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

Unmanned aerial vehicle image-based flight state detection method and device

A technology of flight state and UAV, which is applied in the field of image processing, can solve problems such as inaccurate image parameters, inaccurate flight belt division, and irregular side overlap, and achieve accurate calculation results and accurate flight belt division results. Effect

Active Publication Date: 2017-05-31
SICHUAN SURVEYING & MAPPING PROD QUALITY SUPERVISION & INSPECTION STATION OF THE MINIST OF NATURAL RESOURCES SICHUAN SURVEYING & MAPPING PROD QUALITY SUPERVISION & INSPECTION STATION
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

UAVs benefit from their lightweight and portable features, but they also have shortcomings such as wind resistance and poor attitude stability, which directly lead to irregular image headings, side overlaps, and unstable rotation angles, and also directly affect aerial surveys. Therefore, in the stage of UAV aerial photography, it is necessary to carry out strict flight quality inspection and evaluation on the image to ensure that it meets the requirements of the result data processing
[0003] At this stage, there are mainly two ways to inspect the flight quality. One is manual visual inspection. This inspection mode is completely manual, time-consuming and labor-intensive, and is not suitable for large-scale UAV flight quality inspection; the other is based on the original Image, the original image is divided into air belts and matched with points of the same name, and the image parameters reflecting the flight quality of the UAV are calculated according to the matching results
[0004] However, the existing division of flight belts is usually only based on the order of image acquisition time, and the division of flight belts is not accurate, resulting in inaccurate image parameters that reflect the flight quality of UAVs.

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
  • Unmanned aerial vehicle image-based flight state detection method and device
  • Unmanned aerial vehicle image-based flight state detection method and device
  • Unmanned aerial vehicle image-based flight state detection method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0028] figure 2 A flow chart of a method for detecting a flight state based on an image of a drone provided by an embodiment of the present invention is shown. See figure 2 , the method includes:

[0029] Step S110: According to the location information of the drone corresponding to each of the multiple images obtained by the drone, multiple images included in each of the multiple flight lanes that the drone flies are acquired.

[0030] For multiple images captured by the aerial survey of the UAV, the shooting sequence of the images and the position information of the UAV corresponding to each image are stored. The position information of the drone corresponding to the image refers to the position information of the drone when the image is taken, and the position information may be POS information. According to the shooting sequence of multiple images and the position information of the UAV corresponding to each image, the multiple images can be divided into flight zones,...

no. 2 example

[0147] This embodiment provides a flight status detection device 200 based on drone images, please refer to Figure 6 , the device 200 includes:

[0148] The flight zone division module 210 is used to obtain multiple images included in each flight belt in the multiple flight belts of the drone flight according to the position information of the drone corresponding to each image in the multiple images obtained by the drone; The same-named point acquisition module 220 is used to acquire the same-named points that match each other between two adjacent images, and the two adjacent images include every two adjacent images in each flight zone and between different flight belts. For every two adjacent images; the parameter acquisition module 230 is configured to acquire a plurality of image parameters reflecting the flight state of the UAV according to the obtained matching points of the same name.

[0149] Wherein, the air belt division module 210 includes: a sequence determination...

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 provides an unmanned aerial vehicle image-based flight state detection method and device, and relates to the field of image processing. The method comprises the following steps of: obtaining a plurality of images included in each air strip in a plurality of air strips for the flight of an unmanned aerial vehicle according to unmanned aerial vehicle position information corresponding to each image in a plurality of images obtained by the unmanned aerial vehicle; obtaining mutually matched same name points between every two adjacent images, wherein every two adjacent images comprise every two adjacent images in each air strip and every two adjacent images between different air strips; and obtaining a plurality of image references reflecting the flight state of the unmanned aerial vehicle according to the obtained matched same name points. According to the method and the device provided by the invention, air strip division is carried out on the basis of the unmanned aerial vehicle position information corresponding to the images, so that the same name points obtained after the division and the image parameters obtained according to the same name points are more correct.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and device for detecting a flight state based on an image of an unmanned aerial vehicle. Background technique [0002] UAV aerial photography system has the characteristics of flexibility, low cost, and high efficiency, and has been widely used in various fields such as surveying and mapping, agriculture, and emergency response. UAVs benefit from their lightweight and portable features, but they also have shortcomings such as wind resistance and poor attitude stability, which directly lead to irregular image headings, side overlaps, and unstable rotation angles, and also directly affect aerial surveys. Therefore, in the stage of UAV aerial photography, it is necessary to carry out strict flight quality inspection and evaluation on the image to ensure that it meets the requirements of the result data processing. [0003] At this stage, there are mainly two ways to inspect...

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): G06K9/00
CPCG06V20/13
Inventor 李冲佘毅李昊霖
Owner SICHUAN SURVEYING & MAPPING PROD QUALITY SUPERVISION & INSPECTION STATION OF THE MINIST OF NATURAL RESOURCES SICHUAN SURVEYING & MAPPING PROD QUALITY SUPERVISION & INSPECTION STATION