CN112418111A - Offshore culture area remote sensing monitoring method and device, equipment and storage medium - Google Patents
Offshore culture area remote sensing monitoring method and device, equipment and storage medium Download PDFInfo
- Publication number
- CN112418111A CN112418111A CN202011348627.8A CN202011348627A CN112418111A CN 112418111 A CN112418111 A CN 112418111A CN 202011348627 A CN202011348627 A CN 202011348627A CN 112418111 A CN112418111 A CN 112418111A
- Authority
- CN
- China
- Prior art keywords
- offshore
- remote sensing
- culture area
- data
- image
- 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
- 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a remote sensing monitoring method for an offshore culture area, which comprises the following steps: acquiring a remote sensing image at the monitored offshore area based on a satellite remote sensing technology; inputting the obtained remote sensing image into a pre-trained image recognition network, recognizing the remote sensing image by the image recognition network, and extracting offshore culture area data in the remote sensing image; and after the data of the offshore culture area are post-processed, acquiring a corresponding monitoring result according to the post-processed data of the offshore culture area. Compared with the prior art, the method has the advantages that the information of the offshore culture area is extracted in a visual interpretation mode based on the remote sensing image, the period of information extraction is effectively shortened, the efficiency of information extraction is improved, and accordingly the acquisition of the monitoring result is accelerated.
Description
Technical Field
The application relates to the technical field of sea area monitoring, in particular to a remote sensing monitoring method, a remote sensing monitoring device, equipment and a storage medium for an offshore culture area.
Background
With the comprehensive implementation of national development strategy planning in coastal regions, the collection and the utilization of the tidal flats in the water areas of the offshore region cultivation areas become increasingly important for the development planning of later-stage coastal economic zones. Under the current situation that offshore fishery resources in China decline, monitoring and analyzing offshore aquaculture areas are beneficial to strengthening the national grasp of relevant basic data of coastal areas, and important basic information support is provided for illegal fishery behavior supervision, fishery yield prediction, marine disaster relief and defense, scientific planning and realization of sustainable development of coastal zone resources. In the related art, the monitoring of the offshore culture area is mainly performed by using a field survey mode, or by using a visual interpretation mode based on remote sensing images to extract information of the offshore culture area. However, the method of on-site survey cannot meet the requirement of objectively and accurately acquiring the dynamic change of the culture area due to the influence of human factors, and the method of visual interpretation based on remote sensing images has large workload and low efficiency, so that the period of acquiring the information of the offshore culture area by the method is long.
Disclosure of Invention
In view of this, the application provides a remote sensing monitoring method for an offshore culture area, which can effectively improve the monitoring effect of the offshore culture area and shorten the monitoring period of the offshore culture area.
According to an aspect of the application, a remote sensing monitoring method for an offshore culture area is provided, which comprises the following steps:
acquiring a remote sensing image at the monitored offshore area based on a satellite remote sensing technology;
inputting the obtained remote sensing image into a pre-trained image recognition network, recognizing the remote sensing image by the image recognition network, and extracting offshore culture area data in the remote sensing image;
and after the offshore culture area data are post-processed, acquiring a corresponding monitoring result according to the post-processed offshore culture area data.
In one possible implementation, the image recognition network is constructed based on a U-net network model.
In one possible implementation, the post-processing of the offshore farm data includes eliminating object boundary points in the offshore farm data and/or incorporating into the object all background points in the offshore farm data that are in contact with the object.
In one possible implementation, the method is performed by using a corrosion method when eliminating object boundary points in the offshore culture area data;
all background points in the offshore culture area data, which are in contact with the object, are merged into the object and are performed by adopting an expansion method.
In a possible implementation manner, the method further comprises the step of training the image recognition network;
wherein training the image recognition network comprises:
collecting sample data of a plurality of offshore culture areas, and making and obtaining corresponding sample data sets based on the collected sample data of each offshore culture area;
building an image recognition network model based on the U-net network model;
and sequentially inputting the sample data in the sample data set into the image recognition network model, and training the image recognition network model to obtain the image recognition network.
