Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for tracking high-speed target image of unmanned aerial vehicle

A high-speed target, image tracking technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as poor anti-interference ability, long algorithm processing cycle, unable to meet rapidity requirements, etc., to achieve the effect of improving accuracy

Inactive Publication Date: 2017-01-25
SHANDONG INST OF AEROSPACE ELECTRONICS TECH
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In conventional image tracking algorithms, high-speed algorithms, such as difference frame method, template matching method, center of gravity iteration, etc., can meet the requirements of fast tracking, but the anti-interference ability in the actual tracking environment is poor, and strong interference occurs Larger tracking errors will occur when there is noise
However, high-precision tracking algorithms, such as the Mean shift algorithm, have good anti-interference performance, but the processing cycle of the algorithm is long, which cannot meet the rapidity requirements.

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
  • Method for tracking high-speed target image of unmanned aerial vehicle
  • Method for tracking high-speed target image of unmanned aerial vehicle
  • Method for tracking high-speed target image of unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0024] The invention provides a high-speed target image tracking method for UAVs. In order to meet the actual requirements of real-time image tracking for high-speed UAVs, the high-speed algorithm and the high-precision tracking algorithm are integrated: the CCD images collected by the UAV flight are run in parallel High-speed algorithm and high-precision tracking algorithm, image target tracking is carried out at the same time, the result of high-speed algorithm is corrected with the result of high-precision tracking algorithm, and then the corrected result is regarded as the observation of the UAV system, and the Kalman filter equation is established to Real-time forecast of man-machine position, so as to realize real-time tracking of high-speed UAV.

[0025] The position of the UAV at time t is denoted as W t , the UAV image collected by the CCD at tim...

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 method for tracking a high-speed target image of an unmanned aerial vehicle. With the adoption of the method, a high-speed target can be tracked precisely in real time. By means of analysis of real-time tracking errors of the image, two existing image tracking algorithms are introduced, and fast tracking and high-precision tracking are realized with the two algorithms respectively. A high-precision algorithm result is used for correcting the fast algorithm, and the precision of the fast algorithm is improved; meanwhile, motion displacement of the unmanned aerial vehicle in the calculation period is compensated with a Kalman filtering technology, and the requirements of unmanned aerial vehicle image tracking for fastness and accuracy are met.

Description

technical field [0001] The invention relates to the technical field of high-speed image processing and tracking, in particular to a method for tracking an unmanned aerial vehicle's high-speed target image. Background technique [0002] In order to wirelessly recharge UAVs in flight, it is necessary to identify and track highly dynamic UAVs in real time and accurately before wireless energy transmission. This process is divided into two steps: firstly, the CCD device is used to capture the image sequence of the UAV, and the image coordinates of the target are obtained through image processing technology; secondly, the coordinate information is transmitted to the attitude positioning and turntable tracking system to implement the charging action. How to use image processing technology to obtain accurate real-time coordinates of the UAV is a key part of the wireless charging system. [0003] In the field of image processing, the recognition and tracking of dynamic targets has ...

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 Applications(China)
IPC IPC(8): G06T7/292G06N3/06
CPCG06N3/061G06T2207/20024G06T2207/20084
Inventor 王宜贤石德乐
Owner SHANDONG INST OF AEROSPACE ELECTRONICS TECH