Remote Sensing Image Recognition Method Based on Feature Aggregation Convolutional Network
A convolutional network and remote sensing image technology, applied in the field of remote sensing image recognition, can solve problems such as too little training set data, difficulty in training convolutional neural networks, etc., and achieve the effect of improving accuracy.
Active Publication Date: 2020-11-17
XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to solve the problem that the training set data of the original remote sensing scene database is too small and it is difficult to train the convolutional neural network, and propose a remote sensing image recognition method based on the feature aggregation convolutional network to improve the expression of the convolutional neural network for the remote sensing scene ability
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] Such as figure 1 As shown, the remote sensing scene recognition method based on feature aggregation convolutional network provided by the present invention mainly includes the following steps:
[0042] 1) Use the VGG-16 convolutional neural network to extract features;
[0043] Use the convolutional layer, downsampling layer, fully connected layer, and activation function layer to build the VGG-16 convolutional neural network framework, and use the different convolutional layers of VGG-16 to extract the convolutional features of remote sensing images;
[0044] 2) Convolution feature encoding;
[0045] Construct a deep convolutional feature encoding module, which can be embedded into the VGG-16 convolutional neural network to fuse the spatial information and semantic information of different convolutional features, and encode the convolutional features of different convolutional layers into convolutional Express;
[0046] 3) Remote sensing scene expression;
[0047] ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a remote sensing image recognition method based on a feature aggregation convolutional network, comprising the following steps: 1) extracting features using a VGG-16 convolutional neural network; 2) convolutional feature encoding; 3) remote sensing scene expression; 4) training Feature aggregation convolutional network; 5) Predict the scene category of remote sensing images. The invention establishes a remote sensing scene recognition method based on a feature aggregation convolutional network, directly learns remote sensing scene expressions from a remote sensing scene database, improves the accuracy of remote sensing scene recognition, and can be used in fields such as forest fire monitoring and urban planning.
Description
technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image recognition method. Background technique [0002] Remote sensing images are a type of earth observation image data captured by remote sensing imaging systems, which contain detailed information on the composition and distribution of ground features. However, due to the complex composition of remote sensing scenes, the small size of ground objects, and the disordered spatial distribution of ground objects, the differences between images of the same type of remote sensing scenes are relatively large, while the differences between images of different types of remote sensing scenes are small. Therefore, it is still a very challenging task to accurately deduce the category of remote sensing scenes based on the content of remote sensing scene objects. [0003] In recent years, many scholars have proposed many remote sensing scene recognit...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06N3/045
Inventor 卢孝强李学龙孙昊
Owner XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI