculation process is performed using the average precision calculation method of the COCO dataset;

[0224] S3566: Determine whether the classification accuracy information is greater than a preset accuracy threshold, and obtain a classification accuracy determination result;

[0225] When the classification accuracy determination result is negative, executing S3562;

[0226] If the classification accuracy judgment result is yes, obtaining a second application optimization model;

[0227] It should be noted that, in this embodiment, the accuracy threshold is set to 0.5;

[0228] It can be seen that the remote sensing intelligent application model updating method described in the embodiment of the present invention can be implemented to update the remote sensing intelligent application model training data online according to user needs, and the intelligent model can be updated and iterated using the continuously updated data, thereby improving the continuous update learning ability of the remote sensing data intelligent model.

[0229] Example 2

[0230] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a remote sensing intelligent application model updating device disclosed in an embodiment of the present invention. Figure 3 The described device can be applied to a remote sensing object positioning system, such as a local server or cloud server for remote sensing object positioning, and the embodiments of the present invention do not limit this. Figure 3 As shown, the device may include:

[0231] Acquisition module 101, used to acquire remote sensing intelligent application basic model and training data set;

[0232] A first processing module 102 is configured to process the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set;

[0233] The second processing module 103 is used to process the first application optimization model using the measured data set and the training data label set to obtain a remote sensing intelligent application optimization model.

[0234] Example 3

[0235] See also Figure 4 , Figure 4 This is a structural diagram of another remote sensing intelligent application model updating device disclosed in an embodiment of the present invention. Figure 4 The described device can be applied to a satellite observation system, such as a local server or cloud server for satellite observation, etc., and the embodiments of the present invention do not limit this. Figure 4 As shown, the device may include:

[0236] A memory 201 storing executable program code;

[0237] a processor 202 coupled to the memory;

[0238] The processor 202 calls the executable program code stored in the memory 201 to execute the steps of the remote sensing intelligent application model updating method described in the first embodiment.

[0239] Example 4

[0240] 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 intelligent application model updating method described in the first embodiment.

[0241] 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.

[0242] 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 part 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.

[0243] Finally, it should be noted that the remote sensing intelligent application model updating method and device 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 with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A remote sensing intelligent application model updating method, characterized in that: The method comprises: S1, obtain the basic model and training data set of remote sensing intelligent application; S2, processing the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set; S3, processing the first application optimization model using the measured data set and the training data label set to obtain a remote sensing intelligent application optimization model; The method of processing the first application optimization model using the measured data set and the training data label set to obtain the remote sensing intelligent application optimization model includes: S31, obtaining a target area vector mask set; S32, processing the measured data set based on the target area vector mask set to obtain a first positioning classification data set and a second positioning classification data set; The first positioning classification data set includes a plurality of first positioning classification data; The second positioning classification data set includes a plurality of second positioning classification data; S33, using a target uncertainty acquisition model to process the training data set, the first positioning classification data set, and the second positioning classification data set to obtain a training data increment set; S34, labeling the training data incremental set based on the training data label set to obtain an incremental data label set; S35, based on the incremental data label set, using the incremental training data set to process the first application optimization model to obtain a second application optimization model; S36, fusing the incremental training label set and the training data label set to obtain a historical label set; Increase the number of incremental processing times by 1; S37, determining whether the number of incremental processing times is greater than the number of iterations, and obtaining an iteration determination result; When the iterative judgment result is no, the training data increment set is updated to the training data set, the historical label set is updated to the training data label set, and S32 is executed; When the iterative judgment result is yes, the second application optimization model is updated to the remote sensing intelligent application optimization model; Among them, the target uncertainty acquisition model expression is: IA{img i }=1-AP50(TL(img i ),PR(img i )); Among them, i represents the index of the remote sensing image; img i is the i-th remote sensing image; IA{img i } represents the target uncertainty of the i-th remote sensing image; TL(img i ) is the target object label in the i-th remote sensing image; PR(img i ) is the prediction result of the i-th remote sensing image; AP50() represents the first threshold accuracy of calculating the i-th remote sensing image.

