Supercharge Your Innovation With Domain-Expert AI Agents!

Embedded remote sensing image text generation method for satellite in-orbit application

A remote sensing image, embedded technology, applied in the field of aerospace remote sensing

Active Publication Date: 2021-08-24
PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, people's reasoning and understanding of aerospace remote sensing images are mainly based on detection and classification, and there is still a large gap between the results and high-level semantic information

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
  • Embedded remote sensing image text generation method for satellite in-orbit application
  • Embedded remote sensing image text generation method for satellite in-orbit application
  • Embedded remote sensing image text generation method for satellite in-orbit application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0037] Space remote sensing image semantic understanding and text generation technology is to perform a series of operations such as feature extraction, target detection, area attention, and text generation on the remote sensing images obtained after on-board data preprocessing and slicing, and then output the description information of remote sensing images. For the implementation of embedded system algorithms, the design requirements need to meet the following five aspects: (1) Lightweight requirements. The neural network is composed of tens of thousands of parameters. The structure between the networks is complex, the amount of calculation is large, and the processing speed is relatively slow. These deficiencies restrict the embedded transplant...

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 discloses an embedded remote sensing image text generation method for a satellite in-orbit application, which comprises the following steps of: obtaining a preset test model, and quantifying the preset test model to obtain a quantified test model; performing online reasoning on the quantized test model to obtain an online reasoning result; when confirming that the quantized test model can be normally executed according to the online reasoning result and the execution result is correct, enabling the quantized test model to automatically generate an offline model based on a preset model interface; and performing offline reasoning according to the offline model to obtain an updated offline model, and generating a remote sensing image text according to the updated offline model. A test model trained on a server is imported into the server for model quantification, online reasoning and debugging, the offline model is generated, offline reasoning is performed according to the offline model to obtain an updated offline model, then the updated offline model is imported into an embedded platform, and embedded transplantation of a remote sensing image text generation algorithm is realized.

Description

technical field [0001] The invention belongs to the technical field of aerospace remote sensing, and in particular relates to an embedded remote sensing image text generation method for satellite in-orbit applications. Background technique [0002] The rapid progress of modern aerospace remote sensing technology has made remote sensing satellites more mature, and the amount of remote sensing data acquisition has doubled. However, at present, people's reasoning and understanding of aerospace remote sensing images are mainly based on detection and classification, and there is still a large gap between the results and high-level semantic information. Therefore, in the face of massive remote sensing image data, it is urgent to have the interpretation ability that matches the acquisition speed of remote sensing images. How to mine and extract high-value information from the vast remote sensing images has become the direction of further exploration and research in the field of rem...

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): G06F40/30G06K9/20G06K9/46G06N3/04G06N3/08G06N5/04
CPCG06F40/30G06N3/08G06N5/04G06V10/22G06V10/40G06N3/044G06N3/045Y02D10/00
Inventor 夏鲁瑞李森林郁陈雪旗张占月王鹏薛武
Owner PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More