CN117788963B - Remote sensing image data management method and system based on deep learning - Google Patents
Remote sensing image data management method and system based on deep learning Download PDFInfo
- Publication number
- CN117788963B CN117788963B CN202410213864.5A CN202410213864A CN117788963B CN 117788963 B CN117788963 B CN 117788963B CN 202410213864 A CN202410213864 A CN 202410213864A CN 117788963 B CN117788963 B CN 117788963B
- Authority
- CN
- China
- Prior art keywords
- image
- scale
- locations
- attention
- feature extraction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013523 data management Methods 0.000 title claims abstract description 15
- 238000013135 deep learning Methods 0.000 title claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 34
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 238000002372 labelling Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 18
- 230000004913 activation Effects 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a remote sensing image data management method and a remote sensing image data management system based on deep learning, wherein the method comprises the following steps: acquiring an image, dividing the image into image images with multiple scales according to multiple sizes, and inputting the image images into a convolutional neural network; setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed for each region of an image; and labeling each extracted image characteristic value according to a preset characteristic classification label, thereby completing image characteristic classification.
Description
Technical Field
The invention belongs to the technical field of image feature classification, and particularly relates to a remote sensing image data management method and system based on deep learning.
Background
Significant advances have been made in image feature extraction techniques. The following are some of the currently mainstream image feature extraction techniques and trends:
Convolutional Neural Network (CNN): CNN is one of the most successful and widely used deep learning models in image processing.
The pre-trained CNN model (e.g., VGG, resNet, inception, mobileNet, etc.) performs well in tasks such as image classification, object detection, and semantic segmentation.
Transfer learning enables the benefit of these pre-trained models also on small-scale data sets.
Self-supervision study: self-supervised learning learns features by using automatically generated labels in images (e.g., image rotation, contrast learning, etc.), without manually marking large amounts of data. This approach is particularly useful in cases where the data is limited or unlabeled.
However, in the prior art, the accuracy of image extraction is not enough, a large amount of manual correction is required, and the automation and intelligence degree are not high.
Disclosure of Invention
In order to solve the technical problems, the invention provides a remote sensing image data management method based on deep learning, which comprises the following steps:
Acquiring an image, dividing the image into image images with multiple scales according to multiple sizes, and inputting the image images into a convolutional neural network;
Setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed for each region of an image;
And labeling each extracted image characteristic value according to a preset characteristic classification label, thereby completing image characteristic classification.
Further, the image feature extraction model includes:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at.
Further, the firstLocations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism.
Further, the initial image is at the firstLocations on a scale ofActivation function atComprising the following steps:
，
further, the first Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,For controlling the adjustment factor of the weight distribution range.
The invention also provides a remote sensing image data management system based on deep learning, which comprises:
the image acquisition module is used for acquiring an image, dividing the image into image images with a plurality of scales according to a plurality of sizes, and inputting the image images into the convolutional neural network;
The image feature extraction module is used for setting an image feature extraction model, extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, and accordingly, the attention weights are distributed to each region of an image;
And the classification module is used for classifying labels according to preset characteristics and labeling the extracted characteristic values of each image so as to finish image characteristic classification.
Further, the image feature extraction model includes:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at.
Further, the firstLocations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism.
Further, the initial image is at the firstLocations on a scale ofActivation function atComprising the following steps:
，
further, the first Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,For controlling the adjustment factor of the weight distribution range.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
The method comprises the steps of obtaining an image, dividing the image into image images with a plurality of scales according to a plurality of sizes, and inputting the image images into a convolutional neural network; setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed for each region of an image; and labeling each extracted image characteristic value according to a preset characteristic classification label, thereby completing image characteristic classification. According to the technical scheme, the image characteristics in the image can be automatically extracted and the characteristic classification is carried out, namely, the image is automatically classified according to the characteristics of mountains, rivers, buildings and the like, so that the time for a user to identify the topography and the landform in the satellite image is greatly saved, meanwhile, the original image is segmented into a plurality of sizes, the image characteristic values are extracted from the sub-images with the plurality of sizes, the operation speed is greatly increased, and the characteristic extraction efficiency is improved.
Drawings
FIG. 1 is a flow chart of the method of embodiment 1 of the present invention;
fig. 2 is a system configuration diagram of embodiment 2 of the present invention.
