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

A high-efficiency dim space target recognition method

A space target and recognition method technology, applied in the field of high-efficiency dim space target recognition, can solve problems such as prone to misidentification, low extraction speed, and large dependence on prior information, achieving fewer redundant steps, high efficiency, and multiple types Effect

Active Publication Date: 2021-08-10
BEIJING INST OF CONTROL ENG
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The problem solved by the technology of the present invention is: to overcome the deficiencies of the existing technology, a high-efficiency dim space object recognition method is proposed, which solves the problem that the existing method relies heavily on prior information, and is prone to misidentification and extraction in the case of multiple objects. Problems with low speed and inability to sort online

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 high-efficiency dim space target recognition method
  • A high-efficiency dim space target recognition method
  • A high-efficiency dim space target recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] (1) Take a star map and complete star point extraction. First estimate the background gray level, and then use the eight-connected domain algorithm to judge the cluster points satisfying the number of image points greater than 4 as bright spots, and complete the star point extraction. The obtained results are as follows figure 2 shown. The background gray level adopts the regional background prediction method, and the threshold calculation formula is:

[0059]

[0060]

[0061] (2) Eliminate star points. By comparing with the star catalog and eliminating stars, and eliminating the influence of elements such as fixed bad pixels and thermal noise, a queue of suspicious space targets is established. For the suspected targets, see image 3 ;

[0062] (3) For known moving targets, use the target tracking method to judge whether the bright spots in the queue of suspicious space targets are targets, and the obtained moving targets can be found in Figure 4 . In thi...

Embodiment 2

[0069] Embodiment 2 is the same as Example 1, except that step (2) is the multi-frame elimination method of the present invention, and step (3) is that the tracking method adopts the image plane coordinate prediction method. According to the stability characteristics of stars in the inertial system, all useless background stars are eliminated by frame-to-frame comparison. For the implementation method, see Figure 6 . Compared with the previous method, more background stars can be removed. The tracking method adopts the image plane coordinate prediction method, assuming that the position coordinate of the target is X=(u,v), then the prediction method is:

[0070] u=μ u (t-t 0 )+u 0 , v=μ v (t-t 0 )+v 0 ,

[0071] Thus, the position of the target in the image frame is obtained, and the target is extracted. Compared with the aforementioned method, the extraction of the target position is more direct and accurate.

Embodiment 3

[0073] Embodiment 3 is the same as Example 1, except that the different step (3) is to adopt the authentication method of the present invention, which classifies by calculating the target motion speed, size, and motion feature set, determines to contain several types of targets, and judges the corresponding elements in the suspected queue. What kind of space movement target. The implementation steps are as follows:

[0074] 1) Calculate the motion velocity of blocky bright spots in the inertial space in the suspected target queue of each frame, remove all matching star pairs whose velocity is greater than the upper threshold (0.2 degrees), and obtain all motion velocity information after iteratively processing multi-frame information;

[0075] 2) Count all the motion features, calculate the motion ordered feature set based on the frequency, and select the motion feature set with the smallest comprehensive rate as the final A-type ordered feature set. For the diagram, see Fig...

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

A high-efficiency dim space object recognition method, the steps are: 1) star image imaging, to obtain a series of star images containing faint objects; 2) star image processing, to extract blocky bright spots. 3) Stellar removal, which mainly removes most of the star elements from all bright spots; 4) Obtains the motion characteristics of each blocky bright spot in the suspected target queue; 5) Determines the ordered feature set; 6) Target tracking, for the established Confirm the target queue to track, predict the position of the target in the next frame, calculate the target parameters successfully, extract the precise orientation information, and add it to the confirmed target queue. The method of the present invention can remove interference elements, such as stars and noise points, etc. from the extracted bright spots to the greatest extent, and finally realize tasks such as detection, extraction, identification, and tracking of space dim targets, and is especially suitable for low signal-to-noise ratios, complex star map backgrounds, multiple Various occasions where target information is unknown.

Description

technical field [0001] The invention relates to a high-efficiency dim space target recognition method, which belongs to the technical fields of situational awareness, space monitoring and the like. Background technique [0002] The rapid growth of uncatalogued tiny targets in space orbits, such as tiny debris of millimeter or centimeter scale, and space objects in reverse orbits of spacecraft, has posed a direct threat to the construction and maintenance of space stations, satellite protection, and spacecraft launch missions. High-sensitivity detection technology has been Facing real needs. There are more than 30,000 debris and satellites with a diameter of more than 10 cm, about 500,000 pieces with a diameter of 1 cm to 10 cm, and more than 10 billion pieces with a diameter of less than 1 cm. For targets smaller than 10cm and whose high orbit is smaller than 0.5m, the above methods are already difficult to monitor. [0003] For the extraction of point-shaped moving target...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/13G06F18/24
Inventor 张俊孙大开张洪健王立武延鹏张春明田玉松卢欣钟红军赵春晖李春艳郑然
Owner BEIJING INST OF CONTROL ENG
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