In a possible implementation manner, creating a corresponding sample data set based on the collected sample data of each offshore culture area includes:
performing data enhancement processing on the collected sample data of each offshore culture area, and storing the sample data as newly added sample data;
wherein the data enhancement processing of the sample data of the offshore culture area comprises: at least one of translation, flipping, rotation, mirroring, noise addition, increased ambiguity, increased illumination, and random cropping.
In one possible implementation, when collecting sample data of a plurality of offshore culture areas, the sample data is collected by using visual interpretation experience.
According to one aspect of the application, the remote sensing monitoring device for the offshore culture area comprises an image acquisition module, a culture area data extraction module and a monitoring result acquisition module;
the image acquisition module is configured to acquire a remote sensing image at the monitored offshore area based on a satellite remote sensing technology;
the culture area data extraction module is configured to input the acquired remote sensing image into a pre-trained image recognition network, recognize the remote sensing image by the image recognition network, and extract offshore culture area data in the remote sensing image;
the monitoring result acquisition module is configured to perform post-processing on the offshore culture area data and acquire a corresponding monitoring result according to the post-processed offshore culture area data.
According to another aspect of the application, there is also provided an offshore culture area remote sensing monitoring device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute the executable instructions to implement any of the methods described above.
According to another aspect of the present application, there is also provided a non-transitory computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any of the preceding.
According to the offshore culture area remote sensing monitoring method, the satellite remote sensing technology is used for obtaining the remote sensing image of the offshore area, the deep learning mode is combined, the constructed and trained image recognition network is used for recognizing the remote sensing image, corresponding offshore culture area data are extracted from the remote sensing image, and therefore monitoring of the offshore culture area is achieved. Compared with the prior art, the information of the offshore culture area is extracted by using a visual interpretation mode based on the remote sensing image, the period of information extraction is effectively shortened, the efficiency of information extraction is improved, and therefore the acquisition of the monitoring result is accelerated.
Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the application and, together with the description, serve to explain the principles of the application.
FIG. 1 shows a flow chart of a method for remote sensing monitoring of an offshore culture area according to an embodiment of the present application;
fig. 2 shows a remote sensing image map of a monitored offshore area obtained by a satellite remote sensing technology in the remote sensing monitoring method for the offshore culture area according to the embodiment of the application;
fig. 3 shows a network structure diagram of an image recognition network used for recognizing remote sensing images in the remote sensing monitoring method for offshore culture areas according to an embodiment of the present application;
FIG. 4 is a diagram illustrating a result of data of the offshore farm extracted from the remote sensing image shown in FIG. 2 by using the remote sensing monitoring method for the offshore farm according to an embodiment of the present disclosure;
fig. 5a to 5f respectively show sample data acquired when an image recognition network model is trained in the remote sensing monitoring method for the offshore culture area according to the embodiment of the present application;
FIG. 6 shows a block diagram of a remote monitoring device for offshore culture areas according to an embodiment of the present application;
FIG. 7 shows a block diagram of a remote sensing monitoring device for an offshore farm according to an embodiment of the present application.
Detailed Description
Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present application.
FIG. 1 shows a flow chart of a method for remote monitoring of an offshore culture area according to an embodiment of the present application. As shown in fig. 1, the method includes: and S100, acquiring a remote sensing image at the offshore area to be monitored based on a satellite remote sensing technology. Here, it should be noted that the satellite remote sensing image has the characteristics of abundant response ground information, large coverage area, strong real-time performance, short observation period, high spatial resolution, strong synchronism, relatively low cost and the like, and provides a new scientific means for the investigation of aquaculture areas. The method has the characteristics of objectivity and quickness, can quickly acquire the map spot boundary of the aquaculture area, provides high-precision offshore aquaculture area data with high accuracy, strong real-time property and flexible operability for collection and collection of offshore aquaculture areas, practically reflects the actual area, and provides good hardware support. Meanwhile, the acquisition of high-precision remote sensing image data provides reliable basic information for collection and compensation of offshore sea area culture areas and reasonable utilization of compensation. As shown in fig. 2, a remote sensing image of the offshore area is acquired by using a satellite remote sensing technology in the remote sensing monitoring method for the offshore culture area according to an embodiment of the present application.