Detailed Description
In order to better understand the above technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
The method provided by the invention can be implemented in a terminal environment, wherein the terminal can comprise one or more of the following components: processor, storage medium, and display screen. Wherein the storage medium has stored therein at least one instruction that is loaded and executed by the processor to implement the method described in the embodiments below.
The processor may include one or more processing cores. The processor connects various parts within the overall terminal using various interfaces and lines, performs various functions of the terminal and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the storage medium, and invoking data stored in the storage medium.
The storage medium may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (ROM). The storage medium may be used to store instructions, programs, code sets, or instructions.
The display screen is used for displaying a user interface of each application program.
All subscripts in the formula of the invention are only used for distinguishing parameters and have no practical meaning.
In addition, it will be appreciated by those skilled in the art that the structure of the terminal described above is not limiting and that the terminal may include more or fewer components, or may combine certain components, or a different arrangement of components. For example, the terminal further includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, a power supply, and the like, which are not described herein.
Example 1
As shown in fig. 1, an embodiment of the present invention provides a remote sensing image data management method based on deep learning, including:
Step 101, obtaining an image, dividing the image into image images with multiple scales according to multiple sizes (specifically, one scale corresponds to one spatial size range in the image, for example, a small scale can be used for detecting local details, and a large scale is suitable for capturing a whole structure, and introducing multiple scales to help extract features at different detail levels so as to improve understanding ability of a model to a complex image;
102, setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed to each region of an image;
Specifically, the image feature extraction model includes:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at.
Specifically, the firstLocations on a scale ofAttention weight atComprising the following steps:
，
Wherein, For an adjustment factor for controlling the degree of influence of the attention mechanism,The range of (2) is typically a non-negative real number, which may be any positive number, but typically will not be chosen to be too large or too small to avoid problems with gradient explosion or gradient extinction, typically,May range between 0, 1,The acquisition mode of (a) generally comprises: fixed value: a fixed one can be selectedThe value, which is set according to experience or a priori knowledge, may be set to 1, for example, representing that the calculation of the attention weight is affected only by the pixel values of the input image; searching super parameters: the best may be selected by cross-validation or grid search, etcValues, during training, may be tried differentlyValues, and selects the most appropriate value based on model performance.
At the given attention weightingIn the calculation formula of (2), the numerator and the denominator respectively represent different calculation parts, and the specific meaning is as follows:
1. Molecular part
，
This part calculates the current positionAttention weight at. Wherein,Represent the firstAre positioned on the scalePixel value atThen represent the firstIs located at the current position on the scalePixel values at. This part evaluates the importance of the current position by calculating the correlation between the current position and surrounding pixels.
2. Denominator part
，
This part calculates the sum of the attention weights of all the positions for normalization. By calculating the correlations at all locations, a normalized weight distribution can be obtained to ensure that the sum of the attention weights is 1.
Thus, the overall attention weightIs calculated by indexing the correlation of the current position with surrounding pixels and then normalizing the result to represent the importance of the current position.
Specifically, the initial image is at the firstLocations on a scale ofActivation function atComprising the following steps:
。
Specifically, the first Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,For controlling the adjustment factor of the weight distribution range.
All "·" appearing in the above formula are multiplicative.
And 103, labeling each extracted image characteristic value according to a preset characteristic classification label (the characteristic classification label comprises a mountain characteristic label, a river characteristic label, a building classification label and the like and is used for classifying the topography and the building on the image, so as to finish image characteristic classification). In general, the feature labeling may be performed by manual labeling or semantic segmentation, which is not limited by the present invention.
Example 2
As shown in fig. 2, the embodiment of the present invention further provides a remote sensing image data management system based on deep learning, including:
the image acquisition module is used for acquiring an image, dividing the image into image images with a plurality of scales according to a plurality of sizes, and inputting the image images into the convolutional neural network;
The image feature extraction module is used for setting an image feature extraction model, extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, and accordingly, the attention weights are distributed to each region of an image;
Specifically, the image feature extraction model includes:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at.
Specifically, the firstLocations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism.
Specifically, the initial image is at the firstLocations on a scale ofActivation function atComprising the following steps:
。
Specifically, the first Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,For controlling the adjustment factor of the weight distribution range.
And the classification module is used for classifying labels according to preset characteristics and labeling the extracted characteristic values of each image so as to finish image characteristic classification.
Example 3
The embodiment of the invention also provides a storage medium which stores a plurality of instructions for realizing the remote sensing image data management method based on deep learning.
