Supercharge Your Innovation With Domain-Expert AI Agents!

Multi-target continuous positioning method and system based on unmanned aerial vehicle image recognition

A multi-target positioning and image recognition technology, which is applied in the field of multi-target continuous positioning methods and systems to achieve the effect of improving positioning efficiency and improving recognition accuracy.

Active Publication Date: 2020-11-03
NAT UNIV OF DEFENSE TECH
View PDF17 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the consideration of the amount of calculation, there are few works that conduct research on both aspects at the same time

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
  • Multi-target continuous positioning method and system based on unmanned aerial vehicle image recognition
  • Multi-target continuous positioning method and system based on unmanned aerial vehicle image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0027] like figure 1 As shown, the multi-target continuous positioning method based on UAV image recognition of the present embodiment includes steps:

[0028] 1) Image recognition: After acquiring the image of the ground target, the ground station performs target recognition based on the GOTURN neural network and offline training, and performs target tracking based on the YOLO algorithm (conventional algorithm);

[0029] 2) Single target position calculation: According to the drone's own GPS and IMU data returned by the drone, as well as the camera's status data, the ground station is used to calculate the high-precision ground target position;

[0030] 3) Route design: Design the UAV flight route according to the position of a single ground target, and the UAV will sample all targets without affecting the track and ensuring concealment;

[...

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 multi-target continuous positioning method based on unmanned aerial vehicle image recognition, and the method comprises the steps: 1) image recognition: obtaining a ground target image, carrying out the target recognition and target tracking through a ground station based on a GOTURN neural network and offline training; 2) resolving a single target position: resolving a high-precision ground target position through a ground station according to the GPS and IMU data of the unmanned aerial vehicle returned by the unmanned aerial vehicle and the state data of the camera;3) route design: designing a flight route of the unmanned aerial vehicle according to the position of a single ground target, and ensuring that the unmanned aerial vehicle samples all targets; and 4)multi-target positioning: after sampling is completed, the data is transmitted back to the ground station, enabling the ground station to perform fusion of multiple pairs of sampling data, and enabling the unmanned aerial vehicle to continuously identify and lock a new target to realize continuous positioning of multiple targets. The method has the advantages of high target recognition accuracy,high recognition precision, high target position positioning precision and the like.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to a multi-target continuous positioning method and system based on unmanned aerial vehicle image recognition. Background technique [0002] In recent years, drones are being widely used, and have developed very important applications in both military and civilian fields. Locating the ground target is one of the important functions of the UAV, and its purpose is to obtain the longitude and latitude coordinates of the target. At present, high-precision UAV target positioning has become a research hotspot for domestic and foreign researchers. The target positioning of UAV can be divided into active positioning and passive positioning. For small unmanned aerial vehicles, the laser ranging instrument required for active positioning is not only heavy, but also has the disadvantages of high cost and unfavorable concealment, so passive positioning is often used. Passive...

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): G01C21/00G01C21/16G01C21/20G01S19/45G01S19/47
CPCG01C21/005G01C21/165G01C21/20G01S19/45G01S19/47
Inventor 喻煌超王祥科陆俊麒肖乃经曹粟
Owner NAT UNIV OF DEFENSE TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com