CN113792809A - Remote sensing picture classification method based on random semi-supervised feature extraction model - Google Patents

Remote sensing picture classification method based on random semi-supervised feature extraction model Download PDF

Info

Publication number
CN113792809A
CN113792809A CN202111101521.2A CN202111101521A CN113792809A CN 113792809 A CN113792809 A CN 113792809A CN 202111101521 A CN202111101521 A CN 202111101521A CN 113792809 A CN113792809 A CN 113792809A
Authority
CN
China
Prior art keywords
network
feature extraction
layer
semi
data
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.)
Granted
Application number
CN202111101521.2A
Other languages
Chinese (zh)
Other versions
CN113792809B (en
Inventor
向雪霜
刘雪娇
徐遥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Academy of Space Technology CAST
Original Assignee
China Academy of Space Technology CAST
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Academy of Space Technology CAST filed Critical China Academy of Space Technology CAST
Priority to CN202111101521.2A priority Critical patent/CN113792809B/en
Publication of CN113792809A publication Critical patent/CN113792809A/en
Application granted granted Critical
Publication of CN113792809B publication Critical patent/CN113792809B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—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
    • G06N3/08—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)
  • Bioinformatics & Computational Biology (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

本发明涉及一种基于随机半监督特征提取模型的遥感图片分类方法，包括以下步骤：a、建立遥感场景图片数据库；b、构建随机半监督特征提取模型；c、构建分类网络；d、建立随机半监督特征提取模型的优化目标；e、博弈交替训练随机半监督特征提取模型；f、训练分类器；g、完成遥感图片分类任务。本发明可以有效提高海量弱标注遥感数据的利用率，提升遥感图片分类任务性能。

Figure 202111101521

The invention relates to a remote sensing image classification method based on a random semi-supervised feature extraction model, comprising the following steps: a. establishing a remote sensing scene image database; b. building a random semi-supervised feature extraction model; c. building a classification network; d. establishing a random The optimization goal of the semi-supervised feature extraction model; e, game alternately trains the random semi-supervised feature extraction model; f, trains the classifier; g, completes the remote sensing image classification task. The invention can effectively improve the utilization rate of massive weakly labeled remote sensing data, and improve the performance of remote sensing image classification task.

Figure 202111101521

Description

Remote sensing picture classification method based on random semi-supervised feature extraction model
Technical Field
The invention relates to a remote sensing picture classification method based on a random semi-supervised feature extraction model.
Background
With the improvement of the spatial resolution of the remote sensing data, the scene classification task becomes a research hotspot of the remote sensing image classification task. The remote sensing image scene classification is to correctly label a given scene image with predefined semantic categories. In the prior art, a method based on deep learning is generally adopted for image classification. The method is widely applied to the picture classification task of life scenes, and reaches or surpasses the level of human beings. However, the remote sensing scene classification algorithm based on deep learning mainly focuses on supervised learning, which requires a large amount of labeled data. However, compared with the life scene pictures, the remote sensing pictures have large intra-class difference, small inter-class separability and multi-scale targets, and the remote sensing data samples have high labeling cost and strong specialization and show the characteristics of massive weak labels, so that the remote sensing picture classification task faces a larger challenge.
The existing methods based on deep learning are mainly divided into three categories: convolutional neural network CNN based methods, variational self-encoders VAE based methods and methods based on generation of antagonistic networks GAN. In the face of a large number of remote sensing images, CNN-based methods require the use of a large number of labeled samples to train the model or fine tune a pre-trained convolutional neural network. However, the remote sensing data sample labeling cost is high, and the specialization is strong, so that the application is not ideal. Although the method based on the VAE is an unsupervised generation type model learning method, the method has good effect in the scene classification of the remote sensing image, but the general feature representation of the original image cannot be learned sometimes in the process of reconstructing the similar image through the input image, so most of the VAE-based methods cannot learn the optimal distinguishable features of different scene classes. GAN-based methods are another generative model learning method that can be used unsupervised or semi-supervised, which is widely used in the task of remote sensing images.
For example, patent CN111339935A discloses an optical remote sensing image classification method based on an interpretable CNN image classification model, which focuses mainly on the interpretability problem of a deep learning model, and improves the accuracy of remote sensing image classification by proposing an interpretable CNN image classification model. For another example, patent CN108596248 discloses a remote sensing image classification model based on an improved deep convolutional neural network, which provides an improved deep convolutional neural network, and through dimension reduction, convolutional multi-channel optimization, feature extraction capability improvement and wave-band processing of spatial location features on a remote sensing feature image, the computing resource consumption of the deep convolutional neural network is reduced, meanwhile, the feature extraction effect is ensured, and the recognition degree of the spatial location features is improved. Therefore, the technologies are proposed around the remote sensing classification problem, the purpose is to reduce the consumption of computing resources and improve the remote sensing classification effect, and all the adopted technologies are fully supervised models, so that a large amount of labeled data is needed.
Of course, there are also some techniques proposed to classify pictures using a generation countermeasure network. The generation countermeasure network is composed of a generation network and a discrimination network, and deep feature representation of the data is learned under the condition of no-marking or weak-marking training data through a countermeasure training process between the generation network and the discrimination network. In the prior art, the generation of the countermeasure network is widely applied to the typical picture classification task of the life scene, and a competitive result is obtained. However, the mode of generating the countermeasure network is not widely applied to the remote sensing scene classification task, and the remote sensing picture has the characteristics of large intra-class difference, small inter-class separability, multi-scale target and the like compared with a typical life scene picture, so that the remote sensing picture classification task still faces a larger challenge.
Disclosure of Invention
The invention aims to provide a remote sensing picture classification method based on a random semi-supervised feature extraction model.
In order to achieve the purpose, the invention provides a remote sensing picture classification method based on a random semi-supervised feature extraction model, which comprises the following steps:
a. establishing a remote sensing scene picture database;
b. constructing a random semi-supervised feature extraction model;
c. constructing a classification network;
d. establishing an optimization target of a random semi-supervised feature extraction model;
e. game alternative training random semi-supervised feature extraction model;
f. training a classifier;
g. and finishing the task of classifying the remote sensing pictures.
According to one aspect of the invention, in the step (a), remote sensing scene picture data is collected and labeled according to land use types, then all data are divided into labeled data sets and unlabeled data sets according to whether category labels are provided, wherein one part of the labeled data sets is used as test data and does not participate in training, the rest part and all unlabeled data form a training data set, and finally data enhancement is performed on the training data set in a mode of horizontally overturning, vertically overturning and rotating by 90 degrees.
According to an aspect of the present invention, the constructing of the random semi-supervised feature extraction model in the step (b) includes constructing a random generation network G and a semi-supervised feature extraction network D;
the random generation network G comprises an input noise layer, a random layer, a resampling layer, a deconvolution layer and an output picture layer;
the semi-supervised feature extraction network D comprises an input picture layer, a convolution layer, a feature layer, a full connection layer and an output layer;
the optimization goal of the randomly generated network G is to find α so that:
Figure BDA0003271109510000031
wherein p iszThe method comprises the following steps that pre-defined distribution obeyed by an input variable z, epsilon is a middle variable of a random layer, and obey Gaussian distribution N (0, I), an output variable of the random layer obeys Gaussian prior distribution, alpha is a parameter to be trained, f (·) represents an output feature of a picture after semi-supervised feature extraction network D, E is a mathematical expectation about the variable, and x is an input picture;
the semi-supervised feature extraction network D is optimized to find η so that:
Figure BDA0003271109510000041
wherein eta is a parameter to be trained of the feature extraction network; y isiAn ith dimension component representing label y; di() represents the ith dimension component of the network output, K is the total number of classes of the classification task;
the random generation network G is constructed by the following steps:
b11, randomly sampling noise from a predefined distribution as an input of the random generation network G;
b12, setting the widths and depths of the random layer, the resampling layer and the deconvolution layer according to the specific task difficulty, wherein the output variables of the random layer obey Gaussian prior distribution;
b13, outputting pseudo data with the same size as the original data and serving as the input of the semi-supervised feature extraction network D;
when constructing the semi-supervised feature extraction network D:
in the game training stage, inputting pictures including real labeled data, real unlabelled data and generated pseudo data, and outputting values including true and false logic output and picture category output;
in the classifier training stage, the input of the semi-supervised feature extraction network D is labeled data, and the output is corresponding high-dimensional features which are used as the input of a classifier;
in the stage of realizing the remote sensing classification task, the input of the semi-supervised feature extraction network D is a remote sensing picture to be classified, and the output is corresponding high-dimensional features;
the random generation network G comprises 9 layers in total, and the first layer is an input layer; the second layer is a random layer and consists of two identical fully-connected networks and is used for learning the mean value and the variance of Gaussian prior distribution obeyed by the output variable of the layer; the third layer is a resampling layer; the subsequent five layers are deconvolution layers, wherein the size of a convolution kernel is 4 multiplied by 4, and the step length is 2; the last layer is an output layer, and 3-channel pictures with the size of 256 multiplied by 256 are output; the deconvolution layers all adopt ReLU-form activation functions, and the output layer adopts tanh-type activation functions;
the semi-supervised feature extraction network D comprises 9 layers, wherein the first layer is a picture input layer, and input pictures comprise marked real pictures, unmarked real pictures and generated pictures; the subsequent six layers are convolution layers, wherein the size of a convolution kernel is 5 multiplied by 5, the step length is 2, the activation function is LEAKYRELU, and the parameter is 0.2; the characteristic layer combines the characteristic information of the previous three layers; the last layer is a full connection layer, and the category or the authenticity information of the picture is output.
According to an aspect of the present invention, in the step (C), a linear support vector machine network is used to construct the classification network, and the regularization parameter C is 1000.
According to an aspect of the present invention, in step (D), the optimization goal of establishing the random semi-supervised feature extraction model is game-play-a maximum and minimum value about the randomly generated network G and the semi-supervised feature extraction network D, and is composed of supervised learning loss and unsupervised learning loss, as follows:
Figure BDA0003271109510000051
wherein p is the true remote sensing data distribution; p is a radical ofGIs the distribution of the generated data of the randomly generated network G; p is a radical ofD(y | x, y ≦ K) represents the probability that the input picture x is determined to be the label y; p is a radical ofD(y ≦ K | x) represents the probability that the input picture x is real data; p is a radical ofD(K +1| x) represents the probability that the input picture x is generating dummy data, J is a loss function with respect to networks G and D.
According to one aspect of the present invention, in said step (e), the training goal of the semi-supervised feature extraction network D is to maximize the probability that the labeled data classification is correct, by minimizing the cross-entropy
Figure BDA0003271109510000061
To realize the operation; maximizing the probability that the true data is judged true and the generated data is judged false by minimizing
Figure BDA0003271109510000062
And
Figure BDA0003271109510000063
to realize the operation;
the training goal of the randomly generated network G is to minimize the probability that the generated data is judged to be false data by minimizing
Figure BDA0003271109510000064
To realize the operation; while minimizing the distance between the generated data features and the real data features by minimizing
Figure BDA0003271109510000065
To realize the operation;
and repeating the alternate training between the semi-supervised feature extraction network D and the random generation network G until reaching the specified training step number, and storing the trained random semi-supervised feature extraction network.
According to one aspect of the invention, the step (e) is game alternate training according to the following steps:
e1, setting the total training round number N to be 200, randomly generating a network G to update k to be 2 times every time the semi-supervised feature extraction network D updates, and optimizing the learning rate lambda and the momentum parameter beta in the parameter of the Adam optimization algorithm1λ ═ 0.0002 and β, respectively10.5, small batch size m 64, hidden spatial dimension d 100, and for UC-merceded dataset K21;
e2, randomly initializing network parameters eta and alpha;
e3, training N times alternately according to the following modes:
e 31: randomly sampling m hidden variables z1，...，zm}～Ud[-1，1]And the Gaussian variable { ∈1，...，∈mN (0, I), calculating and judging the loss L of the network about the generated pictureD1：
Figure BDA0003271109510000071
e 32: randomly selecting m true samples { x ] from the label-free training dataset1，...，xmCalculating the loss L of the discrimination network about the unmarked pictureD2：
Figure BDA0003271109510000072
e 33: randomly selecting m true samples from a labeled training dataset (x)1，y1)，...，(xm，ym) Calculating the loss L of the marked picture of the judgment networkD3：
Figure BDA0003271109510000073
e 34: updating a semi-supervised feature extraction network parameter eta:
Figure BDA0003271109510000074
e 35: randomly sampling m hidden variables z1，...，zm}～Ud[-1，1]And the Gaussian variable { ∈1，...，∈mN (0, I), calculating the true and false loss L of the random generation network G about the generated pictureG1：
Figure BDA0003271109510000075
e 36: randomly selecting m true samples { x ] from the label-free training dataset1，...，xmCalculating the characteristic loss L of the random generation network G about the generated pictureG2：
Figure BDA0003271109510000081
e 37: updating the randomly generated network parameter α:
Figure BDA0003271109510000082
e 38: repeating said steps (e35) to (e37) k times, returning to said step (e 31);
e4, storing the trained random semi-supervised feature extraction network;
wherein U is uniformly distributed, I is a unit matrix +ηIs a gradient on a network parameter η +αIs a gradient with respect to the network parameter alpha.
According to one aspect of the present invention, in step (f), all the labeled data in the training data set are input into the trained random semi-supervised feature extraction network to obtain corresponding high-dimensional features, and the features and the label information are input into the support vector machine network for training.
According to one aspect of the invention, in the step (g), the trained random semi-supervised feature extraction model and the support vector machine network are saved to form a classification model;
selecting remote sensing data to be classified from the test data set, and preprocessing the remote sensing data to be classified;
inputting the processed picture into a trained random semi-supervised feature extraction network to obtain corresponding high-dimensional features;
and inputting the high-dimensional features into a trained classifier, outputting the class information of the remote sensing picture, and completing the task of classifying the remote sensing picture.
According to one aspect of the invention, the predefined distribution of input variables is a uniform distribution between [ -1,1 ].
According to the concept of the invention, the remote sensing picture classification method based on the random semi-supervised feature extraction model is provided aiming at the characteristics of complex data distribution and mass weak labeling of the remote sensing picture.
According to the scheme of the invention, the random semi-supervised feature extraction network with higher high-dimensional feature capability for capturing the remote sensing data is obtained through game alternate training of the random generation network with higher expression capability and the semi-supervised feature extraction network, so that the utilization rate of mass weakly labeled remote sensing data is effectively improved, and the game alternate training is finally used for improving the task performance of remote sensing image classification.
Drawings
FIG. 1 is a schematic flow chart of a remote sensing picture classification method based on a random semi-supervised feature extraction model according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a randomly generated network architecture in a remote sensing picture classification method based on a random semi-supervised feature extraction model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a semi-supervised feature extraction network architecture in a remote sensing picture classification method based on a random semi-supervised feature extraction model according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a confusion matrix result of a surface feature scene classification task in a remote sensing image classification method based on a random semi-supervised feature extraction model according to an embodiment of the present invention.
Detailed Description
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 embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
The present invention is described in detail below with reference to the drawings and the specific embodiments, which are not repeated herein, but the embodiments of the present invention are not limited to the following embodiments.
Referring to fig. 1, the invention discloses a remote sensing picture classification method based on a random semi-supervised feature extraction model, relates to the technical field of remote sensing image interpretation, and belongs to the key intelligent theory and algorithm research of a space intelligent system. The method comprises the steps of firstly establishing a remote sensing scene picture database, establishing a random semi-supervised feature extraction model, establishing a classification network, establishing an optimization target of the random semi-supervised feature extraction model, training the random semi-supervised feature extraction model in a game alternating mode, training a classifier and finishing a remote sensing picture classification task.
In the embodiment, in order to show the effect and the capability of the method for processing the scene classification task of the remote sensing picture, a UC-merceded remote sensing data set is taken as an example to complete the scene classification task of 21 types of ground objects. UC-Merced data set, comprising 21 land use categories, as shown in fig. 4, 1: mobile home park; 2: beach (beach); 3: tenis court; 4: airplane (airplane); 5: dense residential area; 6: harbor (seaport); 7: building; 8: forest; 9: intersectional (crossroad); 10: river (river); 11: sparse residence; 12: runway (runway); 13: park lot; 14: baseball Diamond (baseball field); 15: agricultural (agricultural); 16: storage tanks; 17: chaparral (jungle); 18: golf course; 19: freeway (expressway); 20: medium residential area; 21: overpass (overpass). Each class consists of 100 aerial images, 256 × 256 pixels in size. Of course, the method of the embodiment is mainly used for completing the task of classifying the remote sensing picture, and in other embodiments, other interpretation tasks based on picture features, such as a target detection task, can also be completed by using the method of the present invention.
In the invention, when the remote sensing scene picture database is established, the remote sensing scene picture data is collected and is labeled according to the land use type, and then the remote sensing scene picture data is divided into a labeled data set and a non-labeled data set according to whether a category label is provided. Of course, data division is also required, and for the data set of this embodiment, specifically, all samples in the data set are randomly divided into training data (accounting for 80%, 1680) and test data (accounting for 20%, 420). In addition, because the data set comprises more categories, and each category only comprises 100 pictures, the training data set also needs to be subjected to data enhancement, specifically, 3 times of enhanced data is obtained by means of horizontal turning, vertical turning and 90-degree rotation, the extended training data set comprises 6720 pictures in total by combining the original data, and because the data set is labeled data, the invention adopts a form of removing corresponding labels of the training data set to construct a required label-free data set.
In the invention, the random semi-supervised feature extraction model construction comprises a random generation network G and a semi-supervised feature extraction network D.
As shown in fig. 2, the random generation network G includes an input noise layer, a random layer, a resampling layer, a deconvolution layer, and an output picture layer. The random generation network G comprises 9 layers in total, and the first layer is an input layer; the second layer is a random layer and consists of two identical fully-connected networks and is used for learning the mean value and the variance of Gaussian prior distribution obeyed by the output variable of the layer; the third layer is a resampling layer; the subsequent five layers are deconvolution layers, wherein the size of a convolution kernel is 4 multiplied by 4, and the step length is 2; the last layer is an output layer, and 3-channel pictures with the size of 256 multiplied by 256 are output; the deconvolution layers all adopt ReLU-form activation functions, and the output layer adopts tanh-type activation functions;
the optimization goal of the randomly generated network G is to find α so that:
Figure BDA0003271109510000111
wherein p iszThe method comprises the steps of obtaining a pre-defined distribution obeyed by an input variable z, representing an intermediate variable of a random layer by epsilon, obeying a Gaussian distribution N (0, I), obtaining an output variable of the random layer by obeying a Gaussian prior distribution, wherein alpha is a parameter to be trained, f (-) represents an output characteristic of a picture after semi-supervised characteristic extraction network D, E is a mathematical expectation about the variable, and x is an input picture.
When the random generation network G is constructed, random sampling noise in predefined distribution is used as input of the random generation network G, the widths and depths of a random layer, a resampling layer and a deconvolution layer are set according to specific task difficulty, output variables of the random layer obey Gaussian prior distribution, and finally pseudo data with the same size as original data are output and used as input of a semi-supervised feature extraction network D.
As shown in fig. 3, the semi-supervised feature extraction network D includes an input picture layer, a convolutional layer, a feature layer, a full connection layer and an output layer. The semi-supervised feature extraction network D comprises 9 layers, wherein the first layer is a picture input layer, and input pictures comprise marked real pictures, unmarked real pictures and generated pictures; the subsequent six layers are convolution layers, wherein the size of a convolution kernel is 5 multiplied by 5, the step length is 2, the activation function is LEAKYRELU, and the parameter is 0.2; the characteristic layer combines the characteristic information of the previous three layers; the last layer is a full connection layer, and the category or the authenticity information of the picture is output.
The semi-supervised feature extraction network D is optimized to find η so that:
Figure BDA0003271109510000121
wherein eta is a parameter to be trained of the feature extraction network; y isiAn ith dimension component representing label y; di(. cndot.) represents the ith dimension component of the network output, and K is the total number of classes for the classification task.
When a semi-supervised feature extraction network D is constructed, in a game training stage, inputting pictures including real labeled data, real unlabelled data and generated pseudo data, and outputting values including true and false logic output and picture category output; in the classifier training stage, the input of the semi-supervised feature extraction network D is labeled data, and the output is corresponding high-dimensional features which are used as the input of a classifier; in the stage of realizing the remote sensing classification task, the input of the semi-supervised feature extraction network D is a remote sensing picture to be classified, and the output is corresponding high-dimensional features.
In the invention, a classification network is constructed by adopting a linear support vector machine network, and the regularization parameter C is 1000.
In the invention, the optimization target for establishing the random semi-supervised feature extraction model is the problem of the maximum and minimum values of a game about a randomly generated network G and a semi-supervised feature extraction network D, and the random semi-supervised feature extraction model consists of two parts of supervised learning loss and unsupervised learning loss, and specifically comprises the following steps:
Figure BDA0003271109510000131
wherein p is the true remote sensing data distribution; p is a radical ofGIs the distribution of the generated data of the randomly generated network G; p is a radical ofD(y | x, y ≦ K) represents the probability that the input picture x is determined to be the label y; p is a radical ofD(y ≦ K | x) represents the probability that the input picture x is real data; p is a radical ofD(K +1| x) represents the probability that the input picture x is generating dummy data, J is a loss function with respect to networks G and D.
In the invention, the training goal of the semi-supervised feature extraction network D is to maximize the probability of correct classification of labeled data by minimizing the cross entropy
Figure BDA0003271109510000132
To realize the operation; simultaneously maximizing the probability that the true data is judged to be true and the generated data is judged to be false, by minimizing
Figure BDA0003271109510000133
And
Figure BDA0003271109510000134
to be implemented.
The training goal of the randomly generated network G is to minimize the probability that the generated data is judged to be false data by minimizing
Figure BDA0003271109510000135
To realize the operation; while minimizing the distance between the generated data features and the real data features by minimizing
Figure BDA0003271109510000141
To be implemented.
And repeating the alternate training between the semi-supervised feature extraction network D and the random generation network G until reaching the specified training step number, and storing the trained random semi-supervised feature extraction network.
When the game alternative training is carried out, firstly, parameter setting is carried out, specifically, the total training round number N is set to be 200, the semi-supervised feature extraction network D randomly generates the network G to update k to be 2 times every time the semi-supervised feature extraction network D updates, and Adam optimizes algorithm parameters (the learning rate lambda is 0.0002, and the momentum parameter beta is 0.0002)10.5), mini-batch size m 64, hidden spatial dimension d 100, and K for UC-merceded dataset21. Network parameters η and α are randomly initialized. Alternately training in the following way:
for total number of training rounds, ndo
Randomly sampling m hidden variables z1，...，zm}～Ud[-1，1]And the Gaussian variable { ∈1，...，∈mN (0, I), calculating and judging the loss L of the network about the generated pictureD1：
Figure BDA0003271109510000142
Randomly selecting m true samples { x ] from the label-free training dataset1，...，xmCalculating the loss L of the discrimination network about the unmarked pictureD2：
Figure BDA0003271109510000143
Randomly selecting m true samples from a labeled training dataset (x)1，y1)，...，(xm，ym) Calculating the loss L of the marked picture of the judgment networkD3：
Figure BDA0003271109510000144
Updating a semi-supervised feature extraction network parameter eta:
Figure BDA0003271109510000145
randomly sampling m hidden variables z1，...，zm}～Ud[-1，1]And the Gaussian variable { ∈1，...，∈mN (0, I), calculating the true and false loss L of the random generation network G about the generated pictureG1：
Figure BDA0003271109510000151
Randomly selecting m true samples { x ] from the label-free training dataset1，...，xmCalculating the characteristic loss L of the random generation network G about the generated pictureG2：
Figure BDA0003271109510000152
Updating the randomly generated network parameter α:
Figure BDA0003271109510000153
repeating the steps to calculate the loss LG1And characteristic loss LG2And updating the randomly generated network parameter alpha for a plurality of times (k), namely, the picture loss L can be calculatedD1A step (2);
end for
and finally, storing the trained random semi-supervised feature extraction network.
Wherein U is uniformly distributed, I is a unit matrix,
Figure BDA0003271109510000154
in order to be a gradient with respect to the network parameter η,
Figure BDA0003271109510000155
is a gradient with respect to the network parameter alpha.
In the invention, when training a classifier, all labeled data of a training data set are input into a trained random semi-supervised feature extraction network to obtain corresponding high-dimensional features, and the features and label information are input into a support vector machine network to train the support vector machine network.
In the invention, a trained random semi-supervised feature extraction model and a support vector machine network are stored to form a classification model, the remote sensing picture to be classified is input into the classification model, and finally the class information of the remote sensing picture is output. Specifically, firstly, remote sensing data to be classified is selected from the test data set, the remote sensing data to be classified is preprocessed, and the pictures are uniformly cut into 256 × 256 pictures. And then inputting the processed picture into a trained random semi-supervised feature extraction network to obtain corresponding high-dimensional features. And finally, inputting the high-dimensional features into a trained classifier, and finally outputting the class information of the remote sensing picture, thereby completing the task of classifying the remote sensing picture.
In the present invention, the predefined distribution of input variables is a uniform distribution between [ -1,1 ].
The average classification accuracy of the method can reach more than 98%, and a confusion matrix of the classification result is shown in figure 4.
In summary, the invention combines the randomly generated countermeasure network with stronger expression capability and the semi-supervision method by utilizing the capability of generating the distribution of the countermeasure network capturing data and the advantage of processing mass weak annotation data by the semi-supervision method, is applied to the remote sensing picture classification task, can effectively utilize mass weak annotation remote sensing data, has stronger picture characteristic extraction capability, can be used for completing the remote sensing picture classification task, and can also be widely applied to other remote sensing interpretation tasks based on picture characteristics, such as target detection, ground feature segmentation and the like.
The above description is only one embodiment of the present invention, and is not intended to limit the present invention, and it is apparent to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1.一种基于随机半监督特征提取模型的遥感图片分类方法，包括以下步骤：1. A remote sensing image classification method based on a random semi-supervised feature extraction model, comprising the following steps: a、建立遥感场景图片数据库；a. Establish a remote sensing scene image database; b、构建随机半监督特征提取模型；b. Build a random semi-supervised feature extraction model; c、构建分类网络；c. Build a classification network; d、建立随机半监督特征提取模型的优化目标；d. Establish the optimization objective of the random semi-supervised feature extraction model; e、博弈交替训练随机半监督特征提取模型；e. Game alternate training random semi-supervised feature extraction model; f、训练分类器；f. Training the classifier; g、完成遥感图片分类任务。g. Complete the task of remote sensing image classification. 2.根据权利要求1所述的方法，其特征在于，在所述步骤(a)中，收集遥感场景图片数据，并按土地利用类型进行标注，然后按照是否具备类别标签将所有数据划分为有标注数据集和无标注数据集，其中有标注数据集的一部分作为测试数据，不参与训练，剩余的部分和所有无标注数据构成训练数据集，最后对训练数据集通过水平翻转、垂直翻转和旋转90度的方式进行数据增强。2. method according to claim 1, is characterized in that, in described step (a), collect remote sensing scene picture data, and carry out labeling by land use type, then divide all data according to whether there is a class label into have. Labeled data set and unlabeled data set, in which a part of the labeled data set is used as test data and does not participate in training. The remaining part and all unlabeled data constitute a training data set. Finally, the training data set is flipped horizontally, vertically and rotated. Data augmentation in a 90-degree manner. 3.根据权利要求1所述的方法，其特征在于，所述步骤(b)中构建随机半监督特征提取模型包括构建随机生成网络G和半监督特征提取网络D；3. The method according to claim 1, wherein in the step (b), constructing a random semi-supervised feature extraction model comprises constructing a random generation network G and a semi-supervised feature extraction network D; 随机生成网络G包括输入噪声层、随机层、重采样层、反卷积层和输出图片层；The random generation network G includes an input noise layer, a random layer, a resampling layer, a deconvolution layer and an output image layer; 半监督特征提取网络D包括输入图片层、卷积层、特征层、全连接层和输出层；The semi-supervised feature extraction network D includes an input image layer, a convolutional layer, a feature layer, a fully connected layer and an output layer; 随机生成网络G的优化目标为寻找α*使得：The optimization objective of the randomly generated network G is to find α* such that:
Figure FDA0003271109500000021
Figure FDA0003271109500000021
 其中，pz是输入变量z服从的预定义分布，∈为随机层的中间变量，服从高斯分布N(0，I)，随机层的输出变量服从高斯先验分布，α为待训练参数，f(·)表示图片经过半监督特征提取网络D的输出特征，E为关于变量的数学期望，x为输入图片；Among them, p z is the predefined distribution that the input variable z obeys, ∈ is the intermediate variable of the random layer, which obeys the Gaussian distribution N(0, I), and the output variable of the random layer obeys the Gaussian prior distribution, α is the parameter to be trained, f ( ) represents the output feature of the image through the semi-supervised feature extraction network D, E is the mathematical expectation about the variable, and x is the input image; 半监督特征提取网络D的优化目标为寻找η*使得：The optimization goal of the semi-supervised feature extraction network D is to find η* such that:
Figure FDA0003271109500000022
Figure FDA0003271109500000022
 其中，η为特征提取网络的待训练参数；yi表示标签y的第i维分量；Di(·)表示网络输出的第i维分量，K为分类任务的总类别数；Wherein, n is the parameter to be trained of the feature extraction network; y i represents the i-th dimension component of the label y; D i ( ) represents the i-th dimension component of the network output, and K is the total number of categories of the classification task; 构建随机生成网络G包括以下步骤：Building a random generation network G includes the following steps: b11、从预定义分布中随机采样噪声作为随机生成网络G的输入；b11. Randomly sample noise from a predefined distribution as the input of the random generation network G; b12、根据具体任务难度设定随机层、重采样层、反卷积层的宽度和深度，其中随机层的输出变量服从高斯先验分布；b12. Set the width and depth of the random layer, resampling layer, and deconvolution layer according to the difficulty of the specific task, wherein the output variable of the random layer obeys the Gaussian prior distribution; b13、输出与原始数据相同尺寸的伪数据，并且作为半监督特征提取网络D的输入；b13. Output pseudo data of the same size as the original data, and use it as the input of the semi-supervised feature extraction network D; 构建半监督特征提取网络D时：When building a semi-supervised feature extraction network D: 在博弈训练阶段，输入图片包括真实有标注数据、真实无标注数据和生成伪数据，输出值包括真伪逻辑输出和图片类别输出；In the game training stage, the input pictures include real labeled data, real unlabeled data and generated pseudo data, and the output values include true and false logic output and picture category output; 在分类器训练阶段，半监督特征提取网络D的输入是有标注数据，输出为对应的高维特征，作为分类器的输入；In the classifier training stage, the input of the semi-supervised feature extraction network D is labeled data, and the output is the corresponding high-dimensional feature as the input of the classifier; 在实现遥感分类任务阶段，半监督特征提取网络D的输入是待分类遥感图片，输出为对应的高维特征；In the stage of realizing remote sensing classification task, the input of the semi-supervised feature extraction network D is the remote sensing image to be classified, and the output is the corresponding high-dimensional feature; 随机生成网络G共包含9层，第一层为输入层；第二层为随机层，由两个相同的全连接网络组成，用于学习该层输出变量所服从的高斯先验分布的均值和方差；第三层为重采样层；后续五层为反卷积层，其中卷积核的大小为4×4，步长为2；最后一层为输出层，输出大小为256×256的3通道图片；其中，反卷积层均采用ReLU形式的激活函数，输出层采用tanh类型的激活函数；The random generation network G consists of 9 layers, the first layer is the input layer; the second layer is the random layer, which consists of two identical fully connected networks, which are used to learn the mean and sum of the Gaussian prior distributions that the output variables of this layer obey. variance; the third layer is the resampling layer; the next five layers are the deconvolution layers, where the size of the convolution kernel is 4×4, and the stride is 2; the last layer is the output layer, and the output size is 3 with a size of 256×256 Channel picture; among them, the deconvolution layer adopts the activation function in the form of ReLU, and the output layer adopts the activation function of the tanh type; 半监督特征提取网络D包含9层，第一层为图片输入层，输入的图片包括有标注的真图片、无标注的真图片以及生成图片；后续六层为卷积层，其中卷积核的大小为5×5，步长为2，激活函数为leakyReLU，参数为0.2；特征层联合了之前三层的特征信息；最后一层为全连接层，输出图片的类别或真伪信息。The semi-supervised feature extraction network D consists of 9 layers. The first layer is the image input layer. The input images include labeled real pictures, unlabeled real pictures, and generated pictures; the subsequent six layers are convolutional layers, in which the convolution kernels are The size is 5×5, the step size is 2, the activation function is leakyReLU, and the parameter is 0.2; the feature layer combines the feature information of the previous three layers; the last layer is a fully connected layer, which outputs the category or authenticity information of the picture. 4.根据权利要求1所述的方法，其特征在于，所述步骤(c)中采用线性支持向量机网络构建分类网络，正则化参数C为1000。4 . The method according to claim 1 , wherein in the step (c), a linear support vector machine network is used to construct a classification network, and the regularization parameter C is 1000. 5 . 5.根据权利要求1所述的方法，其特征在于，在所述步骤(d)中，建立随机半监督特征提取模型的优化目标为博弈一个关于随机生成网络G和半监督特征提取网络D的极大极小值，由监督学习损失和无监督学习损失两部分组成，如下式：5. method according to claim 1, is characterized in that, in described step (d), the optimization goal of establishing random semi-supervised feature extraction model is a game about randomly generating network G and semi-supervised feature extraction network D. The maximum and minimum values are composed of two parts: supervised learning loss and unsupervised learning loss, as follows:
Figure FDA0003271109500000041
Figure FDA0003271109500000041
 其中，p是真实的遥感数据分布；pG是随机生成网络G的生成数据分布；pD(y|x，y≤K)表示输入图片x被判断为标签y的概率；pD(y≤K|x)表示输入图片x是真实数据的概率；pD(K+1|x)表示输入图片x是生成伪数据的概率，J为关于网络G和D的损失函数。Among them, p is the real remote sensing data distribution; p G is the generated data distribution of the random generation network G; p D (y|x, y≤K) represents the probability that the input image x is judged as the label y; p D (y≤ K|x) represents the probability that the input image x is the real data; p D (K+1|x) represents the probability that the input image x is the generated fake data, and J is the loss function of the network G and D. 6.根据权利要求1所述的方法，其特征在于，在所述步骤(e)中，半监督特征提取网络D的训练目标是最大化有标注数据分类正确的概率，通过最小化交叉熵
Figure FDA0003271109500000042
来实现；最大化真实数据判断为真以及生成数据判断为假的概率，通过最小化
Figure FDA0003271109500000043
知
Figure FDA0003271109500000044
来实现；6. The method according to claim 1, wherein in the step (e), the training objective of the semi-supervised feature extraction network D is to maximize the probability that the labeled data is classified correctly, by minimizing the cross-entropy
Figure FDA0003271109500000042
To achieve; maximize the probability that the real data is judged to be true and the generated data is judged to be false, by minimizing
Figure FDA0003271109500000043
Know
Figure FDA0003271109500000044
to fulfill; 随机生成网络G的训练目标是最小化生成数据被判断为假数据的概率，通过最小化
Figure FDA0003271109500000045
来实现；同时最小化生成数据特征与真实数据特征之间的距离，通过最小化
Figure FDA0003271109500000046
来实现；The training goal of the random generation network G is to minimize the probability that the generated data is judged to be false data, by minimizing
Figure FDA0003271109500000045
To achieve; at the same time minimize the distance between the generated data features and the real data features, by minimizing
Figure FDA0003271109500000046
to fulfill; 重复半监督特征提取网络D与随机生成网络G之间的交替训练，直到达到指定的训练步数，保存训练好的随机半监督特征提取网络。Repeat the alternate training between the semi-supervised feature extraction network D and the random generation network G until the specified number of training steps is reached, and save the trained random semi-supervised feature extraction network. 7.根据权利要求6所述的方法，其特征在于，所述步骤(e)中按以下步骤进行博弈交替训练：7. method according to claim 6, is characterized in that, in described step (e), carry out game alternating training according to the following steps: e1、设定总训练轮数N＝200，半监督特征提取网络D每更新一次则随机生成网络G更新k＝2次，Adam优化算法参数中的学习率λ和动量参数β1分别为λ＝0.0002和β1＝0.5，小批量尺寸m＝64，隐空间维度d＝100，对于UC-Merced数据集，K＝21；e1. Set the total number of training rounds N=200, and the semi-supervised feature extraction network D will randomly generate the network G to update k=2 times each time it is updated. The learning rate λ and the momentum parameter β1 in the parameters of the Adam optimization algorithm are λ = 0.0002 and β 1 =0.5, mini-batch size m=64, latent space dimension d=100, K=21 for UC-Merced dataset; e2、随机初始化网络参数η和a；e2. Randomly initialize network parameters η and a; e3、按以下方式交替训练N次：e3. Alternately train N times as follows: e31：随机采样m个隐变量{z1，...，zm}～Ud[-1，1]和高斯变量{∈1，...，∈m}～N(0，I)，计算判别网络关于生成图片损失LD1：e31: randomly sample m latent variables {z 1 ,...,z m }～U d [-1,1] and Gaussian variables {∈ 1 ,...,∈ m }～N(0,I), Calculate the loss L D1 of the discriminative network for generating images:
Figure FDA0003271109500000051
Figure FDA0003271109500000051
 e32：从无标注训练数据集中随机选取m个真样本{x1，...，xm}，计算判别网络关于无标注图片损失LD2： e32 : Randomly select m real samples {x 1 , .
Figure FDA0003271109500000052
Figure FDA0003271109500000052
 e33：从有标注训练数据集中随机选取m个真样本{(x1，y1)，...，(xm，ym)}，计算判别网络关于有标注图片损失LD3：e33: Randomly select m real samples {(x 1 , y 1 ), ..., (x m , y m )} from the labeled training data set, and calculate the loss L D3 of the discriminant network for labeled images:
Figure FDA0003271109500000053
Figure FDA0003271109500000053
 e34：更新半监督特征提取网络参数η：e34: Update semi-supervised feature extraction network parameters η:
Figure FDA0003271109500000054
Figure FDA0003271109500000054
 e35：随机采样m个隐变量{z1，...，zm}～Ud[-1，1]和高斯变量{∈1，...，∈m}～N(0，I)，计算随机生成网络G关于生成图片的真伪损失LG1：e35: randomly sample m latent variables {z 1 ,...,z m }～U d [-1,1] and Gaussian variables {∈ 1 ,...,∈ m }～N(0,I), Calculate the authenticity loss L G1 of the generated image by the random generation network G:
Figure FDA0003271109500000061
Figure FDA0003271109500000061
 e36：从无标注训练数据集中随机选取m个真样本{x1，...，xm}，计算随机生成网络G关于生成图片的特征损失LG2： e36 : Randomly select m real samples {x 1 , .
Figure FDA0003271109500000062
Figure FDA0003271109500000062
 e37：更新随机生成网络参数α：e37: Update randomly generated network parameters α:
Figure FDA0003271109500000063
Figure FDA0003271109500000063
 e38：重复所述步骤(e35)至所述步骤(e37)k次，返回所述步骤(e31)；e38: repeat the step (e35) to the step (e37) k times, and return to the step (e31); e4、保存训练好的随机半监督特征提取网络；e4. Save the trained random semi-supervised feature extraction network; 其中，U为均匀分布，I为单位矩阵，
Figure FDA0003271109500000064
为关于网络参数η的梯度，
Figure FDA0003271109500000065
为关于网络参数α的梯度。Among them, U is the uniform distribution, I is the identity matrix,
Figure FDA0003271109500000064
is the gradient with respect to the network parameter η,
Figure FDA0003271109500000065
is the gradient with respect to the network parameter α. 8.根据权利要求1所述的方法，其特征在于，在所述步骤(f)中，将训练数据集中所有标注数据输入训练好的随机半监督特征提取网络中，得到相应的高维特征，并将特征与标签信息输入到支持向量机网络中进行训练。8. method according to claim 1, is characterized in that, in described step (f), all label data in training data set is input into trained random semi-supervised feature extraction network, obtains corresponding high-dimensional feature, And input the feature and label information into the support vector machine network for training. 9.根据权利要求1所述的方法，其特征在于，在所述步骤(g)中，保存训练好的随机半监督特征提取模型和支持向量机网络，组成分类模型；9. method according to claim 1, is characterized in that, in described step (g), save training good random semi-supervised feature extraction model and support vector machine network, form classification model; 从测试数据集中选取待分类遥感数据，对待分类遥感数据进行预处理；Select remote sensing data to be classified from the test data set, and preprocess the remote sensing data to be classified; 将处理后的图片输入到训练好的随机半监督特征提取网络中，得到相应的高维特征；Input the processed images into the trained random semi-supervised feature extraction network to obtain corresponding high-dimensional features; 将高维特征输入到训练好的分类器中，输出该遥感图片的类别信息，完成遥感图片分类任务。Input the high-dimensional features into the trained classifier, output the category information of the remote sensing image, and complete the remote sensing image classification task. 10.根据权利要求1-9中任一项所述的方法，其特征在于，输入变量的预定义分布为[-1,1]之间的均匀分布。10. The method according to any one of claims 1-9, wherein the predefined distribution of the input variable is a uniform distribution between [-1, 1].
CN202111101521.2A 2021-09-18 2021-09-18 Remote sensing picture classification method based on random semi-supervised feature extraction model Active CN113792809B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111101521.2A CN113792809B (en) 2021-09-18 2021-09-18 Remote sensing picture classification method based on random semi-supervised feature extraction model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111101521.2A CN113792809B (en) 2021-09-18 2021-09-18 Remote sensing picture classification method based on random semi-supervised feature extraction model

Publications (2)

Publication Number Publication Date
CN113792809A true CN113792809A (en) 2021-12-14
CN113792809B CN113792809B (en) 2024-07-02

Family

ID=79184168

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111101521.2A Active CN113792809B (en) 2021-09-18 2021-09-18 Remote sensing picture classification method based on random semi-supervised feature extraction model

Country Status (1)

Country Link
CN (1) CN113792809B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117409262A (en) * 2023-12-14 2024-01-16 厦门瑞为信息技术有限公司 Method for quickly constructing image classification model based on CLIP

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102129571A (en) * 2011-01-31 2011-07-20 重庆大学 Method for classifying multi-spectral remote sensing data land use based on semi-supervisor manifold learning
CN102938073A (en) * 2012-10-23 2013-02-20 中国人民解放军空军工程大学 Method for classifying remote sensing images
US20130346346A1 (en) * 2012-06-21 2013-12-26 Microsoft Corporation Semi-supervised random decision forests for machine learning
CN107358142A (en) * 2017-05-15 2017-11-17 西安电子科技大学 Polarimetric SAR Image semisupervised classification method based on random forest composition
CN108038448A (en) * 2017-12-13 2018-05-15 河南理工大学 Semi-supervised random forest Hyperspectral Remote Sensing Imagery Classification method based on weighted entropy
US20200019817A1 (en) * 2018-07-11 2020-01-16 Harbin Institute Of Technology Superpixel classification method based on semi-supervised k-svd and multiscale sparse representation

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102129571A (en) * 2011-01-31 2011-07-20 重庆大学 Method for classifying multi-spectral remote sensing data land use based on semi-supervisor manifold learning
US20130346346A1 (en) * 2012-06-21 2013-12-26 Microsoft Corporation Semi-supervised random decision forests for machine learning
CN102938073A (en) * 2012-10-23 2013-02-20 中国人民解放军空军工程大学 Method for classifying remote sensing images
CN107358142A (en) * 2017-05-15 2017-11-17 西安电子科技大学 Polarimetric SAR Image semisupervised classification method based on random forest composition
CN108038448A (en) * 2017-12-13 2018-05-15 河南理工大学 Semi-supervised random forest Hyperspectral Remote Sensing Imagery Classification method based on weighted entropy
US20200019817A1 (en) * 2018-07-11 2020-01-16 Harbin Institute Of Technology Superpixel classification method based on semi-supervised k-svd and multiscale sparse representation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
吴俊峰;姜志国;张浩鹏;蔡博文;罗鹏浩: "半监督条件随机场的高光谱遥感图像分类", 遥感学报, no. 004, 31 December 2017 (2017-12-31) *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117409262A (en) * 2023-12-14 2024-01-16 厦门瑞为信息技术有限公司 Method for quickly constructing image classification model based on CLIP
CN117409262B (en) * 2023-12-14 2024-03-01 厦门瑞为信息技术有限公司 Method for quickly constructing image classification model based on CLIP

Also Published As

Publication number Publication date
CN113792809B (en) 2024-07-02

Similar Documents

Publication Publication Date Title
CN109614985B (en) Target detection method based on densely connected feature pyramid network
Wang et al. RSNet: The search for remote sensing deep neural networks in recognition tasks
US11195051B2 (en) Method for person re-identification based on deep model with multi-loss fusion training strategy
Deng et al. Active transfer learning network: A unified deep joint spectral–spatial feature learning model for hyperspectral image classification
Zhong et al. SAR target image classification based on transfer learning and model compression
Teow Understanding convolutional neural networks using a minimal model for handwritten digit recognition
CN108389211B (en) Image segmentation method based on improved whale optimized fuzzy clustering
CN110136154A (en) Semantic Segmentation Method of Remote Sensing Image Based on Fully Convolutional Network and Morphological Processing
CN108985252B (en) Improved spiking deep neural network for image classification
CN107092661A (en) A kind of image search method based on depth convolutional neural networks
CN112561796B (en) Laser point cloud super-resolution reconstruction method based on self-attention generation countermeasure network
Badawi et al. A hybrid memetic algorithm (genetic algorithm and great deluge local search) with back-propagation classifier for fish recognition
CN111611972B (en) Crop leaf type identification method based on multi-view multi-task integrated learning
Vallet et al. A multi-label convolutional neural network for automatic image annotation
Chen et al. A novel localized and second order feature coding network for image recognition
CN107194438A (en) A kind of depth characteristic method for expressing based on multiple stack own coding
CN111310609A (en) Video target detection method based on time sequence information and local feature similarity
CN113792809A (en) Remote sensing picture classification method based on random semi-supervised feature extraction model
CN107529647A (en) A kind of cloud atlas cloud amount computational methods based on the unsupervised sparse learning network of multilayer
CN114612450A (en) Image detection segmentation method and system based on data augmentation machine vision and electronic equipment
Yildirim et al. REGP: A NEW POOLING ALGORITHM FOR DEEP CONVOLUTIONAL NEURAL NETWORKS.
CN113221683A (en) Expression recognition method based on CNN model in teaching scene
Sarraf Binary image segmentation using classification methods: Support vector machines, artificial neural networks and k th nearest neighbours
CN117788869A (en) Improved FCM information entropy point cloud simplification method based on DEAMPOA
CN111209886A (en) Rapid pedestrian re-identification method based on deep 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