2. The remote sensing intelligent application model updating method according to claim 1, characterized in that: The step of processing the remote sensing intelligent application basic model using the training data set to obtain a first application optimization model and a training data label set includes: S21, obtaining the training data set; S22, dividing the training data set according to a preset ratio to obtain a data training set and a data test set; Set the number of training times to 1; S23, using the remote sensing intelligent application basic model, processing the data training set to obtain first image object information; S24, based on the model loss function, using the first image object information and the training data label set to update the parameters of the remote sensing intelligent application basic model; S25, determining whether the training number value is greater than a preset training number threshold, and obtaining a training number determination result; When the result of the training number judgment is yes, executing S23; When the result of the training number judgment is no, the training number value is increased by 1, and S26 is executed; S26, using the remote sensing intelligent application basic model, processing the data test set to obtain second image object information; S27, comparing the second image object information with the data test label set to obtain prediction accuracy information; S28, determining whether the prediction accuracy information is greater than a preset accuracy threshold, and obtaining an accuracy determination result; When the accuracy determination result is no, executing S22; If the accuracy determination result is yes, a first application optimization model is obtained and S29 is executed; S29, fusing the data training label set and the data test label set to obtain a training data label set.

3. The remote sensing intelligent application model updating method according to claim 1, characterized in that: The obtaining of the target area vector mask set includes: S311, acquiring a remote sensing image set of the target area; S312, traversing the target area remote sensing image set to obtain all the target area remote sensing images; S313, using the first application optimization model, processing any of the target area remote sensing images to obtain target positioning classification result information; S314, verifying the target positioning and classification result information to obtain a target area vector mask; S315, using the regional vector mask acquisition model to process the target regional vector mask to obtain a target regional vector mask set; The regional vector mask acquisition model expression is: Wherein, A represents the target area vector mask set; A i； Represents the i-th target region vector mask; i represents the index of the target region; U represents the union calculation.

4. The remote sensing intelligent application model updating method according to claim 1, characterized in that: The target uncertainty acquisition model is used to process the training data set, the first positioning classification data set, and the second positioning classification data set to obtain a training data increment set, including: S331, processing the training data set and the first positioning classification data set to obtain a first incremental training sample subset; The first incremental training sample subset includes a plurality of first incremental training samples; S332: Process the second positioning classification data set based on the uncertainty calculation model to obtain a second incremental training sample subset; The second incremental training sample subset includes a plurality of second incremental training samples; S333: All the first incremental training samples and the second incremental training samples are arranged and combined in order to obtain an incremental set of training data.

5. The remote sensing intelligent application model updating method according to claim 4, characterized in that: The processing of the training data set and the first positioning classification data set to obtain a first incremental training sample subset includes: S3311: Perform a combination calculation on the training dataset and the first positioning classification dataset to obtain a third positioning classification dataset; S3312, traverse the third positioning classification data set to obtain all third positioning classification data; S3313: Process any of the third positioning classification data using the first application optimization model to obtain positioning target type information; The positioning target type information includes target quantity information and target type information; S3314: Arrange and combine all the third positioning classification data in order according to the target quantity information to obtain a fourth positioning classification data set; S3315: Perform uniform sampling processing on the fourth positioning classification data set to obtain a first incremental training sample subset.

6. The remote sensing intelligent application model updating method according to claim 1, characterized in that: The step of processing the first application optimization model based on the incremental data label set and utilizing the incremental training data set to obtain a second application optimization model includes: S351, obtaining the training data incremental set; The incremental training data set includes a plurality of incremental training data; the incremental training data is training data or first classification positioning data or second classification positioning data; S352, traversing the training data incremental set to obtain all incremental training data; S353, parsing any of the incremental training data to obtain data type information; S354, performing matching processing on the training data label set based on the data type information to obtain incremental training label information; S355, combining all the incremental training label information in order to obtain an incremental training label set; S356: Based on the incremental training label set, the first application optimization model is processed using the training data incremental set to obtain a second application optimization model.

7. A remote sensing intelligent application model updating 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 intelligent application model updating method according to any one of claims 1-6.

Images