CN113837134A - A Wetland Vegetation Recognition Method Based on Object-Oriented Deep Learning Model and Transfer Learning - Google Patents
A Wetland Vegetation Recognition Method Based on Object-Oriented Deep Learning Model and Transfer Learning Download PDFInfo
- Publication number
- CN113837134A CN113837134A CN202111152307.XA CN202111152307A CN113837134A CN 113837134 A CN113837134 A CN 113837134A CN 202111152307 A CN202111152307 A CN 202111152307A CN 113837134 A CN113837134 A CN 113837134A
- Authority
- CN
- China
- Prior art keywords
- training
- classification
- learning
- model
- deep learning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013136 deep learning model Methods 0.000 title claims abstract description 20
- 238000013526 transfer learning Methods 0.000 title claims abstract description 14
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 16
- 230000003595 spectral effect Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 52
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000013508 migration Methods 0.000 claims description 15
- 230000005012 migration Effects 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims 1
- 238000013507 mapping Methods 0.000 claims 1
- 238000003709 image segmentation Methods 0.000 abstract description 8
- 239000002028 Biomass Substances 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a wetland vegetation identification method based on an object-oriented deep learning model and transfer learning, which improves the classification precision and efficiency of wetland vegetation clusters by applying the transfer learning capability of a convolutional neural network; the wetland vegetation is identified by expanding the spatial resolution gradient and the spectral dimension of the remote sensing image, so that the problem that various wetland vegetation cannot be accurately identified by a single image is solved; accurate classification at vegetation boundaries is improved by using a convolutional neural network model that incorporates image segmentation.
Description
Technical Field
The invention relates to a classification algorithm model of wetland vegetation, in particular to a method for realizing high-precision classification of wetland vegetation based on an object-oriented deep learning model and a migration learning mode, aiming at the problems of complicated construction, long training time and easy confusion of vegetation classification of the conventional wetland vegetation model, and particularly overcoming the defects of low efficiency and low precision of wetland vegetation classification.
Background
The wetland vegetation is an important component of the wetland, is an important characteristic for judging the mature development of a wetland ecosystem, and is a premise and a foundation for maintaining the stability of the wetland ecological function and promoting the virtuous cycle of the ecological environment. The method has the advantages that the space-time distribution information of the wetland vegetation is accurately identified and monitored, the method has important theoretical significance for systematically researching the structure and ecological function of the wetland, and the method plays a vital role in protecting and reasonably developing the wetland.
At present, most of vegetation measurement and calculation are realized through a machine learning algorithm, for example, patent application 202011322693.8 discloses an arbor biomass measurement and calculation method based on unmanned aerial vehicle hyperspectral and machine learning algorithms, which is used for better realizing biomass monitoring of target area type arbors. Firstly, acquiring a hyperspectral image of a terrestrial plant in a target area by using an unmanned aerial vehicle, modeling based on the hyperspectral image, and extracting elevation information of a digital surface model; extracting spectral information from the original image picture, monitoring the type of vegetation classification according to the ecological environment of terrestrial plants, and performing quantitative inversion model training by adopting a machine learning algorithm by combining high-level information, characteristic wave bands and vegetation indexes of various plants in a target area to obtain an inversion model; classifying the vegetation types of the target area by using an inversion model so as to extract classification data of the arbor; and finally, calculating the biomass of the arbor by utilizing the classification data extracted from the arbor and combining an aboveground biomass formula.
Referring to the research of wetland vegetation in the existing scientific literature, the most extensive classification method is to use a convolutional neural network algorithm for intelligent identification, the algorithm has a deep multilayer structure, an end-to-end training mode and strong generalization capability, and can identify the wetland vegetation with higher precision, but the following problems exist: when different remote sensing images are classified by using a convolutional neural network algorithm, a large amount of iterative training is required, and a large amount of time is spent; the convolutional neural network algorithm cannot accurately and newly identify context information when performing wetland vegetation classification pixel by pixel, so that vegetation boundaries are easy to be confused.
Disclosure of Invention
In order to solve the above problems, a primary object of the present invention is to provide a wetland vegetation identification method based on an object-oriented deep learning model and migration learning, which aims at the problems of complicated construction, long training time and easy confusion of vegetation classification of the existing wetland vegetation model, especially the disadvantages of low efficiency and low precision of wetland vegetation classification, and provides a method for realizing high-precision classification of wetland vegetation clusters and vegetation boundaries based on an object-oriented deep learning model and a migration learning method.
Another objective of the present invention is to provide a wetland vegetation identification method based on an object-oriented deep learning model and transfer learning, the classification model constructed by the method can effectively solve the above problems, and the transfer learning capability of the convolutional neural network is used to improve the classification accuracy and efficiency of wetland vegetation clusters; the wetland vegetation is identified by expanding the spatial resolution gradient and the spectral dimension of the remote sensing image, so that the problem that various wetland vegetation cannot be accurately identified by a single image is solved; accurate classification at vegetation boundaries is improved by using a convolutional neural network model that incorporates image segmentation.
The invention further aims to provide a wetland vegetation identification method based on an object-oriented deep learning model and migration learning, which selects a new generation of China high spatial resolution earth observation satellites GF-1, GF-2 and ZY-3 and international earth observation satellites Sentinel-2A and Landsat 8OLI as data sources to perform high-precision classification of wetland vegetation based on a deep learning algorithm, is beneficial to simply developing a wetland vegetation data set meeting the deep learning model, improves the classification precision by expanding the spatial resolution gradient and spectral dimension of remote sensing images, and improves the classification efficiency of the wetland vegetation by utilizing the migration learning capability of a convolutional neural network.
In order to achieve the purpose, the invention provides the following technical scheme:
a wetland vegetation identification method based on an object-oriented deep learning model and transfer learning comprises the following steps:
step (1): making a deep learning semantic label according to the measured data;
step (2): preprocessing the remote sensing image; the remote sensing image is obtained by observing a satellite;
and (3): matching the data in the steps (1) and (2), matching the remote sensing image with the same spatial resolution with the label data to prepare a training sample, and inputting the training sample and the training sample into a classification model to form a training sample set;
and (4): establishing a classification scheme of the multi-source data remote sensing image;
respectively integrating remote sensing images with different spatial resolution gradients and spectral dimensions, and establishing a multi-source data remote sensing image classification scheme;
and (5): performing enhancement processing on the training sample;
and (6): performing iterative training on each classification scheme by using a convolutional neural network algorithm;
and (7): taking the training record in the step (6) as a training reference of other schemes to carry out transfer learning training;
selecting a weight record with the highest training precision in 30 times of iterative training, taking the weight record as a reference of transfer learning training, training images of other schemes, and finely adjusting all convolutional layers at a learning rate 10 times smaller than a default learning rate during training;
and (8): classifying and predicting the image corresponding to each scheme; selecting the weight record with the highest training precision in the iterative training for classification prediction;
and (9): performing multi-scale segmentation on the image;
the segmentation is to perform multi-scale segmentation on the image, and segment the image into objects with relatively uniform characteristics by setting 3 important parameters of shape/color, tightness/smoothness and scale and adopting a bottom-up region merging technology;
step (10): fusing the classification result of the step (8) with the segmentation result of the step (9);
step (11): constructing a deep learning model classification result evaluation index;
5 precision indexes including drawing Precision (PA), user precision (UA), average precision (mean value of PA and UA, AA), Kappa value and overall classification precision (OA) are adopted to verify the classification condition of the model to the vegetation;
step (12): and (5) comparing the classification results of the steps (8) and (10) with the actually measured data, and performing model judgment according to the evaluation indexes.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, the high-precision classification of the wetland vegetation is realized by making deep learning semantic label data and training a model. By utilizing the advantages of the convolutional neural network, the constructed classification model can effectively solve the problem of the efficiency of the current vegetation classification, and the classification precision and efficiency of wetland vegetation clusters are improved by utilizing the migration learning capacity; the wetland vegetation is identified by expanding the spatial resolution gradient and the spectral dimension of the remote sensing image, so that the problem that various wetland vegetation cannot be accurately identified by a single image is solved; accurate classification at vegetation boundaries is improved by using a convolutional neural network model that incorporates image segmentation.
