CN114511702A - Remote sensing image segmentation method and system based on multi-scale weighted attention - Google Patents
Remote sensing image segmentation method and system based on multi-scale weighted attention Download PDFInfo
- Publication number
- CN114511702A CN114511702A CN202210040070.4A CN202210040070A CN114511702A CN 114511702 A CN114511702 A CN 114511702A CN 202210040070 A CN202210040070 A CN 202210040070A CN 114511702 A CN114511702 A CN 114511702A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- feature map
- feature
- scale
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a remote sensing image segmentation method and a system based on multi-scale weighted attention, wherein the method comprises the following steps: s1, obtaining remote sensing images of a target object in different scales, and respectively carrying out feature extraction on each remote sensing image to generate a plurality of first feature maps with different high and low resolutions; s2, randomly selecting a part of the remote sensing image, and capturing the spatial dependence between any two positions of the remote sensing image corresponding to the first characteristic diagram to obtain a second characteristic diagram; and step S3, performing corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map, and performing object segmentation based on the first feature map, the second feature map, and the third feature map. By inputting the feature maps with different scales in the model training stage and then fusing the different feature maps, the problem of ground object class confusion caused by different object class scales under different resolutions is solved, and the class classification precision is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of semantic segmentation of remote sensing images, in particular to a remote sensing image segmentation method and system based on multi-scale weighted attention.
Background
In recent years, with the rapid development of remote sensing acquisition technology, the application of remote sensing images is more and more extensive. The remote sensing image has a large amount of ground feature information, and due to the diversity and complexity of different ground feature information, the semantic segmentation of the remote sensing image is difficult.
The semantic segmentation of the current remote sensing image mainly comprises two modes of a traditional image segmentation algorithm and image segmentation based on deep learning. The traditional algorithm is low in segmentation precision and low in segmentation efficiency. The image segmentation based on deep learning solves the segmentation problem of the remote sensing image by utilizing the powerful characteristic learning capability of a convolutional neural network. The ground features in the remote sensing images under different ground resolutions have different scales and ground feature characteristics, different ground feature class confusion is easy to occur in a convolutional neural network model which is input into a single-scale feature map, and target detail information is easy to lose in multi-class segmentation of the remote sensing images.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a remote sensing image segmentation method and system based on multi-scale weighted attention.
In order to solve the above technical problem, in a first aspect, an embodiment of the present invention provides a remote sensing image segmentation method based on multi-scale weighted attention, including:
s1, obtaining remote sensing images of a target object in different scales, and respectively carrying out feature extraction on each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
s2, randomly selecting a part of the remote sensing image, and capturing the spatial dependence between any two positions of the remote sensing image corresponding to the first characteristic diagram to obtain a second characteristic diagram;
step S3, performing corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map, and performing object segmentation based on the first feature map, the second feature map, and the third feature map.
Preferably, after generating a plurality of feature maps with different high and low resolutions in step S1, the method further includes:
and performing feature enhancement processing on the feature map based on an ocrnet model to enhance the context semantic information of the feature map.
Preferably, the step S1 specifically includes:
s11, obtaining a remote sensing image containing a target object, performing convolution, batch normalization and activation function processing on the remote sensing image, and scaling the remote sensing image into remote sensing images with different scales, wherein the remote sensing images with different scales at least comprise a first scale remote sensing image and a second scale remote sensing image;
and S12, extracting the features of the remote sensing image based on an hrnetV2 backbone feature extraction model to obtain a plurality of first feature maps with different resolutions.
Preferably, the step S2 specifically includes:
carrying out feature enhancement processing on a first feature map corresponding to the first-scale remote sensing image and the second-scale remote sensing image;
and adopting the position attention with different weight coefficients to capture the spatial dependence between any two positions of the first characteristic diagram corresponding to the first-scale remote sensing image to obtain a second characteristic diagram.
Preferably, in step S3, the dividing the object based on the first feature map, the second feature map, and the third feature map specifically includes:
and inputting the first feature map, the second feature map and the third feature map into a pre-trained segmentation model to predict the pixel class of each feature map under the original size of the remote sensing image and output a segmentation image of each target object in the remote sensing image.
In a second aspect, an embodiment of the present invention provides a remote sensing image segmentation system based on multi-scale weighted attention, including:
the scale characteristic diagram module is used for acquiring remote sensing images of the target object in different scales;
the backbone feature extraction module is used for extracting features of each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
the weighted attention module randomly selects part of the remote sensing image, captures the spatial dependence between any two positions of the part of the remote sensing image corresponding to the first characteristic diagram, and obtains a second characteristic diagram;
the feature fusion module is used for carrying out corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map;
and the post-processing output module is used for segmenting the target object based on the first feature map, the second feature map and the third feature map.
Preferably, the method further comprises the following steps:
and the feature enhancement module is used for carrying out feature enhancement processing on the feature graph based on the ocrnet model so as to enhance the context semantic information of the feature graph.
Preferably, the remote sensing images with different scales at least comprise the first-scale remote sensing image and the second-scale remote sensing image;
the feature fusion module is specifically used for capturing the spatial dependence between any two positions of the first feature map corresponding to the first scale remote sensing image by adopting the position attention of different weight coefficients to obtain a second feature map;
and the post-processing output module is used for predicting pixel categories of all feature maps of the remote sensing images under the original sizes based on the first scale remote sensing image, the second scale remote sensing image and the second feature map corresponding to the first scale remote sensing image after feature fusion of the first scale remote sensing image, and outputting segmentation images of all target objects in the remote sensing images.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the program, implements the steps of the remote sensing image segmentation method based on multi-scale weighted attention according to the embodiment of the first aspect of the present invention.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for remote sensing image segmentation based on multi-scale weighted attention according to an embodiment of the first aspect of the present invention.
The invention has the beneficial effects that: compared with the traditional image segmentation algorithm, the feature maps with different scales are input in the model training stage, and then the different feature maps are fused, so that the problem of ground feature class confusion caused by different object class scales at different resolutions is solved, and the class classification precision is improved; the segmentation precision is higher, and the efficiency is higher; compared with a convolutional neural network model with a single-scale characteristic diagram as input, the remote sensing image segmentation method based on multi-scale weighted attention can effectively reduce confusion of different ground object categories and improve segmentation precision; can pay more attention to the detailed information expression among ground object categories and improve the segmentation precision
Drawings
FIG. 1 is a flow chart of a remote sensing image segmentation method based on multi-scale weighted attention according to an embodiment of the invention;
FIG. 2 is a flow chart of a remote sensing image segmentation method based on multi-scale weighted attention according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a remote sensing image to be segmented;
FIG. 4 is a schematic diagram of a remote sensing segmented image segmented by the method according to the embodiment of the invention;
FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the invention;
fig. 6 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the embodiment of the present application, the term "and/or" is only one kind of association relationship describing an associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, the terms "comprise" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a system, product or apparatus that comprises a list of elements or components is not limited to only those elements or components but may alternatively include other elements or components not expressly listed or inherent to such product or apparatus. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Fig. 1 to fig. 2 provide a remote sensing image segmentation method based on multi-scale weighted attention in an embodiment of the present invention, including:
s1, obtaining remote sensing images of a target object in different scales, and respectively carrying out feature extraction on each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
s11, obtaining a remote sensing image containing a target object, performing convolution, batch normalization and activation function processing on the remote sensing image, and scaling the remote sensing image into remote sensing images with different scales, wherein the remote sensing images with different scales at least comprise a first scale remote sensing image and a second scale remote sensing image; for example, the original image is zoomed into a scale of 0.5 to generate a first scale remote sensing image, and the original image is zoomed into a scale of 1 to generate a second scale remote sensing image; the first scale remote sensing image and the second scale remote sensing image are obtained after convolution, batch normalization and activation function activation.
And S12, extracting the features of the remote sensing image based on an hrnetV2 backbone feature extraction model to obtain a plurality of first feature maps with different resolutions. The features of the HRNeTV2 mainly come from a parallel feature extraction part, and high-resolution and medium-low resolution features are always kept in the feature extraction process.
And performing feature enhancement processing on the feature map based on an ocrnet model to enhance the context semantic information of the feature map. The ocrnet model integrates context information through the correlation between the current pixel position and the contextual pixels, resulting in enhanced pixel representation.
S2, randomly selecting a part of the remote sensing image, capturing the spatial dependence between any two positions of the remote sensing image corresponding to the first feature map, and obtaining a second feature map which is more concerned with edge details;
as shown in fig. 2, in this embodiment, a double-line processing is performed on an original remote sensing image, and a feature enhancement processing is performed on a first feature map corresponding to the first-scale remote sensing image and the second-scale remote sensing image;
and adopting the position attention with different weight coefficients to capture the spatial dependence between any two positions of the first characteristic diagram corresponding to the first-scale remote sensing image to obtain a second characteristic diagram.
Step S3, performing corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map, and performing object segmentation based on the first feature map, the second feature map, and the third feature map.
And inputting the first feature map, the second feature map and the third feature map into a pre-trained segmentation model to predict the pixel class of each feature map under the original size of the remote sensing image and output a segmentation image of each target object in the remote sensing image. As shown in fig. 3 and fig. 4, which are images of segmentation effect of the remote sensing image segmentation method based on multi-scale weighted attention according to the embodiment of the present invention, where fig. 3 is a remote sensing image to be segmented, fig. 4 is a remote sensing segmented image segmented based on this method, and different gray colors in the images represent different ground object categories.
The embodiment of the invention also provides a remote sensing image segmentation system based on multi-scale weighted attention, and the remote sensing image segmentation method based on multi-scale weighted attention in the embodiment comprises the following steps:
the scale characteristic diagram module is used for acquiring remote sensing images of the target object in different scales;
the backbone feature extraction module is used for extracting features of each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
the weighted attention module randomly selects part of the remote sensing image, captures the spatial dependence between any two positions of the part of the remote sensing image corresponding to the first characteristic diagram, and obtains a second characteristic diagram;
the feature fusion module is used for carrying out corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map;
and the post-processing output module is used for segmenting the target object based on the first feature map, the second feature map and the third feature map.
Preferably, the method further comprises the following steps:
and the feature enhancement module is used for carrying out feature enhancement processing on the feature graph based on the ocrnet model so as to enhance the context semantic information of the feature graph.
Preferably, the remote sensing images with different scales at least comprise the first-scale remote sensing image and the second-scale remote sensing image;
the feature fusion module is specifically used for capturing the spatial dependence between any two positions of the first feature map corresponding to the first scale remote sensing image by adopting the position attention of different weight coefficients to obtain a second feature map;
and the post-processing output module is used for predicting pixel categories of all feature maps of the remote sensing images under the original sizes based on the first scale remote sensing image, the second scale remote sensing image and the second feature map corresponding to the first scale remote sensing image after feature fusion of the first scale remote sensing image, and outputting segmentation images of all target objects in the remote sensing images.
Referring to fig. 5, fig. 5 is a schematic view of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 5, an embodiment of the present invention provides an electronic device 500, which includes a memory 510, a processor 520, and a computer program 511 stored in the memory 520 and executable on the processor 520, wherein the processor 520 executes the computer program 511 to implement the following steps:
s1, obtaining remote sensing images of a target object in different scales, and respectively carrying out feature extraction on each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
s2, randomly selecting a part of the remote sensing image, and capturing the spatial dependence between any two positions of the remote sensing image corresponding to the first characteristic diagram to obtain a second characteristic diagram;
step S3, performing corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map, and performing object segmentation based on the first feature map, the second feature map, and the third feature map.
Referring to fig. 6, fig. 6 is a schematic diagram illustrating an embodiment of a computer-readable storage medium according to the present invention. As shown in fig. 6, the present embodiment provides a computer-readable storage medium 600 having a computer program 611 stored thereon, the computer program 611, when executed by a processor, implementing the steps of:
s1, obtaining remote sensing images of a target object in different scales, and respectively carrying out feature extraction on each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
s2, randomly selecting a part of the remote sensing image, and capturing the spatial dependence of the part of the remote sensing image between any two positions corresponding to the first characteristic diagram to obtain a second characteristic diagram;
step S3, performing corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map, and performing object segmentation based on the first feature map, the second feature map, and the third feature map.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A remote sensing image segmentation method based on multi-scale weighted attention is characterized by comprising the following steps:
s1, obtaining remote sensing images of a target object in different scales, and respectively carrying out feature extraction on each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
s2, randomly selecting a part of the remote sensing image, and capturing the spatial dependence between any two positions of the remote sensing image corresponding to the first characteristic diagram to obtain a second characteristic diagram;
step S3, performing corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map, and performing object segmentation based on the first feature map, the second feature map, and the third feature map.
2. The method for segmenting remote sensing images based on multi-scale weighted attention according to claim 1, wherein after generating a plurality of feature maps with different high and low resolutions in step S1, the method further comprises:
and performing feature enhancement processing on the feature map based on an ocrnet model to enhance the context semantic information of the feature map.
3. The remote sensing image segmentation method based on multi-scale weighted attention of claim 1, wherein the step S1 specifically comprises:
s11, obtaining a remote sensing image containing a target object, performing convolution, batch normalization and activation function processing on the remote sensing image, and scaling the remote sensing image into remote sensing images with different scales, wherein the remote sensing images with different scales at least comprise a first scale remote sensing image and a second scale remote sensing image;
and S12, performing feature extraction on the remote sensing image based on the hrnetV2 backbone feature extraction model to obtain a plurality of first feature maps with different resolutions.
4. The remote sensing image segmentation method based on multi-scale weighted attention of claim 2, wherein the step S2 specifically comprises:
carrying out feature enhancement processing on a first feature map corresponding to the first-scale remote sensing image and the second-scale remote sensing image;
and adopting the position attention with different weight coefficients to capture the spatial dependence between any two positions of the first characteristic diagram corresponding to the first-scale remote sensing image to obtain a second characteristic diagram.
5. The method for segmenting the remote sensing image based on the multi-scale weighted attention according to claim 4, wherein in the step S3, segmenting the object based on the first feature map, the second feature map and the third feature map specifically comprises:
and inputting the first feature map, the second feature map and the third feature map into a pre-trained segmentation model to predict the pixel class of each feature map under the original size of the remote sensing image and output a segmentation image of each target object in the remote sensing image.
6. A remote sensing image segmentation system based on multi-scale weighted attention is characterized by comprising:
the scale characteristic diagram module is used for acquiring remote sensing images of the target object in different scales;
the backbone feature extraction module is used for extracting features of each remote sensing image to generate a plurality of first feature maps with different high and low resolutions;
the weighted attention module randomly selects part of the remote sensing image, captures the spatial dependence between any two positions of the part of the remote sensing image corresponding to the first characteristic diagram, and obtains a second characteristic diagram;
the feature fusion module is used for carrying out corresponding position information fusion processing on each first feature map and the corresponding second feature map to obtain a third feature map;
and the post-processing output module is used for segmenting the target object based on the first feature map, the second feature map and the third feature map.
7. The remote sensing image segmentation system based on multi-scale weighted attention of claim 6, further comprising:
and the feature enhancement module is used for carrying out feature enhancement processing on the feature graph based on the ocrnet model so as to enhance the context semantic information of the feature graph.