After the remote sensing image at the monitored offshore area is obtained, step S200 may be executed, the obtained remote sensing image is input into a pre-trained image recognition network, the remote sensing image is recognized by the image recognition network, and offshore culture area data in the remote sensing image is extracted. Then, in step S300, after the offshore culture area data is post-processed, a corresponding monitoring result is obtained according to the post-processed offshore culture area data.
Therefore, the remote sensing monitoring method for the offshore culture area obtains the remote sensing image of the offshore area by using the satellite remote sensing technology, identifies the remote sensing image by the constructed and trained image identification network in combination with a deep learning mode, extracts corresponding offshore culture area data from the remote sensing image, and accordingly monitors the offshore culture area. Compared with the prior art, the information of the offshore culture area is extracted by using a visual interpretation mode based on the remote sensing image, the period of information extraction is effectively shortened, the efficiency of information extraction is improved, and therefore the acquisition of the monitoring result is accelerated.
In a possible implementation manner, when the remote sensing image is identified by the image identification network, a corresponding image identification network model can be built based on a U-net network model. Referring to fig. 3, the U-Net network is a full convolution network based on FCN improvement, and has a structure similar to a U-shape, so that the U-Net network is named as U-Net. Compared with other convolutional neural networks, the network needs less training sets and has high segmentation accuracy, and the U-Net network structure consists of two parts, namely a contraction path and an expansion path, as shown in FIG. 3. The contraction path is used to obtain context information and the expansion path is used for accurate positioning. On the left is the systolic path, consisting of a repeated 3 × 3 convolution kernel and a maximum pooling level of 2 × 2, the activation function uses ReLU, doubling the number of feature channels after each sample. And the right side is an expansion path, the number of channels is reduced by half by using deconvolution at each step, then the deconvolution result is spliced with the corresponding feature map of the contraction path, and then the spliced feature map is subjected to 3 × 3 convolution for 2 times. The last layer of the expansion path maps each 2-bit feature vector to the output layer of the network using a 1 x 1 convolution kernel. The black frame in the network structure diagram represents a multi-channel feature diagram, the lower left corner of the frame represents the resolution of an image, the white frame represents a feature diagram obtained by copying, and the top mark of the frame represents the number of channels. The network adopts a Sigmoid function as a neuron activation function and uses a cross entropy as a cost function, so that the problem of too slow weight updating is solved, and the speed of the training process is effectively improved. And after the model is trained, monitoring the offshore culture area on the remote sensing image which can be input into the target area.
Further, after the remote sensing image is subjected to feature extraction and identification through a pre-trained image identification network and corresponding offshore culture area data is extracted from the remote sensing image, in order to further improve the accuracy of the monitoring result, in a possible implementation manner, the extracted offshore culture area data needs to be subjected to post-processing, and then the monitoring result is obtained based on the post-processed offshore culture area data.
Wherein the post-processing of the offshore farm includes eliminating object boundary points in the offshore farm data and/or merging all background points in the offshore farm data that are in contact with the object into the object. Specifically, the object boundary points are eliminated, the target is reduced, and noise points smaller than the structural elements can be eliminated. All background points in contact with the object are merged into the object, so that the object is enlarged, and the holes in the object can be supplemented.
More specifically, the elimination of object boundary points in the offshore culture area data may be performed by using a corrosion method. All background points which are in contact with the object in the data of the near-sea culture area are merged into the object, and the method of expansion can be adopted. By the method, the step length of the sliding window is reduced, 1/3 areas in the output window are removed, and a connected set with a smaller threshold value and a smaller cavity are removed, so that the monitoring result is more accurate. As shown in fig. 4, the extraction accuracy of the offshore culture area extracted from the remote sensing image by the method according to the embodiment of the present application is verified to be more than 80%.
