WO2022052367A1 - Procédé d'optimisation de réseau neuronal pour une classification d'image de détection à distance, terminal, et support de stockage - Google Patents

Procédé d'optimisation de réseau neuronal pour une classification d'image de détection à distance, terminal, et support de stockage Download PDF

Info

Publication number
WO2022052367A1
WO2022052367A1 PCT/CN2020/138818 CN2020138818W WO2022052367A1 WO 2022052367 A1 WO2022052367 A1 WO 2022052367A1 CN 2020138818 W CN2020138818 W CN 2020138818W WO 2022052367 A1 WO2022052367 A1 WO 2022052367A1
Authority
WO
WIPO (PCT)
Prior art keywords
noise
remote sensing
model
sensing image
network model
Prior art date
Application number
PCT/CN2020/138818
Other languages
English (en)
Chinese (zh)
Inventor
林创
陈劲松
李洪忠
Original Assignee
中国科学院深圳先进技术研究院
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 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2022052367A1 publication Critical patent/WO2022052367A1/fr

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

Definitions

  • the application belongs to the technical field of remote sensing image processing, and in particular relates to a neural network optimization method, a terminal and a storage medium for remote sensing image classification.
  • the classification problem of remote sensing images corresponds to the semantic segmentation problem in computer vision, which is to assign a classification category to each pixel in the image.
  • there is a noise problem in the data set labels in the remote sensing image classification process mainly including more or less labeling of category pixels. Similar to the expansion or corrosion of the image, using a noisy data set to train the neural network will lead to the neural network. The classification performance is degraded and the obtained results are inaccurate.
  • the present application provides a neural network optimization method, terminal, and storage medium for remote sensing image classification, aiming to solve one of the above-mentioned technical problems in the prior art at least to a certain extent.
  • a neural network optimization method for remote sensing image classification comprising:
  • the anti-noise network model includes an image segmentation model and a loss selection model, and the image segmentation model is a U-Net network based on the SE module;
  • the remote sensing image data set into the anti-noise network model for iterative training and the anti-noise network model performs image segmentation through the U-Net network based on the SE module to obtain image classification results, and selects through the loss
  • the model uses the ksigma criterion to select the loss, eliminates the error exceeding the set deviation interval, and obtains the optimal network model parameters.
  • the obtaining of the remote sensing image data set includes:
  • the remote sensing image data set is divided into training set, validation set and test set according to a set ratio, and the images of the training set, validation set and test set are cropped into images of a set size, and the training set images are Perform data cleaning and data enhancement.
  • performing image segmentation through the SE module-based U-Net network includes:
  • the input feature map passes through a standard convolutional layer
  • two branches are generated.
  • the first branch passes through two standard convolutional layers to obtain the first feature map
  • the second branch is the SE module, which includes a Globalpooling layer, two layers
  • the FullyConnected layer and the sigmoid function layer firstly perform global average pooling on the input feature map through the Globalpooling layer to obtain the second feature map; and then activate the sigmoid function layer after passing through two Fully Connected layers to obtain the same feature as the second feature.
  • the weight corresponding to the size of the image is multiplied by the first feature map generated by the first branch to obtain the image classification output result.
  • the technical solution adopted in the embodiment of the present application further includes: the loss selection using the ksigma criterion through the loss selection model includes:
  • the inputting the remote sensing image dataset into the anti-noise network model for iterative training includes:
  • the training set is input into the anti-noise network model, the learning rate, the number of iterations, and the K value of the loss selection model are set, and the loss function for optimizing the network parameters is set, and the model training process is adjusted according to the loss curve.
  • the technical solution adopted in the embodiment of the present application further includes: the inputting the remote sensing image dataset into the anti-noise network model for iterative training further includes:
  • 0%, 25% and 50% of the sample images are randomly selected from the training set, and 5*5, 7*7 and 9*9 convolution kernels are used to dilate and corrode the selected sample images to generate different types of and
  • the noise-marked images of the level are trained according to the anti-noise network model according to the noise-marked images of different types and levels.
  • the technical solutions adopted in the embodiments of the present application further include: after obtaining the optimal network model parameters, the following further includes:
  • the test set image is input into the anti-noise network model, the classification result of the test set image is obtained, and the performance of the anti-noise network model is evaluated according to the classification result.
  • a neural network optimization system comprising:
  • Data acquisition module used to acquire remote sensing image datasets
