Remote sensing image semantic description method based on multistage feature fusion

A remote sensing image and semantic description technology, applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of inability to generate variable length, flexible description sentences, limit the diversity of description text, etc., to improve the reliability Readability and accuracy, the effect of solving long-term dependency problems

Inactive Publication Date: 2021-08-24
NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above two types of methods limit the diversity of description text, and cannot generate variable-length, flexible description sentences

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
  • Remote sensing image semantic description method based on multistage feature fusion
  • Remote sensing image semantic description method based on multistage feature fusion
  • Remote sensing image semantic description method based on multistage feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further explained below in conjunction with the accompanying drawings and specific examples.

[0045] Such as figure 1 As shown, a semantic description method of remote sensing images based on multi-level feature fusion includes the following steps:

[0046] Step 1. Constructing a semantic description dataset of remote sensing images, the steps are as follows: obtain the original high-resolution remote sensing images; perform preprocessing on the above-mentioned obtained high-resolution remote sensing images, including image denoising and cropping, and the size obtained in this embodiment is Image data sets between 300-1000; for each image, artificially add semantic description, describe the image content in the form of natural language, each image is described by T sentences, and the image and semantic annotation together form a complete remote sensing image semantic description Dataset; at the same time, download the public remote sensin...

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 provides a remote sensing image semantic description method based on multistage feature fusion, and belongs to the field of remote sensing image processing and computer vision, and the method comprises the following steps: obtaining a high-resolution remote sensing image, and constructing a remote sensing image semantic description data set; training a semantic classification model of the image by using the semantic annotation data set, extracting word description from the image and encoding to obtain semantic features; training a target detection model by using the target detection data set, extracting region-level features of the image and encoding the region-level features to obtain visual features; aggregating the obtained semantic and visual features, namely splicing the two groups of features together; and taking the aggregated multi-level features as the input of Transform, and training an image natural language generation model. The semantic and visual features of the image are utilized, the extracted information comprises the scene information, the regional visual information and the semantic relation of the object, and the generated image semantic description is high in readability and high in accuracy.

Description

technical field [0001] The invention belongs to the field of remote sensing image processing and computer vision, and in particular relates to a natural semantic description method of remote sensing images based on image vision, semantic feature fusion and attention mechanism. Background technique [0002] With the rapid development of sensor technology, human beings' ability to observe the earth is getting higher and higher, and the amount of data obtained has increased significantly. However, the level of information processing seriously lags behind the development of remote sensing data acquisition technology, which makes the massive data not be effectively utilized. It is very important to research and explore the rapid and accurate understanding of remote sensing images with a huge amount of data, extract useful information, and then guide scientific decision-making in agriculture, environment, transportation, military and other fields. [0003] Remote sensing image se...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/044G06F18/253G06F18/214
Inventor 王港高峰陈金勇帅通王敏郭争强
Owner NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap