Semantic segmentation method and system for space science experiment data

A semantic segmentation and space science technology, applied in the semantic segmentation method and system field of space science experiment data, can solve the problems of real-time and accurate semantic segmentation and achieve the effect of precise segmentation

Inactive Publication Date: 2020-12-18
TECH & ENG CENT FOR SPACE UTILIZATION CHINESE ACAD OF SCI
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a semantic segmentation method and system for space science experimental data b

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
  • Semantic segmentation method and system for space science experiment data
  • Semantic segmentation method and system for space science experiment data
  • Semantic segmentation method and system for space science experiment data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The principles and features of the present invention will be described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0025] Space station scientific experiments involve many fields such as biomedicine and basic physics. With the progress of space station scientific experiments and the continuous development and deepening of space science research, the types of space science experiments will continue to enrich, and the number of images and videos will show explosive growth. Through semantic segmentation, it is possible to mine the intelligent semantic understanding technology in the neutrality of space science experiment data, quickly and automatically understand the content in a large amount of data, and automatically add explanatory content to highly specialized space science experiment images / videos, making complex scientific ...

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 a semantic segmentation method and system for space science experiment data, and relates to the field of image processing. The method comprises the following steps: simulatinga space science experiment on the ground, acquiring ground experiment data, performing semantic segmentation annotation on the ground experiment data, and dividing the annotated ground experiment datainto a training set and a verification set; training a pre-adjusted UNet semantic segmentation network according to the training set and the verification set to obtain a semantic segmentation model;and obtaining space science experiment data, and inputting the space science experiment data into the semantic segmentation model to obtain a semantic segmentation result of the space science experiment data. According to the method, the problems of few space science experiment samples and non-uniform distribution are solved, accurate segmentation of space science experiment objects is realized, and the problem that real-time accurate semantic segmentation of small samples and small targets is difficult is solved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a semantic segmentation method and system for space science experiment data. Background technique [0002] Semantic segmentation provides rich semantic and visual information by segmenting regions of interest, and is widely used. At present, the traditional image segmentation methods mainly include threshold method, pixel clustering method, edge detection method, region generation method, image cutting and other methods. However, the existing semantic segmentation methods based on deep learning are all based on daily scenes or medical image datasets, and the traditional image segmentation methods need to control a lot of thresholds, and the applicable environment is also very limited, and cannot be well adapted to lighting, In situations such as background transformation, the robustness is poor, and its network structure is not suitable for target segmentation in space science ex...

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): G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/267G06N3/045G06F18/22G06F18/24
Inventor 李沛卓万雪李盛阳
Owner TECH & ENG CENT FOR SPACE UTILIZATION CHINESE ACAD OF SCI
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