A moving target automatic tracking method based on image multi-dimensional feature recognition

A technology of moving targets and multi-dimensional features, applied in the field of automatic tracking of moving targets, can solve the problems of high error rate, complex flight path, missing, etc., and achieve the effect of improving the level of automation

Active Publication Date: 2019-06-07
GUILIN CHANGHAI DEV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The air target automatic tracking system is mainly used to track the aircraft in the air. The technology of automatic target tracking is relatively mature in the industry, mainly in the process of target capture, which has not yet been fully automated; The path is complex and difficult to find by human eyes; in the general automatic tracking system of air targets, the target needs to be manually selected and captured in the process of target capture, and it is difficult for human eyes to detect targets moving in the air, and if the target If the fligh

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 moving target automatic tracking method based on image multi-dimensional feature recognition
  • A moving target automatic tracking method based on image multi-dimensional feature recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0046] Such as figure 2 As shown, the present invention provides a mobile target automatic tracking device based on image multi-dimensional feature recognition, which is characterized in that it includes a data acquisition module, an information processing module, and a terminal;

[0047] The data acquisition module is used to set the control area, collect the image and video information of the control area, and provide the video source of the control area;

[0048] The information processing module is used to collect the multi-dimensional feature information of the moving target in the video source to establish a sample library, deploy and control the control area, detect and identify the multi-dimensional feature of the moving target, and track the moving target with the sample library. The target performs multidimensional feature matching to obtain the tracking target, that is, capture the tracking target;

[0049] The terminal is used to display the decoding of the video s...

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 moving target automatic tracking method based on image multi-dimensional feature recognition. The method comprises the following specific steps: step 1, setting a deploymentand control area; 2, collecting image video information of the monitoring area to obtain a video source of the monitoring area, and collecting multi-dimensional features of a moving target in the video source to establish a sample library; Step 3, deploying and controlling the deploying and controlling area, then detecting all moving targets entering the deploying and controlling area, and identifying multi-dimensional feature information of the moving targets; And 4, matching the multi-dimensional feature information of the moving target with standard multi-dimensional feature information ofa tracking target in a sample library, and capturing the successfully matched tracking target. When the moving target is captured, tracking is started according to the multi-dimensional feature information of the moving target, manual intervention selection is not needed, automatic identification, automatic capture, automatic tracking and other operations of the moving target in the air are achieved, and the automation level is improved.

Description

technical field [0001] The invention relates to an automatic tracking method for a moving target based on image multi-dimensional feature recognition, and belongs to the technical field of video surveillance. Background technique [0002] The air target automatic tracking system is mainly used to track the aircraft in the air. The technology of automatic target tracking is relatively mature in the industry, mainly in the process of target capture, which has not yet been fully automated; The path is complex and difficult to find by human eyes; in the general automatic tracking system of air targets, the target needs to be manually selected and captured in the process of target capture, and it is difficult for human eyes to detect targets moving in the air, and if the target If the flight speed is high, it will be difficult for humans to select the flying target, which will cause the target to be unable to be captured. At present, in the industry, radar guidance is also used ...

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): H04N5/232G06T7/246
Inventor 樊展攒庾新林傅文军黎源祥盘海玲李志峰彭涛常健杰覃宗选魏文新
Owner GUILIN CHANGHAI DEV
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