Alternatively, in this embodiment, the storage medium may be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: step 101, obtaining an image, dividing the image into image images with a plurality of scales according to a plurality of sizes, and inputting the image images into a convolutional neural network;
102, setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed to each region of an image;
Specifically, the image feature extraction model includes:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at.
Specifically, the firstLocations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism.
Specifically, the initial image is at the firstLocations on a scale ofActivation function atComprising the following steps:
。
Specifically, the first Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,For controlling the adjustment factor of the weight distribution range.
And 103, labeling each extracted image characteristic value according to a preset characteristic classification label, thereby completing image characteristic classification.
Example 4
The embodiment of the invention also provides electronic equipment, which comprises a processor and a storage medium connected with the processor, wherein the storage medium stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute a remote sensing image data management method based on deep learning.
Specifically, the electronic device of the present embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.
The storage medium may be used to store a software program and a module, for example, in an embodiment of the present invention, a remote sensing image data management method based on deep learning, and the processor executes various functional applications and data processing by running the software program and the module stored in the storage medium, that is, implements the remote sensing image data management method based on deep learning. The storage medium may include a high-speed random access storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage medium. In some examples, the storage medium may further include a storage medium remotely located with respect to the processor, and the remote storage medium may be connected to the terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor may invoke the information stored in the storage medium and the application program through the transmission system to perform the steps of: step 101, obtaining an image, dividing the image into image images with a plurality of scales according to a plurality of sizes, and inputting the image images into a convolutional neural network;
102, setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed to each region of an image;
Specifically, the image feature extraction model includes:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at.
Specifically, the firstLocations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism.
Specifically, the initial image is at the firstLocations on a scale ofActivation function atComprising the following steps:
。
Specifically, the first Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,For controlling the adjustment factor of the weight distribution range.
And 103, labeling each extracted image characteristic value according to a preset characteristic classification label, thereby completing image characteristic classification.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed technology may be implemented in other manners. The system embodiments described above are merely exemplary, and for example, the division of the units is merely a logic function division, and there may be another division manner in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or partly in the form of a software product or all or part of the technical solution, which is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random-access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, etc., which can store program codes.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.
Claims (2)
1. The remote sensing image data management method based on deep learning is used for classifying image features and is characterized by comprising the following steps of:
Acquiring an image, dividing the image into image images with multiple scales according to multiple sizes, and inputting the image images into a convolutional neural network;
setting an image feature extraction model, and extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that respective attention weights are distributed to each region of an image, and the image feature extraction model comprises:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at;
First, the Locations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism;
The initial image is at the first Locations on a scale ofActivation function atComprising the following steps:
，
First, the Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,An adjustment factor for controlling the weight distribution range;
And labeling each extracted image characteristic value according to a preset characteristic classification label, thereby completing image characteristic classification.
2. A remote sensing image data management system based on deep learning, which is used for classifying image features, and is characterized by comprising:
the image acquisition module is used for acquiring an image, dividing the image into image images with a plurality of scales according to a plurality of sizes, and inputting the image images into the convolutional neural network;
The setting model module is used for setting an image feature extraction model, extracting an image feature value at each coordinate according to a pixel value at each coordinate on each scale, wherein attention weights are set in the image feature extraction model, so that the respective attention weights are distributed to each region of an image, and the image feature extraction model comprises:
，
Wherein, To be positioned atThe image characteristic value of the position is calculated,As a total number of dimensions,Is the firstThe vertical dimension of the convolution kernel in the individual dimensions,Is the firstThe horizontal dimension of the convolution kernel in each dimension,Is the firstLocations on a scale ofThe attention weight of the person,Is the firstLocation on scaleThe adaptive weights at which to place,Is the firstLocations on a scale ofAt the pixel values of the original video image,In the first imageLocations on a scale ofAn activation function at;
