Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A remote sensing image ground object labeling method based on an attention mechanism convolution neural network

A remote sensing image and attention technology, applied in computer parts, instruments, character and pattern recognition, etc., to improve classification results and performance

Active Publication Date: 2018-12-18
BEIHANG UNIV +1
View PDF4 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The attention mechanism has a wide range of applications in the fields of computer vision and natural language processing, but has little application in the field of remote sensing image processing

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A remote sensing image ground object labeling method based on an attention mechanism convolution neural network
  • A remote sensing image ground object labeling method based on an attention mechanism convolution neural network
  • A remote sensing image ground object labeling method based on an attention mechanism convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to better understand the technical solution of the present invention, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings:

[0025] The structural diagram of the convolutional neural network (AICNet) of the attention mechanism proposed by the present invention is as follows: figure 1 As shown, each box represents a piece of the neural network, where the convolutional layer performs convolution operations on the input data, and 1 to 5 sets of convolutional layers (conv1~conv5) contain 2, 2, 3, 3 , 3 sub-convolutional layers, where 1 to 3 sets of convolutional layers are followed by a maximum pooling operation with a stride of 2, while 4 and 5 sets of convolutional layers are followed by a maximum pooling operation with a stride of 1. The flow chart is shown in 2. The thesis uses an NVIDIA GTX 1080Ti graphics card with a main frequency of 4.0GHz, a memory of 64GB Intel(R) Core(TM) i7-7700K process...

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

No PUM Login to View More

Abstract

The invention relates to a remote sensing image ground object labeling method based on an attention mechanism convolution neural network, which comprises the following four steps: a computer reads data, constructs convolution neural network of attention mechanism, trains network model, and tests network to obtain labeling result. By adding an attention mechanism module, the invention enables the network to pertinently extract the information of the key position, makes up for the deficiency of the lack of the spatial information at the network end, and improves the classification effect of thenetwork to the ground object details. By using the mechanism of in-depth monitoring and using the characteristics extracted from the middle of the network to supervise the classification, the trainingspeed of the network can be further increased and the comprehensive performance of the network can be improved; through the up-sampling module of deconvolution, the resolution of feature extraction is increased and the method can overcome the problem that small objects are difficult detect to a certain extent, and can automatically classify remote sensing image pixels into corresponding object categories, reduce the trouble of manual interpretation, greatly accelerate the interpretation process, and obtain refined labeling results.

Description

(1) Technical field [0001] The invention relates to a method for marking remote sensing image features based on convolutional neural network of attention mechanism, and belongs to the technical field of visible light remote sensing image scene marking. (2) Background technology [0002] Remote sensing is a scientific activity that uses sensors to remotely measure electromagnetic radiation in a geographical area, and then uses mathematical and statistical methods to extract valuable information from the data. Remote sensing images are digital or analog images converted from electromagnetic signals received by sensors, which belong to the category of imaging remote sensing. [0003] Remote sensing image feature labeling requires pixel-by-pixel labeling of remote sensing images, by extracting the features of each point and using a classifier to classify them into corresponding categories. By counting the category of each pixel in the whole map, the distribution and quantity of...

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
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/176G06F18/2413
Inventor 史振威陈浩冯鹏铭吴犀石天阳
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com