Furthermore, in the remote sensing monitoring method for the offshore culture area in the embodiment of the application, the constructed and trained image recognition network is adopted to extract the data of the offshore culture area. Therefore, before the extraction of the offshore farm data, the constructed image recognition network model needs to be trained.
Specifically, training the image recognition network includes: firstly, sample data of a plurality of offshore culture areas are collected, and a corresponding sample data set is manufactured and obtained based on the collected sample data of each offshore culture area. And then, building an image recognition network model based on the U-net network model. And then, sequentially inputting the sample data in the sample data set into the image recognition network model, and training the image recognition network model to obtain the image recognition network.
Based on the collected sample data of each offshore culture area, a corresponding sample data set is produced and obtained, and the method comprises the following steps: and performing data enhancement processing on the collected sample data of each offshore culture area, and storing the sample data as newly added sample data. Here, it should be noted that, in one possible implementation, the data enhancement processing performed on the sample data of the offshore culture area includes: at least one of translation, flipping, rotation, mirroring, noise addition, increased ambiguity, increased illumination, and random cropping.
Meanwhile, when the sample data of a plurality of offshore culture areas are collected, the sample data can be collected by using visual interpretation experience.
For example, in order to obtain high-quality sample data, improve the accuracy of monitoring results, and improve the performance and robustness of a model framework, the sample data of the offshore culture area is acquired by utilizing abundant visual interpretation experience on the basis of fully learning the relevant knowledge of the offshore culture area. After visual interpretation of the high resolution image (as shown in fig. 2), a total of 830 high precision samples are obtained.
Due to the small number of visually interpreted samples and the poor sample data balance, in order to further improve the generalization capability and robustness of the model, data enhancement processing needs to be performed on the existing data set. The step is to use the existing data set to generate a new sample by increasing the data quantity through a transformation method such as turning, rotating or translating. The amount of data in the final data set will become the product of the enhancement factor (number of transitions) and the number of original data sets. The main principle is that the convolution neural network considers the translation, the view angle conversion, the scale scaling or the illumination influence of the image (or the combination of the changes) to be different images, which is also the premise of the data enhancement method. The method performs data enhancement processing such as rotation, mirroring, noise increase, ambiguity increase, illumination increase, random clipping and the like on high-precision samples obtained by the manual visual interpretation method, and finally obtains 4980 samples, as shown in fig. 5a to 5 f.
After the sample data set is obtained, the constructed image recognition network can be trained based on each sample data in the obtained sample data set. Wherein the image recognition network is available on the basis of a U-net network, according to the above. Here, the description is omitted.
And after the built image recognition network model is trained and a corresponding image recognition network is obtained, the trained image recognition network can be used for carrying out feature recognition on the obtained remote sensing image at the offshore region.
By adopting the offshore culture area remote sensing monitoring method, the identification network structure corresponding to the offshore culture area is more intelligent in the aspect of offshore culture area remote sensing monitoring identification, the offshore culture area can be accurately identified in a generic target, the limitations of subjectivity, low precision, large influence of samples and the like of a manual investigation method, a visual interpretation method and a classifier identification method are overcome, the application popularization capability is strong, and the offshore culture area monitoring identification can be effectively carried out.
It should be noted that, although fig. 1 to 5 are taken as examples to describe the remote monitoring method for the offshore culture area, the skilled person in the art can understand that the present application should not be limited thereto. In fact, the user can flexibly set the specific implementation mode of each step according to personal preference and/or practical application scene, as long as the satellite remote sensing image and deep learning are combined to carry out remote sensing monitoring on the offshore culture area.
Correspondingly, based on any one of the offshore culture area remote sensing monitoring methods, the application also provides an offshore culture area remote sensing monitoring device. The working principle of the offshore culture area remote sensing monitoring device provided by the application is the same as or similar to that of the offshore culture area remote sensing monitoring method provided by the application, so repeated parts are not repeated.
Referring to fig. 6, the remote sensing monitoring device 100 for offshore culture area of the present application includes an image obtaining module 110, a culture area data extracting module 120, and a monitoring result obtaining module 130. The image acquiring module 110 is configured to acquire a remote sensing image at the monitored offshore area based on a satellite remote sensing technology. The culture area data extraction module 120 is configured to input the acquired remote sensing image into a pre-trained image recognition network, recognize the remote sensing image by the image recognition network, and extract offshore culture area data in the remote sensing image. And a monitoring result obtaining module 130 configured to obtain a corresponding monitoring result according to the post-processed offshore culture zone data after the offshore culture zone data is post-processed.
Still further, according to another aspect of the present application, there is also provided an offshore farm remote monitoring apparatus 200. Referring to FIG. 7, the remote sensing monitoring device 200 for an offshore farm according to an embodiment of the present disclosure includes a processor 210 and a memory 220 for storing instructions executable by the processor 210. Wherein the processor 210 is configured to execute the executable instructions to implement any of the remote monitoring methods for offshore culture areas described above.
Here, it should be noted that the number of the processors 210 may be one or more. Meanwhile, in the remote sensing monitoring device 200 for the offshore culture area according to the embodiment of the application, an input device 230 and an output device 240 may be further included. The processor 210, the memory 220, the input device 230, and the output device 240 may be connected via a bus, or may be connected via other methods, which is not limited in detail herein.
The memory 220, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and various modules, such as: the program or the module corresponding to the offshore culture area remote sensing monitoring method is provided by the embodiment of the application. The processor 210 executes various functional applications and data processing of the remote sensing monitoring device 200 for offshore farm locations by executing software programs or modules stored in the memory 220.
The input device 230 may be used to receive an input number or signal. Wherein the signal may be a key signal generated in connection with user settings and function control of the device/terminal/server. The output device 240 may include a display device such as a display screen.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A remote sensing monitoring method for an offshore culture area is characterized by comprising the following steps:
acquiring a remote sensing image at the monitored offshore area based on a satellite remote sensing technology;
inputting the obtained remote sensing image into a pre-trained image recognition network, recognizing the remote sensing image by the image recognition network, and extracting offshore culture area data in the remote sensing image;
and after the offshore culture area data are post-processed, acquiring a corresponding monitoring result according to the post-processed offshore culture area data.
2. The method of claim 1, wherein the image recognition network is constructed based on a U-net network model.
3. The method of claim 1, wherein post-processing the offshore farm data comprises eliminating object boundary points in the offshore farm data and/or merging all background points in the offshore farm data that are in contact with objects into objects.
4. The method of claim 3, wherein the elimination of object boundary points in the offshore farm data is performed using a corrosion method;
all background points in the offshore culture area data, which are in contact with the object, are merged into the object and are performed by adopting an expansion method.
5. The method according to any one of claims 1 to 4, further comprising the step of training the image recognition network;
wherein training the image recognition network comprises:
collecting sample data of a plurality of offshore culture areas, and making and obtaining corresponding sample data sets based on the collected sample data of each offshore culture area;
building an image recognition network model based on the U-net network model;
and sequentially inputting the sample data in the sample data set into the image recognition network model, and training the image recognition network model to obtain the image recognition network.
6. The method of claim 5, wherein creating a corresponding sample data set based on the collected sample data of each offshore culture area comprises:
performing data enhancement processing on the collected sample data of each offshore culture area, and storing the sample data as newly added sample data;
wherein the data enhancement processing of the sample data of the offshore culture area comprises: at least one of translation, flipping, rotation, mirroring, noise addition, increased ambiguity, increased illumination, and random cropping.
7. The method of claim 5, wherein the collection of sample data from a plurality of said offshore farm locations is performed using visual interpretation experience.
8. The remote sensing monitoring device for the offshore culture area is characterized by comprising an image acquisition module, a culture area data extraction module and a monitoring result acquisition module;
the image acquisition module is configured to acquire a remote sensing image at the monitored offshore area based on a satellite remote sensing technology;
the culture area data extraction module is configured to input the acquired remote sensing image into a pre-trained image recognition network, recognize the remote sensing image by the image recognition network, and extract offshore culture area data in the remote sensing image;
the monitoring result acquisition module is configured to perform post-processing on the offshore culture area data and acquire a corresponding monitoring result according to the post-processed offshore culture area data.
9. An offshore farm remote sensing monitoring device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to carry out the executable instructions when implementing the method of any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011348627.8A CN112418111A (en) | 2020-11-26 | 2020-11-26 | Offshore culture area remote sensing monitoring method and device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011348627.8A CN112418111A (en) | 2020-11-26 | 2020-11-26 | Offshore culture area remote sensing monitoring method and device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112418111A true CN112418111A (en) | 2021-02-26 |
Family
ID=74842166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011348627.8A Pending CN112418111A (en) | 2020-11-26 | 2020-11-26 | Offshore culture area remote sensing monitoring method and device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418111A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095169A (en) * | 2021-03-26 | 2021-07-09 | 生态环境部卫星环境应用中心 | Extraction method of oil storage tank with large space range |
-
2020
- 2020-11-26 CN CN202011348627.8A patent/CN112418111A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095169A (en) * | 2021-03-26 | 2021-07-09 | 生态环境部卫星环境应用中心 | Extraction method of oil storage tank with large space range |
| CN113095169B (en) * | 2021-03-26 | 2022-03-29 | 生态环境部卫星环境应用中心 | Extraction method of oil storage tank with large space range |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Commonality autoencoder: Learning common features for change detection from heterogeneous images | |
| CN108537191B (en) | Three-dimensional face recognition method based on structured light camera | |
| CN106971152B (en) | Method for detecting bird nest in power transmission line based on aerial images | |
| CN111986099A (en) | Tillage monitoring method and system based on convolutional neural network with residual error correction fused | |
| CN114092832A (en) | High-resolution remote sensing image classification method based on parallel hybrid convolutional network | |
| CN103745453B (en) | Urban residential areas method based on Google Earth remote sensing image | |
| CN109712128A (en) | Feature point detecting method, device, computer equipment and storage medium | |
| CN111951289B (en) | Underwater sonar image data segmentation method based on BA-Unet | |
| CN117496347A (en) | Remote sensing image building extraction method, device and medium | |
| Duan et al. | Research on the natural image super-resolution reconstruction algorithm based on compressive perception theory and deep learning model | |
| CN112488963A (en) | Method for enhancing crop disease data | |
| CN111079807B (en) | Ground object classification method and device | |
| CN110135435B (en) | Saliency detection method and device based on breadth learning system | |
| CN117036715A (en) | Deformation region boundary automatic extraction method based on convolutional neural network | |
| CN111666813A (en) | Subcutaneous sweat gland extraction method based on three-dimensional convolutional neural network of non-local information | |
| CN115457296A (en) | Structure extraction method oriented to non-stationary texture structure attributes | |
| Mu et al. | Salient object detection in low contrast images via global convolution and boundary refinement | |
| CN112418111A (en) | Offshore culture area remote sensing monitoring method and device, equipment and storage medium | |
| Dhawan et al. | Deep Learning Based Sugarcane Downy Mildew Disease Detection Using CNN-LSTM Ensemble Model for Severity Level Classification | |
| CN111881818B (en) | Medical action fine-grained recognition device and computer-readable storage medium | |
| CN107358625B (en) | SAR image change detection method based on SPP Net and region-of-interest detection | |
| CN117788810A (en) | Learning system for unsupervised semantic segmentation | |
| CN117292117A (en) | Small target detection method based on attention mechanism | |
| CN117197456A (en) | HE dyeing-oriented pathological image cell nucleus simultaneous segmentation classification method | |
| CN112330562A (en) | Heterogeneous remote sensing image transformation method and system |
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 |