First, the Locations on a scale ofAttention weight atComprising the following steps:
，
Wherein, Is an adjustment factor for controlling the degree of influence of the attention mechanism;
The initial image is at the first Locations on a scale ofActivation function atComprising the following steps:
，
First, the Location on scaleAdaptive weights atComprising the following steps:
，
Wherein, To at the firstLocations on a scale ofAt a distance from the central position,To at the firstLocations on a scale ofAt a distance from the central position,An adjustment factor for controlling the weight distribution range;
And the classification module is used for classifying labels according to preset characteristics and labeling the extracted characteristic values of each image so as to finish image characteristic classification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410213864.5A CN117788963B (en) | 2024-02-27 | 2024-02-27 | Remote sensing image data management method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410213864.5A CN117788963B (en) | 2024-02-27 | 2024-02-27 | Remote sensing image data management method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117788963A CN117788963A (en) | 2024-03-29 |
| CN117788963B true CN117788963B (en) | 2024-07-05 |
Family
ID=90394862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410213864.5A Active CN117788963B (en) | 2024-02-27 | 2024-02-27 | Remote sensing image data management method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117788963B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115063704A (en) * | 2022-06-28 | 2022-09-16 | 南京邮电大学 | Unmanned aerial vehicle monitoring target classification method based on three-dimensional feature fusion semantic segmentation |
| CN116342931A (en) * | 2023-02-26 | 2023-06-27 | 深圳大学 | Fur image classification method, system and storage medium for multi-scale attention |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220114424A1 (en) * | 2020-10-08 | 2022-04-14 | Niamul QUADER | Multi-bandwidth separated feature extraction convolution layer for convolutional neural networks |
| CN113537254B (en) * | 2021-08-27 | 2022-08-26 | 重庆紫光华山智安科技有限公司 | Image feature extraction method and device, electronic equipment and readable storage medium |
| FR3133256B3 (en) * | 2022-03-01 | 2024-03-08 | Univ Anhui Sci & Technology | Regularization method to improve training adequacy of a convolutional neural network |
| CN114780767B (en) * | 2022-04-14 | 2024-08-13 | 武汉大学 | Large-scale image retrieval method and system based on deep convolutional neural network |
| CN116012722A (en) * | 2022-09-08 | 2023-04-25 | 中国人民解放军战略支援部队信息工程大学 | Remote sensing image scene classification method |
| CN115620054A (en) * | 2022-10-12 | 2023-01-17 | 南京旭锐软件科技有限公司 | Defect classification method and device, electronic equipment and storage medium |
-
2024
- 2024-02-27 CN CN202410213864.5A patent/CN117788963B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115063704A (en) * | 2022-06-28 | 2022-09-16 | 南京邮电大学 | Unmanned aerial vehicle monitoring target classification method based on three-dimensional feature fusion semantic segmentation |
| CN116342931A (en) * | 2023-02-26 | 2023-06-27 | 深圳大学 | Fur image classification method, system and storage medium for multi-scale attention |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117788963A (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229591B (en) | Neural network adaptive training method and apparatus, device, program, and storage medium | |
| CN108288051B (en) | Pedestrian re-recognition model training method and device, electronic equipment and storage medium | |
| CN112651438A (en) | Multi-class image classification method and device, terminal equipment and storage medium | |
| CN111325271B (en) | Image classification method and device | |
| CN109583449A (en) | Character identifying method and Related product | |
| CN112668579A (en) | Weak supervision semantic segmentation method based on self-adaptive affinity and class distribution | |
| CN111428557A (en) | Method and device for automatically checking handwritten signature based on neural network model | |
| WO2018196718A1 (en) | Image disambiguation method and device, storage medium, and electronic device | |
| CN110765882B (en) | Video tag determination method, device, server and storage medium | |
| CN113869282A (en) | Face recognition method, hyper-resolution model training method and related equipment | |
| CN112818995B (en) | Image classification method, device, electronic equipment and storage medium | |
| CN115861462B (en) | Training method and device for image generation model, electronic equipment and storage medium | |
| CN112528318A (en) | Image desensitization method and device and electronic equipment | |
| CN111373393B (en) | Image retrieval method and device and image library generation method and device | |
| CN116681960A (en) | Intelligent mesoscale vortex identification method and system based on K8s | |
| Ji et al. | Apple fruit recognition based on a deep learning algorithm using an improved lightweight network | |
| CN113610016A (en) | Training method, system, equipment and storage medium of video frame feature extraction model | |
| CN111429414B (en) | Artificial intelligence-based focus image sample determination method and related device | |
| CN117830701A (en) | Attention mechanism-based multiscale feature fusion star map identification method and device | |
| CN117788963B (en) | Remote sensing image data management method and system based on deep learning | |
| CN110768864B (en) | Method and device for generating images in batches through network traffic | |
| CN111797737A (en) | Remote sensing target detection method and device | |
| CN113569809A (en) | Image processing method, device and computer readable storage medium | |
| CN113033263A (en) | Face image age feature recognition method | |
| CN115311573B (en) | Site line detection and target positioning method, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |