CN112560706B - Method and device for identifying water body target of multi-source satellite image - Google Patents
Method and device for identifying water body target of multi-source satellite image Download PDFInfo
- Publication number
- CN112560706B CN112560706B CN202011505634.4A CN202011505634A CN112560706B CN 112560706 B CN112560706 B CN 112560706B CN 202011505634 A CN202011505634 A CN 202011505634A CN 112560706 B CN112560706 B CN 112560706B
- Authority
- CN
- China
- Prior art keywords
- image
- enhanced image
- color space
- source satellite
- space domain
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for identifying a water body target of a multi-source satellite image, wherein the method comprises the following steps: acquiring a multi-source satellite image; inputting the multi-source satellite image into a preset multi-branch fast convolution model; the multi-branch fast convolution model has a plurality of network branches; extracting feature data from the multi-source satellite image through the network branch, performing feature fusion on the feature data, and outputting a segmentation result; the method comprises the steps of obtaining a multi-source satellite image; extracting a plurality of feature data from a multi-source satellite image; inputting a plurality of feature data into a preset multi-branch fast convolution model, performing feature fusion on the feature data through the branch fast convolution model, and outputting a segmentation result; and identifying the water body target according to the segmentation result. The technical problem of low accuracy of water body identification in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method and a device for recognizing a water body target of a multi-source satellite image.
Background
The transmission line corridor area is wide in distribution range and complex in environment, so that traditional daily inspection of power grid personnel is caused, efficiency is low, and effectiveness is insufficient. The development of modern remote sensing technology and the appearance of rapid and various commercial remote sensing image data enable people to conveniently acquire required satellite image data. The satellite image coverage area is wide, the spectrum information is rich, the resolution ratio is high, the targets such as houses, roads, rivers, channels and ponds can be distinguished, and the satellite image is used for routing inspection, so that the method is an important method for establishing a wide-area, real-time and accurate power grid monitoring system. In recent years, artificial intelligence technology develops rapidly, and particularly a deep learning algorithm based on a convolutional neural network makes it possible for a robot to replace a human to identify some specific targets.
The existing method for identifying the water body target in the satellite image mostly adopts a mode of manually designing features, the manually designed features are seriously dependent on personal prior knowledge, and meanwhile, the algorithm is poor in universality because of being usually based on a small number of data sets. The existing method is difficult to be suitable for complex multi-source satellite data. The multi-source satellite data presents different styles, and a single deep learning model is difficult to learn simultaneously. And the water target under the same satellite source can also present different color states, so that the identification accuracy of the prior art scheme is reduced.
Disclosure of Invention
The invention provides a method and a device for identifying a water body target of a multi-source satellite image, which are used for solving the technical problem of low accuracy rate of water body identification in the prior art.
The invention provides a method for identifying a water body target of a multi-source satellite image, which comprises the following steps:
acquiring a multi-source satellite image;
inputting the multi-source satellite image into a preset multi-branch fast convolution model; the multi-branch fast convolution model has a plurality of network branches;
extracting feature data from the multi-source satellite image through the network branch, performing feature fusion on the feature data, and outputting a segmentation result;
and identifying a water body target according to the segmentation result.
Optionally, the method further comprises:
acquiring a training image;
performing color space domain conversion on the training image to generate an enhanced image;
and training a preset convolution model by adopting the enhanced image to generate the multi-branch fast convolution model.
Optionally, the color space domain comprises an HSV color space domain; the enhanced image comprises a first enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image includes:
acquiring pixel data of the training image;
normalizing the pixel data to obtain normalized data;
calculating an intermediate variable according to the normalized data;
calculating a channel variable value of the HSV color space domain by using the intermediate variable;
generating the first enhanced image based on the channel variable values.
Optionally, the color space domain further comprises a YCbCr color space domain; the enhanced image further comprises a second enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image further includes:
and performing YCbCr color space domain conversion on the training image to generate the second enhanced image.
Optionally, the color space domain further comprises an XYZ color space domain; the enhanced image further comprises a third enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image further includes:
and carrying out XYZ color spatial domain conversion on the training image to generate the third enhanced image.
Optionally, the color space domain further comprises a Lab color space domain; the step of performing color space domain conversion on the training image to generate an enhanced image further comprises:
and carrying out Lab color spatial domain conversion on the third enhanced image to generate the fourth enhanced image.
The invention also provides a multi-source satellite image water body target recognition device, which comprises:
the multi-source satellite image acquisition module is used for acquiring a multi-source satellite image;
the input module is used for inputting the multi-source satellite image into a preset multi-branch fast convolution model; the multi-branch fast convolution model has a plurality of network branches;
the output module is used for extracting characteristic data from the multi-source satellite image through the network branch, performing characteristic fusion on the characteristic data and outputting a segmentation result;
and the identification module is used for identifying the water body target according to the segmentation result.
Optionally, the method further comprises:
the training image acquisition module is used for acquiring a training image;
the enhanced image generation module is used for performing color space domain conversion on the training image to generate an enhanced image;
and the multi-branch fast convolution model generation module is used for training a preset convolution model by adopting the enhanced image to generate the multi-branch fast convolution model.
The invention also provides an electronic device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the multi-source satellite image water body target identification method according to instructions in the program code.
The invention also provides a computer-readable storage medium for storing program code for executing the multi-source satellite image water body target identification method as described in any one of the above.
According to the technical scheme, the invention has the following advantages: the method comprises the steps of obtaining a multi-source satellite image; extracting a plurality of feature data from a multi-source satellite image; inputting a plurality of feature data into a preset multi-branch fast convolution model, performing feature fusion on the feature data through the branch fast convolution model, and outputting a segmentation result; and identifying the water body target according to the segmentation result. The technical problem of low accuracy of water body identification in the prior art is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating steps of a method for identifying a water body from a multi-source satellite image according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of a method for identifying a water target in a multi-source satellite image according to another embodiment of the present invention;
FIG. 3 is a block diagram of a multi-branch fast convolution model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of DSConv;
FIG. 5 is a schematic diagram of DWConv configuration;
FIG. 6 is a schematic structural diagram of Bottleneck;
fig. 7 is a structural block diagram of a multi-source satellite image water body target recognition device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a device for identifying a water body target of a multi-source satellite image, which are used for solving the technical problem of low accuracy rate of water body identification in the prior art.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, fig. 1 is a flowchart illustrating steps of a method for identifying a water body from a multi-source satellite image according to an embodiment of the present invention.
The invention provides a multi-source satellite image water body identification method, which comprises the following steps:
in the embodiment of the invention, the multi-source satellite image is obtained by intelligently synthesizing the acquired data after a large number of different satellite sensors such as optical, thermal infrared and microwave are used for acquiring the data of the power transmission line corridor, so that the estimation and judgment are more accurate, more complete and more reliable than the single information source. Its advantages are high robustness, high resolution and definition of image, high accuracy and reliability of plane mapping and classification, high interpreting and dynamic monitoring power, low ambiguity, and high utilization rate of satellite image data.
103, extracting characteristic data from the multi-source satellite image through the network branch, performing characteristic fusion on the characteristic data, and outputting a segmentation result;
and 104, identifying the water body target according to the segmentation result.
The multi-branch fast convolution model provided by the embodiment of the invention can comprise three network branches which are used for respectively extracting the characteristics of three different information source input data. The three branches of the network have similar network structures, and the three branches are respectively subjected to feature fusion in different feature extraction stages in the overall view. And according to the fusion, the features reflecting the water body target are obtained by segmentation. To identify water targets based on the analysis of the features.
The method comprises the steps of obtaining a multi-source satellite image; extracting a plurality of feature data from a multi-source satellite image; inputting a plurality of feature data into a preset multi-branch fast convolution model, performing feature fusion on the feature data through the branch fast convolution model, and outputting a segmentation result; and identifying the water body target according to the segmentation result. The technical problem of low accuracy of water body identification in the prior art is solved.
Referring to fig. 2, fig. 2 is a flowchart illustrating steps of a method for identifying a water target in a multi-source satellite image according to another embodiment of the present invention. The method may specifically comprise the steps of:
in the embodiment of the invention, in the training process of the multi-branch fast convolution model, data enhancement needs to be performed on an input training image in a multi-color spatial domain conversion mode to obtain an enhanced image.
In one example, the color space domain comprises an HSV color space domain; the enhanced image comprises a first enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image includes:
acquiring pixel data of the training image;
normalizing the pixel data to obtain normalized data;
calculating an intermediate variable according to the normalized data;
calculating a channel variable value of the HSV color space domain by using the intermediate variable;
generating the first enhanced image based on the channel variable values.
HSV (Hue, Saturation, brightness) is a color space created according to the intuitive nature of color.
In a specific implementation, converting pixel data RGB of a training image into an HSV color space domain, firstly, normalizing RGB values of the image, and calculating according to the following formula:
the intermediate variables are then calculated, the formula is as follows:
and finally, calculating the variable values of three channels of H (hue), S (saturation) and V (brightness), wherein the calculation formula is as follows:
V＝Cmax
through the above conversion process, the training data may be converted into a third enhanced image in the HSV color space domain.
In one example, the training image is subjected to YCbCr color spatial domain conversion, generating the second enhanced image.
YCbCr is a type of color space that is commonly used for image continuation processing in motion pictures, or in digital photography systems. Y is the luminance component of the color and Cb and Cr are the density offset components of the blue and red colors.
In a specific implementation, the conversion calculation formula for RGB to YCbCr color space domain is as follows:
Y＝0.257*R+0.564*G+0.098*B+16
Cb＝-0.148*R-0.291*G+0.439*B+128
Cr＝0.439*R-0.368*G-0.071*B+128
through the above conversion process, the training data may be converted into a third enhanced image in the YCbCr color space domain.
In one example, the color space domain further comprises an XYZ color space domain; the enhanced image further comprises a third enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image further includes:
and carrying out XYZ color spatial domain conversion on the training image to generate the third enhanced image.
In the XYZ color space domain, Y denotes luminance, X, Y reflects the chromatic properties of the color.
In a specific implementation, the conversion calculation formula for converting RGB into XYZ color space domain is as follows:
through the above conversion process, the training data can be converted into the third enhanced image in the XYZ color space domain.
In one example, the color space domain further comprises a Lab color space domain; the step of performing color space domain conversion on the training image to generate an enhanced image further comprises:
and carrying out Lab color spatial domain conversion on the third enhanced image to generate the fourth enhanced image.
The Lab color space domain is a color-opponent space with dimension L representing the luminance and a and b representing the color opponent dimensions.
In a specific implementation, the RGB to Lab color space domain conversion calculation formula is as follows:
L＝116f(Y)-16
a＝500[f(X)-f(Y)]
b＝200[f(Y)-f(Z)]
wherein the content of the first and second substances,
through the conversion process, the training data can be converted into a third enhanced image in an XYZ color space domain, and then the third enhanced image is converted into a fourth enhanced image in a Lab color space domain.
by adopting the enhanced image, a multi-branch fast convolution model can be obtained through training.
and step 207, identifying the water body target according to the segmentation result.
As shown in fig. 3, the multi-branch fast convolution model of the embodiment of the present invention has three network branches with similar structures, and the overall structure includes convolution layers such as Conv2D, DSConv, Bottleneck, Pyramid power, DWConv, Softmax, etc.; wherein, the DSConv structure includes convolution layers such as Conv2d, BatchNorm2d, ReLU, etc., and the structure distribution is shown in FIG. 4; the DWConv structure comprises convolution layers such as Conv2d, BatchNorm2d, convolution layers such as ReLU and the like, and the specific structure distribution is shown in FIG. 5; the structure of Bottleneck includes convolution layers such as ConBNRelu, DWConv, ReLU, Conv2d, BatchNorm2d, etc., and the specific structure distribution is shown in FIG. 6. On the whole, after the image is input in the multi-branch fast convolution model, feature fusion is carried out in different feature extraction stages through three branches respectively. At nodes 1 and 2, the shallow features are merged. At nodes 3 and 4, the mid-level features are fused. At the nodes 5 and 6, the high-level features are fused, and finally, a segmentation result with the water body target features can be output.
The method comprises the steps of obtaining a multi-source satellite image; extracting a plurality of feature data from a multi-source satellite image; inputting a plurality of feature data into a preset multi-branch fast convolution model, performing feature fusion on the feature data through the branch fast convolution model, and outputting a segmentation result; and identifying the water body target according to the segmentation result. The technical problem of low accuracy of water body identification in the prior art is solved.
Referring to fig. 7, fig. 7 is a block diagram of a device for identifying a water target in a multi-source satellite image according to an embodiment of the present invention.
The embodiment of the invention provides a multi-source satellite image water body target recognition device, which comprises:
a multi-source satellite image obtaining module 701, configured to obtain a multi-source satellite image;
an input module 702, configured to input the multi-source satellite image into a preset multi-branch fast convolution model; the multi-branch fast convolution model has a plurality of network branches;
an output module 703, configured to extract feature data from the multi-source satellite image through the network branch, perform feature fusion on the feature data, and output a segmentation result;
and the identifying module 704 is used for identifying the water body target according to the segmentation result.
In an embodiment of the present invention, the apparatus further includes:
the training image acquisition module is used for acquiring a training image;
the enhanced image generation module is used for performing color space domain conversion on the training image to generate an enhanced image;
and the multi-branch fast convolution model generation module is used for training a preset convolution model by adopting the enhanced image to generate the multi-branch fast convolution model.
In an embodiment of the present invention, the color space domain comprises an HSV color space domain; the enhanced image comprises a first enhanced image; the enhanced image generation module comprises:
the pixel data acquisition sub-module is used for acquiring the pixel data of the training image;
the normalization submodule is used for performing normalization processing on the pixel data to obtain normalized data;
the intermediate variable calculation submodule is used for calculating an intermediate variable according to the normalized data;
the channel variable value calculation submodule is used for calculating the channel variable value of the HSV color space domain by adopting the intermediate variable;
a first enhanced image generation sub-module to generate the first enhanced image based on the channel variable values.
In the embodiment of the present invention, the color space domain further includes a YCbCr color space domain; the enhanced image further comprises a second enhanced image; the enhanced image generation module further comprises:
and the second enhanced image generation sub-module is used for carrying out YCbCr color space domain conversion on the training image to generate the second enhanced image.
In an embodiment of the present invention, the color space domain further comprises an XYZ color space domain; the enhanced image further comprises a third enhanced image; the enhanced image generation module further comprises:
and the third enhanced image generation sub-module is used for carrying out XYZ color spatial domain conversion on the training image to generate the third enhanced image.
In an embodiment of the present invention, the color space domain further comprises a Lab color space domain; the enhanced image comprises a fourth enhanced image, and the enhanced image generation module further comprises:
and the fourth enhanced image generation submodule is used for carrying out Lab color spatial domain conversion on the third enhanced image to generate the fourth enhanced image.
An embodiment of the present invention further provides an electronic device, where the device includes a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the multi-source satellite image water body target identification method according to the instructions in the program codes.
The embodiment of the invention also provides a computer-readable storage medium, which is used for storing program codes, and the program codes are used for executing the multi-source satellite image water body target identification method provided by the embodiment of the invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of 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, embodiments of 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.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (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 processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, 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 terminal 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 terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal 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 of these 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 embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A multi-source satellite image water body target identification method is characterized by comprising the following steps:
acquiring a multi-source satellite image;
inputting the multi-source satellite image into a preset multi-branch fast convolution model; the multi-branch fast convolution model has a plurality of network branches;
extracting feature data from the multi-source satellite image through the network branches, performing feature fusion on the feature data at different feature extraction stages through the network branches, and outputting a segmentation result;
identifying a water body target according to the segmentation result;
wherein, still include:
acquiring a training image;
performing color space domain conversion on the training image to generate an enhanced image; the color space domain comprises an HSV color space domain, a YCbCr color space domain, an XYZ color space domain and a Lab color space domain;
and training a preset convolution model by adopting the enhanced image to generate the multi-branch fast convolution model.
2. The method of claim 1, wherein the enhanced image comprises a first enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image includes:
acquiring pixel data of the training image;
normalizing the pixel data to obtain normalized data;
calculating an intermediate variable according to the normalized data;
calculating a channel variable value of the HSV color space domain by using the intermediate variable;
generating the first enhanced image based on the channel variable values.
3. The method of claim 2, wherein the enhanced image further comprises a second enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image further includes:
and performing YCbCr color space domain conversion on the training image to generate the second enhanced image.
4. The method of claim 3, wherein the enhanced image further comprises a third enhanced image; the step of performing color space domain conversion on the training image to generate an enhanced image further includes:
and carrying out XYZ color spatial domain conversion on the training image to generate the third enhanced image.
5. The method of claim 4, wherein the enhanced image comprises a fourth enhanced image, and wherein the step of color space domain converting the training image to generate the enhanced image further comprises:
and carrying out Lab color spatial domain conversion on the third enhanced image to generate the fourth enhanced image.
6. A multi-source satellite image water body target recognition device is characterized by comprising:
the multi-source satellite image acquisition module is used for acquiring a multi-source satellite image;
the input module is used for inputting the multi-source satellite image into a preset multi-branch fast convolution model; the multi-branch fast convolution model has a plurality of network branches;
the output module is used for extracting feature data from the multi-source satellite image through the network branches, performing feature fusion on the feature data at different feature extraction stages through the network branches and outputting a segmentation result;
the identification module is used for identifying the water body target according to the segmentation result;
wherein, still include:
the training image acquisition module is used for acquiring a training image;
the enhanced image generation module is used for performing color space domain conversion on the training image to generate an enhanced image;
and the multi-branch fast convolution model generation module is used for training a preset convolution model by adopting the enhanced image to generate the multi-branch fast convolution model.
7. An electronic device, comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the multi-source satellite image water body target identification method of any one of claims 1-5 according to instructions in the program code.
8. A computer-readable storage medium for storing program code for performing the multi-source satellite image water body target identification method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011505634.4A CN112560706B (en) | 2020-12-18 | 2020-12-18 | Method and device for identifying water body target of multi-source satellite image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011505634.4A CN112560706B (en) | 2020-12-18 | 2020-12-18 | Method and device for identifying water body target of multi-source satellite image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112560706A CN112560706A (en) | 2021-03-26 |
| CN112560706B true CN112560706B (en) | 2022-03-29 |
Family
ID=75030369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011505634.4A Active CN112560706B (en) | 2020-12-18 | 2020-12-18 | Method and device for identifying water body target of multi-source satellite image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560706B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113887466A (en) * | 2021-10-14 | 2022-01-04 | 广东电网有限责任公司 | Method, device, equipment and medium for identifying hidden danger of water body in power transmission line corridor |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991359A (en) * | 2019-12-06 | 2020-04-10 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Satellite image target detection method based on multi-scale depth convolution neural network |
| CN111914631A (en) * | 2020-06-19 | 2020-11-10 | 北京理工大学 | Multi-channel convolution network method for forest land fine identification based on multi-source sensor data |
| CN112861774A (en) * | 2021-03-04 | 2021-05-28 | 山东产研卫星信息技术产业研究院有限公司 | Method and system for identifying ship target by using remote sensing image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122796B (en) * | 2017-04-01 | 2019-07-12 | 中国科学院空间应用工程与技术中心 | A kind of remote sensing image classification method based on multiple-limb network integration model |
| CN111738111B (en) * | 2020-06-10 | 2023-08-29 | 杭州电子科技大学 | Road extraction method of high-resolution remote sensing image based on multi-branch cascade cavity space pyramid |
-
2020
- 2020-12-18 CN CN202011505634.4A patent/CN112560706B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991359A (en) * | 2019-12-06 | 2020-04-10 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Satellite image target detection method based on multi-scale depth convolution neural network |
| CN111914631A (en) * | 2020-06-19 | 2020-11-10 | 北京理工大学 | Multi-channel convolution network method for forest land fine identification based on multi-source sensor data |
| CN112861774A (en) * | 2021-03-04 | 2021-05-28 | 山东产研卫星信息技术产业研究院有限公司 | Method and system for identifying ship target by using remote sensing image |
Non-Patent Citations (2)
| Title |
|---|
| Fast-SCNN: Fast Semantic Segmentation Network;Rudra PK Poudel et al.;《arXiv:1902.04502v1》;20190212;第3节，图1 * |
| 基于卷积神经网络的高分辨率遥感图像上的水体识别技术;徐文健;《中国优秀博硕士学位论文全文数据库（硕士） 工程科技II辑》;20190115;正文第3-4章，第6.1.3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112560706A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537742B (en) | Remote sensing image panchromatic sharpening method based on generation countermeasure network | |
| CN109934154B (en) | Remote sensing image change detection method and detection device | |
| CN110458077B (en) | Vehicle color identification method and system | |
| CN111860351B (en) | Remote sensing image fishpond extraction method based on line-row self-attention full convolution neural network | |
| CN109558806A (en) | The detection method and system of high score Remote Sensing Imagery Change | |
| CN104484658A (en) | Face gender recognition method and device based on multi-channel convolution neural network | |
| CN112906550B (en) | Static gesture recognition method based on watershed transformation | |
| An et al. | CBIR based on adaptive segmentation of HSV color space | |
| CN112164005A (en) | Image color correction method, device, equipment and storage medium | |
| Ganesan et al. | Value based semi automatic segmentation of satellite images using HSV color space, histogram equalization and modified FCM clustering algorithm | |
| CN109920018A (en) | Black-and-white photograph color recovery method, device and storage medium neural network based | |
| CN110059597A (en) | Scene recognition method based on depth camera | |
| CN114998667B (en) | Multispectral target detection method, multispectral target detection system, multispectral target detection computer equipment and multispectral target storage medium | |
| CN113409355A (en) | Moving target identification system and method based on FPGA | |
| CN112560706B (en) | Method and device for identifying water body target of multi-source satellite image | |
| Nie et al. | Adap-EMD: Adaptive EMD for aircraft fine-grained classification in remote sensing | |
| CN111695436B (en) | High spatial resolution remote sensing image scene classification method based on target enhancement | |
| CN108416782A (en) | View-based access control model identifies and the tobacco leaf ranking method and system of illumination correction | |
| CN116543325A (en) | Unmanned aerial vehicle image-based crop artificial intelligent automatic identification method and system | |
| Huang et al. | Adaptive color image processing and recognition for varying backgrounds and illumination conditions | |
| CN113052194A (en) | Garment color cognition system based on deep learning and cognition method thereof | |
| CN115565082A (en) | Method, system and device for removing cloud noise of satellite remote sensing image | |
| Jordan et al. | Hyperspectral image visualization with a 3-D self-organizing map | |
| Vršnak et al. | Illuminant estimation error detection for outdoor scenes using transformers | |
| Zhang et al. | Colour correction method of interior decoration engineering based on dense convolution neural network |
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 |