8. The remote sensing image segmentation system based on multi-scale weighted attention of claim 7, characterized in that the remote sensing images of different scales at least comprise the first scale remote sensing image and the second scale remote sensing image;
the feature fusion module is specifically used for capturing the spatial dependence between any two positions of the first feature map corresponding to the first scale remote sensing image by adopting the position attention of different weight coefficients to obtain a second feature map;
and the post-processing output module is used for predicting pixel categories of all feature maps of the remote sensing images under the original sizes based on the first scale remote sensing image, the second scale remote sensing image and the second feature map corresponding to the first scale remote sensing image after feature fusion of the first scale remote sensing image, and outputting segmentation images of all target objects in the remote sensing images.
9. An electronic device, comprising:
a memory for storing a computer software program;
a processor for reading and executing the computer software program to further implement the method for segmenting the remote sensing image based on the multi-scale weighted attention as claimed in any one of claims 1 to 7.
10. A non-transitory computer readable storage medium, wherein the storage medium stores therein a computer software program for implementing the method for remote sensing image segmentation based on multi-scale weighted attention according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210040070.4A CN114511702A (en) | 2022-01-13 | 2022-01-13 | Remote sensing image segmentation method and system based on multi-scale weighted attention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210040070.4A CN114511702A (en) | 2022-01-13 | 2022-01-13 | Remote sensing image segmentation method and system based on multi-scale weighted attention |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114511702A true CN114511702A (en) | 2022-05-17 |
Family
ID=81549426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210040070.4A Pending CN114511702A (en) | 2022-01-13 | 2022-01-13 | Remote sensing image segmentation method and system based on multi-scale weighted attention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114511702A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116993762A (en) * | 2023-09-26 | 2023-11-03 | 腾讯科技（深圳）有限公司 | Image segmentation method, device, electronic equipment and storage medium |
-
2022
- 2022-01-13 CN CN202210040070.4A patent/CN114511702A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116993762A (en) * | 2023-09-26 | 2023-11-03 | 腾讯科技（深圳）有限公司 | Image segmentation method, device, electronic equipment and storage medium |
| CN116993762B (en) * | 2023-09-26 | 2024-01-19 | 腾讯科技（深圳）有限公司 | Image segmentation method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108710847B (en) | Scene recognition method and device and electronic equipment | |
| CN106934397B (en) | Image processing method and device and electronic equipment | |
| US9036905B2 (en) | Training classifiers for deblurring images | |
| US10832069B2 (en) | Living body detection method, electronic device and computer readable medium | |
| CN111681273B (en) | Image segmentation method and device, electronic equipment and readable storage medium | |
| CN108961180B (en) | Infrared image enhancement method and system | |
| CN112329702B (en) | Method and device for rapid face density prediction and face detection, electronic equipment and storage medium | |
| CN109816694B (en) | Target tracking method and device and electronic equipment | |
| CN111784624B (en) | Target detection method, device, equipment and computer readable storage medium | |
| CN111476719A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN111444365B (en) | Image classification method, device, electronic equipment and storage medium | |
| CN110738103A (en) | Living body detection method, living body detection device, computer equipment and storage medium | |
| CN110958469A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN112906794A (en) | Target detection method, device, storage medium and terminal | |
| CN112836625A (en) | Face living body detection method and device and electronic equipment | |
| CN114444565A (en) | Image tampering detection method, terminal device and storage medium | |
| CN116994000A (en) | Part edge feature extraction method and device, electronic equipment and storage medium | |
| CN114511702A (en) | Remote sensing image segmentation method and system based on multi-scale weighted attention | |
| CN113807354B (en) | Image semantic segmentation method, device, equipment and storage medium | |
| CN116883770A (en) | Training method and device of depth estimation model, electronic equipment and storage medium | |
| CN113496228A (en) | Human body semantic segmentation method based on Res2Net, TransUNet and cooperative attention | |
| CN112633065A (en) | Face detection method, system, storage medium and terminal based on data enhancement | |
| CN112634126A (en) | Portrait age reduction processing method, portrait age reduction training device, portrait age reduction equipment and storage medium | |
| CN112672052A (en) | Image data enhancement method and system, electronic equipment and storage medium | |
| CN116310959B (en) | Method and system for identifying low-quality camera picture in complex scene |
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 |