  • Anti-noise network building module used to construct an anti-noise network model, the anti-noise network model includes an image segmentation model and a loss selection model, and the image segmentation model is a U-Net network based on the SE module;
  • Model training module used to input the remote sensing image data set into the anti-noise network model for iterative training, and the anti-noise network model performs image segmentation through the U-Net network based on the SE module to obtain an image classification result, And through the loss selection model, the ksigma criterion is used to select the loss, and the error exceeding the set deviation interval is eliminated to obtain the optimal network model parameters.
  • a terminal includes a processor and a memory coupled to the processor, wherein,
  • the memory stores program instructions for implementing the neural network optimization method for remote sensing image classification
  • the processor is configured to execute the program instructions stored in the memory to control neural network optimization for remote sensing image classification.
  • a storage medium storing program instructions executable by a processor, where the program instructions are used to execute the neural network optimization method for remote sensing image classification.
  • the beneficial effects of the embodiments of the present application are: the neural network optimization method, system, terminal and storage medium for remote sensing image classification according to the embodiments of the present application improve the network model based on the semantic segmentation network U-Net , build an anti-noise network model, use the ksigma criterion for loss selection, add SE module to the anti-noise network model, improve the feature extraction ability of the network model, and solve the problem of neural network classification accuracy decline due to noise in labels in remote sensing image datasets. question.
  • FIG. 1 is a flowchart of a neural network optimization method for remote sensing image classification according to a first embodiment of the present application
  • FIG 2 is an architecture diagram of an anti-noise network model according to an embodiment of the present application.
  • Fig. 3 is the existing U-Net network structure diagram
  • Fig. 4 is the structure diagram of the SE module of the embodiment of the present application.
  • FIG. 5 is a flowchart of a neural network optimization method for remote sensing image classification according to the second embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a neural network optimization system for remote sensing image classification according to an embodiment of the application
  • FIG. 7 is a schematic structural diagram of a terminal according to an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a storage medium according to an embodiment of the present application.
  • FIG. 1 is a flowchart of the neural network optimization method for remote sensing image classification according to the first embodiment of the present application.
  • the neural network optimization method for remote sensing image classification according to the first embodiment of the present application includes the following steps:
  • the number of images and the size of the images in the remote sensing image dataset can be set according to the actual operation.
  • the anti-noise network model architecture is shown in Figure 2, which includes an image segmentation model and a loss selection model.
  • the image segmentation model is a U-Net network based on the SE module.
  • the network structure of the existing U-Net is shown in Figure 3, which includes two parts: a feature extraction part and an upsampling part.
  • the feature extraction part is divided into five layers, and the image resolution is halved after each layer of pooling layer; correspondingly, the upsampling part is also divided into five layers, each of which has a standard volume containing two layers.
  • the convolutional module of the stack is shown in Figure 2, which includes an image segmentation model and a loss selection model.
  • the image segmentation model is a U-Net network based on the SE module.
  • the network structure of the existing U-Net is shown in Figure 3, which includes two parts: a feature extraction part and an upsampling part.
  • the feature extraction part is divided into five layers, and the image resolution is halved after each layer of pooling layer
  • the network model is improved on the basis of the existing U-Net, and the SE module (Squeeze-and-Excitation Networks) is added to the U-Net network structure to expand the perception of global information and improve the network's ability to deal with difficult problems.
  • the learning ability of the sample is improved on the basis of the existing U-Net, and the SE module (Squeeze-and-Excitation Networks) is added to the U-Net network structure to expand the perception of global information and improve the network's ability to deal with difficult problems. The learning ability of the sample.
  • the improvement point of the network model in the embodiment of the present application is that the convolution module in the existing U-Net network structure is replaced by the SE module, which is used to improve the feature extraction capability of the network; the structure of the SE module is shown in FIG. 4 .
  • the image segmentation process of the image segmentation model is as follows: after inputting the feature map, it first passes through a standard convolution layer (Conv), and then generates two branches.
  • Conv convolution layer
  • the first branch passes through two standard convolution layers to obtain The first feature map of size C*3*3 (C is the feature map channel);
  • the second branch is the SE module, including Globalpooling (global pooling layer), two layers of Fully Connected (full connection layer) and sigmoid function layer,
  • Globalpooling global pooling layer
  • Fully Connected full connection layer
  • sigmoid function layer sigmoid function layer
  • the loss selection model In the process of network training, the loss obtained by samples with noisy labels will be larger than that obtained by samples with clean labels. Therefore, the loss selection model usually uses the ksigma algorithm to select the obtained losses and eliminate abnormal loss values. Thereby removing noise samples. However, when all high-loss samples are removed, the samples that are difficult to learn will also be removed. However, these samples that are difficult to learn play an important role in improving network performance. In view of this deficiency, in the embodiment of the present application, the loss selection model adopts the ksigma criterion to select the loss. It is assumed that a set of detection data roughly obeys the normal distribution and only contains random errors, and the random errors are processed to obtain the standard deviation, which is determined according to the set probability. A deviation interval, and the errors exceeding the deviation interval are determined as gross errors and eliminated.
  • S14 Input the test set into the trained anti-noise network model, obtain the classification result of the test set image, and evaluate the performance of the anti-noise network model according to the test result.
  • the neural network optimization method for remote sensing image classification uses the SE module to improve the semantic segmentation network U-Net, builds an anti-noise network model, improves the feature extraction capability of the network model, and uses ksigma Criterion for loss selection, to solve the problem of neural network classification accuracy decline due to noise in labels in remote sensing image datasets.
  • FIG. 5 is a flowchart of the neural network optimization method for remote sensing image classification according to the second embodiment of the present application.
  • the neural network optimization method for remote sensing image classification according to the second embodiment of the present application includes the following steps:
  • this embodiment uses the Inria Aerial Image Labeling Dataset (which is a remote sensing image data set used for urban building detection) as the data set.
  • the dataset includes a total of 180 remote sensing images with a size of 5000*5000 pixels.
  • the annotation information of the dataset includes two types of buildings and non-buildings, which are mainly used for semantic segmentation.
  • S21 Construct training set, validation set and test set according to remote sensing image data set, at the same time crop the training set, validation set and test set images into images of a set size, and perform data cleaning and data enhancement operations on the training set images;
  • this embodiment only takes 135 images in the data set as the training set, 20 images as the validation set, and 25 images as the test set as examples, the three are independent of each other, and the images are randomly cropped into 256*256 images.
  • Data enhancement includes, but is not limited to, rotation, mirror symmetry, or/and adding Gaussian noise.
  • the model training process is specifically: input the constructed training set into the anti-noise network model, set the hyperparameters such as the learning rate, the number of iterations, the K value of the loss selection model, and set the loss function used to optimize the network parameters.
  • a good loss curve adjusts the training process, and finally gets the trained network model parameters.
  • the embodiment of the present application randomly selects 0%, 25% and 50% of the sample images from the training set, and then uses 5*5, 7*7 and 9*9 convolution kernels to dilate and Corrosion is used to remove some noise samples to generate different types and levels of noise labeled images, and the anti-noise network model is trained according to the different types and levels of noise labeled images.
  • S24 Input the test set into the trained anti-noise network model, obtain the classification result of the test set image, and evaluate the performance of the anti-noise network model according to the classification result.
  • p ij represents the number of pixels labeled as class i but predicted to be class j
  • p ii indicates that the label is class i and the prediction is also a class
  • the number of pixels in i p ji is the number of pixels labeled as class j but predicted to be class i
  • p o is the sum of the number of correctly distributed samples for each class divided by the total number of samples
  • p e is the assumed number of each class
  • the number of real samples is a1, a2 respectively, and the number of predicted samples of each class is b1, b2, and the total number of samples is n, then:
  • the embodiments of the present application can solve the problem that the classification accuracy of the neural network is reduced due to the existence of noise in the labels in the remote sensing image dataset.
  • FIG. 6 is a schematic structural diagram of a neural network optimization system for remote sensing image classification according to an embodiment of the present application.
  • the neural network optimization system for remote sensing image classification according to the embodiment of the present application includes:
  • Data acquisition module used to acquire remote sensing image datasets
  • Data segmentation module It is used to divide the remote sensing image dataset into training set, validation set and test set according to the set ratio;
  • Anti-noise network building block used to build an anti-noise network model
  • the anti-noise network model includes an image segmentation model and a loss selection model.
  • the image segmentation model is a U-Net network based on the SE module.
  • the existing U-Net network structure includes two parts: the feature extraction part and the upsampling part.
  • the feature extraction part is divided into five layers, and the image resolution is halved after each layer of pooling layer; correspondingly, the upsampling part is also divided into five layers, each of which has a standard volume containing two layers.
  • the convolutional module of the stack is a convolutional module of the stack.
  • the network model is improved on the basis of the existing U-Net, and the SE module (Squeeze-and-Excitation Networks) is added to the U-Net network structure to expand the perception of global information and improve the network's ability to deal with difficult problems.
  • the learning ability of the sample is improved on the basis of the existing U-Net, and the SE module (Squeeze-and-Excitation Networks) is added to the U-Net network structure to expand the perception of global information and improve the network's ability to deal with difficult problems. The learning ability of the sample.
  • the improvement point of the network model in the embodiment of the present application is that the convolution module in the existing U-Net network structure is replaced by the SE module, which is used to improve the feature extraction capability of the network; the structure of the SE module is shown in FIG. 4 .
  • the image segmentation process of the image segmentation model is as follows: after inputting the feature map, it first goes through a standard convolution layer (Conv), and then generates two branches. The first branch passes through two standard convolution layers, and the size is C* The first feature map of 3*3 (C is the feature map channel); the second branch is the SE module, including Globalpooling (global pooling layer), two layers of Fully Connected (full connection layer) and sigmoid function layer.
  • the input feature map is subjected to global average pooling to obtain a second feature map of size C*1*1; then it is activated by the sigmoid function layer after two layers of Fully Connected (dimension reduction first and then dimension increase) to obtain a size of C*1 *1 weight, and multiply the weight with the first feature map generated by the first branch at the corresponding position to obtain the image classification output result.
  • the loss selection model In the process of network training, the loss obtained by samples with noisy labels will be larger than that obtained by samples with clean labels. Therefore, the loss selection model usually uses the ksigma algorithm to select the obtained losses and eliminate abnormal loss values. Thereby removing noise samples. However, when all the high-loss samples are removed, the samples that are difficult to learn will also be removed. However, these samples that are difficult to learn play an important role in improving network performance. In view of this deficiency, in the embodiment of the present application, the loss selection model adopts the ksigma criterion to select the loss. It is assumed that a set of detection data roughly obeys the normal distribution and only contains random errors, and the random errors are processed to obtain the standard deviation, which is determined according to the set probability. A deviation interval, and the errors exceeding the deviation interval are determined as gross errors and eliminated.
  • Model training module used to input the training set into the anti-noise network model for training, and obtain the trained network model parameters
  • Model evaluation module It is used to input the test set into the trained anti-noise network model, obtain the classification results of the test set images, and evaluate the performance of the anti-noise network model according to the test results.
  • FIG. 7 is a schematic structural diagram of a terminal according to an embodiment of the present application.
  • the terminal 50 includes a processor 51 and a memory 52 coupled to the processor 51 .
  • the memory 52 stores program instructions for implementing the above-described neural network optimization method for remote sensing image classification.
  • the processor 51 is configured to execute program instructions stored in the memory 52 to control neural network optimization for remote sensing image classification.
  • the processor 51 may also be referred to as a CPU (Central Processing Unit, central processing unit).
  • the processor 51 may be an integrated circuit chip with signal processing capability.
  • the processor 51 may also be a general purpose processor, digital signal processor (DSP), application specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component .
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • FIG. 8 is a schematic structural diagram of a storage medium according to an embodiment of the present application.
  • the storage medium of this embodiment of the present application stores a program file 61 capable of implementing all the above methods, wherein the program file 61 may be stored in the above-mentioned storage medium in the form of a software product, and includes several instructions to enable a computer device (which may It is a personal computer, a server, or a network device, etc.) or a processor that executes all or part of the steps of the methods in the various embodiments of the present invention.
  • a computer device which may It is a personal computer, a server, or a network device, etc.
  • a processor that executes all or part of the steps of the methods in the various embodiments of the present invention.
  • the aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes , or terminal devices such as computers, servers, mobile phones, and tablets.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

La présente demande concerne un procédé d'optimisation de réseau neuronal pour une classification d'image de détection à distance, ainsi qu'un terminal, et un support de stockage. Le procédé comprend les étapes consistant à : acquérir un ensemble de données d'image de détection à distance ; construire un modèle de réseau anti-bruit, le modèle de réseau anti-bruit comprenant un modèle de segmentation d'image et un modèle de sélection de perte, et le modèle de segmentation d'image étant un réseau U-Net basé sur un module SE ; et entrer l'ensemble de données d'image de détection à distance dans le modèle de réseau anti-bruit pour un entraînement itératif, effectuer, par l'intermédiaire du modèle de réseau anti-bruit, une segmentation d'image au moyen du réseau U-Net basé sur le module SE, de façon à obtenir un résultat de classification d'image, utiliser, par l'intermédiaire du modèle de sélection de perte, un critère ksigma pour effectuer une sélection de perte, et éliminer une erreur qui dépasse un intervalle de déviation défini, de façon à obtenir un paramètre de modèle de réseau optimal. Au moyen des modes de réalisation de la présente demande, la capacité d'extraction de caractéristiques d'un modèle de réseau est améliorée, et le problème d'une diminution de la précision de classification d'un réseau neuronal provoquée par le bruit d'étiquettes dans un ensemble de données d'image de détection à distance est résolu.
PCT/CN2020/138818 2020-09-10 2020-12-24 Procédé d'optimisation de réseau neuronal pour une classification d'image de détection à distance, terminal, et support de stockage WO2022052367A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010944670.4 2020-09-10
CN202010944670.4A CN112132193A (zh) 2020-09-10 2020-09-10 一种用于遥感图像分类的神经网络优化方法、终端以及存储介质

