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

Space-based starry sky background weak point target tracking method based on threshold separation cluster

A technology of starry sky background and point target, which can be used in instruments, image analysis, image data processing, etc.

Active Publication Date: 2019-10-01
深空探测科技(北京)有限责任公司
View PDF11 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention is: the present invention provides a space-based starry sky background weak point target tracking method based on a threshold separation clusterer, which solves the problem of poor tracking accuracy of space-based starry sky background weak and small target caused by the existing moving target background and star interference

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
  • Space-based starry sky background weak point target tracking method based on threshold separation cluster
  • Space-based starry sky background weak point target tracking method based on threshold separation cluster
  • Space-based starry sky background weak point target tracking method based on threshold separation cluster

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] It is difficult for the existing algorithms to deal with the background noise that always exists in the scene, and it is easy to regard these background noises as new targets. When clustering, the stars at special positions are grouped into one category, and the threshold is set to a fixed value, resulting in a huge Tracking error; on the other hand, the moving sensor platform causes the moving target background, which is the difficulty of space-based infrared weak and small target tracking; therefore, based on the above problems, this application provides a high-precision space-based starry sky background weak point target tracking method ,Details as follow:

[0075] The space-based starry sky background weak point target tracking method based on the threshold separation clusterer includes the following steps:

[0076] Step 1: After detecting weak and small targets in the image frame, convert them into target point sets to complete point target detection, and obtain fr...

Embodiment 2

[0144] The present invention is based on embodiment 1, and this embodiment is data set 2 of scenario 2, such as image 3 As shown, the star movement is frequent in this data set. The target in the lower left corner will move in a small constellation for more than 5 time steps, and other targets will be disturbed by the stars during the movement process; the effect is as follows Figure 7 Shown:

[0145] As shown in Figures a and b, the GM-PHD algorithm still recognizes close stars as real targets. In the first 34 time steps, the forward-backward smoothing filter algorithm showed a very good tracking and prediction ability, but in the subsequent time steps, because the target in the lower left corner entered a constellation consisting of three stars , causing the algorithm to identify all three stars as real targets. Although the N-scan algorithm has no false missed detection in this data set, it loses the position information of the real target when the target in the lower ...

Embodiment 3

[0147] On the basis of embodiment 1, the present invention is data set 3 of scenario 3, such as Figure 4 As shown in , the special case where two targets are disturbed by close stars during the encounter process is used to evaluate the robustness of the algorithm when clustering different targets at close range. The effect is as Figure 8 Shown:

[0148] Scenario 3 tests the special situation where two targets are disturbed by close stars during the encounter process. By observing the pictures a to h, it is found that the three comparison algorithms recognize the star at the intersection position as the real target, and the N-scan algorithm is also behind False missed detections occurred in the time step of . However, the algorithm of this application can obtain the overlapping clusters formed by two real objects during clustering, and remove the interference information of stars through the dynamic weight extraction method, so that the algorithm can well avoid this kind of...

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 space-based starry sky background weak point target tracking method based on a threshold separation cluster, and relates to the field of space-based starry sky background weak point target tracking methods. The space-based starry sky background weak point target tracking method comprises the following steps: detecting a point target, and realizing frame registration by utilizing position coordinates of two continuous frames of target point sets; and after the target point set is clustered through a threshold separation cluster to obtain a prediction target with the maximum weight in each class group, obtaining a final prediction result through a dynamic weight extraction algorithm, and completing target tracking. According to the space-based starry sky backgroundweak point target tracking method, ICP image frame registration, a threshold separation cluster and a dynamic weight extraction algorithm are utilized to solve the problem of poor space-based starry sky background weak small target tracking precision caused by existing moving target background and fixed star interference, and high-precision detection and tracking of weak small point targets undera space-based observation platform and a starry sky background are effectively realized.

Description

technical field [0001] The invention relates to the field of space-based starry sky background weak point target tracking methods, in particular to a space-based starry sky background weak point target tracking method based on a threshold separation clusterer. Background technique [0002] The detection and tracking of midpoint targets in space-based moving backgrounds has always been one of the hot issues in the field of aerospace research, and it plays a very important role in space surveillance, early warning, and spacecraft safety. The detection of deep space based on space-based platforms in low-Earth orbit and infrared sensors has the advantages of long detection distance, wide coverage, high measurement accuracy, and strong concealment, and has become the main way to track and monitor space targets; The detection and tracking of weak and small targets in deep space has the following difficulties: (1) The imaging distance is long, and point targets often appear in the ...

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): G06T7/246G06T7/33
CPCG06T7/246G06T7/33G06T2207/10032Y02A90/10
Inventor 高志升罗清清
Owner 深空探测科技(北京)有限责任公司
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