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

A long-term and stable target tracking method based on the distribution characteristics of radar video data

A technology of video data and distribution characteristics, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., can solve problems such as stability problems and difficulties, and achieve the effects of improving robustness, stable target tracking, and reducing target tracking loss

Active Publication Date: 2021-04-30
THE 724TH RES INST OF CHINA SHIPBUILDING IND
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual battlefield environment, there are more and more complex interference effects such as weather, electromagnetic, and similar targets. The measurement set includes not only target measurement, but also a large amount of clutter and interference information, making traditional target tracking methods want to Accurate tracking of targets has become particularly difficult, especially in tasks of tracking targets for a long time, and stability has become more and more difficult for target tracking

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 long-term and stable target tracking method based on the distribution characteristics of radar video data
  • A long-term and stable target tracking method based on the distribution characteristics of radar video data
  • A long-term and stable target tracking method based on the distribution characteristics of radar video data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] (1) Target feature extraction

[0016] In the area where the target is tracked, the amplitude distribution histogram and gradient distribution histogram of the radar video data in the three measurement dimensions of distance, azimuth and elevation angle are calculated.

[0017] (2) Target detection

[0018] The Adaboost classification detector is used to detect the target. The structure of the detector is a cascaded structure, which uses a group of serial weak classifiers to be cascaded into a strong classifier. When the weak classifier classifies the recognized samples, only the positive samples judged by the previous classifier are sent to the subsequent classifier for further processing, and the negative samples are directly output. Finally, only the samples that are judged as positive by the classifiers of each level are output as positive samples. The decision result of the strong classifier is the weighted sum of the decisions of all weak classifiers.

[0019] ...

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 relates to a long-term radar target tracking method MM-TLD based on an online learning mechanism. The tracking method uses a target distribution histogram to establish a target feature space, and a radar target detector is used to detect all objects in the area where the tracked target in the radar video is located. Target, use the radar tracker to track the detected targets in the area, use the learner to learn the results of target detection and tracking, and feed back the false detection results of the detector to the detector, retrain the detector, and the detector is trained. Afterwards, the target is reclassified, and the result is sent to the learner until the convergence conditions are met. When the tracker fails to track the target, the detector reinitializes the tracker.

Description

technical field [0001] The invention belongs to the technical field of radar data processing. Background technique [0002] Radar target tracking technology is a key technology in the field of radar data processing. The traditional radar target tracking method correlates and filters the information after radar target detection. This method is very effective in the case of less background clutter and strong target signal amplitude. It worked. However, in the actual battlefield environment, there are more and more complex interference effects such as weather, electromagnetic, and similar targets. The measurement set includes not only target measurement, but also a large amount of clutter and interference information, making traditional target tracking methods want to Accurate tracking of the target becomes particularly difficult, especially in the task of tracking the target for a long time, and stability becomes more and more difficult for target tracking. [0003] The trac...

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): G06K9/62
CPCG06F18/2415G06F18/214
Inventor 耿利祥付林尹晓燕蔡文彬童卫勇李伟闫龙
Owner THE 724TH RES INST OF CHINA SHIPBUILDING IND
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