Publications (1)

Publication Number Publication Date
WO2022052367A1 true WO2022052367A1 (fr) 2022-03-17

Family

ID=73845354

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/138818 WO2022052367A1 (fr) 2020-09-10 2020-12-24 Procédé d'optimisation de réseau neuronal pour une classification d'image de détection à distance, terminal, et support de stockage

Country Status (2)

Country Link
CN (1) CN112132193A (fr)
WO (1) WO2022052367A1 (fr)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114821299A (zh) * 2022-03-28 2022-07-29 西北工业大学 一种遥感图像变化检测方法
CN115035402A (zh) * 2022-04-15 2022-09-09 南京信息工程大学 一种用于土地覆盖分类问题的多级特征聚合系统及方法
CN115035406A (zh) * 2022-06-08 2022-09-09 中国科学院空间应用工程与技术中心 遥感场景数据集的标注方法、系统、存储介质及电子设备
CN115063692A (zh) * 2022-07-06 2022-09-16 西北工业大学 一种基于主动学习的遥感图像场景分类方法
CN115223063A (zh) * 2022-07-13 2022-10-21 河南省农业科学院农业经济与信息研究所 基于深度学习的无人机遥感小麦新品种倒伏面积提取方法及系统
CN115423829A (zh) * 2022-07-29 2022-12-02 江苏省水利科学研究院 一种单波段遥感影像水体快速提取方法及系统
CN115576014A (zh) * 2022-10-26 2023-01-06 江苏科技大学 一种基于声波远探测成像的裂缝型储层智能识别方法
CN115841590A (zh) * 2022-11-16 2023-03-24 中国烟草总公司湖南省公司 神经网络推理优化方法、装置、设备及可读存储介质
CN116030358A (zh) * 2022-12-20 2023-04-28 中国科学院空天信息创新研究院 面向星群分布式的参数特征融合的遥感细粒度分类方法
CN116030347A (zh) * 2023-01-06 2023-04-28 山东建筑大学 一种基于注意力网络的高分辨率遥感影像建筑物提取方法
CN116091953A (zh) * 2023-04-11 2023-05-09 耕宇牧星(北京)空间科技有限公司 一种基于分组小波校准网络的建筑垃圾识别方法
CN116168295A (zh) * 2023-02-24 2023-05-26 中国地质大学（武汉） 一种岩性遥感智能解译模型建立方法及解译方法
CN116188816A (zh) * 2022-12-29 2023-05-30 广东省新黄埔中医药联合创新研究院 一种基于循环一致性变形图像匹配网络的穴位定位方法
CN116434037A (zh) * 2023-04-21 2023-07-14 大连理工大学 基于双层优化学习的多模态遥感目标鲁棒识别方法
CN116486273A (zh) * 2023-06-20 2023-07-25 南昌工程学院 一种小样本遥感图像水体信息提取方法
CN116660876A (zh) * 2023-05-26 2023-08-29 吉林大学 一种中华白海豚回声定位信号自动检测和定位方法
CN116761179A (zh) * 2023-07-14 2023-09-15 青岛科技大学 基于轻量化MS-Net的移动TAS-EH系统安全通信性能智能预测方法
CN116188816B (zh) * 2022-12-29 2024-05-28 广东省新黄埔中医药联合创新研究院 一种基于循环一致性变形图像匹配网络的穴位定位方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112766313B (zh) * 2020-12-29 2023-11-14 厦门贝启科技有限公司 基于U-net结构的水晶体分割及定位方法、装置、设备和介质
CN112991354B (zh) * 2021-03-11 2024-02-13 东北大学 一种基于深度学习的高分辨率遥感影像语义分割方法
CN113673530B (zh) * 2021-08-18 2023-06-16 中国人民解放军国防科技大学 遥感图像语义分割方法、装置、计算机设备和存储介质
CN115937681B (zh) * 2022-12-05 2024-04-19 中铁第四勘察设计院集团有限公司 一种遥感影像样本数据清洗方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190057245A1 (en) * 2017-08-15 2019-02-21 Regents Of The University Of Minnesota Satellite image classification across multiple resolutions and time using ordering constraint among instances
CN110211137A (zh) * 2019-06-08 2019-09-06 西安电子科技大学 基于残差网络和U-Net分割网络的卫星图像分割方法
CN110443143A (zh) * 2019-07-09 2019-11-12 武汉科技大学 多分支卷积神经网络融合的遥感图像场景分类方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110717420A (zh) * 2019-09-25 2020-01-21 中国科学院深圳先进技术研究院 一种基于遥感图像的耕地提取方法、系统及电子设备

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190057245A1 (en) * 2017-08-15 2019-02-21 Regents Of The University Of Minnesota Satellite image classification across multiple resolutions and time using ordering constraint among instances
CN110211137A (zh) * 2019-06-08 2019-09-06 西安电子科技大学 基于残差网络和U-Net分割网络的卫星图像分割方法
CN110443143A (zh) * 2019-07-09 2019-11-12 武汉科技大学 多分支卷积神经网络融合的遥感图像场景分类方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LI WANQI, LI KEJIAN;CHEN SHAOBO: "Multi-modal fusion based method for high resolution remote sensing image segmentation", ZHONGNAN MINZU DAXUE XUEBAO (ZIRAN KEXUE BAN) - JOURNAL OF SOUTH-CENTRAL UNIVERSITY FOR NATIONALITIES ( NATURAL SCIENCE EDITION, ZHONGNAN MINZU DAXUE, CN, vol. 39, no. 4, 31 August 2020 (2020-08-31), CN , pages 405 - 412, XP055911374, ISSN: 1672-4321, DOI: 10.12130/znmdzk.20200412 *
LIU HAO, JIANCHENG LUO, BO HUANG, HAIPING YANG, XIAODONG HU, NAN XU, LIEGANG XIA: "Building Extraction based on SE-Unet", JOURNAL OF GEO-INFORMATION SCIENCE, vol. 21, no. 11, 25 November 2019 (2019-11-25), pages 1779 - 1789, XP055911485, ISSN: 1560-8999 *

Cited By (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114821299A (zh) * 2022-03-28 2022-07-29 西北工业大学 一种遥感图像变化检测方法
CN114821299B (zh) * 2022-03-28 2024-03-19 西北工业大学 一种遥感图像变化检测方法
CN115035402A (zh) * 2022-04-15 2022-09-09 南京信息工程大学 一种用于土地覆盖分类问题的多级特征聚合系统及方法
CN115035402B (zh) * 2022-04-15 2023-09-12 南京信息工程大学 一种用于土地覆盖分类问题的多级特征聚合系统及方法
CN115035406A (zh) * 2022-06-08 2022-09-09 中国科学院空间应用工程与技术中心 遥感场景数据集的标注方法、系统、存储介质及电子设备
CN115035406B (zh) * 2022-06-08 2023-08-04 中国科学院空间应用工程与技术中心 遥感场景数据集的标注方法、系统、存储介质及电子设备
CN115063692A (zh) * 2022-07-06 2022-09-16 西北工业大学 一种基于主动学习的遥感图像场景分类方法
CN115063692B (zh) * 2022-07-06 2024-02-27 西北工业大学 一种基于主动学习的遥感图像场景分类方法
CN115223063A (zh) * 2022-07-13 2022-10-21 河南省农业科学院农业经济与信息研究所 基于深度学习的无人机遥感小麦新品种倒伏面积提取方法及系统
CN115223063B (zh) * 2022-07-13 2023-05-30 河南省农业科学院农业经济与信息研究所 基于深度学习的无人机遥感小麦新品种倒伏面积提取方法及系统
CN115423829B (zh) * 2022-07-29 2024-03-01 江苏省水利科学研究院 一种单波段遥感影像水体快速提取方法及系统
CN115423829A (zh) * 2022-07-29 2022-12-02 江苏省水利科学研究院 一种单波段遥感影像水体快速提取方法及系统
CN115576014A (zh) * 2022-10-26 2023-01-06 江苏科技大学 一种基于声波远探测成像的裂缝型储层智能识别方法
CN115576014B (zh) * 2022-10-26 2023-07-11 江苏科技大学 一种基于声波远探测成像的裂缝型储层智能识别方法
CN115841590A (zh) * 2022-11-16 2023-03-24 中国烟草总公司湖南省公司 神经网络推理优化方法、装置、设备及可读存储介质
CN115841590B (zh) * 2022-11-16 2023-10-03 中国烟草总公司湖南省公司 神经网络推理优化方法、装置、设备及可读存储介质
CN116030358A (zh) * 2022-12-20 2023-04-28 中国科学院空天信息创新研究院 面向星群分布式的参数特征融合的遥感细粒度分类方法
CN116030358B (zh) * 2022-12-20 2023-06-23 中国科学院空天信息创新研究院 面向星群分布式的参数特征融合的遥感细粒度分类方法
CN116188816B (zh) * 2022-12-29 2024-05-28 广东省新黄埔中医药联合创新研究院 一种基于循环一致性变形图像匹配网络的穴位定位方法
CN116188816A (zh) * 2022-12-29 2023-05-30 广东省新黄埔中医药联合创新研究院 一种基于循环一致性变形图像匹配网络的穴位定位方法
CN116030347A (zh) * 2023-01-06 2023-04-28 山东建筑大学 一种基于注意力网络的高分辨率遥感影像建筑物提取方法
CN116030347B (zh) * 2023-01-06 2024-01-26 山东建筑大学 一种基于注意力网络的高分辨率遥感影像建筑物提取方法
CN116168295B (zh) * 2023-02-24 2023-12-05 中国地质大学（武汉） 一种岩性遥感智能解译模型建立方法及解译方法
CN116168295A (zh) * 2023-02-24 2023-05-26 中国地质大学（武汉） 一种岩性遥感智能解译模型建立方法及解译方法
CN116091953A (zh) * 2023-04-11 2023-05-09 耕宇牧星(北京)空间科技有限公司 一种基于分组小波校准网络的建筑垃圾识别方法
CN116434037B (zh) * 2023-04-21 2023-09-22 大连理工大学 基于双层优化学习的多模态遥感目标鲁棒识别方法
CN116434037A (zh) * 2023-04-21 2023-07-14 大连理工大学 基于双层优化学习的多模态遥感目标鲁棒识别方法
CN116660876A (zh) * 2023-05-26 2023-08-29 吉林大学 一种中华白海豚回声定位信号自动检测和定位方法
CN116486273A (zh) * 2023-06-20 2023-07-25 南昌工程学院 一种小样本遥感图像水体信息提取方法
CN116486273B (zh) * 2023-06-20 2023-09-01 南昌工程学院 一种小样本遥感图像水体信息提取方法
CN116761179A (zh) * 2023-07-14 2023-09-15 青岛科技大学 基于轻量化MS-Net的移动TAS-EH系统安全通信性能智能预测方法
CN116761179B (zh) * 2023-07-14 2024-04-30 青岛科技大学 基于轻量化MS-Net的移动发射天线选择和能量收集TAS-EH系统安全通信性能智能预测方法

Also Published As

Publication number Publication date
CN112132193A (zh) 2020-12-25

Similar Documents

Publication Publication Date Title
WO2022052367A1 (fr) Procédé d'optimisation de réseau neuronal pour une classification d'image de détection à distance, terminal, et support de stockage
WO2018108129A1 (fr) Procédé et appareil destinés à l'identification d'un type d'objet, et dispositif électronique
WO2019233166A1 (fr) Appareil et procédé de détection de défaut de surface, et dispositif électronique
US11256982B2 (en) Noise-enhanced convolutional neural networks
US10810721B2 (en) Digital image defect identification and correction
WO2019232847A1 (fr) Procédé d'apprentissage de modèle d'écriture manuscrite, procédé et appareil de reconnaissance de caractères manuscrits, dispositif et support
CN107784288B (zh) 一种基于深度神经网络的迭代定位式人脸检测方法
CN109086654B (zh) 手写模型训练方法、文本识别方法、装置、设备及介质
US20220172456A1 (en) Noise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
WO2019232854A1 (fr) Procédé et appareil d'entraînement de modèle manuscrit, procédé et appareil de reconnaissance de caractère manuscrit, et dispositif et support
US11120297B2 (en) Segmentation of target areas in images
WO2023035926A1 (fr) Procédé de prédiction d'instabilité de microsatellite à partir d'une image pathologique sur la base d'un mécanisme d'auto-attention
WO2023116632A1 (fr) Procédé et appareil de segmentation d'instance vidéo sur la base d'informations de mémoire spatiotemporelles
WO2019232855A1 (fr) Procédé d'entraînement de modèle d'écriture manuscrite, procédé et dispositif de reconnaissance de caractère manuscrit, appareil, et support
US11410016B2 (en) Selective performance of deterministic computations for neural networks
CN114974421A (zh) 基于扩散-降噪的单细胞转录组测序数据补插方法及系统
WO2019218482A1 (fr) Procédé et appareil de dépistage de masse fondé sur des mégadonnées, dispositif terminal et support d'informations lisible
CN116912923B (zh) 一种图像识别模型训练方法和装置
CN112818946A (zh) 年龄识别模型的训练、年龄识别方法、装置及电子设备
CN113011532A (zh) 分类模型训练方法、装置、计算设备及存储介质
US11688175B2 (en) Methods and systems for the automated quality assurance of annotated images
CN117011222A (zh) 一种电缆缓冲层缺陷检测方法、装置、存储介质和设备
US11756319B2 (en) Shift invariant loss for deep learning based image segmentation
WO2022237065A1 (fr) Procédé de formation de modèle de classification, procédé de classification de vidéo et dispositif associé
CN115170599A (zh) 通过图神经网络的链路预测进行血管分割的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20953152

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20953152

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 14.08.2023)