Drawings
FIG. 1 is a flow chart of an implementation of the present invention.
FIG. 2 is a result diagram of the fused image segmentation algorithm of the present invention.
FIG. 3 is a graph of the results of the fused image segmentation algorithm of the present invention.
Detailed Description
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 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.
As shown in fig. 1, the flow chart of the implementation of the present invention is that iterative training is performed on the corresponding remote sensing image and the label data according to the classification scheme, the trained records are used to predict wetland vegetation, and finally the performance of the classification model is evaluated through the constructed evaluation indexes.
The various implementation steps are described separately below to provide reference.
Step (1): making a deep learning semantic label according to the measured data;
manufacturing wetland deep learning semantic tag data according to the actually measured data and by combining artificial visual interpretation;
step (2): preprocessing the remote sensing image;
preprocessing remote sensing images obtained by earth observation satellites GF-1, GF-2 and ZY-3 and international earth observation satellites Sentinel-2A and Landsat 8OLI by utilizing software such as ArcGIS 10.6, ENVI 5.3, SNAP and the like, such as radiometric calibration, atmospheric correction, cutting, geographic registration and the like;
and (3): matching the data in the step (1) and the data in the step (2) to form a training sample set;
matching the remote sensing image with the same spatial resolution with the label data to make a training sample, and inputting the training sample and the label data into a classification model;
and (4): establishing a classification scheme of the multi-source data remote sensing image;
respectively integrating remote sensing images with different spatial resolution gradients and spectral dimensions, and establishing a multi-source data remote sensing image classification scheme;
and (5): performing enhancement processing on the training sample;
in order to increase the number of samples, the image and the label data are divided into 256 × 256 pixels, and the image and the sample data are subjected to enhancement processing such as overturning, channel exchange, random rotation and the like in the dividing process;
and (6): performing iterative training on each classification scheme by using a convolutional neural network algorithm;
to achieve a stable training accuracy, 30 iterative trainings were performed for each protocol. Wherein the model optimizer algorithm is set to Adam, the initial learning rate is set to 0.001, and the momentum parameter is set to 0.8; the loss function is set to a conditional _ cross _ learning loss, the initial learning rate is set to 0.001, the momentum parameter is set to 0.8, and the loss function is set to a conditional _ cross _ learning loss.
And (7): taking the training record in the step (6) as a training reference of other schemes to carry out transfer learning training;
selecting a weight record with the highest training precision in 30 times of iterative training, taking the weight record as a reference of transfer learning training, training images of other schemes, and finely adjusting all convolutional layers at a learning rate 10 times smaller than a default learning rate during training;
and (8): classifying and predicting the image corresponding to each scheme;
selecting the weight record with the highest training precision in the iterative training for classification prediction;
and (9): performing multi-scale segmentation on the image;
performing multi-scale segmentation on the image based on eCogination Developer 9.4 software, and segmenting the image into objects with relatively uniform characteristics by setting 3 important parameters of shape/color, tightness/smoothness and scale and adopting a bottom-up region merging technology;
step (10): fusing the classification result of the step (8) with the segmentation result of the step (9);
combining the classification result of the step (8) with the multi-scale segmentation result of the step (9) by adopting an area optimization method;
step (11): constructing a deep learning model classification result evaluation index;
5 precision indexes including drawing Precision (PA), user precision (UA), average precision (mean value of PA and UA, AA), Kappa value and overall classification precision (OA) are adopted to verify the classification condition of the model to the vegetation;
step (12): and (5) comparing the classification results of the steps (8) and (10) with the actually measured data, and performing model judgment according to the evaluation indexes.
The migration-learned wetland vegetation classification result and the wetland vegetation classification result fused with the image segmentation algorithm are shown in fig. 2 and 3.
The method improves the classification precision and efficiency of the wetland vegetation cluster by applying the migration learning capacity of the convolutional neural network; the wetland vegetation is identified by expanding the spatial resolution gradient and the spectral dimension of the remote sensing image, so that the problem that various wetland vegetation cannot be accurately identified by a single image is solved; accurate classification at vegetation boundaries is improved by using a convolutional neural network model that incorporates image segmentation.
In summary, the advantages of the present invention are as follows:
1. the classification precision and efficiency of wetland vegetation clusters are improved through the transfer learning capacity;
2. the wetland vegetation is identified by expanding the spatial resolution gradient and the spectral dimension of the remote sensing image, so that the problem that various wetland vegetation cannot be accurately identified by a single image is solved;
3. accurate classification at vegetation boundaries is improved by using a convolutional neural network model that incorporates image segmentation.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152307.XA CN113837134A (en) | 2021-09-29 | 2021-09-29 | A Wetland Vegetation Recognition Method Based on Object-Oriented Deep Learning Model and Transfer Learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152307.XA CN113837134A (en) | 2021-09-29 | 2021-09-29 | A Wetland Vegetation Recognition Method Based on Object-Oriented Deep Learning Model and Transfer Learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837134A true CN113837134A (en) | 2021-12-24 |
Family
ID=78967400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111152307.XA Pending CN113837134A (en) | 2021-09-29 | 2021-09-29 | A Wetland Vegetation Recognition Method Based on Object-Oriented Deep Learning Model and Transfer Learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837134A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114529721A (en) * | 2022-02-08 | 2022-05-24 | 山东浪潮科学研究院有限公司 | Urban remote sensing image vegetation coverage identification method based on deep learning |
| CN115965812A (en) * | 2022-12-13 | 2023-04-14 | 桂林理工大学 | Evaluation method of wetland vegetation species and ground features classification by UAV images |
| CN116168290A (en) * | 2022-12-28 | 2023-05-26 | 二十一世纪空间技术应用股份有限公司 | Method and device for classifying arbor and shrub in remote sensing image |
| CN116433596A (en) * | 2023-03-07 | 2023-07-14 | 南京林业大学 | Slope vegetation coverage measuring method and device and related components |
| CN116863243A (en) * | 2023-07-26 | 2023-10-10 | 航天恒星科技有限公司 | A method, electronic equipment and storage medium for identifying wetland ecological drought conditions based on multi-source data |
| CN117611909A (en) * | 2023-12-04 | 2024-02-27 | 桂林理工大学 | A wetland vegetation classification method based on deep learning and image spatial resolution |
| CN116433596B (en) * | 2023-03-07 | 2025-07-25 | 南京林业大学 | Slope vegetation coverage measuring method and device and related components |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170249746A1 (en) * | 2015-10-23 | 2017-08-31 | International Business Machines Corporation | Imaging segmentation using multi-scale machine learning approach |
| CN110853026A (en) * | 2019-11-16 | 2020-02-28 | 四创科技有限公司 | Remote sensing image change detection method integrating deep learning and region segmentation |
| CN111652193A (en) * | 2020-07-08 | 2020-09-11 | 中南林业科技大学 | Wetland classification method based on multi-source imagery |
-
2021
- 2021-09-29 CN CN202111152307.XA patent/CN113837134A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170249746A1 (en) * | 2015-10-23 | 2017-08-31 | International Business Machines Corporation | Imaging segmentation using multi-scale machine learning approach |
| CN110853026A (en) * | 2019-11-16 | 2020-02-28 | 四创科技有限公司 | Remote sensing image change detection method integrating deep learning and region segmentation |
| CN111652193A (en) * | 2020-07-08 | 2020-09-11 | 中南林业科技大学 | Wetland classification method based on multi-source imagery |
Non-Patent Citations (1)
| Title |
|---|
| 腾文秀 等: ""结合面向对象和深度特征的高分影像树种分类"", 《测绘通报》, no. 4, pages 38 - 42 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114529721A (en) * | 2022-02-08 | 2022-05-24 | 山东浪潮科学研究院有限公司 | Urban remote sensing image vegetation coverage identification method based on deep learning |
| CN114529721B (en) * | 2022-02-08 | 2024-05-10 | 山东浪潮科学研究院有限公司 | Urban remote sensing image vegetation coverage recognition method based on deep learning |
| CN115965812A (en) * | 2022-12-13 | 2023-04-14 | 桂林理工大学 | Evaluation method of wetland vegetation species and ground features classification by UAV images |
| CN115965812B (en) * | 2022-12-13 | 2024-01-19 | 桂林理工大学 | Assessment method of wetland vegetation species and surface object classification using drone images |
| CN116168290A (en) * | 2022-12-28 | 2023-05-26 | 二十一世纪空间技术应用股份有限公司 | Method and device for classifying arbor and shrub in remote sensing image |
| CN116168290B (en) * | 2022-12-28 | 2023-08-08 | 二十一世纪空间技术应用股份有限公司 | Arbor-shrub grass classification method based on high-resolution remote sensing image and three-dimensional data |
| CN116433596A (en) * | 2023-03-07 | 2023-07-14 | 南京林业大学 | Slope vegetation coverage measuring method and device and related components |
| CN116433596B (en) * | 2023-03-07 | 2025-07-25 | 南京林业大学 | Slope vegetation coverage measuring method and device and related components |
| CN116863243A (en) * | 2023-07-26 | 2023-10-10 | 航天恒星科技有限公司 | A method, electronic equipment and storage medium for identifying wetland ecological drought conditions based on multi-source data |
| CN117611909A (en) * | 2023-12-04 | 2024-02-27 | 桂林理工大学 | A wetland vegetation classification method based on deep learning and image spatial resolution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113837134A (en) | A Wetland Vegetation Recognition Method Based on Object-Oriented Deep Learning Model and Transfer Learning | |
| CN118470550B (en) | A natural resource asset data collection method and platform | |
| CN114742272A (en) | A Soil Cadmium Risk Prediction Method Based on Spatial and Temporal Interaction | |
| CN113449594A (en) | Multilayer network combined remote sensing image ground semantic segmentation and area calculation method | |
| CN109409261B (en) | A crop classification method and system | |
| CN112347970B (en) | Remote sensing image ground object identification method based on graph convolution neural network | |
| CN110929607A (en) | Remote sensing identification method and system for urban building construction progress | |
| CN112001121B (en) | Large-area gentle region predictive soil mapping method based on solar radiation | |
| CN116403123B (en) | Remote sensing image change detection method based on deep convolutional network | |
| CN113936214B (en) | Karst wetland vegetation community classification method based on fusion of aerospace remote sensing images | |
| CN109948697B (en) | Method for extracting urban built-up area by using multi-source data to assist remote sensing image classification | |
| Zheng et al. | Partial domain adaptation for scene classification from remote sensing imagery | |
| CN113469226B (en) | A land use classification method and system based on street view images | |
| CN114898089B (en) | Functional area extraction and classification method fusing high-resolution images and POI data | |
| CN116630610A (en) | ROI Region Extraction Method Based on Semantic Segmentation Model and Conditional Random Field | |
| CN118501878A (en) | A real estate surveying method | |
| Yang et al. | Extraction of land covers from remote sensing images based on a deep learning model of NDVI-RSU-Net | |
| CN113159154B (en) | Crop classification-oriented time sequence feature reconstruction and dynamic identification method | |
| CN115457403A (en) | A method for intelligent identification of crops based on multi-type remote sensing images | |
| CN117172255B (en) | Geographic entity alignment method, device and electronic equipment considering spatial semantic relationship | |
| CN110533118B (en) | Sparse representation classification method for remote sensing images based on multi-kernel learning | |
| CN116704378A (en) | Homeland mapping data classification method based on self-growing convolution neural network | |
| Cheng et al. | Automated detection of impervious surfaces using night-time light and Landsat images based on an iterative classification framework | |
| Yu et al. | Mapping the planting area of winter wheat at 10-m resolution using sentinel-2 data and multimodel fusion method | |
| Yang et al. | Fast processing method of high resolution remote sensing image based on decision tree classification |
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 |